New module: ddg: search on internet through Duckduckgo and Wolfram|Alpha

modules/ddg/DDGSearch.py

@@ -0,0 +1,68 @@
+# coding=utf-8
+
+import http.client
+import re
+from urllib.parse import quote
+
+import module_states_file as xmlparser
+
+class DDGSearch:
+  def __init__(self, terms):
+    self.terms = terms
+    self.curRT = -1
+    (res, page) = getPage(terms)
+    if res == http.client.OK:
+      self.ddgres = xmlparser.parse_string(page)
+    else:
+      self.ddgres = None
+
+  @property
+  def type(self):
+    return self.ddgres.getFirstNode("Type").getContent()
+
+  @property
+  def definition(self):
+    if self.ddgres.hasNode("Definition"):
+      return self.ddgres.getFirstNode("Definition").getContent()
+    else:
+      return "Sorry, no definition found for %s" % self.terms
+
+  @property
+  def nextRes(self):
+    if self.type == "D":
+      if len(self.ddgres.getFirstNode("RelatedTopics").getNodes("RelatedTopic")) > self.curRT + 1:
+        self.curRT += 1
+        node = self.ddgres.getFirstNode("RelatedTopics").getNodes("RelatedTopic")[self.curRT]
+        return node.getFirstNode("Text").getContent()
+    elif self.ddgres.hasNode("Answer"):
+      if self.curRT < 0:
+        self.curRT = 0
+        return striphtml(self.ddgres.getFirstNode("Answer").getContent())
+    elif self.ddgres.hasNode("Abstract") and len (self.ddgres.getNode("Abstract").getContent()) > 0:
+      if self.curRT < 0:
+        self.curRT = 0
+        return self.ddgres.getNode("Abstract").getContent() + " <" + self.ddgres.getNode("AbstractURL").getContent() + ">"
+      elif len(self.ddgres.getFirstNode("RelatedTopics").getNodes("RelatedTopic")) > self.curRT:
+        node = self.ddgres.getFirstNode("RelatedTopics").getNodes("RelatedTopic")[self.curRT]
+        self.curRT += 1
+        return node.getFirstNode("Text").getContent()
+    return "No more results"
+
+
+def striphtml(data):
+    p = re.compile(r'<.*?>')
+    return p.sub('', data)
+
+def getPage(terms):
+  conn = http.client.HTTPConnection("api.duckduckgo.com")
+  try:
+    conn.request("GET", "/?q=%s&format=xml" % quote(terms))
+  except socket.gaierror:
+    print ("impossible de récupérer la page %s."%(p))
+    return (http.client.INTERNAL_SERVER_ERROR, None)
+
+  res = conn.getresponse()
+  data = res.read()
+
+  conn.close()
+  return (res.status, data)

modules/ddg/WFASearch.py

@@ -0,0 +1,69 @@
+# coding=utf-8
+
+import http.client
+import re
+import socket
+from urllib.parse import quote
+
+import module_states_file as xmlparser
+
+class WFASearch:
+  def __init__(self, terms):
+    self.terms = terms
+    self.curPod = 1
+    self.curSubPod = 0
+    (res, page) = getPage(terms)
+    if res == http.client.OK:
+      self.wfares = xmlparser.parse_string(page)
+    else:
+      self.wfares = None
+
+  @property
+  def success(self):
+    try:
+      return self.wfares["success"] == "true"
+    except:
+      return False
+
+  @property
+  def error(self):
+    return self.wfares["error"] == "true"
+
+  @property
+  def nextRes(self):
+    try:
+      if len(self.wfares.getNodes("pod")) > self.curPod:
+        txt = ""
+        while txt == "" or subnode.getFirstNode("plaintext").getContent().strip() == "":
+          node = self.wfares.getNodes("pod")[self.curPod]
+          subnode = node.getNodes("subpod")[self.curSubPod]
+
+          self.curSubPod += 1
+          if len(node.getNodes("subpod")) <= self.curSubPod:
+            self.curPod += 1
+            self.curSubPod = 0
+
+          txt = node["title"] + ": " + subnode.getFirstNode("plaintext").getContent().strip()
+        return txt
+    except IndexError:
+      pass
+    self.curPod = 1
+    return "No more results"
+
+
+def getPage(terms):
+  conn = http.client.HTTPConnection("api.wolframalpha.com")
+  try:
+    conn.request("GET", "/v2/query?input=%s&appid=%s" % (quote(terms), CONF.getNode("wfaapi")["key"]))
+  except socket.gaierror:
+    print ("impossible de récupérer la page Wolfram|Alpha.")
+    return (http.client.INTERNAL_SERVER_ERROR, None)
+  except (TypeError, KeyError):
+    print ("You need an Wolfram|Alpha API key in order to use this module. Add it to the configuration file:\n<wfaapi key=\"XXXXXX-XXXXXXXXXX\" />\nRegister at http://products.wolframalpha.com/api/")
+    return (http.client.INTERNAL_SERVER_ERROR, None)
+
+  res = conn.getresponse()
+  data = res.read()
+
+  conn.close()
+  return (res.status, data)

modules/ddg/__init__.py

@@ -0,0 +1,50 @@
+# coding=utf-8
+
+nemubotversion = 3.0
+
+from .DDGSearch import DDGSearch
+from . import WFASearch
+
+lastSearch = dict()
+
+def load():
+  global CONF
+  WFASearch.CONF = CONF
+
+def parseanswer(msg):
+  global lastSearch
+  req = None
+  if msg.cmd[0] == "def" or msg.cmd[0] == "d" or msg.cmd[0] == "define" or msg.cmd[0] == "defini" or msg.cmd[0] == "definit" or msg.cmd[0] == "definition":
+    req = "def"
+  elif msg.cmd[0] == "g" or msg.cmd[0] == "ddg" or msg.cmd[0] == "d":
+    req = "link"
+  elif msg.cmd[0] == "wfa" or msg.cmd[0] == "calc" or msg.cmd[0] == "wa":
+    req = "wfa"
+
+  if msg.cmd[0] == "more" or msg.cmd[0] == "plus":
+    if msg.channel in lastSearch and lastSearch[msg.channel] is not None:
+      msg.send_chn(lastSearch[msg.channel].nextRes)
+    else:
+      msg.send_chn("There is no ongoing research.")
+  elif req is not None:
+    if len(msg.cmd) > 1:
+      if req == "wfa":
+        s = WFASearch.WFASearch(' '.join(msg.cmd[1:]))
+        if not s.success:
+          msg.send_chn("An error occurs during computation")
+          return True
+      else:
+        s = DDGSearch(' '.join(msg.cmd[1:]))
+
+      if req == "def":
+        msg.send_chn(s.definition)
+      else:
+        msg.send_chn(s.nextRes)
+      lastSearch[msg.channel] = s
+    else:
+      msg.send_chn("What are you looking for?")
+    return True
+
+  return False
+
+