new imdb title code

scrapeit/imdb.py

@@ -157,11 +157,16 @@ class IMDb:
     #Title, Year
     title = u''
     year  = u''
-    flat_data = data.replace('\n', '').replace('\r', '')
-    html_title = re.compile('<strong class="title">(.*?) <small>\(<a href="/Sections/Years/(.*?)">').findall(flat_data)
+    soup = BeautifulSoup(data)
+    html_title = soup('div', {'id': 'tn15title'})
+    if html_title: html_title = html_title[0]('h1')
+    if html_title: html_title = html_title[0].contents
     if html_title:
-      title = html_title[0][0]
-      IMDbDict['year'] = html_title[0][1]
+      title = html_title[0]
+      year = re.compile('(\d\d\d\d)').findall(str(html_title[1]))
+      if year: year = year[0]
+      else: year = ''
+      IMDbDict['year'] = year
       IMDbDict['title'] = stripTags(title).strip()
     else:
       title = _getTerm(data, '<title>(.*?)</title>')

scrapeit/opensubtitles.py

@@ -2,12 +2,20 @@
 # -*- Mode: Python; -*-
 # vi:si:et:sw=2:sts=2:ts=2
 
-from utils import read_url
+import utils
 import feedparser
 import StringIO
 import zipfile
 import re
+import socket
 
+def read_url(url):
+  t0 = socket.getdefaulttimeout()
+  socket.setdefaulttimeout(100)
+  data = utils.read_url(url)
+  socket.setdefaulttimeout(t0)
+  return data
+  
 def searchSubtitlesByIMDb(imdb, parts = 1, language = "eng"):
   url = "http://www.opensubtitles.org/en/search/sublanguageid-%s/subsumcd-%s/subformat-srt/imdbid-%s/rss_2_00" % (language, parts, imdb)
   data = read_url(url)