dates, reduce number of imdb pages loaded

README

@@ -5,6 +5,7 @@ Depends:
  python-chardet (http://chardet.feedparser.org/)
  python-feedparser (http://www.feedparser.org/)
  python-beautifulsoup (http://www.crummy.com/software/BeautifulSoup/)
+ django (optional, otherwise dates < 1900 are not supported)
 
 Usage:
  import ox

ox/utils.py

@@ -0,0 +1,7 @@
+# -*- coding: utf-8 -*-
+# vi:si:et:sw=4:sts=4:ts=4
+try:
+    from django.utils.datetime_safe import datetime
+except:
+    from datetime import datetime
+

ox/web/imdb.py

@@ -26,7 +26,7 @@ class Imdb(SiteParser):
         
         },
         'cast': {
-            'page': 'fullcredits',
+            'page': 'combined',
             're': [
                 '<td class="nm">.*?>(.*?)</a>.*?<td class="char">(.*?)</td>',
                 lambda ll: [stripTags(l) for l in ll]
@@ -34,7 +34,7 @@ class Imdb(SiteParser):
             'type': 'list'
         },
         'cinematographers': {
-            'page': 'fullcredits',
+            'page': 'combined',
             're': [
                 lambda data: data.split('Series Crew')[0],
                 'Cinematography by</a>(.*?)</table>',
@@ -53,7 +53,7 @@ class Imdb(SiteParser):
             'type': 'list'
         },
         'directors': {
-            'page': 'fullcredits',
+            'page': 'combined',
             're': [
                 lambda data: data.split('Series Crew')[0],
                 'Directed by</a>(.*?)</table>',
@@ -62,7 +62,7 @@ class Imdb(SiteParser):
             'type': 'list'
         },
         'editors': {
-            'page': 'fullcredits',
+            'page': 'combined',
             're': [
                 lambda data: data.split('Series Crew')[0],
                 'Film Editing by</a>(.*?)</table>',
@@ -152,7 +152,7 @@ class Imdb(SiteParser):
             'type': 'string'
         },
         'writers': {
-            'page': 'fullcredits',
+            'page': 'combined',
             're': [
                 lambda data: data.split('Series Crew')[0],
                 'Writing credits</a>(.*?)</table>',

ox/web/siteparser.py

@@ -1,10 +1,10 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
 import re
-from datetime import datetime
 
-from ox.cache import readUrlUnicode
+from ..cache import readUrlUnicode
-from ox import stripTags, decodeHtml
+from .. import stripTags, decodeHtml
+from ..utils import datetime
 
 
 def cleanup(key, data, data_type):