0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

parse new movieconnections page, fixes #1045

Browse source
This commit is contained in:
j 2012-09-29 17:55:37 +02:00
parent 52932bccec
commit da09714910
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
ox/web/imdb.py
View file

@ -72,8 +72,8 @@ class Imdb(SiteParser):
'type': 'list' 'type': 'list'
}, },
'connections': { 'connections': {
'page': 'movieconnections', 'page': 'trivia?tab=mc',
're': '<h5>(.*?)</h5>(.*?)\n\n', 're': '<h4 class="li_group">(.*?)</h4>(.*?)(<\/div>\n <a|<script)',
'type': 'list' 'type': 'list'
}, },
'country': { 'country': {
@ -383,7 +383,7 @@ class Imdb(SiteParser):
cc={} cc={}
if len(self['connections']) == 2 and isinstance(self['connections'][0], basestring): if len(self['connections']) == 2 and isinstance(self['connections'][0], basestring):
self['connections'] = [self['connections']] self['connections'] = [self['connections']]
for rel, data in self['connections']: for rel, data, _ in self['connections']:
#cc[unicode(rel)] = re.compile('<a href="/title/tt(\d{7})/">(.*?)</a>').findall(data) #cc[unicode(rel)] = re.compile('<a href="/title/tt(\d{7})/">(.*?)</a>').findall(data)
def get_conn(c): def get_conn(c):
title = c[1] title = c[1]