From ee442c40902df22f88e5a65e373c512dc6101300 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Sun, 16 Sep 2007 19:00:22 +0000
Subject: [PATCH] use wikipedia search stupid

---
 scrapeit/wikipedia.py | 35 ++++++++++-------------------------
 1 file changed, 10 insertions(+), 25 deletions(-)

diff --git a/scrapeit/wikipedia.py b/scrapeit/wikipedia.py
index ff3597a..6856120 100644
--- a/scrapeit/wikipedia.py
+++ b/scrapeit/wikipedia.py
@@ -10,29 +10,14 @@ 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 = ''
-  q = u'%s %s site:en.wikipedia.org' % (title, director)
-  #print q.encode('utf-8')
-  for g in google(q, 7):
-    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.')))
-    if edit_url:
-      edit_url = edit_url[0]['href']
-      edit_url = "http://en.wikipedia.org%s" % edit_url.replace('&amp;', '&')
-      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
+def searchByImdb(imdb_id):
+  if len(imdb_id) != 7: return ''
+  url = "http://en.wikipedia.org/w/index.php?title=Special%3ASearch&search=imdb_id%20" + imdb_id + "&fulltext=Search"
+  data = read_url(url)
+  soup = BeautifulSoup(data)
+  result = soup('li', {"style":"padding-bottom: 1em;"})
+  if result:
+    url = result[0]('a')[0]['href']
+    url = "http://en.wikipedia.org%s" % url
+    return url
   return ''