From cf8262d3cb90d3cb9774c4fb3f8b338500fbdf95 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?N=C3=A9munaire?= Date: Mon, 5 Mar 2012 22:46:25 +0100 Subject: [PATCH] New version --- dl.sh | 61 +- htdocs/dl.php | 81 +- htdocs/favicon.ico | Bin 0 -> 165662 bytes htdocs/images/background.jpg | Bin 0 -> 2544 bytes htdocs/index.php | 231 +- htdocs/style.css | 166 ++ users/users | 0 youtube-dl | 4648 ++++++++++++++++++++++++++++++++++ 8 files changed, 5056 insertions(+), 131 deletions(-) create mode 100644 htdocs/favicon.ico create mode 100644 htdocs/images/background.jpg create mode 100644 htdocs/style.css create mode 100644 users/users create mode 100755 youtube-dl diff --git a/dl.sh b/dl.sh index f683c06..5a30b26 100755 --- a/dl.sh +++ b/dl.sh @@ -2,38 +2,47 @@ pwd=`echo "$0" | sed -e "s/[^\/]*$//"` -if [ `cat $pwd/urls | wc -l` -gt 0 ] && [ ! -e /tmp/dlEnCours ]; then - transmission-remote -asu 10 -as +# Don't do anything if this script is already launched +if [ ! -e /tmp/dlEnCours ]; then + for f in "$pwd"/users/*.dlist; do + if [ `cat $f | wc -l` -gt 0 ]; then + transmission-remote -asu 10 -as + touch /tmp/dlEnCours - touch /tmp/dlEnCours + lign=`sed '2,$d' $f | tr -d '\n'` - lign=`sed '2,$d' $pwd/urls | tr -d '\n'` + while [ -n "$lign" ] && [ `cat $f | wc -l` -gt 0 ] + do + if [ -z "$lign" ]; then + sed -i '1d' $f + lign=`sed '2,$d' $f | tr -d '\n'` + fi - if [ -z "$lign" ]; then - sed -i '1d' $pwd/urls - lign=`sed '2,$d' $pwd/urls | tr -d '\n'` - fi + echo "Action: $lign" + if [ "$lign" = "clear" ]; then + echo "-- " >> $f.done + transmission-remote -AS + else + echo "$lign" >> $pwd/database + $pwd/youtube-dl --get-title --get-thumbnail --get-filename "$lign" >> $pwd/database + echo "-- " >> $pwd/database - while [ -n "$lign" ] && [ `cat $pwd/urls | wc -l` -gt 0 ] - do - echo "Action: $lign" - if [ "$lign" = "clear" ]; then - sed -i '1d' $pwd/urls - mkdir $pwd/content/`date +%Y%m%d%H%M%S` - mv $pwd/content/*.mp3 $pwd/content/`date +%Y%m%d%H%M%S` - transmission-remote -AS - else - $pwd/youtube-dl -e $lign > $pwd/dlEc + echo "$lign" > $f.ec + $pwd/youtube-dl --no-progress -c -o "$pwd/content/%(id)s.%(ext)s" "$lign" + echo "$lign" >> $f.ec + $pwd/youtube-dl --no-progress -c -k -o "$pwd/content/%(id)s.%(ext)s" --extract-audio --audio-format=mp3 "$lign" + echo "" > $f.ec - sed -i '1d' $pwd/urls + echo "$lign" >> $f.done + fi - $pwd/youtube-dl --no-progress -c -k -o "$pwd/content/%(title)s.%(ext)s" --extract-audio --audio-format=mp3 "$lign" + #Remove the action from the file + sed -i '1d' $f - echo "" > $pwd/dlEc - fi - - lign=`sed '2,$d' $pwd/urls | tr -d '\n'` + #What's next? + lign=`sed '2,$d' $f | tr -d '\n'` + done + fi done - - rm /tmp/dlEnCours + rm /tmp/dlEnCours 2> /dev/null fi diff --git a/htdocs/dl.php b/htdocs/dl.php index d86cd70..1b2c30a 100644 --- a/htdocs/dl.php +++ b/htdocs/dl.php @@ -1,20 +1,73 @@ $t) +{ + if (empty($t)) + { + $user = $k; + break; + } +} +if (!preg_match("#^[a-zA-Z0-9_]+$#", $user)) + die ("Le nom d'utilisateur contient des caractères interdits."); + + +if (isset($_GET["f"])) +{ + if (is_file(MAIN_DIR."/users/".$user.".dlist.done")) + { + $ec = file(MAIN_DIR."/users/".$user.".dlist.done",FILE_IGNORE_NEW_LINES|FILE_SKIP_EMPTY_LINES); + + foreach ($ec as $k => $lign) + { + if ($k == $_GET["f"]) + { + $musik = get_info($lign); + if (isset($musik) && is_file(MAIN_DIR."/content/".$musik[4])) + { + $filename = MAIN_DIR."/content/".$musik[4]; + + header('Content-Description: File Transfer'); + header('Content-Type: application/octet-stream'); + header("Content-Disposition: attachment; filename=\"".$musik[1].".mp3\""); + header('Content-Transfer-Encoding: binary'); + header('Expires: 0'); + header('Cache-Control: must-revalidate, post-check=0, pre-check=0'); + header('Pragma: public'); + header('Content-Length: ' . filesize($filename)); + readfile($filename); + exit; + } + } + } + } +} +die ("Fichier introuvable"); ?> \ No newline at end of file diff --git a/htdocs/favicon.ico b/htdocs/favicon.ico new file mode 100644 index 0000000000000000000000000000000000000000..69df2c65583bc042c474b23194864eefef3d785b GIT binary patch literal 165662 zcmeF42VhmlnYQD^#x#M1P(|&k_bwrt5lEu*x+8`mfoDcN!IM9 zZ8ov9oBaPKfzAFKSBwD{Of^m4|32s35r>OF5(bPD9sA`T-7;t9oA3R~%$zx&`OInh z@3+7GjQ-8|OxHU;`$LOelt8BhIwjC4fldi@N}y8$of7Dj zK&J#cCD18>P6>2Mpi=^!66lmbrvy4B&?$jV33N)JQv#h5=#)UG1Ue`omcOaz=@GSq@FuId`_1;65My(Yp{$HQ_Id$J0);(B@onUr|0nD^f1oQt3wx^ zJGl4U_jq-`cV+6W&f^r4fa{l|y`DnV{lu%{ez$@odf;`dNoySR*Kx97$ZJ_I;;47a8`;6b8>?2rb&RgSgWF3!ZJ>B)W zhKr-nX>{9h0^N@m`UtT?UxC|`K|=U7POrSrcla(`=^;3uf#&;40xDzA56L{u)3D=-K$E*G-s`F?=0#4ShpV4_|16^!@ zEprI^f8u5O%<;sPrMFJ#!F8OzJN>5~j>9gFcYnJ&x_a{4k6Tw)2d+=~=rA&Z7wER* z1$v(;bc3ZFs@2H)rlC-37?e-+nxv_k^)GkuKixPA`W zK>CONcEJCm11?r}wvFFA{iDp|eNd)Du)gRFb#U3*`8ae2E})xm zn0jM(9r&BisH@`%^`*^}1J|5A)@i$rNV!oi<--khI#WQ$@e$}fd>AYY6^027LSq=5 z^B$iK5^9A?0Z!!zL0=N&2=zafy6b11M;j6d>Kigfx1Ie(m(VR2FVojqLU#Byq*r2S z^dJ}~2kmo5^-V<`^`O3#NnO!t$7OhdUcy!C;^KVjmMZWHr+FXUg+J(+;|V%;EP6(L zf^wrwCo^P)&!`a4^&!G=VT3SR7$b}o#)mO3{P!rm!kKyjp5Rm9NUng)X$$S-T0vPO z4`kDM96t%rzpjtb59E!mp+D#u+@PPaf%tp+sVw|jq*vaDFW5Hx3H`?JDF?fb?zn5{ z^kW~68`RZt89l)_5PzUM83J`epYjCi$T{zY1nLS`98ah(Hi7!0W7N4ldPckW9=~yN zqaJWDQ$Sw$40OC+7%9MkiNa)IiZE4}9>%or-;?wTXW-8WVVHp5DHjR^`h#}DL)uQ= zk%i+o_3Au6z66jXKp&88SHbBTx{e;@2ymiGz>WGy0!?Ll5yK=!WA6RTvKXX-_KLfx_9@EVq7`re*8Qy;!Z8(mz5 zO+jv4gXX7!T^ExV3(*r9FOEkd+V;B zb{=g=AgFKXGJV`fK*!NFY;K7FFNh83qXwZd4F2YQ`pt19L+9vfv_N_2&hh9o>gwtX zH=MnO8=-^wRq0b~Zy0cVTpUu2BmKxfb$XaBHW6ND)OHjwy$SN?`4d|ofOKFid3k`N=%UuOue zzjWH+!_}8E&|Sync%3^xhyS9!^@8Ivb)FOk=dP}eI)_7Wzf?e<;WX`!5?q~+reD;F z&ygW@>LtJr%E=Wf1;>wZI!C{e+iYQOM&`UHbMlvb7Zes>_3N_o+tvflGcxBs)w_4z z<@z2xnJ2(0I6_gN2ovcf2mC#K1?Xq`4340CO~OC{Jw-oK1p12@3l5@3T=Q6tpf0-lQnssaiO#9- zPyt^tUZ7s+BXtCvPZiKH^c4=FW7R^DfR5oiqXp`W&cjD1FP$E81nWfm;0OGo-N+F8 zf;@%`*pCT$g_nJ!vikllg9p86=gob^E?M}BEjw?6U3%^|Td`=HT`!KEL(3i zHP4&)vaWaU{1y7`d;yu$4(g9TLf-JNQpguF1US-1p#I3|4B=>P(8rxegam^9iVh%4 z>^!;=67bnI0`?Vdp!?|7ECGK{UxA=qLl@BjeuKVY)3EFDLQjF~94kMlF9`Y$beOU; zghGL9qU-29^@Rs;*|XJpb#)DL8jdsw=x~LQE1=u(&e>pBXRaT41nUJq_>JRirp}85 zDy$LaAnH$!00Z z8?3zIdCQZJ5l@z@EXNUi5gc*#FV}gVfXpM~L^y(7a`n||=WzrHAR}ajt|2$#6zpD{ zfNmh;DuEmjAC4VH*WkvyQ0BZRTui{Z`s}jsXVdgbf7J`M0=f|r=&PWvaovs{uFmMH z^Bvg8WFbdzaUi-v9pI|-bMS%~Wq}aMY3wlkhtudWJWCUhMQ;Jw9E~6P*wZ=W$@loa z<87+Wsar{5$u&<6uYb|5U$)I|ywq%bqgh#@S-&K+_*k>p7_*q(X1#iuMfGg9?%fYq z*RK1mTekz&y<4;O=q|3Lzv6sJBuB>R8pDMFg5wBnz;?Jc1Z`6%Muvg$=ElYNVhF1lFX!yfay z{sKNIB)|{&7xeY|vqJ~34J(Jt!3L9cKyX`b1$yQgoMPO$E{4o>1K9S97ZS zZkbjVw+=MsMZcKTyUS%s(Pu8v_u#$LuR5KV2(HdCI`1L0WqYZcs~>IbDZt%CA-%lv zju%HZuC=Q!_IVLXH%o{UC;FK6?$sx3*}W+9Vt|68%fHgMZx!(i{BZsQ zJLdS|`bTfI`v~eEbw+2=-6SE%=LY@l`3~{oTUSjeu0G@IK$ZcB3XnV0A{_{Syze_19_CS?ct0XJPebb8p~9@teFg`PgfsOSeCgh!*?LO8QSvQa#gU#pwmFVmrfVQ;{5JhG zLcm7g2c7I)JE#vn1dg=T7JcO(_Mjh;4{~z8qp!}fH8}$MK`f5G;0vbqiY{CVHztf) zZ?ndk$yKh0A-8!SfZkt(Q_nqC}ZWc#Y zjLxxh2PWId!sxH1#dam`q734bY=O89AAm1tk4`!6AX_-nt+@EcF-65M+Mp_5X2=U) z(M`NKv+JIA0DcJieow_*y%m4O$mewLrq`GaVV_-asjh`@#}Cq9aAdH6Ot5ts0=Ca_ zJ(45(sPhO*fIf73Mjr<4FnWy5L9gotVvfne3}UK=v)0>4`HQrE@WPJ;x~t#lKVoI# z<{mxFx^z)oUH-gfWGuKqzeRV6fAH~Ki@rHlegrw)TjjvH3;_;eFNX=ECzi#my?suV z{nM?}?cTF%?aFcacG<`*TQWS|E*hF@7Ys@9fd5!AI@c~6k!6bp^|P6kv40H3b(^j- zDg^8V_M#*F(APcxf_%NYR@OdvYbf-xMN6-{cbBZX?Xjff1J);YztHTVceHGbI74jJ ztsC*wp}gs;_dqxOzNh3KtvscVd=T*#94Rh-YD;vq$B`MjF8wuD7%mJDuywftb_5@e z+=#R2d)E)>MCaj409iOaLr&OX^bGl-%jgES2j79eo>o+P?a%9nthL6$$|aNOOU1|$ z{Yc+M$2417n!Y3c#Pr!zkXEb7O8- zImiHhFirul+v`8{Rqvp#aOAVq{ntDf7r$Qdli6j<_uJRLZg$=E8n0SpHb&!B{p-xK z6`RJzD;Mdj_^EfZ$C0jGKa$-EK)mYKU3RF)KI^6Lzz@FPRemI1<@+2dT&ior5pt2y zLcM^kD-~Qn5GT;*#0~gFI6{3p+8_GK-`(NlfJ~4N_ME&UsAuGM*dBbx)QqeJkJQz@ zXv5TxsTybO(UV+p&tZK>zhMt^a?Pq0V-pA9L(Mjp=T7_XuZ#(dL8iW zS$=`pfPsEL=NGFJZvLu8znI;ud62=1T~kuSenj$YjU(ORM~}Vg3qL+f)Yx#G^1yEL zBjkM*6}SCaR}bbQjru#7i_q8DE9@e2gd@k=C;I8%&EfTxT0?AuOt2rp7zH0pjM5+w zzfLKuxc$%N#TzUqgE4uHp&Z4g(O)r&ud=c=o;ASl=akf!t)Sp)e7%c#@#n{CtEe}> zcXcP0&Jc|_1e{S)lwDJ6=RGVB7yPHo|0#a7GYGp>{Gcx1^~yL;hKyWp%;8(-4r zQI&Tze(2*49j8^-K6GQXcv4XGqI~R2mX)*4N=moctXXEyKX3NE@0neFwc;)Lk!1Pl zSjA7h#1UlPt=sN{kbUaj10S+iV_EyHZ{KF``)~w5f=vo#&3{a_n<-2dhy#WT*eU#M zwm{s7eZfBBi;*kxbvmNcf4GCTqnpSAnYjGc`HpJ6*D{`~xa#4`%C%OSuUsNp{nXPh-LtEhcOB*vi|MB2OBkcb38@xPZYGvQ=t4#Re#;>rmK^@Yc9X_1y zomNxx(8B84ho2E%O_N_KDA;C86=SVh<>w_8m73#_Um%8x!Y(=4BmXdXuSd^4%0>1o zcWG|%J7=8X$F<>neY$EnQE<6Pf1P7bkeh2;Fc&%2{!wwC>ceq^_7mgaJBZ(rQI>#? z4HWRj<9fvuUsTioVJlKD5yv=5&oDOv{p0${z0zMjqxLGsY8EfBeOeol^^)?&oAE`? zM!`?&($Rz85Cc$m$8F+hY#}yr;NwbDF7o;y74_bTm zY?=BhO8pqE{$y5 zg&M1B51jw_{J289_q<{D(Bjdyd}NNzt&V?7WnyDpF6;Plto&9{haIj@S~!xLy3M9c zF$>U; zVTv$bfFs0NWddWBE*HUv;FtdqIpX@k`3`Iaz61Tj{+0;HtWg-RocxBe@)s>P(=1x+ z9uDi1VE=F)?xUVj_>gIc}ZCckf%NGU4MH0{Tr|j^%LtfM+gmB8K+3-9IgA z8RJ&?kBh|(#&X+(ONg)JKR!RU!0tV_-qu_^(k_+%XoVji*Z&=<&8}|_;mFjfX6K$~ zHf*>*rqx#*iH_MXKSJ(-%nzc6&ZG2xuiksTI4f0gE%^&`BY|ARab%1tf*q_Ch#7JO zAh z_S`KWzgsp8Kfh1*?0}tinjZtJyhxj*w~pzc4Z-@;pV+=zdgldfz24}P>4 z%#AD)Kd!`oh##vjY!W}RY-UZ|?^JF`ApRh}I#K*k(Voq~FP&apv*x+X?3XN6V_0(( zW1X#dYv4eCK8ZX$I$Gmak~N$N!jr!^5+e>JCN^tc*7rLHa}jUMmt16$&?L~`s_=I(q zqdCL*^UY?=FsmeASANl_&jHOV?eRF$v*%8|I^aWgd!NN>UcO&HpCf%We;CL`mgpMO z1oFWKVUU1rED#tc$7Z4%#FEbE|GjerxzndX+sj-8@*p-rKFDc=FbUt0ow>o{WvkHp zgYtL%5c%r&ORruZ$+of1MB^<{8%%S?zf^f}gX=n-qAtgB1lxd~_7dWR453)4WBt@+ zjUjKY{1Wk_y;vfCTq-_XHKEweYF07aX@^? zgb8Mag>Xdk=6&{y2ju0EeX&#a366ZE`Sb(c_#u9Td0OTt!@0;TT_-r^%a}~LkRzZI z$klNKdm8j3!G5Gq9CZ4rJ!nJFchJ}Lc}T!_Fy2=$j7d%&dp*7*gZxhGM_QAAot9kHcjTv@{){%4s ztjA*Q)zuS=HGVbB19K-~|ABuxnf%b@ymr!GXEOHNtM@jmt@UHA#zwPD@^$HcOboty zm-=YOp@ZkGc-qQ7`fV_jU=bX>zgI@GQ?_IK0AL*VQ*6y~%RW5dQ^3f$e))8z6{J{TX z*RzGP@ujg(UM#<{Om=^X@{f+-QpIE|Mru9ElyZAexyL;V&+_L7eSVPt!w+of$>N7D z)e>i&QC{`HdCZNZrERk@W6UN`_H&VB&B6BVyH_01xRv_B>l4>EdgZ-naU@PWN=?<8 zhVVFXbhPf#_19>Ti%b#52~7g)PZ;ATpTq9pM~Jo1nVtf2M~Cnyjw|?c5abKzL7oK9 zojydq>L(}ta5{wzr%kjG-$7oUBM@_vcQgv)ic7Eimr&XU>!W$5UI95r%ALQF{XuRp zma@MkuBxoOf04>Veq5J29FN1bg?3=i;0JkgwopE`qR$T(D^6M_bc7px*YV@VX%)8S zq9(h0!C)`9pI92ZMrFefbj0z)wdr`ZOGUSOP`+#P8H{Pg#jmqWjkiyqt~I~nNrBe5 zB`SW3jol+25aVLEwzq)4d-vWc{_M7d1jSj(L-@TnFQQx|u>J&&j1?LL^dZO*#(l9v zltsFUTF_qJi_jrKT!Ngu}NjIt91>RuOd6HeX{tWOSR|?*Yt9c zKCynjK69q#MHFvkW@`Oz{C;tSu@P(*{c{k#d++ex=ksLUZ-NhD%@1=^%&iA#KQh-#;9baZuizBXcKre0!HJ+&6ewT;=S7 zia#y~?V(I;6>Xu9@c+3&CG+NtT`g67#r#J{z?kqAx=)z* zI)M(HY<}pHEqZc#e(6=Y|~WS93H z;;ig!)A~5wqtIRV=6dT-3YO_Q(*?&7;)x*w_Onzd5b)C>0e=ctuub@HV$UFF@G*`z zaE88uGmba(pYu0C&R|a+P6l6`K53ug%<@g3aznWC}vURp;IDPQ+@ zZ^_vqI!1n5{lT6Zj8`G&(#qRLsyw(z`y4-YdRz|5qg-U`;zar>FDIe*NjqHI&nQ>y zN-h$w`>43DYP`mL%XQyB_aer{?eY4AKI+w5_AQLwdX3h5@FyX0zv3+a{+t-yf5<&s z<>j}oQ%hzGjw8fcO#=E+ClGI8Pm2X~2cME9goF$MAB&u@S8xVD6DJUpwdQMD;|w|q z&>x5P@g7yBh@gjul_c&wW{Y%iud08$2jmckX12oZ$ts zX1&~JKg&AAm$i4<>gQD!*P>0w+jpqQmi9P)Aba{Ge@LkJqVqg{WXOkTE<@aCFD?^5 zF4sM`+()%?POUw$Y>eGDyT%r2U3`EaTnqm}`yBUmdeRR15}A6oj=4i}?2yK7S*JB( zgvQggzB(yMYk1*^Y*%zNetug3+r9T=V|Ta2S^PdQ=6jpUcO03l^Kk<9Zn%Ii87TA@ z;7YlGUqO$G1UQo`WDA)>hJYQ0H%Id|ZTXoXUue4neSkcG({=Z%x7s`ok*B_mZ=;W? zEA6Nd1`D)*B5QOLS=*yE)Q8H{$=A0(F)`SnoffJ|b2}_6dcLlM%sy#; zs0yAQAX{{#D{)p-l;Wc@pCiOup-{8(@V)AvUFsk4BU=3z0Gx^GvqK#ENaI-ty!&~X z7jf%P!h4s&kr~2NVWNO9K~I{5;R5-pPJ zdu&GbIctgv*IEMiJZl|EP@cha#|>mlA9U@ixau^m%@wz@3zs4b>drOY^>upO4p%1S z(;j4pOtDV|6H5C$eu>7RmMcHUA9Mt8>I&uNSLCQcw%I@@y+pYU`_IYclS$jxarM(w!S2@%hPIF!A zal8-Lwj=UmvBs=ch#zpIBUmv)>vl(LZcuwT+_PYi_%TL%VwHRRC{F2#txOW&2W|W$ z`Jv0V*dFBIjrp>UF!V}f$A<@@zx(vruKRO#D$d%k z@hs)*IpHzi9PP)HzwEmz8^1YEm@B}OnF3tFr+`TUoEa~`nX$qs0p5%d(5>M@y#Q~B zRUCI5Zz}a(xlk-%U-N}rAzR20@H6;s%wL z$LX<7kL%&erCnSL|J&j}rj_^k0r@z(jz8!KR*;+Pev#`Y71@2~4Ds@h8>g1({_`Z$ zHL?WyCq_8YHb9qX*MThPYh=-tT!giUtYe%o(QN2Y(|xZd)*y%lHm5kF$Yj{stH z9vi#e`#d#uzvb%wH|9pTcfCOOPox_(Yg5yk(H>35w z<4u#!8-#kn#b|H_UqgIWB{*MGr1KzOLi(Fn0lvT$H)a;e6?_3a0r&a9!#%Oc=v_V3x*o`)ECMl*Vm?GIZyCBwtUKaXXd&X+4kTnOLL1`l_PR z>#!a8J?i54q0{4jw8js7Fq|(8@&k@^1ecH0y4|t4cKzgHTXo)0ds6Y$4Z3$d%nxKn zf1FDEP<1>z1V`xWZpuYoBX6uxe8s#W_pYa>A5edNq+DaC{Do|sI1xl2jS=_lyF*;~ zNZdH!<@emndqx+HMQVRoJxk#VmAz1aCypzTe1S8w!r)&h*#caHdiy6H0^vAy>d=!58|Tn27#C7h(na34KQ=0elH^#&HK5%jej3 z>@4NrJK!h2u8}d_;u6^k);?#CD_<=9zD9Amo z8kgtsWAz2Y6kmvKh{F}-^N1aWj zkI>%}bx=0IULM8|+4{FXFF$a_D9wY5BOSq&;>XqE2m4e%bWwvnv2>L9l5ewW;$GIZ zkR9^G=D4<=NI$8|bm%}P)W_#Yc+9s#zGIxmvj*y(!%%3y{0jGiXnduwd`7r$TV7+~ zi26BhoA;eW`J04<-P$`__aG{kt}JS{y6W{-SF_gY>hye`iYMPa_)M!gPana@EL5F< z^EHk;#AiW7@@A$!pCRC9f<9(~{toh`L4OYu;L8A^R&c&0$QR-mjBsI0vEPL+f2=qk`RCt7Dt z(>1`6`7v5~HvH%yt{lVIZl2vTz1$wTxX~V8GSZtX4D%yH*F2T^q3X5B<&ZJo;qo8s z?NC+CTKK*44_aTMaZ0$*M|~R!-j4)vSwD?&)s!8uvy|I3X^v&YSsEuBy3K|U-e80K zueX79;?02Pbsg{7R^eyC&3QWDZx*VKK^%=ULB8N?BKblt`e z+iaivoIl^8GKlH0r(Fbe7TrCO$5Hulw)TU=58y+5_*^;s@5uL+dyL7^{=E5`6Rfbu zmW;5+7LU;WC)uAC|AEYr4fctCI79mcJs+nzTlOzu{YiuJk)mSu#oDW}dCl#{!2|K5 z?*~T(-vN9-KK?^XPTX#(DZ4F{vCs0e4_H~j0jn!NV8gWjYxFRUFN=?3hi|i{vo_eE z+VwV|HtcW8gZ{>QhN6qp7OK7ujx%TLJ>YyykT0|JKES`Y+<%hJiN)ZGi^UprUN69x z!2&T8oPh)Q8Mx!XdwlM=F^)0aVy(4`)&5A_tK6ELTI8a8a*~pFTe`+KdTTG_sDpVq z@dm!*WaXmgtd z&_zIEOhtN0f194@m_uII5y$T5l zAIiUMxAe5#mYuoJit`kYl^n3aHO=1h;l_wJqcwLqYWM~lu08*U41zN+y5}ecpF8Tt z$`(qXpf$e0l}NtK)O&D+SS;vUh{Z+=jx$X<$Irl>VG-bcz6;MLD=+_gmSU^k+Czc) z@z&(z$w4+FF=>bAo6|H_$bJj#^A;G>Jz2g()%J7|9r&DZSpMPoapmZ?`EbyuWQkK* zc9q7i;KvVe(FkPt=&?F>s`HT?zBXLfrY3)GJvEIvUai5B{quZ6-}jYg9!Ge7<^%Z| zL7a&P2}0tBx~^ih)SVhL*lYPY2dunEF0Dl1I_#Zx>m6SB<))LKm`21izqZPS?+l3!SmKj>})=kfZ4CLkL z39%Krak6YD*KvIx=|2kaA6F?(avVYL+XZpz8pd`tcYe?OI(v4-cw4<_sMg4b*qiz> zU9(U~7ZQb7!EuE4pD8%5FhzHt8?6UpjD-5EuWxcg^^O4?NB!ByJUF@HM+EGqlh0#F-NLn%eSa8(OFO%ICqC z>dIHVF@Q4VG7)@nJaMl<9}^jmIo>#51AhR2^V!^@(rbR1p0-}|dpvsxAA7iLkQsbW z?zcnS*r##b1Hrr;9l?g88_s6x^n@Qy&(J}~4{SPP+&(|XhWUXX=>V?L*wqb_wYFs8 zKzsi46YYWXhUos>bZgRn4=S6nk6a;5fFoQJ{~0A92kHV>j>HouBkF&$4z7iq@Nvwo zze->8{GCx6&#KkjdPZoE?A=bq&mW$2js$hi=ga%jH|boW5679*ROK`p3m~VdE>&!% zakzn1dS*tAp10J(m)q94xf!)}q2PEDe07|0uP*nGd_B8R{?;3}(q1FPlEJ!iPJO9s zqHIg5a;{J&d&q?6%d7AIimvZsEA+wjy-rW~5y=nq)A1vpeXp)o9&xqjL*PmKz;CV{ zpKmv5J;|zb2HOjtpX9xAPkKXc%t~FORwxmOv(klRAzr{vIG&J~5N`&3it{H&@+tcI z2|I$a>QY#G`zYqt*}s>$^^uxeFOz*vS8kA;vR!>mu1(*+cZvWV^pPOWfTZLPEnPk@ zGdy-yl7B#B&duI4vCB&|H=}u(!lH*;xYEj;|3XO{1bK7Fd3xr&Co{8@mut^r);+f- z54Zt;llyJ=Yz+K3^GuhQUqgQHVk>OZ$+U^OTuXd~9y)%c=scf$HLe+#BaUx#3qew}Bs;6sLLOers4dzz%NhF3Xt;<51qJw|`w7_XGm z0#C<3KIh^S-cyWzSfJquR4EVDawsQ>H94&>wr~g{JOG8V-OYV^<1E}hvfP> z`Afd*kdZm}Db`-L#-E~+tACZ8xIwWM&*Z|d9$I(m!S$1pw|a65Wis!oI81U4ueD+f z$K|K=`HAjhUE+{~>(SqiAJ}m8G!K4U{W17)%d}GE9cS5>zc5+P@vQUsQI*p3N|oIt z3>5|ll|rdNPJ%xP3B-4iJ_Q>R^eMsE3%Nz|MEM8Ua{mD&BaU}y}_oATW?dwthWiH*W2)+Yps9vT5o)rJVreE zykv7uVq(*s++R*?#eGhG9CfHHT>JZ_Y?JTU?X6eqrG495$;+{c=;_HmTz|t4^bdY8 zwv-D$u2r6WjpC(_fZyDpv8!9Pw&Y>0z541^Q|(^m>Fiz7FXqhiRW@UPBZc9@V4+T^ z7RXDAg*+i!AoijzE=R$ZMDnC9e{#HeLU~SRXSz76kJe1E?}>}E=<5_cPa#RVi=B2l z=;>ZquhDVz0(hK|-|=;1kJi%5hAZC5Ri2QS->fxX_$Jmm9`HWP&el_*JNlPtBOj0Z5h5J zi`Yu~&fK4qLGabdgZ5`>%sMTt+1m?|@nFfB7y_N7kDU$F=}A3W`dU||F4PIzokRX{ ztzsqOrH27nl`5S( zp8{7h1#)@n#k?XMc6mxL_QIziM<+|{ywhi1kJsVK%4 zh>za&kRYyL@8M2b`VLFWILL|of_=IVtJ%x-$Bp-&<1<714Y9Z5oVjMxrXQTUXKu1a zd!w?RxLErL7ZkE?l5sTd@7?F|#&O2^8tTFIU0vGy>ebn+_xrj>Y^(f=d|UwRua~a& zgfcY7t$iw(1I$Q&#k&WVyrY+%J;0cEz<@k={ z*@x}b1+Ix6!BKP#8=WL%!;kC44LH&fTql0qq_L}&;>V-#dQUQ?i5%f%va2p5TwsU*visc!Jz0o9lSvS==ka zeTJ+*AA3{m^~|mKH?=1s z_Zbss`fU%s^8KV_#c`=0da}yO=6N{&bJ0pmZ(S<6l6w-@xY+8G6K%j1W1 z9ewWzuGhM&o2L}p?OJ>F_$7_@^=qcteab(0USU%2E|;n7c>?3(%rn6g{K+K2`IM15 zZxEbMA(tmlDG>^U93evp#$L{!-~$;ShVQ`~1&$nVo=_ef>{3*E=Sar0h_mn?{=Fg^ zgON_ArfHp(^dK<_z4C!xpr?FZs+fiRe)b%*MT^YNImh42kv&v+*40fn`Oi-L%2&*O z_A|4WUorddznZ=Jn%V#SKeIpm+3eqcYxYk+(Q|wCod+H?`@&Uve#6=R9RDEA^;c>P z*YSlh1jm>34DuP(&*KYqMDGvQvqR@q{M~-C9dH((m!94n zelFUYHzZTWQ5nB(I#ILWoC2lYYEu+5oTpSYnTyl~$=8b1zn)8S+nj{FK!`knOU zclymb#cAub28q{gR#c?>AoM-<9$FxuapR3<&pc!HufH%`zus))MzhUZ{O7>`{y)rq z@I$l5pD?@r2J!A(zh1;|XKQ`gtCg5&%-kBW*r?^bWnkJveU$0x-NUAjd_yf{IBGo}hZ zLfq?j{e(R0C~laTZ?{Y>wmW83*b|Ez?Hkulv-=nL{-Ytk*Z0JcD^xxlIXeu;6~~hq zdLN%MSs?xzE8tUx3&dUn1!6CF!nhYa$rRuTzAsK7kLo3~*PrOC$8^9E7iW2E7>Tpk zA84ZPTgP^1=P0hpU|foEOxfnJzHsjA#}3){172LjKE5$p1Ihj#nVILT&dOSJe_`S0 zpDQiD^@o+!cmKYs=D`hBHEZ5vjZ1dUOUeh(T~lZcv8HQPg-=oACsLm)SurhRh@ml?9&*)M~ZnELu2gV1Mx-U zzaC!>*59=w@--=WOAAN%UF7Hdo!k%m@Sg0!hib=e-RIAG50u_kk<$WSTHVa6BQOZxo2V98X-167(nJ^6=zH{sg&$$oxcab@*uE zNHET7kpCDrfjpY$)}w2VBU{81AHI%kmHqrk{zE=Qc|&ZhY`S8#q@=MosV3M6+FUQx z3FKnff<)G|R#e=5A$x4s^k4IH=JY+@==txN+3WPoAKgzf-0b3u%^rQ!>^Hyhc>-VF z+F03R!>Fd&FPsdWz-uLvbuxP(GcE!FY zJ$t%6e2Xqond1c7Iz+%0&^~-6{X{%Wdx#-VFRi^NR9*M*(3;vuzF6J=k-s^3LG~s_gL#28t)c?S*B- zG}m6N`9q&8C5b)m2y=z_E9g@kPw*+&RrF@GfbI+v(4YPSJSi3O1$dGsIGzx91$jc7 zJ>AkP{scV-&Tiwf#keec&E*$Jr$Qe}FVH7nmy-K!7GK_#p1rR) zW2eSzwZ=oXJ2}~ZZd)j8!6UjlZ5<;t2>1}%M!RSeybq4^xHh=@oEGE@oXM7d$q4Zb zMt_|?;{o^I@AHK??A`bLxa>dv)9kz7GkZk7=bCH%F*3#x7@PCQl@G|bh%0%!rRO{3 zAK{94qV~`(xWcPDciicxwx^`N>wQ00zh$p{Vygn}-J`a^d2BTOg1w;~pY%Z;kSjJ7 z`-;p{XV>)oE$emh2OYspn)|p#{^DrAfhT-#<@6GJV1Bi@GDv=9xIJ|40Ij3X@y5CW zKE>rJE}wTinW}oCJINqsZRBv6j_JMj9LSMA?ZQ5c zjA!wDDspN3$bf8cD!P#4QP8*J@SB@_=br1b3d|~}ydipx;*X8>c;;|={qx|k=vki*FwkY3! z?RB%?{?6JUJF$!f)VL7w_3Sx+jgb&He-Y!mP zJ%?;G@mY-4Ayrh|_GgucEx=zk3bcv#&=wbGwdO#y3z3k|B|WkvXT=2 zxms6TVfK};Dqs1(W}7yfz4MOQI*pZ)yAX@raHGc37W!+@n0qNJ7gyvf(SO?1!V|TV z_NJ!cJ3jDiMV?|S_O=SFC&9PV5A*?g2|nq=@dM5h_Yu?fn^G3L`U>rXc(ZtMGH{D{ z0&bhC`$lGK?)_ZdJF;Y`tzOvQ+pF|^&7Va06vvf0sxNaXF7CqCGUkQ79WD@ep;I*i zdX+C^2`)b&p2P;j6YK;1gDir+#M!d8`isx`uIERHv&bdz2h4$!iF+UGF_~t43=$81L=X%l9FHTz$049wyWZ#RBa}5~x3Qcl>ts)mt4qoPTlo zOOE&w3dz3LY%`u8bh~o-mtK-jdCm7NZ)%JTU-QjxDNb8ucIjpQTt9P_rDfWKBo$uJ z#!WiMSH3GBgRfLvrgf0)Z53WmLO;+4t_^L;x?>GH_HR=U&*teBe!$_R@kOy$vM2S; zlM7EeZqYS~(eNn`oLy~CUO3pESv=Ic=jy_;`v98b`9r*p{bNPXu%B+A!88q8})W|c6HHP$8>nV zuj;?19$yI8iN%=dE-{ZR&bm+AALNMjP=n;J*Wr$k59vP!r{b;MX^^b);$}ZuA;A>0B+Sa0XhA> zvn%Y8^Xlx2mz-tyDZh95JUofu3jW09D8yZic@dk85*h^jNu5C4RVt95WD4*ETkLp3 z%;k8}k(kTrrN-enGV?JmL<#@VLQhxL3a_vJ^RlDYm;?if{ zA{I;2n#9V=Z8lB$$c>7%R^F~Td3;4A)V{RzEuN3e%irORTSe=+YQ$Ehr8h6rH5|XW z7W#N99YKB|673^YuAJ)x5=m6HKWW{hx3$G@+~~$aKV7&E#cT}h3ZZo z4;)XNKY=I2T_c3y0=X_csSt{UTp?3H*RaRfGx`jkpmWYHW80kWp+Bu1jw8smWz3iT zu4m2i=dsB}ay8}}%4D959ONDGW0QOeKI8-CynEzBn!Wu}x}4#1^}@v}k9NRy{2_5x zp^zcq1EU4%>uj*Ar`|fIgLcpc+Kvp6hc|z$*W&ch?2AjvZu&`O^#dD2n)C13gMGo^ z`a6dqHEpxnw#92(VG-lQ&E9=bf!GSY!)H7B>hzR3kOB3ge#kezEUo7tp09T66xr|& z;`ZsKviTb0RW8xd-?r!bluPWjDm+g7)P)1Rdlp;CQ5;WZt4%Y6X~IMSo}gp!1b@P~ zFgz(1@FyXG^~l@N-l%b{qT-#(*SE^1 zzT2W#aD~5fazE5M!~NcK*%|LmNqL2RZhoP%Xv27+Nf<2PL*O=XR-8axoey!kMqQ5O z;CDg2AkV?a<_KJOkT4>z=<=_m^joian*)dO!f}Om!4KM1RIGi&wD((JtuEyTV?%g- zDjn3v$pJk;&KW$<2Akbc+%9h1Kd;8_R!nre#&C&`I$B11zki3yzkhC(<{k&wQx^{M z_7w{71b;GLa6BRIa{k2eWQ5)uCeYW|V|ap1&KAhw;R*hPKE%c$AMA+Z2)5-&b{hTi z?62GJntgg$2haE@>vr?PuZ?1#BEXggSElW8nwC0q6yMqwUxV;?R77_!J*J8XpiP-@!A293O(OzF*wz z`O5r)9cuG_Z|uR3t!`baGJ<*evDR0`oUp_31DVqQ$T)3&b^M#m@nNq!0{C&C){;DY z-e8SC4e-wIR9wXS9#=Y8UVE+$5AT~>X^(2$>#2(ddpu#ya3JnF8c#;6z1ZV=0iIL~ zB?5YY-k}rDmk`6CD{zFk!|?o?&l?i1|Uoo6*NFTODX2iudK^S7jrpV?fN&^$4<}qtcx4-Ez^3y*|Yszq^w+fzKIK&S(*pQAWz>YAF@gI zc8kWkwrgzFU%%M9_aV8ui?i?{E>|bcg3H)>Y;rfj=^gdx$ierq<@_G~#eXtqkG&wa zBDV8ms}#jnJ(?qUagZmjEqVDLdgI%PNqW8k_d!+N|5cTNuAy@u$JgoSC-ex)g1RD$ ze#{YaZxp)h;v`S6;mT3KcZsbY5FcK7e7XJP_OtDU6=Up4@#T?4_>?-?`YO9~rhG~` z{yJKD9sLY`5_jD_AxCiYCfGga zOOP4<#Q75R%5fz4ddQeB&r6u8e7(ubMRtfItl85zZw5B^9nYWOS4v8Edp@MFDE!<{ zJtrVK+RN49HFYIdC(eS)=r1_}eTZJWdbxV&tu~J!r};fxqrGr1Prz=}3uB0_diQLW zZ{uER@zsWeM8I2Zd;-uUTSWziN^_v$W|jpK_;s3S4PV`R)DA9jfo0 zGssWmPl&t7PxQ>t2%fmyWVYIjFPSP#62=Nm!Z5+bTxB}X7cvEOg}em&hrG~5XRn;znFbg@F{*( z^h~{KLDEsXTE6wafvk(4g+yC>c_FrGR&VF$7YPa0N1bAE_P`7@9i?gT`y51fgbh_YiS-*i_*Z|7I zH(?_ViLH7??e}?+A$|mquJcglJBk}Od+jPM-ygM>X(^KwnGC_Wh z9|=u4F|#~=NMEt9r@0e=Ed80!kgTqE`OZ~+~x70QL6FCi~xT%$E#;`Gw_5dQY=r{a0* zjQP%+=RXUyqH?!%iS@i1?~(t=2yK*pZPHxHd&<>!Ys^c}#?_u%XP&9&AsmdeCaSzq z!Z3k&5dMY);w*H~*=VPS)Z<7;P#3W4F1Era(cVe{Tj9r6QQWh_p3-k02I>w!a&q5Q zUcOzq)PCz3<;PY9C10S<$O`}DQ^Nkk_N%8JQ3Gf7t;7iC&h`F3EY1H|VdGB>7ha9ibEa75J69ZGkD!uL#z0xG$Xp0M#OFvs;Z}|LFrH=F=b3vG z*GA5XjL@|hb0t405Yh$WB77S@q&;y=Oa1hH7hA!7_(p7nZD@#$t&YSGxJ_Hi%C+~L z_D1ZX^=N_npwKhyG5k1HxuL4H#HG%s5=-No)8^I2y+Lepx9l#j?FH*W@B_~*X%s)^ z*|)EmtaV&P8c!;+@7^%WHvHmo+wZwZnK}=vB17^`Pf5z z%Bp$QEk32ab!h8*v8vR#)dNU678>cO*XJRSe1+va+{fi;Ib*AQGaCfA-_HqzF8{bt+w z>aVPM&j;ek9<#k0Z2z18YMWkKW4~T~v3>KZiT3Q$Mtkz2p;~`6P`19-8^67KR#`jh zq{y!H6Rb-G7Lan^i)Ze+kf?Oj;JI&kLI;K$q2wRaSIy{BCLBQMTkFNnT< z-?F@dhqZpOW$norl}nwl^VBC>K)+p_1y{K~*QU>bJ2C0jRf`0%-X295Ke1viQ;`;-o&_7;2v|X!L{JzseS}yLto;P`!NT?{k7QI zgF1O+ee+|NQcs8B$J3V#w;$ay$G(5#Oz*zi$rZ6bR=MR<%Hke`dzaLw*_v|(+1h&- z*_Pjb!}jgaO>76mlV^Wz{Z^57{})h4>udyr_7qm&GedE6@YsCGJZ_bg)fw!s`7{CMi(di&wc zv+T#W&QZ=@Y11p?{!`_mLwQ2#*plc8b87m&uxL>7t5@q8x8JyWvc2|`Rrb-QKbq~^ zDW9_2Y}a3H&${o~|9)qsy>!)j)t(w@2<={x)$+&8D(9@Kq}k819O z+$SRD!k5eu;0gLTNf;-L5b6czONw=#BV-89m-N;-`sv~=_~F@W)}N4zu>OSovlgD? z?_X6~woUQ-yPoejXp=W9p5LMUQ8XqjpToMRaIU^ojb#T7S z>1L20^gnuw{(3QlUULQd49*=MTZP^dM-C#C$-dni<@@0B2U|0k)vgejHc^rI9d!($+Nxh`pZokMmrwGsO7kXbl)FE+sLtDCHNuy; zn2WpwUxH4K7SK!ds8%QyXlJJ2@&I&$_7Yp5ALyf}ldOf$%znwccW{>G*5SzTh65V= z`9K`mESM-g+yZ2i2z!>u}#X44GN*<880brDY##EL!7M;&4Q4g^tl~ z>;t-Ysvp!b$PeTbKQcFF#-$Az9xu=v#}Q|1kM!#J@%RNp?0Yv%_v}78EI(l?7u`YT z83KNv{&Mm|T-Mq>eb*1Grz4_Vvm`xKwkN2+IQ@6*ovfP4~p$%D$@@g=%jg0rkPh@g2UK zEtClZgeGFEVm&XdPxO9Wi+ceN{JOqF=hwu45v~w>eN%JqZ~XIW+q32WDE4C9OLHl^{>S$G z<$LzmZ{A`*)i~MLUF;>EJfi&`h?CIs_SW0A%i~9wC$!}O`K5;z%9m(7nCJg^bMSf5 zFRGsN1@e;F0($9u3A#BdY>x9Y*D>-Wk|Ulk(VWR6=hTWP+H+gJg#Eh$_by2k2=dr?Yf$NtDaMWEJ9&lYag6sjdojT#y zsV8;}e_t<*CC~Bqo!+5!`Qk|Ts%~B=JF@16MEiO{ez#=76)>Y2j*4CmuO$2Mg27!d|D3259*H{q2ChW z2mA0~Pkr4A$LHbrBWP!X=lBn7_g9r0{OdjE*>^NY$bP=z=MYw^>^yy1^CfU(fIz&0p5i~zL*gB5gtO=PksjnC z?7LZ1crX_kJY9JVvKE^&?uniPVN~x z$4Ah|a0L0gK8Lf!VFd!Q;ZVVgt$c#fZqXC3c#<8wV5iv4u9w5?a?KfZL?2wQvC0{ihTv%EFBlPdcBNaZ4T z?AOYbO+FZhpGG{maK~?}z^ro=17l^Cxfr(|wA& z7JB~Vxu8E$yws64@m+@p=2gmGe&Q3bO9Ip=z}`3vIl1@_ zpReT=Tg6pBwhHf!$aU!BpbbRdK1~Pp1*Z%2PcNY_>v-AgXO-fN2hb0_wg;=dSiQgU zfCl^7%DMJ0;>ZKa+2>TnZ&bPcg(3kvg}vfhToc>UUViASEk{d^at-q+%H`kw`6IS( z+yDAJIqcw?=-`GdRcr90-^Hx=_yucs~|kJlP3)wLsS z#&ZgI22W)bu|07XdB~fx*&7sRy{9v6rh9e>)p`wATlvbIe6QeM!Cj=;oPT4uU=| z(zzhx&JE(pUX2gGW&8g61N-l4h!d{T$w2YQM<$Cf3rR_dOaCAM0+03L)ZZGi7RB3*m({6Y4et0vfQ#E)-lJZX7T zrW?be53rl$sOW=}A@SYE=7-Ag4#$)0^<3Sb+&b6Z|Km3_-lfg{;EC=<`AGLS{+};i zVc)-QihWtR(lhdRPiS2FA^DPywAIOG4IE+KU2}?$Ghd>6l*4oH%T*!AktsTdBj_p| z!B&?E$b*=Nm=oKC-SzwkahBV!lrgOlqj>HV`qS6_HC8pxH(4WjluwdKEPKLguyv>3;$j(jL9op{&k*38`pQQw^lcjAGvw2%Xhpf zPHd3h+N|+rovBl9(soZLTe!;&x8$%8PKaRT`9Zzo5^AUfp^^iN( z|497U>c?H%{$wBi=4tzl#*4o#E`Lcm{L_jBS*OT2LtE{1pZoHu^484LcIMrgQ*`lG zgdc$;*mHE1n1{TeM930?9DyI*$wkO@xnG3mw~e2`eYqcr51T#R%o9gIVG+-udSAKv zM_O0D--xsPJs4Z&)+ehxI5J#tV+HV}LZ}kp#!z8|Fp;&oG1?mgT7_fo`55&?anp9D6mu4{YNa@x$55wqCKL zk89q6_~qvsKlOtNMQk&$l$D`;PLC4|Kh~cKYe6m;W4d=R1hkk850@@;<2p|3_Ph z7qMNjlS}$8U!l3Z)#_vJC*rj|K(Dx`0(<<@9rNrL_nsqt8|22Y@bAPF=mIgflO?|E zM8~P8v36z2uyoy{GR$84!JW2e>wo)WUHdoMM}PW`{o$$Q_Tn`Yy`1S8%`f5y+S~Ru zni~NREzmw-;e6zY^9QudyEkeKIQ+b87xRo$o6$*h6&qe4goGrakKl3z49TOCrL`&Wf@v)m76bq1dylmf_V0n)*x8fOr@G8ZIUGOW zJaJ}Um-hOh+Z2OJov^i&Qgm8|IPtO(@KS2-Rqq8-i z)%gjHRaxW3eEj93vh3SePqO!3c|q%iS+kT>=oCkS% zik>$M7b3xR;73X6+ls5S9=K04sW}7VSWyd_;#JYYih|w_IP8yJa5Av^DW?-aD-Tk7;mxwCwS%W=^1*yTUPeVmJp}? zNwn{De*UY6!n?-n$~)dv*&Dsj(4D&=qSDso%P1B?$^4j zW8ufsdWOgMuASuZgIC6MYEz>wQ@M3Qk&qz}W5Gpa%C%jLbwYiJuHz1mCria$){1TV z)nghDep9|=hc$2frTy*Ow|X4^@?}jP-??Yq_a#TS5%A=2jtsV^6lbzmJ!4y8KZ34K z6h;c<0N4&>6B3XO{uP}gC-mYho+r(Hgrl{NacKQ6<>MR05%K}}@tSn^4e!0W0Uzjd z*4%0@H*ftsW4<0oW~(fC0zV!2dv;m*%D=?*-KN+|^W~Zg%r6i>B2ZZLx~_+xVqEzH z?GvYGxGO&j&v{T!Vu6!s>vXx3a=?#Z4w5jZHvZq(OX?A=r(mv_*M}F-_eaO$TI-6< z{Pq{d+P^<|zWwx8?zJtlk%ckO=^EsNr9zhAVyqrI$L4VTljTEnDeq`m19^jL#^sc9#hyFq+Ypuq!G}b$U=Tq@)whv^>H&|gYanC`Hpud9# zZx{CHo^|%~U8{RcuKtzEnJ>%}<^(V|DQVNzjT=9KL;yzk~}1rqsf8Koa~4>@u|-#7vt4&Bsu!b#kw{z z4!OWEp}$Zf;6upOiL>w_#P$Ebz3YIlqS)Ty`TjPfS5YJ&AT1%J(Fr6Z^p5muqe$;4 zkO0z~AVujAYUsT~D1rzUR0IUV1?j!Fl=J_-*`1rsB|&@-A4GS5zwhqeot?60&Nt`G z?CdP(XE|QQd)@i+8Q%a5D*q5;tax_{Z8~)~e}NO&J5(D_9WGV+4%+${jK3Od`DV>p zaWK+p=8A$Iy?5qxXTO~92y(u9R071OYuG3MqF9?cd$jdin=B*i@L9BR$o4Pas3X)( z?PH~{?+=AEuctGPzjtRaK>ygW13*m?`!Y&L8~luCzb5lok9dKUg2{hsqk_Zrq;FrIms zz7>7)7XjVAQJ<3Q#42>4qkl<$pneG+PXb3KvEGvaubT#bghLND45%mj z#YhI8zWuzMcGE?2DFc*`*qKfA1IEJ%fHBxK3K?^DL;kkRqAejk{aDJkaNfNTqGSV`nTxO%KAjf7Pes`>QT&GCJgUFXQqzb_H zL-)~g;h6HF4N?5SJ~ii_a9yc4-Y{%PaL7Z9S6#&XtW#3Z13p$k=yRbHupuWEZ%UNB zhUbg-Fjpi_*vI$s8h8jC>4vmg5P9;oUzR5i`{j6N9P2JZ6$T- zTkvC5-&*S1Qoe7d>W*~jW6{s%cqV}`57fF>0-?8#o zif0>*rXih{L;>0kjOo6PxmJAEk-y;a1YlZ)zzvVWC&k;B<5t%&Z!uc+%YA*v%tab3 z8|}Yt+bF-}v}qnt?=;8-SMdJW255d{XzZVP7uUy`jC!5&Avj{OBWx3s!c_VasQab8 zs^S^Q2eK7@7Uy4>eUNg8gnKOKE`&TI6__F7-ut+pZbK??!7fUE%R zIooJ*%yj&~HNNZd;)}+*y7&fMRkKXg8R}DV;)W|P zSbog`^1v0;O@i$>^)&KwNBB$4jV{xd# z5%^lO+LnfV430cbE|eW*Nk5DIkfj*oTim^pk}Wy%X1bR?z`ch6B>*oVFQA`?uujMi z`l2amL-@X7UVIn2OhBBJDSH#`J8X#J2z{*MuoZ@G7x6hQ#Yjm?gY{1vqI@mI5u;C{ZHjeI9bmgSw*&hi@2Wn?^4?X2YX`x{ zqVH=R%Y1`*0jztL>v`b^ilXY9vV4IY;kQT+&gdf1=eJ1Q(WT;u=m(C}mie6wj#zE1 zRUX!3Ez243vm&~N!1t^v3p$rq-|4DeINcWHRT(G?=;tBsIJWlFSwGJCiy86E!q*pT zXJIU>cu9=A7C8xDi2V=n0~{#?j(8Myh>zb{^y#mHM_3ydeT~<%{fd6X7RjP)2j;63 zI`#-ue9tJ@ppz=TkKa{{S;eTih-SZ>b*9@i@*_EHR&G$&G$+Uf%9i&;Kb9a52>oB5 zV|&hiL00xbzQ8k&>G&=a+db+4^?&jQn5zq(Bn4i}KFEqss>?TH>0>og>r`3BdFf;2 z2eO-aF>jVp^W%AGi?lpnfWH~p58tNxWm+eRj#??PKhFn8&}T>gifsXP-e^OTmJ8)Y zTRiQf;)oL{D?hD)_%)S3YOx_fkORjtXhYrxIMz!ai!!30#d^d$>tlDY&z(IxzW-S| z4s)|^VSEX5ql%!v0KG2caSS%(82CXQcZh$na~RLMjy`s@q{4ckZ)UqDIo)rnIfw

U_bxAI>%;Yw8jxwcesrMWYq3&k_ z==&4=&+}}@2_Ex&HqLeDdOzgH^wuR*-9D)f%xq({k@T_lj{8uxv($kc8DDOQwCQ6N z0^9-SMV_+WpGRA*B9*WI_>+9D?%{#H2;MU+ zS(@v#;W?fc><09^kjGJ_=bqpQ&lfLw0pnR%`?nk~}-$Gr(>k@#xIN_*Se(?N5={)HmJ-+aB_PeLc3<92a5V*xdw=d7i!w!Er_I z->P0PLwBy%Kz_`CzO&t9`#0r7`qD{b>W4*DAB64d`T=#}W3`f1eX2`GyxZ>gW~#18 zn?817AQxcmgR zV;CjjTLsCwu-dX^a6_5bF;F^SJj>^e*Lp$*fq)+Cb;q&Q$D&>muX;mQv%R@jJy$PQ zEEau?TNv*>jec|#I0Alnk{?H*>&Kw$QLr7q!_T^e^@G5X;%8krVRFR0p7FhXPU1QJ zIXwHgj=5H`cs{a>-yx~Wyn*CqJE&LMZm|4pZ)gjse{6$t0(pV_Kmnkj3I1n0l?R|b z=XJ!}1>Q&*$Tpw#Is4<%;0XOJ%@K@i!PiO(GoUBbmzAGZgZ=nGwhe8p-rF|c2PuX0 zIgXhdp#MO-MJ`k3m0Hg$!%xT~7$^yN0@}x-jI_^B-+&y!+^q2@ zxn6qSyzsFCAHs%Q#CR{B=Rv>83(XP!CrA8?ok2eY>pPS@?+nw|XfE+uFYgoT+F~Ux z<6U3VcKDCo#XJGpujkR$qgaVGzgcK`rPJ!pG;I)k7h3mZiPD+VV#(Gy3P-%-G*xUxRkT9mof;9b%uD?REfA7AObMj`Nsx!7%m<$sJxx_|^B# zw0~5i!b;b}+m}&(!Ss)c2{8>EnFfv|24!A!=$ zu6wpiu5#D+#{IL}tYzRa`9WE~LXJ#pU0QzlvaMWL`I)kli@F6XSsAwWG4g@@X2Hjr z+aB)&^sOPgN4JnQ{c5W3@S5WotQ*z=>yJJ$ePrE+Fn`?^;+f(2ldryd6YYE~=A7Jy zZ8(cQLlpEJ{O}?-40w7S1#ganKMpBc9Pa^|=dJs~h*QKTN`;pyeFf_?+);C_@EzLS z$di3V>KFA)w_`Ybt~b`%zW~Zh`&AinOqo*uI1WNPQ5FaRDgjl1sz5dKnCB`0!9WmD z4k$|m|EJ#iAb`jc4W;6bHx!aw0K~`1*4!IG#H^w(^H*lqh)v>!LhVW4c~mgGM1Qa+Lg_ zt|cdau&m@X%g+8dZAUJ^1E7pK9zt%A4>f_>KwY4Yd0Y$o8i3|YWgJ&DQR%%BZ(NuG ze`zkB^YK~VEcg#I;A8(0M`psuo`Z3nWfA=yu};sr*ZFImWZ76oayeDif*Gpu+0J_O9}eO92z7i} z&r0gP>1RDoMwIDn_^biGzqkLBPsUe{lN5(rdosm9eM1MCYz&d3cqUED`%5o?h z!f#@_t z%eIO2Pyd$pLQogTd+MZy)>FOL`ujBYI!(RTd9nIt4=a(T+d{R++dS^BVeCD?h<}9Qat|*HpZFh;=f4MB2pwEhCO&P(CaJ%g6iW zp8r#EEQ{}gXUrIjIVJbePse+(ei+yFVSj?QfgCVU82`PzkD|XGf1by@*4O_8?9VyG zzm0F0N1JPt3>b?%k}E&hUQ$-nC;ITzGmh8h2k5_+0V)8r599$k(HLj~G&R9v+H-<@ z(VXG+^*mlr8P>Cs;bYNvm9<2b@F`VZ8V4gKrLkMPsCpfAF21Db2|lE3c& z?ttb9upyjR$gwE)yW{!6WAeeu4_?D-ixxkHapKE(K5`G=UU#ldk`L)8#g7yS zd!9GV56X!CX=Z@;QULG=$^n&tT0niEk!RMFgZM2A^LrK?D`^H;xnkvu;tk%PzR3Bx z?N` zBhRUW1UW;UB&eUR{Lvhu4r?xHy-sScuhn|bGzjvN&^%zC%%A08nJ8a!nd1uXKpvn# ziJWOZ=!rS&>`Raz+|zcl52o7@SK07C!*m-$yYv0T*0LGnS!_d08(RqJ)5cOR*8T_U zo%~?iNPef{GxgMI&ZxE2%LLp}HpJJTV^-{!(^edIqHqy%gq%67_PoZ|KMJ$X3{H=Q{re$Wb}ogZ-J2lHha{ucZQDUddTYXmeanneaT2f8}3ze#mX1On`-#h*l4Vy$U3LLOr3YykjL;t_v@)IyGAxsHbl3N=DH@n$k!8K z9Z=V(3poJR2l+xhq&`wVvYMcd64Y1CBkHh*=F%VSc|HA6t@}DXrmgd0z8r&QIanr^ z?QMW%WtquuAD|dHKNat)vyZ+U&o!P@M)a|C8^ZQu&zP2KK2L)pnZ8511%aFZ+YHSQ zt(%%7%7*03`@SdFm3#HoI6Twi^TLa;2M*YUqu>a9sv_h<;$XO6(I||6oyB~vJCY-3 zv>MaRm#|X%qbd-$^s1u}{YH%SJSkOHots9>YwDJ}_FY zuKz?%&2A+JCp41@cn7pypu4mv_2yvCf3}q6kv7Xj&eFcoZ?y7* z9N~Y%hG1Q}G??3)EnBPv1z(2^;kxR0oUkrddAPeb z{|IUSUHC!yu{~s+=PeDJ-w*3%T-w-AVt)KwPR(yG-;8)yHuS41%X*ZTMX0|OJ@L(s z{?+B%k@e-<5%uw&bbxfg8t&vuP`=bFOuNzo>9wfimGKaLEcPcNx&*5>k8PjwAxvM3 z{z774`^a%#`dFI=V(n49-yV=V?I@%h43q=Nlac_rQWWq9$Qf^-2v8WHUU~rJ5B1c_ zAJ5D}Uf_Bs z5nalwXMftq(tcKAve7n{aoB(P3D4yzquyvkf^w&AjC9Fe+Bo`xF9K{2Qvl=!_x#WE zujVTlT9q~=RjOF5%^L$-KpS!bb4%F2V80yPNCXV?FBXMyt8-Gd`U8B^19RWs{1)%K z|1InX<;3=b@}ti{pMZVFv)_zrC`YGa4sBRC<8EbfB$*E*DuxoFd8!#AD{y$(nF zwE*qcs$Rje6Q*)VZ<%^^d$^`>eUc_FD7D567BA znn%=Sf_j}4^flCZf^nG+^`B{y1I$PBfO)eFEDyQNGP0}{0mTdKYXNnud8FIMHQ;&A z^B_O&A150vFUpkiTo2#u0LC%)U@VK@;i>1FVG+`O14swF3j80S`GG?xPiRAETT=V@ ze{qU)PIBjtmEa23(Wf|#cmMcYkYiNj#~~LSR@@=^Shr@=DW7hPn#|)bf{;lj?SvC)>tGLyxa&9U7 zddmJNYaM{PRTHQVR0GJFDgb#y9VB-`0P19UKy!$?S{4W}K`v=fpOb>VhWbwE_)L!= zKbZ&fVxG*KWng(&E|!mFWtnROb%FXo!%{iZeAyHC#(RF8Osw+Z@m%<-3pr~8~47NqgCH0(?X=nzDH_+Z6JB@FCYcLjeCNeA$MNmS`M6Zk~VEDo`poihFpLR z!Td!3-@t<-;7CG#@IS+NO;GSfsoxM|#6<<~(jLOx;69U(W`5u;fWCW5fV$>d4xD-} zH!UB^hVn}VWN6@!b&oi9$zX*MhC76G~{~RkoIU4~D0P0pf;9Y>aM$S<02+f@uICkZa zl|!0GnoHE_KLW2M7?-+FTR>Pjz&x2ZxxlipY%C|sOR)UB526YD(az+@oOZO&3EQB@ z{ijS8bS$gdklmx2$v0zKz)vkHjr}t3M7oLjR+=9OPGCb`!GC2#_>F}8`9&&Jx`uxD z@9>}Se8cYuIKuwMp#&g5ij|1MwO6EZlUO`E=Q{3Ae&j=%*#XTD>RNK)2a2lX!}5~X zYV;J%iC-sU~ZBSAxG($!S9v?wSYB5#$E#2l+7{ zX>h%3_GM7cWb%x_#wQ|oEBgj4JMV$_(%d6!%E6uBlTz1t->x!A>ObwUl^@%OHdJfTnfyqLw6$+#wH-LE zHr+-t>?I&2#%0^&f(=QX8sEbWz6Tp}Ugv#LnlS7K`4Lj_vNQre%HZAh zELjgpVeg^KkzQVaJ|20h%Rzgk^TpwFy|J8>4LL#^@*3t~@1P#CpTV}w@PQuH;iT#- zvGbZMOmhM1b4iy##Shl&oJ4d%^MiFyJEN{cT#n0dJPhS*ZUOa6gZidH{i7agXx((> z5cOBvA>FqB(O$>Vy6>w0%uDC1d7!zV%c}381;_pxcxSvE(W`mKyP+@P$j zCsky}utu^0V|?Q=Z@Qs>rnx8seFEw|>-TXw$uR9ls5RwiLkbnbdO(%2HgB0zupz&} zmx2xP13!Gh55ODXxnd=bqrY-N@gp!$)cT}e-b0rm&D;R_kshFZVjjtfA1JPpoAyCp zX$-lJYvzsq0sD!iF^7TexWN_rP5&+CA`Pauuv1xy=v)qCSy=y!>08ofIP+$IhS%|! z{SN9-^+M@)70;D=D%#s2)-f{Nht@aiUhATDuld70byq{{^ONj#9INiT>c7s@S{@#^ zVA;tD-V5((ImgfsO^^rQk5v6Pt1KROtmQ-*v5yuxq(1r~)ns@BPif$jX%O<#I;r`A zQ;BZm2X%mc#H(DFlygqfrWFYexrgU|7o~V9z5_yzuupDqgL}WCcW= ztV*8&&j$^DC5+J+wgj_Hmrt>$6TZSbv>k0 z`CRf*nYS+2Eu86)<_`Ho?zr%$1!}-mSM`6b%YSyS<0rOfeu@h$5BX5rE7M`}VG`CM zSw8+FIk2kE2e78Y|MQUt`z(v$hpp-zBAfbEk?o)18OX?b^79u> z!Os30qQRZ_C!TnE(UpWz0T zQMZ%I&+_pbH=Ey~%A8rGO0`(nhs*G@PGGDG&&$CHA3uX1enk&~A4kzoIU@}lM@z+u zad?KJzF)8#X=Vd50QB>$z7_r^tIf)hfAjsFSy)$N$54#XV$AU8uiD7^e%0|zu%ax* zI1=qS$9(6}5Bdu*A8G1wIvr;EFS~? zpV>xs&TB8{z8)->ejFolzt6y&gXt27xd+idjg?!G{pHMp4)W`y7P1#(=UYOn%DPV~ z!k-Gp^Q9nJOk4dQ$ds~SJF={MuzGIGwetBMFSL(s^`G_isR!EEewpiKQP=%3W?QTF z190R5I1&Xu905nr_W(!8kK!ed!hVn+57ip+v>)a-%{gwx@n!mX$2M3S&@SXPT>fSCGx2)nvz@TJjBalFwr}FNXH#^xTi-(vmK66a2Zoxu4wI zK0qFPJxCsYGgPAY4VRc7MggO-*2pM{{%)i^1Ri`lOz!U)B6oLwCbuI8$j!~6a$`du zxw@veTv^#eE+9R}>^Ab-l=tPpxW=+?L_OIFpNZpk>p!h1YcSrus%Lpw0X{72Ru1Jv zdBOSl|AqYce3tfuU_XsxV2%AU1ff>{EH|hKS_c$I3Kkw7k{{obq7A9@E;v%>F6_i< zygz#kcEsR_VLyIT=j%5Fhk|4AU32nd+)kv&eh0@z+4s=p!C|u9w0zWh%lt;cfk~}I zuIv!Gutn~FH(fo0+B~2Rcv2mG!b*6C2%i8tNj=qV{QXl2>hx3a9qHS0dD zAZrn44fwaFcd(j2z&Qjf(RUzL5a1_yu)G_%fV`H#J}g2xXa}FBeAK<7ZD5)s@!Y(T zZ{}IhKHVQ@eg4@^>j3rnMc<<1wsXxzZ*P&7?~Bx~dkb?(98#k6QSmQ+81~~=Wlw^F zPfNW953nv{EWUw*?|l^gVh7@LUIw|rzDIKFcc93LZdyKyBN14q@5;vE_#XI4d?)Fe z#GT$KXIJ!>yGAER~P-}yXyU(O(BgN@4C*aq{CZe6Q0|x88lM>l1@VOY zDaUpD7ohDsyK(?HatR!X#kY=6N$jx|Sf8e^>>u}@>>Sn*&&F%3KFVs7EA(;LUemVF z_hCC{z^ejIWh!&)To8M z<^I_{=C{D3MIJgt&TN(&Ur&%@;az3l=PhJA`Y2n#l?~|6ufdq(%3c*!-;sUDMc^6j z3;WpCw$DB`#~(~vpyfe1X?dw*{HK3tJ;!Uwji!EC!cdD^4_S9lV~giV(TP!f$FNEj zkqMJTh7KoB9$?PZZE4Wx4!9D9b%L(o*`V=mt)Jhx{wRR8JWs1kPvgFxW*WRNd~+|; zHrB%ujFX&RHBcU0!FQ5k?!unL0XIbM9+cRqRdQqJ7jgnT`eFPB^7ZgWvUOk`*%Ve& z)}vofKWr8FvI4%?QuOaRW<%)u)_U&RU#67scV=X7zWT#y=xn$vnswdXf zQ>=VvnjXGGa`}QInKIv$R;@*L>=N0sO=S2;kv{!627DiDY2A_(DV*QH`6qBAfvEMj zz`KOxlofc-?Uy;-FHm%}`aK2*mf#%%4UQkM4Oxa~A}f1B zK4_Qpdj^yPzsc3A%$wS7Xgy9)Ur+ImO24r8gmUCa_Ut#MYgdt8z0e_w(y$-BhQ1!*@7tP{s>fzI^;G|PaQP^ivS#rcZ=U#dJ^)vXk$6m>vW3RlO zdo$L1pG|Ir{*TL)bZMW15PnmPJn0(pwv1}*jlRdba(vMz_|)-Sd>7^iP~?ii6U7(w zS!iF_Z@Io-VjXMb-j6fo@}?1TazStT1Er{C zeTz*9C|q=m`?Dxaa>$c5rHOymX6&bsFa5Aq`IL`J;l01ca$;#;x$%9tJUoZK{oPY= z!)}8oDG=gD>0qccnT$kCY{<)?`s%C}>h$=Aag$o4_t z4eZU90kzPtso`v2*YyE+(B4wdR>5D>wue3m+h@aHfeoS^QntvjN7|oxqP-bcr=|AY z%=VwpJG9Q5?Z2`Ed?twU&>m{AjI;|Z|5n_`F5DN}h40~m?jPGicH^0RBsj7Gc7u6v z4Kd|QLAIvNNDeAtm+>(YAYYml%{+}(wKzj_mF!v4u^(LEU}cMdI==!^Tn z8E_*Sc13Z;^vh^xqT#FE`BmiV9?aKRr~I>9yC=xSwS!=9ddja;KUO;R4dyo~?hJlc zwY$_g+MP}C*EX8|$$Ic-9r&{rx=E~ozG|$d{{8{K1g`3!4{@QMSK9kgI*^ zin&ewY8H^mtxDn9NgdfYv6Y-%HyC~y?9AC65_{`6@B`0VVzsSd-=DVTCeC3z;6B1{ z?8RKa4H9!~3BEfsOKyWZS2hikGs{CUAEvt;o`yM#6FyLSN8Kccb`GhBF=+4zHi$gh zf_@MCK31?@cZCk8-C{iYK#|aS>iy24^<_84>S*JB9RI!?gw7wC-d=v2(Lvci$J}mm zZt`fH7gMLjc$Ct?&;tl{m zE$$q`j^XbC*d2Tq^UQiY%Umqczl6*E{Zr&FICN{-P4Ur034kJ&R(V!xRr zu{+1fL->jJQT}U)dvZ=!tOAa{I?wa_^V9^5D>XV4*xX9AO+EoD0g#R%2>+zn>;| zzWqvW!4}*^U+D_;{w(~XQww`Z)a=f31Zf|{7&ZO3{hv3NUGUrZOo(f6Pr$s+q4*vH zzZKQD+B=VMf%jqiO;1rl?4**EfR#IH{0w$SKbxWLX&sPV$f2%ySBhh5{FZDe*1qE! zQ5=sZrxf7ReFc1pH6bSv?-i91jf$x2hU49kVR+8NwQc)Ve@FTPD$S5wO82d{fO*p% z5XN|3#sHfONmid7@Ek~h`l)$D|4sXF${v}ztaUo6J+IaJ&iFb_Tlb%X3bu=2OTd_C16XymVhk*TLQKOYzf#Buq9wiz?Oh5 z0b2sL1Z)Y|60jv;OTd_C16XymVhk* zTLQKOYzf#Buq9wiz?Oh50b2sL1Z)Y|60jv;OTd_C16XymVhk*TLQKOYzf#Buq9wiz?Oh50b2sL1Z)Y|60jv;OTddZ}I62wb* z^Dbcy>&@RsBC0HrDkl^sz?rB^82;vPhOy|Dc*r7NFuY|;7>XS)7>5oEGwv*5m|3@G zSeQjPV#!Db*$q-XxNx)Qemu&$VcKqpk~BKN*%}i zG1vv6sg3bm!+0gP9N-NS#u0y*KQ{GhT#`UV*TMG~e;7^YIj zEk|Nu4z^}tV^tt5HR~Q*f;5q~Tj+JS7hS?~@In?ely_n@C@LP#sW7GzkW^S0 zE@Hw7<0&QJO{lP!n1fLkq-lgXaKKD0VYtEw!%e6#;~y?kv5hNH4&~A$7KU6x50;ui%_3Oj9F}O#FeB9j(VSsQ f0H$*5xG0}Kd}MEjJt7iy!j_9I7gq^91D*JP%Ro+M literal 0 HcmV?d00001 diff --git a/htdocs/images/background.jpg b/htdocs/images/background.jpg new file mode 100644 index 0000000000000000000000000000000000000000..983ddd6f8a76ecf94644d16df5dd6d7897e50315 GIT binary patch literal 2544 zcmbW1d010d7QpX&FAF4L2|P9za6$6o=L)F;10f>gMh-V}TC?V=iQUv|^=yK;Wv?TpoXoAY2^1;p2@le~nE@ z{48l(a?0l!nLEGUwOb<1-JAE_zWoRCixnk@OMf_WRH?44s;;Tk)SWzguHpR8jZMuL zu3f)zvrT(Tce|tW!NW(7yMFC{`j6he{$~S&L&n#mZ^le-&F|iiPjf*4`GEB&*?(}+ zaW0rZKnUb%E(qR*PlQe&&RtG&3KfyJra8~^&9*_qicZvDwVm&`{*}w8>3WK*H|yzw z*VAZ!ko|XHIsX^gpJ4yy>IO8t&tN)22W(&=E!uP%ThEg^h$Cc|Bq2GtH1X8~!DVo(-<8xY^Ko zyEK4(JKI$<7@Q_f|B=g$lm%k!Sga|g{+#ESi%;znQ{|U)3nhtfS9}p>W=2|Lv?j4Tuq3nn%1ne>g{^XjPF2AQh|KDqrnx_E*b1*9O%&gCM54}nj$zL?lnvjL)7~F@U~U6`@sac70)b9V*I*)Dq38ivGwpi)Dp_Roe#cg z3N22vq_o6FT`Gy=NZ8`=`n&+PpH#UqHP^d${5~v00SP?EYLY(gBZ>wMc$s`%y?K5{ zt;z~!Y$#yr-XEK2D7jeOoM~at|r!4ogjtAj^ zT4&eAeX(2DHwMyEE=NR|?>(IAnQ8!?zPWAB%o}|2kE{l*J@#E{8DaliMrp!BdF;lb zgjwc6vUshphrhhY@}|=YepeSVr68O_73m1hOUPN2LHV?JTVR^L`Y`kU#f3t$9SShc* z?~uT#t*gz{Tx|Pc|I|x!d(`zuvIVzh4{E0FdQ9A&Wd)M9NEGDwF?`e6O@Ub^(ZEP_&f(t&HAETW;u6WQ9bi!uVInVsS z&Rq>xGWz3Q7ER^_&yRU?sJ1RR68I(lq}x;RTyxiD?oP1|F(#`(p{h8QoFRIdvODT< z)@A-Es-CCK+?V#ea=L1Tg`_B0Hs6sKs7Ww1dg}!PuKn}3#fh>f2UX;t6YK6%*=FvX z{msAZ+oe8~JDH-J(YCD8^YWM+6F0!^7Cpy7tsd>$5gS&k2U;VhA|2flcVWd+vs^q@ z>(kZdk~ZA#Q}`i+wT6y8zZYd)JsjBI( z8Y+p~GBC+Bp5TF-VCDAmh{8Q?)hJ7|kJjoHh9ARaeQ_$Y<>>fl8y`2<`nJsxJ z=w_}I6>+FsA0q}G)7)Kvf)-7cTIS5!p)t?!jRfqSs6o%64Lu%J)w4>Pv~jm(&OZ5{ zXzTG;79>5-oE-9t1QoTXm*DCk^e*^bNJF#)uT+FHhhPa#ZryURB0NlB1r)G3+n9_; z_E^{L_HyS~&5kG2Z}u^c)BA&6JyHs@W%1H zE+{9TCZ1V#@f$M>v;bqPS2(jo2p7lnb>!XB^+-E0;-dQCH`4sG)&O+92+;hH$rzTyXY{mM!;Yw zh0Pv84zb`%)Y6kFl1nl0l-83@W)gHn;VHR7u{PL5Txf&HWk;$B>(^b literal 0 HcmV?d00001 diff --git a/htdocs/index.php b/htdocs/index.php index b4a8e60..10842d4 100644 --- a/htdocs/index.php +++ b/htdocs/index.php @@ -2,46 +2,84 @@ define("MAIN_DIR", __dir__."/.."); +function get_info($url) +{ + $ec = file(MAIN_DIR."/database",FILE_IGNORE_NEW_LINES|FILE_SKIP_EMPTY_LINES); + $nbLign = count($ec); + + for ($i = 0; $i < $nbLign; $i++) + { + if ($ec[$i] == $url) + break; + else + { + while ($i < $nbLign && trim($ec[$i]) != "--") + $i++; + } + } + + if ($i+2 < $nbLign) + { + @$filename = preg_replace("#^(.+)\.([a-zA-Z0-9]{1,4})$#", '\1.mp3', $ec[$i+3]); + return @array($ec[$i], $ec[$i+1], $ec[$i+2], $ec[$i+3], trim($filename)); + } + else + return NULL; +} + header("Content-type: text/html;charset=utf-8"); -?> - - - -En avant la musique ! - - - -

- -

Chansons prêtes à être téléchargées

- -
    - $t) +{ + if (empty($t)) { - if(is_file($dir.'/'.$entry) && preg_match("#^(.*).mp3$#ui", $entry, $out)) - { - if (substr($ec,0,strlen($out[1])) == $out[1]) - $ecD = "convertion"; - else - echo '
  • '.$out[1].'
    • '; - } - } -closedir($musiks); + $user = $k; + break; + } +} +if (!preg_match("#^[a-zA-Z0-9_]+$#", $user)) + die ("Le nom d'utilisateur contient des caractères interdits."); ?> -
+ + + + + .: Pommultimédia - Online Converter :. + + + + + +
+

Chansons prêtes à être téléchargées

+
    Ajouter une chanson à la liste +$someone = false; +if (is_file(MAIN_DIR."/users/".$user.".dlist.done")) +{ + $ec = file(MAIN_DIR."/users/".$user.".dlist.done",FILE_IGNORE_NEW_LINES|FILE_SKIP_EMPTY_LINES); + + foreach ($ec as $k => $lign) + { + $musik = get_info($lign); + if(isset($musik) && is_file($dir.'/'.$musik[4])) + { + $someone = true; + echo '
  • '.$musik[1].'
    • '; + } + } +} + +if (empty($someone)) + echo "

    Aucun élément dans cette liste

    "; +?>
+
+
+

Ajouter une chanson

La demande de vidage de la liste a été ajouté à la file d'attente"; - } + fputs($fp, "clear\n"); + print "

La demande de vidage de la liste a été ajouté à la file d'attente

"; } + } elseif (preg_match("#^http://(www.)?youtube.com/watch\?v=([a-zA-Z0-9_-]+)#", $url, $matched)) + { + //Check if the URL isn't already in the file + if (is_file(MAIN_DIR."/users/".$user.".dlist")) + $content = file(MAIN_DIR."/users/".$user.".dlist",FILE_IGNORE_NEW_LINES|FILE_SKIP_EMPTY_LINES); + else + $content = array(); + if (!in_array($matched[0], $content) && $fp = fopen(MAIN_DIR."/users/".$user.".dlist", "a+")) { - //Check if the URL isn't already in the file - $content = file(MAIN_DIR."/urls",FILE_IGNORE_NEW_LINES|FILE_SKIP_EMPTY_LINES); - if (!in_array($matched[0], $content) && $fp = fopen(MAIN_DIR."/urls", "a+")) - { - fputs($fp, $matched[0]."\n"); - print "

L'adresse a bien été ajoutée avec succès.

"; - } + fputs($fp, $matched[0]."\n"); + print "

L'adresse a bien été ajoutée avec succès.

"; } + } else print "

L'adresse fournie n'est pas valide !

"; } ?> -
- - -
+
+ + +
+
+
+

Chansons en file d'attente

+
+
    Chansons en cours de téléchargement - 1) - echo "Actuellement en cours de ".$ecD." : ".$ec."
    "; - -if (!empty($_GET["a"]) && $_GET["a"] == "del") + if (!empty($ec[0])) { - foreach($_POST as $id => $value) + $musik = get_info($ec[0]); + if(isset($musik)) { - if (preg_match("#^del([a-z0-9]+)$#", $id, $out)) - { - $content = file(MAIN_DIR."/urls",FILE_IGNORE_NEW_LINES|FILE_SKIP_EMPTY_LINES); - $newlist = array(); - for ($i = 0; $i < count($content); $i++) - { - if (sha1($content[$i]) != $out[1]) - $newlist[] = $content[$i]; - } - file_put_contents(MAIN_DIR."/urls", implode("\n", $newlist)."\n"); - print "

    La chanson a été retirée de la liste.

    "; - } + echo '
    Miniature
    '; + + if (count ($ec) == 1) + echo ""; + else if (count ($ec) == 2) + echo ""; + + echo $musik[1]; + $encours = $ec[0]; + $someone = true; } } +} +if (is_file(MAIN_DIR."/users/".$user.".dlist")) +{ + $ec = file(MAIN_DIR."/users/".$user.".dlist",FILE_IGNORE_NEW_LINES|FILE_SKIP_EMPTY_LINES); -$musiks = file(MAIN_DIR."/urls",FILE_IGNORE_NEW_LINES|FILE_SKIP_EMPTY_LINES); -if (empty($musiks)) + foreach ($ec as $k => $lign) { - if (strlen($ec) < 2) - echo "La liste de téléchargement est vide."; - } -else - { - echo '
      '; - foreach($musiks as $musik) - { - if ($musik == "clear") - echo '
    • Supprimer les fichiers télécharger'; - else - echo '
    • '.$musik.''; - echo '
      • '; - } - echo "
    "; - } + if (isset($encours) && $lign == $encours) + continue; -?> - - \ No newline at end of file + $someone = true; + $musik = get_info($lign); + if(isset($musik) && is_file($dir.'/'.$musik[4])) + echo '
  • '.$musik[1].'
    • '; + else + echo '
  • '.$lign.'
    • '; + } +} + +if (empty($someone)) + echo "

    Aucun élément dans cette liste

    "; +?>
+ +
+
+

Chansons déjà téléchargées

+

Prochainement ...

+
+ + diff --git a/htdocs/style.css b/htdocs/style.css new file mode 100644 index 0000000..4337fc4 --- /dev/null +++ b/htdocs/style.css @@ -0,0 +1,166 @@ +body +{ + background: url('images/background.jpg'); + margin-bottom: 234px; +} + +header +{ + margin: auto; + width: 999px; +} +header span +{ + display: none; +} +header h1 +{ + background: url('images/logo.png'); + height: 312px; + width: 100%; +} +header h2 +{ + background: url('images/partage.png'); + float: right; + height: 92px; + margin: -93px 125px 0 0; + width: 171px; +} + +p,ul +{ + margin: auto; + text-align: left; +} + +#res { + font-size: 80%; + text-align: right; +} +#res ul, #res ul li { + display: inline; + padding-right: 10px; +} + +label { + color: #80a92c; + font-weight: bold; + margin-right: 5px; +} +label:hover { + text-decoration: underline; +} + +input[type=text], input[type=password], select, textarea { + transition: background 0.75s; + -moz-transition: background 0.75s; + -webkit-transition: background 0.75s; + -o-transition: background 0.75s; +} +input, select, textarea { + background: #558dd4; + border: #2f588b solid 1px; + border-radius: 5px; + margin-top: 5px; +} +input:hover, input:focus, select:hover, select:focus, textarea:hover, textarea:focus { + background: #95cdff; +} +input.erreur, select.erreur { + background: #df0009; + border: #f7000b solid 1px; +} +input.erreur:hover, select.erreur:hover { + background: #ff2029; +} + +h1 { + color: #75903b; + text-align: center; +} +h2 { + color: #7f9a48; +} +h3 { + color: #89a355; +} +h4, h5, h6 { + color: #95ae64; +} + +form { + text-align: center; +} + +fieldset, div#content, ul#list, .blk { + background: #e3e3e3; + border: none; + border-radius: 10px; + box-shadow: 0px 0px 11px #555; + min-height: 50px; + margin: auto; + width: 750px; +} + +div.blk { + margin-bottom: 15px; + padding-bottom: 15px; +} + +.blk h2 { + background: #88DE66; + border-bottom: solid 2px #208748; + border-radius: inherit; + border-radius: 10px 10px 0 0; + color: #309F60; + text-align: center; + transition: color 1s; + -moz-transition: color 1s; + -webkit-transition: color 1s; + -o-transition: color 1s; +} +.blk:hover h2 { + background: #88DE66; + color: #30609F; +} +.blk h3 { + color: #444; + text-align: center; + font-style: italic; +} + +ul#list +{ + padding: 10px 10px 10px 20px; +} + +div#content { + padding: 5px; + text-align: left; + min-width: 80%; +} + +div#content pre { + overflow-x: auto; +} + +textarea#content { + height: 200px; + width: 90%; +} + +div.answer { + float: right; + font-size: 65%; + font-style: italic; +} + +ins +{ + color: #00DF22; +} +del +{ + color: #DF2200; +} \ No newline at end of file diff --git a/users/users b/users/users new file mode 100644 index 0000000..e69de29 diff --git a/youtube-dl b/youtube-dl new file mode 100755 index 0000000..9de8ca2 --- /dev/null +++ b/youtube-dl @@ -0,0 +1,4648 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- + +__authors__ = ( + 'Ricardo Garcia Gonzalez', + 'Danny Colligan', + 'Benjamin Johnson', + 'Vasyl\' Vavrychuk', + 'Witold Baryluk', + 'Paweł Paprota', + 'Gergely Imreh', + 'Rogério Brito', + 'Philipp Hagemeister', + 'Sören Schulze', + 'Kevin Ngo', + 'Ori Avtalion', + 'shizeeg', + ) + +__license__ = 'Public Domain' +__version__ = '2012.02.26' + +UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' + + +import cookielib +import datetime +import getpass +import gzip +import htmlentitydefs +import HTMLParser +import httplib +import locale +import math +import netrc +import optparse +import os +import os.path +import re +import shlex +import socket +import string +import subprocess +import sys +import time +import urllib +import urllib2 +import warnings +import zlib + +if os.name == 'nt': + import ctypes + +try: + import email.utils +except ImportError: # Python 2.4 + import email.Utils +try: + import cStringIO as StringIO +except ImportError: + import StringIO + +# parse_qs was moved from the cgi module to the urlparse module recently. +try: + from urlparse import parse_qs +except ImportError: + from cgi import parse_qs + +try: + import lxml.etree +except ImportError: + pass # Handled below + +try: + import xml.etree.ElementTree +except ImportError: # Python<2.5: Not officially supported, but let it slip + warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.') + +std_headers = { + 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', + 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', + 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', + 'Accept-Encoding': 'gzip, deflate', + 'Accept-Language': 'en-us,en;q=0.5', +} + +try: + import json +except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): + import re + class json(object): + @staticmethod + def loads(s): + s = s.decode('UTF-8') + def raiseError(msg, i): + raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:])) + def skipSpace(i, expectMore=True): + while i < len(s) and s[i] in ' \t\r\n': + i += 1 + if expectMore: + if i >= len(s): + raiseError('Premature end', i) + return i + def decodeEscape(match): + esc = match.group(1) + _STATIC = { + '"': '"', + '\\': '\\', + '/': '/', + 'b': unichr(0x8), + 'f': unichr(0xc), + 'n': '\n', + 'r': '\r', + 't': '\t', + } + if esc in _STATIC: + return _STATIC[esc] + if esc[0] == 'u': + if len(esc) == 1+4: + return unichr(int(esc[1:5], 16)) + if len(esc) == 5+6 and esc[5:7] == '\\u': + hi = int(esc[1:5], 16) + low = int(esc[7:11], 16) + return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000) + raise ValueError('Unknown escape ' + str(esc)) + def parseString(i): + i += 1 + e = i + while True: + e = s.index('"', e) + bslashes = 0 + while s[e-bslashes-1] == '\\': + bslashes += 1 + if bslashes % 2 == 1: + e += 1 + continue + break + rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)') + stri = rexp.sub(decodeEscape, s[i:e]) + return (e+1,stri) + def parseObj(i): + i += 1 + res = {} + i = skipSpace(i) + if s[i] == '}': # Empty dictionary + return (i+1,res) + while True: + if s[i] != '"': + raiseError('Expected a string object key', i) + i,key = parseString(i) + i = skipSpace(i) + if i >= len(s) or s[i] != ':': + raiseError('Expected a colon', i) + i,val = parse(i+1) + res[key] = val + i = skipSpace(i) + if s[i] == '}': + return (i+1, res) + if s[i] != ',': + raiseError('Expected comma or closing curly brace', i) + i = skipSpace(i+1) + def parseArray(i): + res = [] + i = skipSpace(i+1) + if s[i] == ']': # Empty array + return (i+1,res) + while True: + i,val = parse(i) + res.append(val) + i = skipSpace(i) # Raise exception if premature end + if s[i] == ']': + return (i+1, res) + if s[i] != ',': + raiseError('Expected a comma or closing bracket', i) + i = skipSpace(i+1) + def parseDiscrete(i): + for k,v in {'true': True, 'false': False, 'null': None}.items(): + if s.startswith(k, i): + return (i+len(k), v) + raiseError('Not a boolean (or null)', i) + def parseNumber(i): + mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:]) + if mobj is None: + raiseError('Not a number', i) + nums = mobj.group(1) + if '.' in nums or 'e' in nums or 'E' in nums: + return (i+len(nums), float(nums)) + return (i+len(nums), int(nums)) + CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete} + def parse(i): + i = skipSpace(i) + i,res = CHARMAP.get(s[i], parseNumber)(i) + i = skipSpace(i, False) + return (i,res) + i,res = parse(0) + if i < len(s): + raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')') + return res + +def preferredencoding(): + """Get preferred encoding. + + Returns the best encoding scheme for the system, based on + locale.getpreferredencoding() and some further tweaks. + """ + def yield_preferredencoding(): + try: + pref = locale.getpreferredencoding() + u'TEST'.encode(pref) + except: + pref = 'UTF-8' + while True: + yield pref + return yield_preferredencoding().next() + + +def htmlentity_transform(matchobj): + """Transforms an HTML entity to a Unicode character. + + This function receives a match object and is intended to be used with + the re.sub() function. + """ + entity = matchobj.group(1) + + # Known non-numeric HTML entity + if entity in htmlentitydefs.name2codepoint: + return unichr(htmlentitydefs.name2codepoint[entity]) + + # Unicode character + mobj = re.match(ur'(?u)#(x?\d+)', entity) + if mobj is not None: + numstr = mobj.group(1) + if numstr.startswith(u'x'): + base = 16 + numstr = u'0%s' % numstr + else: + base = 10 + return unichr(long(numstr, base)) + + # Unknown entity in name, return its literal representation + return (u'&%s;' % entity) + + +def sanitize_title(utitle): + """Sanitizes a video title so it could be used as part of a filename.""" + utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) + return utitle.replace(unicode(os.sep), u'%') + + +def sanitize_open(filename, open_mode): + """Try to open the given filename, and slightly tweak it if this fails. + + Attempts to open the given filename. If this fails, it tries to change + the filename slightly, step by step, until it's either able to open it + or it fails and raises a final exception, like the standard open() + function. + + It returns the tuple (stream, definitive_file_name). + """ + try: + if filename == u'-': + if sys.platform == 'win32': + import msvcrt + msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) + return (sys.stdout, filename) + stream = open(_encodeFilename(filename), open_mode) + return (stream, filename) + except (IOError, OSError), err: + # In case of error, try to remove win32 forbidden chars + filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename) + + # An exception here should be caught in the caller + stream = open(_encodeFilename(filename), open_mode) + return (stream, filename) + + +def timeconvert(timestr): + """Convert RFC 2822 defined time string into system timestamp""" + timestamp = None + timetuple = email.utils.parsedate_tz(timestr) + if timetuple is not None: + timestamp = email.utils.mktime_tz(timetuple) + return timestamp + +def _simplify_title(title): + expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE) + return expr.sub(u'_', title).strip(u'_') + +def _orderedSet(iterable): + """ Remove all duplicates from the input iterable """ + res = [] + for el in iterable: + if el not in res: + res.append(el) + return res + +def _unescapeHTML(s): + """ + @param s a string (of type unicode) + """ + assert type(s) == type(u'') + + htmlParser = HTMLParser.HTMLParser() + return htmlParser.unescape(s) + +def _encodeFilename(s): + """ + @param s The name of the file (of type unicode) + """ + + assert type(s) == type(u'') + + if sys.platform == 'win32' and sys.getwindowsversion().major >= 5: + # Pass u'' directly to use Unicode APIs on Windows 2000 and up + # (Detecting Windows NT 4 is tricky because 'major >= 4' would + # match Windows 9x series as well. Besides, NT 4 is obsolete.) + return s + else: + return s.encode(sys.getfilesystemencoding(), 'ignore') + +class DownloadError(Exception): + """Download Error exception. + + This exception may be thrown by FileDownloader objects if they are not + configured to continue on errors. They will contain the appropriate + error message. + """ + pass + + +class SameFileError(Exception): + """Same File exception. + + This exception will be thrown by FileDownloader objects if they detect + multiple files would have to be downloaded to the same file on disk. + """ + pass + + +class PostProcessingError(Exception): + """Post Processing exception. + + This exception may be raised by PostProcessor's .run() method to + indicate an error in the postprocessing task. + """ + pass + +class MaxDownloadsReached(Exception): + """ --max-downloads limit has been reached. """ + pass + + +class UnavailableVideoError(Exception): + """Unavailable Format exception. + + This exception will be thrown when a video is requested + in a format that is not available for that video. + """ + pass + + +class ContentTooShortError(Exception): + """Content Too Short exception. + + This exception may be raised by FileDownloader objects when a file they + download is too small for what the server announced first, indicating + the connection was probably interrupted. + """ + # Both in bytes + downloaded = None + expected = None + + def __init__(self, downloaded, expected): + self.downloaded = downloaded + self.expected = expected + + +class YoutubeDLHandler(urllib2.HTTPHandler): + """Handler for HTTP requests and responses. + + This class, when installed with an OpenerDirector, automatically adds + the standard headers to every HTTP request and handles gzipped and + deflated responses from web servers. If compression is to be avoided in + a particular request, the original request in the program code only has + to include the HTTP header "Youtubedl-No-Compression", which will be + removed before making the real request. + + Part of this code was copied from: + + http://techknack.net/python-urllib2-handlers/ + + Andrew Rowls, the author of that code, agreed to release it to the + public domain. + """ + + @staticmethod + def deflate(data): + try: + return zlib.decompress(data, -zlib.MAX_WBITS) + except zlib.error: + return zlib.decompress(data) + + @staticmethod + def addinfourl_wrapper(stream, headers, url, code): + if hasattr(urllib2.addinfourl, 'getcode'): + return urllib2.addinfourl(stream, headers, url, code) + ret = urllib2.addinfourl(stream, headers, url) + ret.code = code + return ret + + def http_request(self, req): + for h in std_headers: + if h in req.headers: + del req.headers[h] + req.add_header(h, std_headers[h]) + if 'Youtubedl-no-compression' in req.headers: + if 'Accept-encoding' in req.headers: + del req.headers['Accept-encoding'] + del req.headers['Youtubedl-no-compression'] + return req + + def http_response(self, req, resp): + old_resp = resp + # gzip + if resp.headers.get('Content-encoding', '') == 'gzip': + gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') + resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) + resp.msg = old_resp.msg + # deflate + if resp.headers.get('Content-encoding', '') == 'deflate': + gz = StringIO.StringIO(self.deflate(resp.read())) + resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) + resp.msg = old_resp.msg + return resp + + +class FileDownloader(object): + """File Downloader class. + + File downloader objects are the ones responsible of downloading the + actual video file and writing it to disk if the user has requested + it, among some other tasks. In most cases there should be one per + program. As, given a video URL, the downloader doesn't know how to + extract all the needed information, task that InfoExtractors do, it + has to pass the URL to one of them. + + For this, file downloader objects have a method that allows + InfoExtractors to be registered in a given order. When it is passed + a URL, the file downloader handles it to the first InfoExtractor it + finds that reports being able to handle it. The InfoExtractor extracts + all the information about the video or videos the URL refers to, and + asks the FileDownloader to process the video information, possibly + downloading the video. + + File downloaders accept a lot of parameters. In order not to saturate + the object constructor with arguments, it receives a dictionary of + options instead. These options are available through the params + attribute for the InfoExtractors to use. The FileDownloader also + registers itself as the downloader in charge for the InfoExtractors + that are added to it, so this is a "mutual registration". + + Available options: + + username: Username for authentication purposes. + password: Password for authentication purposes. + usenetrc: Use netrc for authentication instead. + quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. + forcethumbnail: Force printing thumbnail URL. + forcedescription: Force printing description. + forcefilename: Force printing final filename. + simulate: Do not download the video files. + format: Video format code. + format_limit: Highest quality format to try. + outtmpl: Template for output names. + ignoreerrors: Do not stop on download errors. + ratelimit: Download speed limit, in bytes/sec. + nooverwrites: Prevent overwriting files. + retries: Number of times to retry for HTTP error 5xx + continuedl: Try to continue downloads if possible. + noprogress: Do not print the progress bar. + playliststart: Playlist item to start at. + playlistend: Playlist item to end at. + matchtitle: Download only matching titles. + rejecttitle: Reject downloads for matching titles. + logtostderr: Log messages to stderr instead of stdout. + consoletitle: Display progress in console window's titlebar. + nopart: Do not use temporary .part files. + updatetime: Use the Last-modified header to set output file timestamps. + writedescription: Write the video description to a .description file + writeinfojson: Write the video description to a .info.json file + """ + + params = None + _ies = [] + _pps = [] + _download_retcode = None + _num_downloads = None + _screen_file = None + + def __init__(self, params): + """Create a FileDownloader object with the given options.""" + self._ies = [] + self._pps = [] + self._download_retcode = 0 + self._num_downloads = 0 + self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] + self.params = params + + @staticmethod + def format_bytes(bytes): + if bytes is None: + return 'N/A' + if type(bytes) is str: + bytes = float(bytes) + if bytes == 0.0: + exponent = 0 + else: + exponent = long(math.log(bytes, 1024.0)) + suffix = 'bkMGTPEZY'[exponent] + converted = float(bytes) / float(1024 ** exponent) + return '%.2f%s' % (converted, suffix) + + @staticmethod + def calc_percent(byte_counter, data_len): + if data_len is None: + return '---.-%' + return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) + + @staticmethod + def calc_eta(start, now, total, current): + if total is None: + return '--:--' + dif = now - start + if current == 0 or dif < 0.001: # One millisecond + return '--:--' + rate = float(current) / dif + eta = long((float(total) - float(current)) / rate) + (eta_mins, eta_secs) = divmod(eta, 60) + if eta_mins > 99: + return '--:--' + return '%02d:%02d' % (eta_mins, eta_secs) + + @staticmethod + def calc_speed(start, now, bytes): + dif = now - start + if bytes == 0 or dif < 0.001: # One millisecond + return '%10s' % '---b/s' + return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) + + @staticmethod + def best_block_size(elapsed_time, bytes): + new_min = max(bytes / 2.0, 1.0) + new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB + if elapsed_time < 0.001: + return long(new_max) + rate = bytes / elapsed_time + if rate > new_max: + return long(new_max) + if rate < new_min: + return long(new_min) + return long(rate) + + @staticmethod + def parse_bytes(bytestr): + """Parse a string indicating a byte quantity into a long integer.""" + matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) + if matchobj is None: + return None + number = float(matchobj.group(1)) + multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) + return long(round(number * multiplier)) + + def add_info_extractor(self, ie): + """Add an InfoExtractor object to the end of the list.""" + self._ies.append(ie) + ie.set_downloader(self) + + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + + def to_screen(self, message, skip_eol=False): + """Print message to stdout if not in quiet mode.""" + assert type(message) == type(u'') + if not self.params.get('quiet', False): + terminator = [u'\n', u''][skip_eol] + output = message + terminator + + if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding(), 'ignore') + self._screen_file.write(output) + self._screen_file.flush() + + def to_stderr(self, message): + """Print message to stderr.""" + print >>sys.stderr, message.encode(preferredencoding()) + + def to_cons_title(self, message): + """Set console/terminal window title to message.""" + if not self.params.get('consoletitle', False): + return + if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): + # c_wchar_p() might not be necessary if `message` is + # already of type unicode() + ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) + elif 'TERM' in os.environ: + sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) + + def fixed_template(self): + """Checks if the output template is fixed.""" + return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) + + def trouble(self, message=None): + """Determine action to take when a download problem appears. + + Depending on if the downloader has been configured to ignore + download errors or not, this method may throw an exception or + not when errors are found, after printing the message. + """ + if message is not None: + self.to_stderr(message) + if not self.params.get('ignoreerrors', False): + raise DownloadError(message) + self._download_retcode = 1 + + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self.params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def temp_name(self, filename): + """Returns a temporary filename for the given filename.""" + if self.params.get('nopart', False) or filename == u'-' or \ + (os.path.exists(_encodeFilename(filename)) and not os.path.isfile(_encodeFilename(filename))): + return filename + return filename + u'.part' + + def undo_temp_name(self, filename): + if filename.endswith(u'.part'): + return filename[:-len(u'.part')] + return filename + + def try_rename(self, old_filename, new_filename): + try: + if old_filename == new_filename: + return + os.rename(_encodeFilename(old_filename), _encodeFilename(new_filename)) + except (IOError, OSError), err: + self.trouble(u'ERROR: unable to rename file') + + def try_utime(self, filename, last_modified_hdr): + """Try to set the last-modified time of the given file.""" + if last_modified_hdr is None: + return + if not os.path.isfile(_encodeFilename(filename)): + return + timestr = last_modified_hdr + if timestr is None: + return + filetime = timeconvert(timestr) + if filetime is None: + return filetime + try: + os.utime(filename, (time.time(), filetime)) + except: + pass + return filetime + + def report_writedescription(self, descfn): + """ Report that the description file is being written """ + self.to_screen(u'[info] Writing video description to: ' + descfn) + + def report_writeinfojson(self, infofn): + """ Report that the metadata file has been written """ + self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) + + def report_destination(self, filename): + """Report destination filename.""" + self.to_screen(u'[download] Destination: ' + filename) + + def report_progress(self, percent_str, data_len_str, speed_str, eta_str): + """Report download progress.""" + if self.params.get('noprogress', False): + return + self.to_screen(u'\r[download] %s of %s at %s ETA %s' % + (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % + (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) + + def report_resuming_byte(self, resume_len): + """Report attempt to resume at given byte.""" + self.to_screen(u'[download] Resuming download at byte %s' % resume_len) + + def report_retry(self, count, retries): + """Report retry in case of HTTP error 5xx""" + self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) + + def report_file_already_downloaded(self, file_name): + """Report file has already been fully downloaded.""" + try: + self.to_screen(u'[download] %s has already been downloaded' % file_name) + except (UnicodeEncodeError), err: + self.to_screen(u'[download] The file has already been downloaded') + + def report_unable_to_resume(self): + """Report it was impossible to resume download.""" + self.to_screen(u'[download] Unable to resume') + + def report_finish(self): + """Report download finished.""" + if self.params.get('noprogress', False): + self.to_screen(u'[download] Download completed') + else: + self.to_screen(u'') + + def increment_downloads(self): + """Increment the ordinal that assigns a number to each file.""" + self._num_downloads += 1 + + def prepare_filename(self, info_dict): + """Generate the output filename.""" + try: + template_dict = dict(info_dict) + template_dict['epoch'] = unicode(long(time.time())) + template_dict['autonumber'] = unicode('%05d' % self._num_downloads) + filename = self.params['outtmpl'] % template_dict + return filename + except (ValueError, KeyError), err: + self.trouble(u'ERROR: invalid system charset or erroneous output template') + return None + + def _match_entry(self, info_dict): + """ Returns None iff the file should be downloaded """ + + title = info_dict['title'] + matchtitle = self.params.get('matchtitle', False) + if matchtitle and not re.search(matchtitle, title, re.IGNORECASE): + return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' + rejecttitle = self.params.get('rejecttitle', False) + if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE): + return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + return None + + def process_info(self, info_dict): + """Process a single dictionary returned by an InfoExtractor.""" + + reason = self._match_entry(info_dict) + if reason is not None: + self.to_screen(u'[download] ' + reason) + return + + max_downloads = self.params.get('max_downloads') + if max_downloads is not None: + if self._num_downloads > int(max_downloads): + raise MaxDownloadsReached() + + filename = self.prepare_filename(info_dict) + + # Forced printings + if self.params.get('forcetitle', False): + print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forceurl', False): + print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: + print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forcedescription', False) and 'description' in info_dict: + print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forcefilename', False) and filename is not None: + print filename.encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forceformat', False): + print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace') + + # Do nothing else if in simulate mode + if self.params.get('simulate', False): + return + + if filename is None: + return + + try: + dn = os.path.dirname(_encodeFilename(filename)) + if dn != '' and not os.path.exists(dn): # dn is already encoded + os.makedirs(dn) + except (OSError, IOError), err: + self.trouble(u'ERROR: unable to create directory ' + unicode(err)) + return + + if self.params.get('writedescription', False): + try: + descfn = filename + u'.description' + self.report_writedescription(descfn) + descfile = open(_encodeFilename(descfn), 'wb') + try: + descfile.write(info_dict['description'].encode('utf-8')) + finally: + descfile.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write description file ' + descfn) + return + + if self.params.get('writeinfojson', False): + infofn = filename + u'.info.json' + self.report_writeinfojson(infofn) + try: + json.dump + except (NameError,AttributeError): + self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') + return + try: + infof = open(_encodeFilename(infofn), 'wb') + try: + json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) + json.dump(json_info_dict, infof) + finally: + infof.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) + return + + if not self.params.get('skip_download', False): + if self.params.get('nooverwrites', False) and os.path.exists(_encodeFilename(filename)): + success = True + else: + try: + success = self._do_download(filename, info_dict) + except (OSError, IOError), err: + raise UnavailableVideoError + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.trouble(u'ERROR: unable to download video data: %s' % str(err)) + return + except (ContentTooShortError, ), err: + self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + return + + if success: + try: + self.post_process(filename, info_dict) + except (PostProcessingError), err: + self.trouble(u'ERROR: postprocessing: %s' % str(err)) + return + + def download(self, url_list): + """Download a given list of URLs.""" + if len(url_list) > 1 and self.fixed_template(): + raise SameFileError(self.params['outtmpl']) + + for url in url_list: + suitable_found = False + for ie in self._ies: + # Go to next InfoExtractor if not suitable + if not ie.suitable(url): + continue + + # Suitable InfoExtractor found + suitable_found = True + + # Extract information from URL and process it + ie.extract(url) + + # Suitable InfoExtractor had been found; go to next URL + break + + if not suitable_found: + self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) + + return self._download_retcode + + def post_process(self, filename, ie_info): + """Run the postprocessing chain on the given file.""" + info = dict(ie_info) + info['filepath'] = filename + for pp in self._pps: + info = pp.run(info) + if info is None: + break + + def _download_with_rtmpdump(self, filename, url, player_url): + self.report_destination(filename) + tmpfilename = self.temp_name(filename) + + # Check for rtmpdump first + try: + subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + except (OSError, IOError): + self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') + return False + + # Download using rtmpdump. rtmpdump returns exit code 2 when + # the connection was interrumpted and resuming appears to be + # possible. This is part of rtmpdump's normal usage, AFAIK. + basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] + args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] + if self.params['verbose']: + try: + import pipes + shell_quote = lambda args: ' '.join(map(pipes.quote, args)) + except ImportError: + shell_quote = repr + self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) + retval = subprocess.call(args) + while retval == 2 or retval == 1: + prevsize = os.path.getsize(_encodeFilename(tmpfilename)) + self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) + time.sleep(5.0) # This seems to be needed + retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) + cursize = os.path.getsize(_encodeFilename(tmpfilename)) + if prevsize == cursize and retval == 1: + break + # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those + if prevsize == cursize and retval == 2 and cursize > 1024: + self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') + retval = 0 + break + if retval == 0: + self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(_encodeFilename(tmpfilename))) + self.try_rename(tmpfilename, filename) + return True + else: + self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) + return False + + def _do_download(self, filename, info_dict): + url = info_dict['url'] + player_url = info_dict.get('player_url', None) + + # Check file already present + if self.params.get('continuedl', False) and os.path.isfile(_encodeFilename(filename)) and not self.params.get('nopart', False): + self.report_file_already_downloaded(filename) + return True + + # Attempt to download using rtmpdump + if url.startswith('rtmp'): + return self._download_with_rtmpdump(filename, url, player_url) + + tmpfilename = self.temp_name(filename) + stream = None + + # Do not include the Accept-Encoding header + headers = {'Youtubedl-no-compression': 'True'} + basic_request = urllib2.Request(url, None, headers) + request = urllib2.Request(url, None, headers) + + # Establish possible resume length + if os.path.isfile(_encodeFilename(tmpfilename)): + resume_len = os.path.getsize(_encodeFilename(tmpfilename)) + else: + resume_len = 0 + + open_mode = 'wb' + if resume_len != 0: + if self.params.get('continuedl', False): + self.report_resuming_byte(resume_len) + request.add_header('Range','bytes=%d-' % resume_len) + open_mode = 'ab' + else: + resume_len = 0 + + count = 0 + retries = self.params.get('retries', 0) + while count <= retries: + # Establish connection + try: + if count == 0 and 'urlhandle' in info_dict: + data = info_dict['urlhandle'] + data = urllib2.urlopen(request) + break + except (urllib2.HTTPError, ), err: + if (err.code < 500 or err.code >= 600) and err.code != 416: + # Unexpected HTTP error + raise + elif err.code == 416: + # Unable to resume (requested range not satisfiable) + try: + # Open the connection again without the range header + data = urllib2.urlopen(basic_request) + content_length = data.info()['Content-Length'] + except (urllib2.HTTPError, ), err: + if err.code < 500 or err.code >= 600: + raise + else: + # Examine the reported length + if (content_length is not None and + (resume_len - 100 < long(content_length) < resume_len + 100)): + # The file had already been fully downloaded. + # Explanation to the above condition: in issue #175 it was revealed that + # YouTube sometimes adds or removes a few bytes from the end of the file, + # changing the file size slightly and causing problems for some users. So + # I decided to implement a suggested change and consider the file + # completely downloaded if the file size differs less than 100 bytes from + # the one in the hard drive. + self.report_file_already_downloaded(filename) + self.try_rename(tmpfilename, filename) + return True + else: + # The length does not match, we start the download over + self.report_unable_to_resume() + open_mode = 'wb' + break + # Retry + count += 1 + if count <= retries: + self.report_retry(count, retries) + + if count > retries: + self.trouble(u'ERROR: giving up after %s retries' % retries) + return False + + data_len = data.info().get('Content-length', None) + if data_len is not None: + data_len = long(data_len) + resume_len + data_len_str = self.format_bytes(data_len) + byte_counter = 0 + resume_len + block_size = 1024 + start = time.time() + while True: + # Download and write + before = time.time() + data_block = data.read(block_size) + after = time.time() + if len(data_block) == 0: + break + byte_counter += len(data_block) + + # Open file just in time + if stream is None: + try: + (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) + assert stream is not None + filename = self.undo_temp_name(tmpfilename) + self.report_destination(filename) + except (OSError, IOError), err: + self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) + return False + try: + stream.write(data_block) + except (IOError, OSError), err: + self.trouble(u'\nERROR: unable to write data: %s' % str(err)) + return False + block_size = self.best_block_size(after - before, len(data_block)) + + # Progress message + speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) + if data_len is None: + self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') + else: + percent_str = self.calc_percent(byte_counter, data_len) + eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) + self.report_progress(percent_str, data_len_str, speed_str, eta_str) + + # Apply rate limit + self.slow_down(start, byte_counter - resume_len) + + if stream is None: + self.trouble(u'\nERROR: Did not get any data blocks') + return False + stream.close() + self.report_finish() + if data_len is not None and byte_counter != data_len: + raise ContentTooShortError(byte_counter, long(data_len)) + self.try_rename(tmpfilename, filename) + + # Update file modification time + if self.params.get('updatetime', True): + info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) + + return True + + +class InfoExtractor(object): + """Information Extractor class. + + Information extractors are the classes that, given a URL, extract + information from the video (or videos) the URL refers to. This + information includes the real video URL, the video title and simplified + title, author and others. The information is stored in a dictionary + which is then passed to the FileDownloader. The FileDownloader + processes this information possibly downloading the video to the file + system, among other possible outcomes. The dictionaries must include + the following fields: + + id: Video identifier. + url: Final video URL. + uploader: Nickname of the video uploader. + title: Literal title. + stitle: Simplified title. + ext: Video filename extension. + format: Video format. + player_url: SWF Player URL (may be None). + + The following fields are optional. Their primary purpose is to allow + youtube-dl to serve as the backend for a video search function, such + as the one in youtube2mp3. They are only used when their respective + forced printing functions are called: + + thumbnail: Full URL to a video thumbnail image. + description: One-line video description. + + Subclasses of this one should re-define the _real_initialize() and + _real_extract() methods and define a _VALID_URL regexp. + Probably, they should also be added to the list of extractors. + """ + + _ready = False + _downloader = None + + def __init__(self, downloader=None): + """Constructor. Receives an optional downloader.""" + self._ready = False + self.set_downloader(downloader) + + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url) is not None + + def initialize(self): + """Initializes an instance (authentication, etc).""" + if not self._ready: + self._real_initialize() + self._ready = True + + def extract(self, url): + """Extracts URL information and returns it in list of dicts.""" + self.initialize() + return self._real_extract(url) + + def set_downloader(self, downloader): + """Sets the downloader for this IE.""" + self._downloader = downloader + + def _real_initialize(self): + """Real initialization process. Redefine in subclasses.""" + pass + + def _real_extract(self, url): + """Real extraction process. Redefine in subclasses.""" + pass + + +class YoutubeIE(InfoExtractor): + """Information extractor for youtube.com.""" + + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' + _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' + _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' + _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' + _NETRC_MACHINE = 'youtube' + # Listed in order of quality + _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] + _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] + _video_extensions = { + '13': '3gp', + '17': 'mp4', + '18': 'mp4', + '22': 'mp4', + '37': 'mp4', + '38': 'video', # You actually don't know if this will be MOV, AVI or whatever + '43': 'webm', + '44': 'webm', + '45': 'webm', + } + _video_dimensions = { + '5': '240x400', + '6': '???', + '13': '???', + '17': '144x176', + '18': '360x640', + '22': '720x1280', + '34': '360x640', + '35': '480x854', + '37': '1080x1920', + '38': '3072x4096', + '43': '360x640', + '44': '480x854', + '45': '720x1280', + } + IE_NAME = u'youtube' + + def report_lang(self): + """Report attempt to set language.""" + self._downloader.to_screen(u'[youtube] Setting language') + + def report_login(self): + """Report attempt to log in.""" + self._downloader.to_screen(u'[youtube] Logging in') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_screen(u'[youtube] Confirming age') + + def report_video_webpage_download(self, video_id): + """Report attempt to download video webpage.""" + self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) + + def report_video_info_webpage_download(self, video_id): + """Report attempt to download video info webpage.""" + self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) + + def report_information_extraction(self, video_id): + """Report attempt to extract video information.""" + self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) + + def report_unavailable_format(self, video_id, format): + """Report extracted video URL.""" + self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) + + def report_rtmp_download(self): + """Indicate the download will use the RTMP protocol.""" + self._downloader.to_screen(u'[youtube] RTMP download detected') + + def _print_formats(self, formats): + print 'Available formats:' + for x in formats: + print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')) + + def _real_initialize(self): + if self._downloader is None: + return + + username = None + password = None + downloader_params = self._downloader.params + + # Attempt to use provided username and password or .netrc data + if downloader_params.get('username', None) is not None: + username = downloader_params['username'] + password = downloader_params['password'] + elif downloader_params.get('usenetrc', False): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + username = info[0] + password = info[2] + else: + raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) + except (IOError, netrc.NetrcParseError), err: + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) + return + + # Set language + request = urllib2.Request(self._LANG_URL) + try: + self.report_lang() + urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) + return + + # No authentication to be performed + if username is None: + return + + # Log in + login_form = { + 'current_form': 'loginForm', + 'next': '/', + 'action_login': 'Log In', + 'username': username, + 'password': password, + } + request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) + try: + self.report_login() + login_results = urllib2.urlopen(request).read() + if re.search(r'(?i)]* name="loginForm"', login_results) is not None: + self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') + return + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) + return + + # Confirm age + age_form = { + 'next_url': '/', + 'action_confirm': 'Confirm', + } + request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form)) + try: + self.report_age_confirmation() + age_results = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) + return + + def _real_extract(self, url): + # Extract video id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(2) + + # Get video webpage + self.report_video_webpage_download(video_id) + request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) + try: + video_webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + # Attempt to extract SWF player URL + mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) + if mobj is not None: + player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) + else: + player_url = None + + # Get video info + self.report_video_info_webpage_download(video_id) + for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: + video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + % (video_id, el_type)) + request = urllib2.Request(video_info_url) + try: + video_info_webpage = urllib2.urlopen(request).read() + video_info = parse_qs(video_info_webpage) + if 'token' in video_info: + break + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) + return + if 'token' not in video_info: + if 'reason' in video_info: + self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8')) + else: + self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') + return + + # Start extracting information + self.report_information_extraction(video_id) + + # uploader + if 'author' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = urllib.unquote_plus(video_info['author'][0]) + + # title + if 'title' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = urllib.unquote_plus(video_info['title'][0]) + video_title = video_title.decode('utf-8') + video_title = sanitize_title(video_title) + + # simplified title + simple_title = _simplify_title(video_title) + + # thumbnail image + if 'thumbnail_url' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + video_thumbnail = '' + else: # don't panic if we can't find it + video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) + + # upload date + upload_date = u'NA' + mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL) + if mobj is not None: + upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) + format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] + for expression in format_expressions: + try: + upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') + except: + pass + + # description + try: + lxml.etree + except NameError: + video_description = u'No description available.' + if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False): + mobj = re.search(r'', video_webpage) + if mobj is not None: + video_description = mobj.group(1).decode('utf-8') + else: + html_parser = lxml.etree.HTMLParser(encoding='utf-8') + vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser) + video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) + # TODO use another parser + + # token + video_token = urllib.unquote_plus(video_info['token'][0]) + + # Decide which formats to download + req_format = self._downloader.params.get('format', None) + + if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): + self.report_rtmp_download() + video_url_list = [(None, video_info['conn'][0])] + elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: + url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') + url_data = [parse_qs(uds) for uds in url_data_strs] + url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) + url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data) + + format_limit = self._downloader.params.get('format_limit', None) + available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats + if format_limit is not None and format_limit in available_formats: + format_list = available_formats[available_formats.index(format_limit):] + else: + format_list = available_formats + existing_formats = [x for x in format_list if x in url_map] + if len(existing_formats) == 0: + self._downloader.trouble(u'ERROR: no known formats available for video') + return + if self._downloader.params.get('listformats', None): + self._print_formats(existing_formats) + return + if req_format is None or req_format == 'best': + video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality + elif req_format == 'worst': + video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality + elif req_format in ('-1', 'all'): + video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats + else: + # Specific formats. We pick the first in a slash-delimeted sequence. + # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. + req_formats = req_format.split('/') + video_url_list = None + for rf in req_formats: + if rf in url_map: + video_url_list = [(rf, url_map[rf])] + break + if video_url_list is None: + self._downloader.trouble(u'ERROR: requested format not available') + return + else: + self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') + return + + for format_param, video_real_url in video_url_list: + # At this point we have a new video + self._downloader.increment_downloads() + + # Extension + video_extension = self._video_extensions.get(format_param, 'flv') + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_real_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': upload_date, + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description, + 'player_url': player_url, + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class MetacafeIE(InfoExtractor): + """Information Extractor for metacafe.com.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' + _DISCLAIMER = 'http://www.metacafe.com/family_filter/' + _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' + _youtube_ie = None + IE_NAME = u'metacafe' + + def __init__(self, youtube_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._youtube_ie = youtube_ie + + def report_disclaimer(self): + """Report disclaimer retrieval.""" + self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_screen(u'[metacafe] Confirming age') + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) + + def _real_initialize(self): + # Retrieve disclaimer + request = urllib2.Request(self._DISCLAIMER) + try: + self.report_disclaimer() + disclaimer = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) + return + + # Confirm age + disclaimer_form = { + 'filters': '0', + 'submit': "Continue - I'm over 18", + } + request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form)) + try: + self.report_age_confirmation() + disclaimer = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) + return + + def _real_extract(self, url): + # Extract id and simplified title from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + # Check if video comes from YouTube + mobj2 = re.match(r'^yt-(.*)$', video_id) + if mobj2 is not None: + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) + return + + # At this point we have a new video + self._downloader.increment_downloads() + + simple_title = mobj.group(2).decode('utf-8') + + # Retrieve video webpage to extract further information + request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) + return + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) + if mobj is not None: + mediaURL = urllib.unquote(mobj.group(1)) + video_extension = mediaURL[-3:] + + # Extract gdaKey if available + mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) + if mobj is None: + video_url = mediaURL + else: + gdaKey = mobj.group(1) + video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) + else: + mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + vardict = parse_qs(mobj.group(1)) + if 'mediaData' not in vardict: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = mobj.group(1).replace('\\/', '/') + video_extension = mediaURL[-3:] + video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) + + mobj = re.search(r'(?im)(.*) - Video', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + video_title = sanitize_title(video_title) + + mobj = re.search(r'(?ms)By:\s*(.+?)<', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = mobj.group(1) + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class DailymotionIE(InfoExtractor): + """Information Extractor for Dailymotion""" + + _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' + IE_NAME = u'dailymotion' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # Extract id and simplified title from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + # At this point we have a new video + self._downloader.increment_downloads() + video_id = mobj.group(1) + + video_extension = 'flv' + + # Retrieve video webpage to extract further information + request = urllib2.Request(url) + request.add_header('Cookie', 'family_filter=off') + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) + return + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + sequence = urllib.unquote(mobj.group(1)) + mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '') + + # if needed add http://www.dailymotion.com/ if relative URL + + video_url = mediaURL + + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = _unescapeHTML(mobj.group('title').decode('utf-8')) + video_title = sanitize_title(video_title) + simple_title = _simplify_title(video_title) + + mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = mobj.group(1) + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class GoogleIE(InfoExtractor): + """Information extractor for video.google.com.""" + + _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' + IE_NAME = u'video.google' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # At this point we have a new video + self._downloader.increment_downloads() + video_id = mobj.group(1) + + video_extension = 'mp4' + + # Retrieve video webpage to extract further information + request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + # Extract URL, uploader, and title from webpage + self.report_extraction(video_id) + mobj = re.search(r"download_url:'([^']+)'", webpage) + if mobj is None: + video_extension = 'flv' + mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = urllib.unquote(mobj.group(1)) + mediaURL = mediaURL.replace('\\x3d', '\x3d') + mediaURL = mediaURL.replace('\\x26', '\x26') + + video_url = mediaURL + + mobj = re.search(r'(.*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + video_title = sanitize_title(video_title) + simple_title = _simplify_title(video_title) + + # Extract video description + mobj = re.search(r'([^<]*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video description') + return + video_description = mobj.group(1).decode('utf-8') + if not video_description: + video_description = 'No description available.' + + # Extract video thumbnail + if self._downloader.params.get('forcethumbnail', False): + request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1) + else: # we need something to pass to process_info + video_thumbnail = '' + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': u'NA', + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class PhotobucketIE(InfoExtractor): + """Information extractor for photobucket.com.""" + + _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + IE_NAME = u'photobucket' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # At this point we have a new video + self._downloader.increment_downloads() + video_id = mobj.group(1) + + video_extension = 'flv' + + # Retrieve video webpage to extract further information + request = urllib2.Request(url) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + # Extract URL, uploader, and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = urllib.unquote(mobj.group(1)) + + video_url = mediaURL + + mobj = re.search(r'(.*) video by (.*) - Photobucket', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + video_title = sanitize_title(video_title) + simple_title = _simplify_title(vide_title) + + video_uploader = mobj.group(2).decode('utf-8') + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader, + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class YahooIE(InfoExtractor): + """Information extractor for video.yahoo.com.""" + + # _VALID_URL matches all Yahoo! Video URLs + # _VPAGE_URL matches only the extractable '/watch/' URLs + _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' + _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' + IE_NAME = u'video.yahoo' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) + + def _real_extract(self, url, new_video=True): + # Extract ID from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # At this point we have a new video + self._downloader.increment_downloads() + video_id = mobj.group(2) + video_extension = 'flv' + + # Rewrite valid but non-extractable URLs as + # extractable English language /watch/ URLs + if re.match(self._VPAGE_URL, url) is None: + request = urllib2.Request(url) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract id field') + return + yahoo_id = mobj.group(1) + + mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract vid field') + return + yahoo_vid = mobj.group(1) + + url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) + return self._real_extract(url, new_video=False) + + # Retrieve video webpage to extract further information + request = urllib2.Request(url) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + # Extract uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + simple_title = _simplify_title(video_title) + + mobj = re.search(r'

(.*)

', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video uploader') + return + video_uploader = mobj.group(1).decode('utf-8') + + # Extract video thumbnail + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + # Extract video description + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video description') + return + video_description = mobj.group(1).decode('utf-8') + if not video_description: + video_description = 'No description available.' + + # Extract video height and width + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video height') + return + yv_video_height = mobj.group(1) + + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video width') + return + yv_video_width = mobj.group(1) + + # Retrieve video playlist to extract media URL + # I'm not completely sure what all these options are, but we + # seem to need most of them, otherwise the server sends a 401. + yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents + yv_bitrate = '700' # according to Wikipedia this is hard-coded + request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + + '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + + '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + # Extract media URL from playlist XML + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + simple_title = _simplify_title(video_title) + + # Extract uploader + mobj = re.search(r'http://vimeo.com/(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video uploader') + return + video_uploader = mobj.group(1).decode('utf-8') + + # Extract video thumbnail + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + # # Extract video description + # mobj = re.search(r'', webpage) + # if mobj is None: + # self._downloader.trouble(u'ERROR: unable to extract video description') + # return + # video_description = mobj.group(1).decode('utf-8') + # if not video_description: video_description = 'No description available.' + video_description = 'Foo.' + + # Vimeo specific: extract request signature + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract request signature') + return + sig = mobj.group(1).decode('utf-8') + + # Vimeo specific: extract video quality information + mobj = re.search(r'(\d+)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video quality information') + return + quality = mobj.group(1).decode('utf-8') + + if int(quality) == 1: + quality = 'hd' + else: + quality = 'sd' + + # Vimeo specific: Extract request signature expiration + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract request signature expiration') + return + sig_exp = mobj.group(1).decode('utf-8') + + video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality) + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': u'mp4', + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description, + 'thumbnail': video_thumbnail, + 'description': video_description, + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') + + +class GenericIE(InfoExtractor): + """Generic last-resort information extractor.""" + + _VALID_URL = r'.*' + IE_NAME = u'generic' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') + self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # At this point we have a new video + self._downloader.increment_downloads() + + video_id = url.split('/')[-1] + request = urllib2.Request(url) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + except ValueError, err: + # since this is the last-resort InfoExtractor, if + # this error is thrown, it'll be thrown here + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + self.report_extraction(video_id) + # Start with something easy: JW Player in SWFObject + mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) + if mobj is None: + # Broaden the search a little bit + mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # It's possible that one of the regexes + # matched, but returned an empty group: + if mobj.group(1) is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_url = urllib.unquote(mobj.group(1)) + video_id = os.path.basename(video_url) + + # here's a fun little line of code for you: + video_extension = os.path.splitext(video_id)[1][1:] + video_id = os.path.splitext(video_id)[0] + + # it's tempting to parse this further, but you would + # have to take into account all the variations like + # Video Title - Site Name + # Site Name | Video Title + # Video Title - Tagline | Site Name + # and so on and so forth; it's just not practical + mobj = re.search(r'(.*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + video_title = sanitize_title(video_title) + simple_title = _simplify_title(video_title) + + # video uploader is domain name + mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_uploader = mobj.group(1).decode('utf-8') + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader, + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class YoutubeSearchIE(InfoExtractor): + """Information Extractor for YouTube search queries.""" + _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' + _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en' + _VIDEO_INDICATOR = r'href="/watch\?v=.+?"' + _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' + _youtube_ie = None + _max_youtube_results = 1000 + IE_NAME = u'youtube:search' + + def __init__(self, youtube_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._youtube_ie = youtube_ie + + def report_download_page(self, query, pagenum): + """Report attempt to download playlist page with given number.""" + query = query.decode(preferredencoding()) + self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) + + def _real_initialize(self): + self._youtube_ie.initialize() + + def _real_extract(self, query): + mobj = re.match(self._VALID_URL, query) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) + return + + prefix, query = query.split(':') + prefix = prefix[8:] + query = query.encode('utf-8') + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_youtube_results) + return + else: + try: + n = long(prefix) + if n <= 0: + self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) + return + elif n > self._max_youtube_results: + self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) + n = self._max_youtube_results + self._download_n_results(query, n) + return + except ValueError: # parsing prefix as integer fails + self._download_n_results(query, 1) + return + + def _download_n_results(self, query, n): + """Downloads a specified number of results for a query""" + + video_ids = [] + already_seen = set() + pagenum = 1 + + while True: + self.report_download_page(query, pagenum) + result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) + request = urllib2.Request(result_url) + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1] + if video_id not in already_seen: + video_ids.append(video_id) + already_seen.add(video_id) + if len(video_ids) == n: + # Specified n videos reached + for id in video_ids: + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) + return + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + for id in video_ids: + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) + return + + pagenum = pagenum + 1 + + +class GoogleSearchIE(InfoExtractor): + """Information Extractor for Google Video search queries.""" + _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' + _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' + _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&' + _MORE_PAGES_INDICATOR = r'Next' + _google_ie = None + _max_google_results = 1000 + IE_NAME = u'video.google:search' + + def __init__(self, google_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._google_ie = google_ie + + def report_download_page(self, query, pagenum): + """Report attempt to download playlist page with given number.""" + query = query.decode(preferredencoding()) + self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) + + def _real_initialize(self): + self._google_ie.initialize() + + def _real_extract(self, query): + mobj = re.match(self._VALID_URL, query) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) + return + + prefix, query = query.split(':') + prefix = prefix[8:] + query = query.encode('utf-8') + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_google_results) + return + else: + try: + n = long(prefix) + if n <= 0: + self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) + return + elif n > self._max_google_results: + self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) + n = self._max_google_results + self._download_n_results(query, n) + return + except ValueError: # parsing prefix as integer fails + self._download_n_results(query, 1) + return + + def _download_n_results(self, query, n): + """Downloads a specified number of results for a query""" + + video_ids = [] + already_seen = set() + pagenum = 1 + + while True: + self.report_download_page(query, pagenum) + result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) + request = urllib2.Request(result_url) + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + video_id = mobj.group(1) + if video_id not in already_seen: + video_ids.append(video_id) + already_seen.add(video_id) + if len(video_ids) == n: + # Specified n videos reached + for id in video_ids: + self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) + return + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + for id in video_ids: + self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) + return + + pagenum = pagenum + 1 + + +class YahooSearchIE(InfoExtractor): + """Information Extractor for Yahoo! Video search queries.""" + _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' + _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' + _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' + _MORE_PAGES_INDICATOR = r'\s*Next' + _yahoo_ie = None + _max_yahoo_results = 1000 + IE_NAME = u'video.yahoo:search' + + def __init__(self, yahoo_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._yahoo_ie = yahoo_ie + + def report_download_page(self, query, pagenum): + """Report attempt to download playlist page with given number.""" + query = query.decode(preferredencoding()) + self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) + + def _real_initialize(self): + self._yahoo_ie.initialize() + + def _real_extract(self, query): + mobj = re.match(self._VALID_URL, query) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) + return + + prefix, query = query.split(':') + prefix = prefix[8:] + query = query.encode('utf-8') + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_yahoo_results) + return + else: + try: + n = long(prefix) + if n <= 0: + self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) + return + elif n > self._max_yahoo_results: + self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) + n = self._max_yahoo_results + self._download_n_results(query, n) + return + except ValueError: # parsing prefix as integer fails + self._download_n_results(query, 1) + return + + def _download_n_results(self, query, n): + """Downloads a specified number of results for a query""" + + video_ids = [] + already_seen = set() + pagenum = 1 + + while True: + self.report_download_page(query, pagenum) + result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) + request = urllib2.Request(result_url) + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + video_id = mobj.group(1) + if video_id not in already_seen: + video_ids.append(video_id) + already_seen.add(video_id) + if len(video_ids) == n: + # Specified n videos reached + for id in video_ids: + self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) + return + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + for id in video_ids: + self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) + return + + pagenum = pagenum + 1 + + +class YoutubePlaylistIE(InfoExtractor): + """Information Extractor for YouTube playlists.""" + + _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' + _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' + _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' + _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' + _youtube_ie = None + IE_NAME = u'youtube:playlist' + + def __init__(self, youtube_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._youtube_ie = youtube_ie + + def report_download_page(self, playlist_id, pagenum): + """Report attempt to download playlist page with given number.""" + self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) + + def _real_initialize(self): + self._youtube_ie.initialize() + + def _real_extract(self, url): + # Extract playlist id + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + # Single video case + if mobj.group(3) is not None: + self._youtube_ie.extract(mobj.group(3)) + return + + # Download playlist pages + # prefix is 'p' as default for playlists but there are other types that need extra care + playlist_prefix = mobj.group(1) + if playlist_prefix == 'a': + playlist_access = 'artist' + else: + playlist_prefix = 'p' + playlist_access = 'view_play_list' + playlist_id = mobj.group(2) + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(playlist_id, pagenum) + url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum) + request = urllib2.Request(url) + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + ids_in_page = [] + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + video_ids.extend(ids_in_page) + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + break + pagenum = pagenum + 1 + + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + video_ids = video_ids[playliststart:playlistend] + + for id in video_ids: + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) + return + + +class YoutubeUserIE(InfoExtractor): + """Information Extractor for YouTube users.""" + + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' + _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' + _GDATA_PAGE_SIZE = 50 + _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' + _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' + _youtube_ie = None + IE_NAME = u'youtube:user' + + def __init__(self, youtube_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._youtube_ie = youtube_ie + + def report_download_page(self, username, start_index): + """Report attempt to download user page.""" + self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % + (username, start_index, start_index + self._GDATA_PAGE_SIZE)) + + def _real_initialize(self): + self._youtube_ie.initialize() + + def _real_extract(self, url): + # Extract username + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + username = mobj.group(1) + + # Download video ids using YouTube Data API. Result size per + # query is limited (currently to 50 videos) so we need to query + # page by page until there are no video ids - it means we got + # all of them. + + video_ids = [] + pagenum = 0 + + while True: + start_index = pagenum * self._GDATA_PAGE_SIZE + 1 + self.report_download_page(username, start_index) + + request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) + + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + ids_in_page = [] + + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + + video_ids.extend(ids_in_page) + + # A little optimization - if current page is not + # "full", ie. does not contain PAGE_SIZE video ids then + # we can assume that this page is the last one - there + # are no more ids on further pages - no need to query + # again. + + if len(ids_in_page) < self._GDATA_PAGE_SIZE: + break + + pagenum += 1 + + all_ids_count = len(video_ids) + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + + if playlistend == -1: + video_ids = video_ids[playliststart:] + else: + video_ids = video_ids[playliststart:playlistend] + + self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" % + (username, all_ids_count, len(video_ids))) + + for video_id in video_ids: + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id) + + +class DepositFilesIE(InfoExtractor): + """Information extractor for depositfiles.com""" + + _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' + IE_NAME = u'DepositFiles' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) + + def _real_extract(self, url): + # At this point we have a new file + self._downloader.increment_downloads() + + file_id = url.split('/')[-1] + # Rebuild url in english locale + url = 'http://depositfiles.com/en/files/' + file_id + + # Retrieve file webpage with 'Free download' button pressed + free_download_indication = { 'gateway_result' : '1' } + request = urllib2.Request(url, urllib.urlencode(free_download_indication)) + try: + self.report_download_webpage(file_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err)) + return + + # Search for the real file URL + mobj = re.search(r'
(Attention.*?)', webpage, re.DOTALL) + if (mobj is not None) and (mobj.group(1) is not None): + restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() + self._downloader.trouble(u'ERROR: %s' % restriction_message) + else: + self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) + return + + file_url = mobj.group(1) + file_extension = os.path.splitext(file_url)[1][1:] + + # Search for file title + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + file_title = mobj.group(1).decode('utf-8') + + try: + # Process file information + self._downloader.process_info({ + 'id': file_id.decode('utf-8'), + 'url': file_url.decode('utf-8'), + 'uploader': u'NA', + 'upload_date': u'NA', + 'title': file_title, + 'stitle': file_title, + 'ext': file_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'ERROR: unable to download file') + + +class FacebookIE(InfoExtractor): + """Information Extractor for Facebook""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P\d+)(?:.*)' + _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' + _NETRC_MACHINE = 'facebook' + _available_formats = ['video', 'highqual', 'lowqual'] + _video_extensions = { + 'video': 'mp4', + 'highqual': 'mp4', + 'lowqual': 'mp4', + } + IE_NAME = u'facebook' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def _reporter(self, message): + """Add header and report message.""" + self._downloader.to_screen(u'[facebook] %s' % message) + + def report_login(self): + """Report attempt to log in.""" + self._reporter(u'Logging in') + + def report_video_webpage_download(self, video_id): + """Report attempt to download video webpage.""" + self._reporter(u'%s: Downloading video webpage' % video_id) + + def report_information_extraction(self, video_id): + """Report attempt to extract video information.""" + self._reporter(u'%s: Extracting video information' % video_id) + + def _parse_page(self, video_webpage): + """Extract video information from page""" + # General data + data = {'title': r'\("video_title", "(.*?)"\)', + 'description': r'
(.*?)
', + 'owner': r'\("video_owner_name", "(.*?)"\)', + 'thumbnail': r'\("thumb_url", "(?P.*?)"\)', + } + video_info = {} + for piece in data.keys(): + mobj = re.search(data[piece], video_webpage) + if mobj is not None: + video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) + + # Video urls + video_urls = {} + for fmt in self._available_formats: + mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage) + if mobj is not None: + # URL is in a Javascript segment inside an escaped Unicode format within + # the generally utf-8 page + video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) + video_info['video_urls'] = video_urls + + return video_info + + def _real_initialize(self): + if self._downloader is None: + return + + useremail = None + password = None + downloader_params = self._downloader.params + + # Attempt to use provided username and password or .netrc data + if downloader_params.get('username', None) is not None: + useremail = downloader_params['username'] + password = downloader_params['password'] + elif downloader_params.get('usenetrc', False): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + useremail = info[0] + password = info[2] + else: + raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) + except (IOError, netrc.NetrcParseError), err: + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) + return + + if useremail is None: + return + + # Log in + login_form = { + 'email': useremail, + 'pass': password, + 'login': 'Log+In' + } + request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) + try: + self.report_login() + login_results = urllib2.urlopen(request).read() + if re.search(r'', login_results) is not None: + self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') + return + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) + return + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('ID') + + # Get video webpage + self.report_video_webpage_download(video_id) + request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id) + try: + page = urllib2.urlopen(request) + video_webpage = page.read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + # Start extracting information + self.report_information_extraction(video_id) + + # Extract information + video_info = self._parse_page(video_webpage) + + # uploader + if 'owner' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = video_info['owner'] + + # title + if 'title' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = video_info['title'] + video_title = video_title.decode('utf-8') + video_title = sanitize_title(video_title) + + simple_title = _simplify_title(video_title) + + # thumbnail image + if 'thumbnail' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + video_thumbnail = '' + else: + video_thumbnail = video_info['thumbnail'] + + # upload date + upload_date = u'NA' + if 'upload_date' in video_info: + upload_time = video_info['upload_date'] + timetuple = email.utils.parsedate_tz(upload_time) + if timetuple is not None: + try: + upload_date = time.strftime('%Y%m%d', timetuple[0:9]) + except: + pass + + # description + video_description = video_info.get('description', 'No description available.') + + url_map = video_info['video_urls'] + if len(url_map.keys()) > 0: + # Decide which formats to download + req_format = self._downloader.params.get('format', None) + format_limit = self._downloader.params.get('format_limit', None) + + if format_limit is not None and format_limit in self._available_formats: + format_list = self._available_formats[self._available_formats.index(format_limit):] + else: + format_list = self._available_formats + existing_formats = [x for x in format_list if x in url_map] + if len(existing_formats) == 0: + self._downloader.trouble(u'ERROR: no known formats available for video') + return + if req_format is None: + video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality + elif req_format == 'worst': + video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality + elif req_format == '-1': + video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats + else: + # Specific format + if req_format not in url_map: + self._downloader.trouble(u'ERROR: requested format not available') + return + video_url_list = [(req_format, url_map[req_format])] # Specific format + + for format_param, video_real_url in video_url_list: + + # At this point we have a new video + self._downloader.increment_downloads() + + # Extension + video_extension = self._video_extensions.get(format_param, 'mp4') + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_real_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': upload_date, + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description.decode('utf-8'), + 'player_url': None, + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + +class BlipTVIE(InfoExtractor): + """Information extractor for blip.tv""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' + _URL_EXT = r'^.*\.([a-z0-9]+)$' + IE_NAME = u'blip.tv' + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + + def report_direct_download(self, title): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if '?' in url: + cchar = '&' + else: + cchar = '?' + json_url = url + cchar + 'skin=json&version=2&no_wrap=1' + request = urllib2.Request(json_url) + self.report_extraction(mobj.group(1)) + info = None + try: + urlh = urllib2.urlopen(request) + if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download + basename = url.split('/')[-1] + title,ext = os.path.splitext(basename) + title = title.decode('UTF-8') + ext = ext.replace('.', '') + self.report_direct_download(title) + info = { + 'id': title, + 'url': url, + 'title': title, + 'stitle': _simplify_title(title), + 'ext': ext, + 'urlhandle': urlh + } + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) + return + if info is None: # Regular URL + try: + json_code = urlh.read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err)) + return + + try: + json_data = json.loads(json_code) + if 'Post' in json_data: + data = json_data['Post'] + else: + data = json_data + + upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') + video_url = data['media']['url'] + umobj = re.match(self._URL_EXT, video_url) + if umobj is None: + raise ValueError('Can not determine filename extension') + ext = umobj.group(1) + + info = { + 'id': data['item_id'], + 'url': video_url, + 'uploader': data['display_name'], + 'upload_date': upload_date, + 'title': data['title'], + 'stitle': _simplify_title(data['title']), + 'ext': ext, + 'format': data['media']['mimeType'], + 'thumbnail': data['thumbnailUrl'], + 'description': data['description'], + 'player_url': data['embedUrl'] + } + except (ValueError,KeyError), err: + self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) + return + + self._downloader.increment_downloads() + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class MyVideoIE(InfoExtractor): + """Information Extractor for myvideo.de.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' + IE_NAME = u'myvideo' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._download.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + # Get video webpage + request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + self.report_extraction(video_id) + mobj = re.search(r'', + webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + video_url = mobj.group(1) + ('/%s.flv' % video_id) + + mobj = re.search('([^<]+)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + + video_title = mobj.group(1) + video_title = sanitize_title(video_title) + + simple_title = _simplify_title(video_title) + + try: + self._downloader.process_info({ + 'id': video_id, + 'url': video_url, + 'uploader': u'NA', + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': u'flv', + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: Unable to download video') + +class ComedyCentralIE(InfoExtractor): + """Information extractor for The Daily Show and Colbert Report """ + + _VALID_URL = r'^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?Pthedailyshow|colbertnation)\.com/full-episodes/(?P.*)$' + IE_NAME = u'comedycentral' + + def report_extraction(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) + + def report_config_download(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) + + def report_index_download(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) + + def report_player_url(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if mobj.group('shortname'): + if mobj.group('shortname') in ('tds', 'thedailyshow'): + url = u'http://www.thedailyshow.com/full-episodes/' + else: + url = u'http://www.colbertnation.com/full-episodes/' + mobj = re.match(self._VALID_URL, url) + assert mobj is not None + + dlNewest = not mobj.group('episode') + if dlNewest: + epTitle = mobj.group('showname') + else: + epTitle = mobj.group('episode') + + req = urllib2.Request(url) + self.report_extraction(epTitle) + try: + htmlHandle = urllib2.urlopen(req) + html = htmlHandle.read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) + return + if dlNewest: + url = htmlHandle.geturl() + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) + return + if mobj.group('episode') == '': + self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url) + return + epTitle = mobj.group('episode') + + mMovieParams = re.findall('(?:[^/]+)/(?P[^/?]+)[/?]?.*$' + IE_NAME = u'escapist' + + def report_extraction(self, showName): + self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) + + def report_config_download(self, showName): + self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + showName = mobj.group('showname') + videoId = mobj.group('episode') + + self.report_extraction(showName) + try: + webPage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) + return + + descMatch = re.search('[0-9]+)/(?P.*)$' + IE_NAME = u'collegehumor' + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('videoid') + + self.report_webpage(video_id) + request = urllib2.Request(url) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + m = re.search(r'id="video:(?P[0-9]+)"', webpage) + if m is None: + self._downloader.trouble(u'ERROR: Cannot extract internal video ID') + return + internal_video_id = m.group('internalvideoid') + + info = { + 'id': video_id, + 'internal_id': internal_video_id, + } + + self.report_extraction(video_id) + xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id + try: + metaXml = urllib2.urlopen(xmlUrl).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err)) + return + + mdoc = xml.etree.ElementTree.fromstring(metaXml) + try: + videoNode = mdoc.findall('./video')[0] + info['description'] = videoNode.findall('./description')[0].text + info['title'] = videoNode.findall('./caption')[0].text + info['stitle'] = _simplify_title(info['title']) + info['url'] = videoNode.findall('./file')[0].text + info['thumbnail'] = videoNode.findall('./thumbnail')[0].text + info['ext'] = info['url'].rpartition('.')[2] + info['format'] = info['ext'] + except IndexError: + self._downloader.trouble(u'\nERROR: Invalid metadata XML file') + return + + self._downloader.increment_downloads() + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class XVideosIE(InfoExtractor): + """Information extractor for xvideos.com""" + + _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + IE_NAME = u'xvideos' + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(1).decode('utf-8') + + self.report_webpage(video_id) + + request = urllib2.Request(r'http://www.xvideos.com/video' + video_id) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + self.report_extraction(video_id) + + + # Extract video URL + mobj = re.search(r'flv_url=(.+?)&', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = urllib2.unquote(mobj.group(1).decode('utf-8')) + + + # Extract title + mobj = re.search(r'(.*?)\s+-\s+XVID', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + + + # Extract video thumbnail + mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + + + self._downloader.increment_downloads() + info = { + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'stitle': _simplify_title(video_title), + 'ext': 'flv', + 'format': 'flv', + 'thumbnail': video_thumbnail, + 'description': None, + 'player_url': None, + } + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download ' + video_id) + + +class SoundcloudIE(InfoExtractor): + """Information extractor for soundcloud.com + To access the media, the uid of the song and a stream token + must be extracted from the page source and the script must make + a request to media.soundcloud.com/crossdomain.xml. Then + the media can be grabbed by requesting from an url composed + of the stream token and uid + """ + + _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' + IE_NAME = u'soundcloud' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + # extract uploader (which is in the url) + uploader = mobj.group(1).decode('utf-8') + # extract simple title (uploader + slug of song title) + slug_title = mobj.group(2).decode('utf-8') + simple_title = uploader + '-' + slug_title + + self.report_webpage('%s/%s' % (uploader, slug_title)) + + request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title)) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + self.report_extraction('%s/%s' % (uploader, slug_title)) + + # extract uid and stream token that soundcloud hands out for access + mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage) + if mobj: + video_id = mobj.group(1) + stream_token = mobj.group(2) + + # extract unsimplified title + mobj = re.search('"title":"(.*?)",', webpage) + if mobj: + title = mobj.group(1) + + # construct media url (with uid/token) + mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s" + mediaURL = mediaURL % (video_id, stream_token) + + # description + description = u'No description available' + mobj = re.search('track-description-value"><p>(.*?)</p>', webpage) + if mobj: + description = mobj.group(1) + + # upload date + upload_date = None + mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage) + if mobj: + try: + upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') + except Exception, e: + print str(e) + + # for soundcloud, a request to a cross domain is required for cookies + request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers) + + try: + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': mediaURL, + 'uploader': uploader.decode('utf-8'), + 'upload_date': upload_date, + 'title': simple_title.decode('utf-8'), + 'stitle': simple_title.decode('utf-8'), + 'ext': u'mp3', + 'format': u'NA', + 'player_url': None, + 'description': description.decode('utf-8') + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class InfoQIE(InfoExtractor): + """Information extractor for infoq.com""" + + _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' + IE_NAME = u'infoq' + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + self.report_webpage(url) + + request = urllib2.Request(url) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + self.report_extraction(url) + + + # Extract video URL + mobj = re.search(r"jsclassref='([^']*)'", webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64')) + + + # Extract title + mobj = re.search(r'contentTitle = "(.*?)";', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + + # Extract description + video_description = u'No description available.' + mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) + if mobj is not None: + video_description = mobj.group(1).decode('utf-8') + + video_filename = video_url.split('/')[-1] + video_id, extension = video_filename.split('.') + + self._downloader.increment_downloads() + info = { + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'stitle': _simplify_title(video_title), + 'ext': extension, + 'format': extension, # Extension is always(?) mp4, but seems to be flv + 'thumbnail': None, + 'description': video_description, + 'player_url': None, + } + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download ' + video_url) + +class MixcloudIE(InfoExtractor): + """Information extractor for www.mixcloud.com""" + _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' + IE_NAME = u'mixcloud' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_json(self, file_id): + """Report JSON download.""" + self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + + def get_urls(self, jsonData, fmt, bitrate='best'): + """Get urls from 'audio_formats' section in json""" + file_url = None + try: + bitrate_list = jsonData[fmt] + if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: + bitrate = max(bitrate_list) # select highest + + url_list = jsonData[fmt][bitrate] + except TypeError: # we have no bitrate info. + url_list = jsonData[fmt] + + return url_list + + def check_urls(self, url_list): + """Returns 1st active url from list""" + for url in url_list: + try: + urllib2.urlopen(url) + return url + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + url = None + + return None + + def _print_formats(self, formats): + print 'Available formats:' + for fmt in formats.keys(): + for b in formats[fmt]: + try: + ext = formats[fmt][b][0] + print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]) + except TypeError: # we have no bitrate info + ext = formats[fmt][0] + print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]) + break + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + # extract uploader & filename from url + uploader = mobj.group(1).decode('utf-8') + file_id = uploader + "-" + mobj.group(2).decode('utf-8') + + # construct API request + file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' + # retrieve .json file with links to files + request = urllib2.Request(file_url) + try: + self.report_download_json(file_url) + jsonData = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err)) + return + + # parse JSON + json_data = json.loads(jsonData) + player_url = json_data['player_swf_url'] + formats = dict(json_data['audio_formats']) + + req_format = self._downloader.params.get('format', None) + bitrate = None + + if self._downloader.params.get('listformats', None): + self._print_formats(formats) + return + + if req_format is None or req_format == 'best': + for format_param in formats.keys(): + url_list = self.get_urls(formats, format_param) + # check urls + file_url = self.check_urls(url_list) + if file_url is not None: + break # got it! + else: + if req_format not in formats.keys(): + self._downloader.trouble(u'ERROR: format is not available') + return + + url_list = self.get_urls(formats, req_format) + file_url = self.check_urls(url_list) + format_param = req_format + + # We have audio + self._downloader.increment_downloads() + try: + # Process file information + self._downloader.process_info({ + 'id': file_id.decode('utf-8'), + 'url': file_url.decode('utf-8'), + 'uploader': uploader.decode('utf-8'), + 'upload_date': u'NA', + 'title': json_data['name'], + 'stitle': _simplify_title(json_data['name']), + 'ext': file_url.split('.')[-1].decode('utf-8'), + 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), + 'thumbnail': json_data['thumbnail_url'], + 'description': json_data['description'], + 'player_url': player_url.decode('utf-8'), + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'ERROR: unable to download file') + +class StanfordOpenClassroomIE(InfoExtractor): + """Information extractor for Stanford's Open ClassRoom""" + + _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' + IE_NAME = u'stanfordoc' + + def report_download_webpage(self, objid): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if mobj.group('course') and mobj.group('video'): # A specific video + course = mobj.group('course') + video = mobj.group('video') + info = { + 'id': _simplify_title(course + '_' + video), + } + + self.report_extraction(info['id']) + baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' + xmlUrl = baseUrl + video + '.xml' + try: + metaXml = urllib2.urlopen(xmlUrl).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err)) + return + mdoc = xml.etree.ElementTree.fromstring(metaXml) + try: + info['title'] = mdoc.findall('./title')[0].text + info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text + except IndexError: + self._downloader.trouble(u'\nERROR: Invalid metadata XML file') + return + info['stitle'] = _simplify_title(info['title']) + info['ext'] = info['url'].rpartition('.')[2] + info['format'] = info['ext'] + self._downloader.increment_downloads() + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + elif mobj.group('course'): # A course page + unescapeHTML = HTMLParser.HTMLParser().unescape + + course = mobj.group('course') + info = { + 'id': _simplify_title(course), + 'type': 'playlist', + } + + self.report_download_webpage(info['id']) + try: + coursepage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) + return + + m = re.search('<h1>([^<]+)</h1>', coursepage) + if m: + info['title'] = unescapeHTML(m.group(1)) + else: + info['title'] = info['id'] + info['stitle'] = _simplify_title(info['title']) + + m = re.search('<description>([^<]+)</description>', coursepage) + if m: + info['description'] = unescapeHTML(m.group(1)) + + links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) + info['list'] = [ + { + 'type': 'reference', + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), + } + for vpage in links] + + for entry in info['list']: + assert entry['type'] == 'reference' + self.extract(entry['url']) + else: # Root page + unescapeHTML = HTMLParser.HTMLParser().unescape + + info = { + 'id': 'Stanford OpenClassroom', + 'type': 'playlist', + } + + self.report_download_webpage(info['id']) + rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' + try: + rootpage = urllib2.urlopen(rootURL).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) + return + + info['title'] = info['id'] + info['stitle'] = _simplify_title(info['title']) + + links = _orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) + info['list'] = [ + { + 'type': 'reference', + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), + } + for cpage in links] + + for entry in info['list']: + assert entry['type'] == 'reference' + self.extract(entry['url']) + +class MTVIE(InfoExtractor): + """Information extractor for MTV.com""" + + _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$' + IE_NAME = u'mtv' + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + if not mobj.group('proto'): + url = 'http://' + url + video_id = mobj.group('videoid') + self.report_webpage(video_id) + + request = urllib2.Request(url) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract song name') + return + song_name = _unescapeHTML(mobj.group(1).decode('iso-8859-1')) + mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract performer') + return + performer = _unescapeHTML(mobj.group(1).decode('iso-8859-1')) + video_title = performer + ' - ' + song_name + + mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to mtvn_uri') + return + mtvn_uri = mobj.group(1) + + mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract content id') + return + content_id = mobj.group(1) + + videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri + self.report_extraction(video_id) + request = urllib2.Request(videogen_url) + try: + metadataXml = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err)) + return + + mdoc = xml.etree.ElementTree.fromstring(metadataXml) + renditions = mdoc.findall('.//rendition') + + # For now, always pick the highest quality. + rendition = renditions[-1] + + try: + _,_,ext = rendition.attrib['type'].partition('/') + format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate'] + video_url = rendition.find('./src').text + except KeyError: + self._downloader.trouble('Invalid rendition field.') + return + + self._downloader.increment_downloads() + info = { + 'id': video_id, + 'url': video_url, + 'uploader': performer, + 'title': video_title, + 'stitle': _simplify_title(video_title), + 'ext': ext, + 'format': format, + } + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download ' + video_id) + + +class PostProcessor(object): + """Post Processor class. + + PostProcessor objects can be added to downloaders with their + add_post_processor() method. When the downloader has finished a + successful download, it will take its internal chain of PostProcessors + and start calling the run() method on each one of them, first with + an initial argument and then with the returned value of the previous + PostProcessor. + + The chain will be stopped if one of them ever returns None or the end + of the chain is reached. + + PostProcessor objects follow a "mutual registration" process similar + to InfoExtractor objects. + """ + + _downloader = None + + def __init__(self, downloader=None): + self._downloader = downloader + + def set_downloader(self, downloader): + """Sets the downloader for this PP.""" + self._downloader = downloader + + def run(self, information): + """Run the PostProcessor. + + The "information" argument is a dictionary like the ones + composed by InfoExtractors. The only difference is that this + one has an extra field called "filepath" that points to the + downloaded file. + + When this method returns None, the postprocessing chain is + stopped. However, this method may return an information + dictionary that will be passed to the next postprocessing + object in the chain. It can be the one it received after + changing some fields. + + In addition, this method may raise a PostProcessingError + exception that will be taken into account by the downloader + it was called from. + """ + return information # by default, do nothing + +class AudioConversionError(BaseException): + def __init__(self, message): + self.message = message + +class FFmpegExtractAudioPP(PostProcessor): + + def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False): + PostProcessor.__init__(self, downloader) + if preferredcodec is None: + preferredcodec = 'best' + self._preferredcodec = preferredcodec + self._preferredquality = preferredquality + self._keepvideo = keepvideo + + @staticmethod + def get_audio_codec(path): + try: + cmd = ['ffprobe', '-show_streams', '--', _encodeFilename(path)] + handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE) + output = handle.communicate()[0] + if handle.wait() != 0: + return None + except (IOError, OSError): + return None + audio_codec = None + for line in output.split('\n'): + if line.startswith('codec_name='): + audio_codec = line.split('=')[1].strip() + elif line.strip() == 'codec_type=audio' and audio_codec is not None: + return audio_codec + return None + + @staticmethod + def run_ffmpeg(path, out_path, codec, more_opts): + if codec is None: + acodec_opts = [] + else: + acodec_opts = ['-acodec', codec] + cmd = ['ffmpeg', '-y', '-i', _encodeFilename(path), '-vn'] + acodec_opts + more_opts + ['--', _encodeFilename(out_path)] + try: + p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + stdout,stderr = p.communicate() + except (IOError, OSError): + e = sys.exc_info()[1] + if isinstance(e, OSError) and e.errno == 2: + raise AudioConversionError('ffmpeg not found. Please install ffmpeg.') + else: + raise e + if p.returncode != 0: + msg = stderr.strip().split('\n')[-1] + raise AudioConversionError(msg) + + def run(self, information): + path = information['filepath'] + + filecodec = self.get_audio_codec(path) + if filecodec is None: + self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe') + return None + + more_opts = [] + if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'): + if self._preferredcodec == 'm4a' and filecodec == 'aac': + # Lossless, but in another container + acodec = 'copy' + extension = self._preferredcodec + more_opts = ['-absf', 'aac_adtstoasc'] + elif filecodec in ['aac', 'mp3', 'vorbis']: + # Lossless if possible + acodec = 'copy' + extension = filecodec + if filecodec == 'aac': + more_opts = ['-f', 'adts'] + if filecodec == 'vorbis': + extension = 'ogg' + else: + # MP3 otherwise. + acodec = 'libmp3lame' + extension = 'mp3' + more_opts = [] + if self._preferredquality is not None: + more_opts += ['-ab', self._preferredquality] + else: + # We convert the audio (lossy) + acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec] + extension = self._preferredcodec + more_opts = [] + if self._preferredquality is not None: + more_opts += ['-ab', self._preferredquality] + if self._preferredcodec == 'aac': + more_opts += ['-f', 'adts'] + if self._preferredcodec == 'm4a': + more_opts += ['-absf', 'aac_adtstoasc'] + if self._preferredcodec == 'vorbis': + extension = 'ogg' + if self._preferredcodec == 'wav': + extension = 'wav' + more_opts += ['-f', 'wav'] + + prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups + new_path = prefix + sep + extension + self._downloader.to_screen(u'[ffmpeg] Destination: ' + new_path) + try: + self.run_ffmpeg(path, new_path, acodec, more_opts) + except: + etype,e,tb = sys.exc_info() + if isinstance(e, AudioConversionError): + self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message) + else: + self._downloader.to_stderr(u'ERROR: error running ffmpeg') + return None + + # Try to update the date time for extracted audio file. + if information.get('filetime') is not None: + try: + os.utime(_encodeFilename(new_path), (time.time(), information['filetime'])) + except: + self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file') + + if not self._keepvideo: + try: + os.remove(_encodeFilename(path)) + except (IOError, OSError): + self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file') + return None + + information['filepath'] = new_path + return information + + +def updateSelf(downloader, filename): + ''' Update the program file with the latest version from the repository ''' + # Note: downloader only used for options + if not os.access(filename, os.W_OK): + sys.exit('ERROR: no write permissions on %s' % filename) + + downloader.to_screen(u'Updating to latest version...') + + try: + try: + urlh = urllib.urlopen(UPDATE_URL) + newcontent = urlh.read() + + vmatch = re.search("__version__ = '([^']+)'", newcontent) + if vmatch is not None and vmatch.group(1) == __version__: + downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')') + return + finally: + urlh.close() + except (IOError, OSError), err: + sys.exit('ERROR: unable to download latest version') + + try: + outf = open(filename, 'wb') + try: + outf.write(newcontent) + finally: + outf.close() + except (IOError, OSError), err: + sys.exit('ERROR: unable to overwrite current version') + + downloader.to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.') + +def parseOpts(): + def _readOptions(filename_bytes): + try: + optionf = open(filename_bytes) + except IOError: + return [] # silently skip if file is not present + try: + res = [] + for l in optionf: + res += shlex.split(l, comments=True) + finally: + optionf.close() + return res + + def _format_option_string(option): + ''' ('-o', '--option') -> -o, --format METAVAR''' + + opts = [] + + if option._short_opts: opts.append(option._short_opts[0]) + if option._long_opts: opts.append(option._long_opts[0]) + if len(opts) > 1: opts.insert(1, ', ') + + if option.takes_value(): opts.append(' %s' % option.metavar) + + return "".join(opts) + + def _find_term_columns(): + columns = os.environ.get('COLUMNS', None) + if columns: + return int(columns) + + try: + sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out,err = sp.communicate() + return int(out.split()[1]) + except: + pass + return None + + max_width = 80 + max_help_position = 80 + + # No need to wrap help messages if we're on a wide console + columns = _find_term_columns() + if columns: max_width = columns + + fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) + fmt.format_option_strings = _format_option_string + + kw = { + 'version' : __version__, + 'formatter' : fmt, + 'usage' : '%prog [options] url [url...]', + 'conflict_handler' : 'resolve', + } + + parser = optparse.OptionParser(**kw) + + # option groups + general = optparse.OptionGroup(parser, 'General Options') + selection = optparse.OptionGroup(parser, 'Video Selection') + authentication = optparse.OptionGroup(parser, 'Authentication Options') + video_format = optparse.OptionGroup(parser, 'Video Format Options') + postproc = optparse.OptionGroup(parser, 'Post-processing Options') + filesystem = optparse.OptionGroup(parser, 'Filesystem Options') + verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') + + general.add_option('-h', '--help', + action='help', help='print this help text and exit') + general.add_option('-v', '--version', + action='version', help='print program version and exit') + general.add_option('-U', '--update', + action='store_true', dest='update_self', help='update this program to latest version') + general.add_option('-i', '--ignore-errors', + action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) + general.add_option('-r', '--rate-limit', + dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') + general.add_option('-R', '--retries', + dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) + general.add_option('--dump-user-agent', + action='store_true', dest='dump_user_agent', + help='display the current browser identification', default=False) + general.add_option('--list-extractors', + action='store_true', dest='list_extractors', + help='List all supported extractors and the URLs they would handle', default=False) + + selection.add_option('--playlist-start', + dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) + selection.add_option('--playlist-end', + dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) + selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') + selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') + selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None) + + authentication.add_option('-u', '--username', + dest='username', metavar='USERNAME', help='account username') + authentication.add_option('-p', '--password', + dest='password', metavar='PASSWORD', help='account password') + authentication.add_option('-n', '--netrc', + action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) + + + video_format.add_option('-f', '--format', + action='store', dest='format', metavar='FORMAT', help='video format code') + video_format.add_option('--all-formats', + action='store_const', dest='format', help='download all available video formats', const='all') + video_format.add_option('--prefer-free-formats', + action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested') + video_format.add_option('--max-quality', + action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') + video_format.add_option('-F', '--list-formats', + action='store_true', dest='listformats', help='list all available formats (currently youtube only)') + + + verbosity.add_option('-q', '--quiet', + action='store_true', dest='quiet', help='activates quiet mode', default=False) + verbosity.add_option('-s', '--simulate', + action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False) + verbosity.add_option('--skip-download', + action='store_true', dest='skip_download', help='do not download the video', default=False) + verbosity.add_option('-g', '--get-url', + action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) + verbosity.add_option('-e', '--get-title', + action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) + verbosity.add_option('--get-thumbnail', + action='store_true', dest='getthumbnail', + help='simulate, quiet but print thumbnail URL', default=False) + verbosity.add_option('--get-description', + action='store_true', dest='getdescription', + help='simulate, quiet but print video description', default=False) + verbosity.add_option('--get-filename', + action='store_true', dest='getfilename', + help='simulate, quiet but print output filename', default=False) + verbosity.add_option('--get-format', + action='store_true', dest='getformat', + help='simulate, quiet but print output format', default=False) + verbosity.add_option('--no-progress', + action='store_true', dest='noprogress', help='do not print progress bar', default=False) + verbosity.add_option('--console-title', + action='store_true', dest='consoletitle', + help='display progress in console titlebar', default=False) + verbosity.add_option('-v', '--verbose', + action='store_true', dest='verbose', help='print various debugging information', default=False) + + + filesystem.add_option('-t', '--title', + action='store_true', dest='usetitle', help='use title in file name', default=False) + filesystem.add_option('-l', '--literal', + action='store_true', dest='useliteral', help='use literal title in file name', default=False) + filesystem.add_option('-A', '--auto-number', + action='store_true', dest='autonumber', + help='number downloaded files starting from 00000', default=False) + filesystem.add_option('-o', '--output', + dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.') + filesystem.add_option('-a', '--batch-file', + dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') + filesystem.add_option('-w', '--no-overwrites', + action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) + filesystem.add_option('-c', '--continue', + action='store_true', dest='continue_dl', help='resume partially downloaded files', default=True) + filesystem.add_option('--no-continue', + action='store_false', dest='continue_dl', + help='do not resume partially downloaded files (restart from beginning)') + filesystem.add_option('--cookies', + dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') + filesystem.add_option('--no-part', + action='store_true', dest='nopart', help='do not use .part files', default=False) + filesystem.add_option('--no-mtime', + action='store_false', dest='updatetime', + help='do not use the Last-modified header to set the file modification time', default=True) + filesystem.add_option('--write-description', + action='store_true', dest='writedescription', + help='write video description to a .description file', default=False) + filesystem.add_option('--write-info-json', + action='store_true', dest='writeinfojson', + help='write video metadata to a .info.json file', default=False) + + + postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False, + help='convert video files to audio-only files (requires ffmpeg and ffprobe)') + postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', + help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default') + postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K', + help='ffmpeg audio bitrate specification, 128k by default') + postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False, + help='keeps the video file on disk after the post-processing; the video is erased by default') + + + parser.add_option_group(general) + parser.add_option_group(selection) + parser.add_option_group(filesystem) + parser.add_option_group(verbosity) + parser.add_option_group(video_format) + parser.add_option_group(authentication) + parser.add_option_group(postproc) + + xdg_config_home = os.environ.get('XDG_CONFIG_HOME') + if xdg_config_home: + userConf = os.path.join(xdg_config_home, 'youtube-dl.conf') + else: + userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf') + argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:] + opts, args = parser.parse_args(argv) + + return parser, opts, args + +def gen_extractors(): + """ Return a list of an instance of every supported extractor. + The order does matter; the first extractor matched is the one handling the URL. + """ + youtube_ie = YoutubeIE() + google_ie = GoogleIE() + yahoo_ie = YahooIE() + return [ + YoutubePlaylistIE(youtube_ie), + YoutubeUserIE(youtube_ie), + YoutubeSearchIE(youtube_ie), + youtube_ie, + MetacafeIE(youtube_ie), + DailymotionIE(), + google_ie, + GoogleSearchIE(google_ie), + PhotobucketIE(), + yahoo_ie, + YahooSearchIE(yahoo_ie), + DepositFilesIE(), + FacebookIE(), + BlipTVIE(), + VimeoIE(), + MyVideoIE(), + ComedyCentralIE(), + EscapistIE(), + CollegeHumorIE(), + XVideosIE(), + SoundcloudIE(), + InfoQIE(), + MixcloudIE(), + StanfordOpenClassroomIE(), + MTVIE(), + + GenericIE() + ] + +def _real_main(): + parser, opts, args = parseOpts() + + # Open appropriate CookieJar + if opts.cookiefile is None: + jar = cookielib.CookieJar() + else: + try: + jar = cookielib.MozillaCookieJar(opts.cookiefile) + if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): + jar.load() + except (IOError, OSError), err: + sys.exit(u'ERROR: unable to open cookie file') + + # Dump user agent + if opts.dump_user_agent: + print std_headers['User-Agent'] + sys.exit(0) + + # Batch file verification + batchurls = [] + if opts.batchfile is not None: + try: + if opts.batchfile == '-': + batchfd = sys.stdin + else: + batchfd = open(opts.batchfile, 'r') + batchurls = batchfd.readlines() + batchurls = [x.strip() for x in batchurls] + batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] + except IOError: + sys.exit(u'ERROR: batch file could not be read') + all_urls = batchurls + args + + # General configuration + cookie_processor = urllib2.HTTPCookieProcessor(jar) + proxy_handler = urllib2.ProxyHandler() + opener = urllib2.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) + urllib2.install_opener(opener) + socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) + + if opts.verbose: + print(u'[debug] Proxy map: ' + str(proxy_handler.proxies)) + + extractors = gen_extractors() + + if opts.list_extractors: + for ie in extractors: + print(ie.IE_NAME) + matchedUrls = filter(lambda url: ie.suitable(url), all_urls) + all_urls = filter(lambda url: url not in matchedUrls, all_urls) + for mu in matchedUrls: + print(u' ' + mu) + sys.exit(0) + + # Conflicting, missing and erroneous options + if opts.usenetrc and (opts.username is not None or opts.password is not None): + parser.error(u'using .netrc conflicts with giving username/password') + if opts.password is not None and opts.username is None: + parser.error(u'account username missing') + if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): + parser.error(u'using output template conflicts with using title, literal title or auto number') + if opts.usetitle and opts.useliteral: + parser.error(u'using title conflicts with using literal title') + if opts.username is not None and opts.password is None: + opts.password = getpass.getpass(u'Type account password and press return:') + if opts.ratelimit is not None: + numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) + if numeric_limit is None: + parser.error(u'invalid rate limit specified') + opts.ratelimit = numeric_limit + if opts.retries is not None: + try: + opts.retries = long(opts.retries) + except (TypeError, ValueError), err: + parser.error(u'invalid retry count specified') + try: + opts.playliststart = int(opts.playliststart) + if opts.playliststart <= 0: + raise ValueError(u'Playlist start must be positive') + except (TypeError, ValueError), err: + parser.error(u'invalid playlist start number specified') + try: + opts.playlistend = int(opts.playlistend) + if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): + raise ValueError(u'Playlist end must be greater than playlist start') + except (TypeError, ValueError), err: + parser.error(u'invalid playlist end number specified') + if opts.extractaudio: + if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']: + parser.error(u'invalid audio format specified') + + # File downloader + fd = FileDownloader({ + 'usenetrc': opts.usenetrc, + 'username': opts.username, + 'password': opts.password, + 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), + 'forceurl': opts.geturl, + 'forcetitle': opts.gettitle, + 'forcethumbnail': opts.getthumbnail, + 'forcedescription': opts.getdescription, + 'forcefilename': opts.getfilename, + 'forceformat': opts.getformat, + 'simulate': opts.simulate, + 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), + 'format': opts.format, + 'format_limit': opts.format_limit, + 'listformats': opts.listformats, + 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) + or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') + or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') + or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') + or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') + or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') + or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') + or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') + or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') + or u'%(id)s.%(ext)s'), + 'ignoreerrors': opts.ignoreerrors, + 'ratelimit': opts.ratelimit, + 'nooverwrites': opts.nooverwrites, + 'retries': opts.retries, + 'continuedl': opts.continue_dl, + 'noprogress': opts.noprogress, + 'playliststart': opts.playliststart, + 'playlistend': opts.playlistend, + 'logtostderr': opts.outtmpl == '-', + 'consoletitle': opts.consoletitle, + 'nopart': opts.nopart, + 'updatetime': opts.updatetime, + 'writedescription': opts.writedescription, + 'writeinfojson': opts.writeinfojson, + 'matchtitle': opts.matchtitle, + 'rejecttitle': opts.rejecttitle, + 'max_downloads': opts.max_downloads, + 'prefer_free_formats': opts.prefer_free_formats, + 'verbose': opts.verbose, + }) + for extractor in extractors: + fd.add_info_extractor(extractor) + + # PostProcessors + if opts.extractaudio: + fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo)) + + # Update version + if opts.update_self: + updateSelf(fd, sys.argv[0]) + + # Maybe do nothing + if len(all_urls) < 1: + if not opts.update_self: + parser.error(u'you must provide at least one URL') + else: + sys.exit() + + try: + retcode = fd.download(all_urls) + except MaxDownloadsReached: + fd.to_screen(u'--max-download limit reached, aborting.') + retcode = 101 + + # Dump cookie jar if requested + if opts.cookiefile is not None: + try: + jar.save() + except (IOError, OSError), err: + sys.exit(u'ERROR: unable to save cookie jar') + + sys.exit(retcode) + +def main(): + try: + _real_main() + except DownloadError: + sys.exit(1) + except SameFileError: + sys.exit(u'ERROR: fixed output name but more than one file to download') + except KeyboardInterrupt: + sys.exit(u'\nERROR: Interrupted by user') + +if __name__ == '__main__': + main() + +# vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: