- Fixed unicode in mininova and btjunkie search engines

src/search_engine/helpers.py

@@ -0,0 +1,59 @@
+#VERSION: 1.0
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import re, htmlentitydefs
+import urllib2
+
+def htmlentitydecode(s):
+    # First convert alpha entities (such as é)
+    # (Inspired from http://mail.python.org/pipermail/python-list/2007-June/443813.html)
+    def entity2char(m):
+        entity = m.group(1)
+        if entity in htmlentitydefs.name2codepoint:
+            return unichr(htmlentitydefs.name2codepoint[entity])
+        return u" "  # Unknown entity: We replace with a space.
+    t = re.sub(u'&(%s);' % u'|'.join(htmlentitydefs.name2codepoint), entity2char, s)
+  
+    # Then convert numerical entities (such as é)
+    t = re.sub(u'&#(\d+);', lambda x: unichr(int(x.group(1))), t)
+   
+    # Then convert hexa entities (such as é)
+    return re.sub(u'&#x(\w+);', lambda x: unichr(int(x.group(1),16)), t)
+    
+def retrieve_url(url):
+    """ Return the content of the url page as a string """
+    req = urllib2.Request(url)
+    response = urllib2.urlopen(req)
+    dat = response.read()
+    info = response.info()
+    charset = 'utf-8'
+    try:
+        ignore, charset = info['Content-Type'].split('charset=')
+    except:
+        pass
+    dat = dat.decode(charset)
+    dat = htmlentitydecode(dat)
+    return dat.encode('utf-8', 'replace')