nemunaire/nemubot
1
0
Fork 0
Code Releases Activity

Webtool: New function to decode htmlentities

Browse Source
This commit is contained in:
nemunaire 2014-07-11 16:37:06 +02:00
parent 509e85f55a
commit 0f01d28528
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
tools/web.py
View File

@ -16,6 +16,7 @@
# You should have received a copy of the GNU Affero General Public License # You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>. # along with this program. If not, see <http://www.gnu.org/licenses/>.
from html.entities import name2codepoint
import http.client import http.client
import json import json
import re import re
@ -136,7 +137,12 @@ def getJSON(url, timeout=15):
# Other utils # Other utils
def htmlentitydecode(s):
"""Decode htmlentities"""
return re.sub('&(%s);' % '|'.join(name2codepoint),
lambda m: chr(name2codepoint[m.group(1)]), s)
def striphtml(data): def striphtml(data):
"""Remove HTML tags from text""" """Remove HTML tags from text"""
p = re.compile(r'<.*?>') p = re.compile(r'<.*?>')
return p.sub('', data).replace("&#x28;", "/(").replace("&#x29;", ")/").replace("&#x22;", "\"") return htmlentitydecode(p.sub('', data).replace("&#x28;", "/(").replace("&#x29;", ")/").replace("&#x22;", "\""))