add wikipedia.searchByImdb

scrapeit/imdb.py

@@ -199,7 +199,7 @@ class IMDb:
           title = imdbpy_utils.normalizeTitle(title[1:title.rfind('"')]) + se + title[title.rfind('"')+1:]
         else:
           title = imdbpy_utils.normalizeTitle(title[1:title.rfind('"')]) + ':' + title[title.rfind('"')+1:]
-    return title
+    return imdbpy_utils.normalizeTitle(title)
     
   def parseYear(self):
     year = ''

scrapeit/wikipedia.py

@@ -0,0 +1,34 @@
+# -*- Mode: Python; -*-
+# -*- coding: utf-8 -*-
+# vi:si:et:sw=2:sts=2:ts=2
+import re
+
+from BeautifulSoup import BeautifulSoup
+
+from utils import read_url
+from imdb import IMDb
+from google import google
+
+
+def searchByImdb(imdb_id, title=None, director=None):
+  if not title:
+    i =  IMDb(imdb_id)
+    title = i.parseTitle()
+    director = i.parseCredits()['director']
+    if director:
+      director = director[0]
+    else:
+      director = ''
+  for g in google('"%s" %s site:en.wikipedia.org' % (title, director), 20):
+    url = g[1]
+    data = read_url(url)
+    soup = BeautifulSoup(data)
+    edit_url = soup('a', dict(href=re.compile('action=edit'), 
+           title=re.compile('You can edit this page.')))[0]['href']
+    edit_url = "http://en.wikipedia.org%s" % edit_url.replace('&', '&')
+    data = read_url(edit_url)
+    w_imdb_id = data.find('imdb_id')
+    if w_imdb_id > 0:
+      if imdb_id in data[w_imdb_id:w_imdb_id+50]:
+        return url
+  return ''