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

use main page for series creator, fixes #3046

Browse source
This commit is contained in:
j 2017-07-26 13:17:40 +02:00
parent 3e589c454a
commit 8aef76e7cd
1 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
ox/web/imdb.py
View file

@ -87,10 +87,11 @@ class Imdb(SiteParser):
'type': 'list' 'type': 'list'
}, },
'creator': { 'creator': {
'page': 'combined', 'page': '',
're': [ 're': [
'<h5>Creator.?:</h5>.*?<div class="info-content">(.*?)</div>', '<div class="credit_summary_item">.*?<h4.*?>Creator.?:</h4>(.*?)</div>',
'<a href="/name/.*?>(.*?)</a>' '<a href="/name/.*?>(.*?)</a>',
lambda ll: strip_tags(ll)
], ],
'type': 'list' 'type': 'list'
}, },
@ -564,7 +565,7 @@ class Imdb(SiteParser):
if 'director' in self: if 'director' in self:
self['episodeDirector'] = self['director'] self['episodeDirector'] = self['director']
if not 'creator' in series and 'director' in series: if 'creator' not in series and 'director' in series:
series['creator'] = series['director'] series['creator'] = series['director']
if len(series['creator']) > 10: if len(series['creator']) > 10:
series['creator'] = series['director'][:1] series['creator'] = series['director'][:1]
@ -767,7 +768,7 @@ def get_movie_id(title, director='', year='', timeout=-1):
}.get((title, director), None) }.get((title, director), None)
if imdbId: if imdbId:
return imdbId return imdbId
params = {'s':'tt','q': title} params = {'s': 'tt', 'q': title}
if director: if director:
params['q'] = u'"%s" %s' % (title, director) params['q'] = u'"%s" %s' % (title, director)
if year: if year:
@ -794,8 +795,8 @@ def get_movie_id(title, director='', year='', timeout=-1):
if results: if results:
return results[0] return results[0]
#print (title, director), ": ''," #print((title, director), ": '',")
#print google_query #print(google_query)
#results = google.find(google_query, timeout=timeout) #results = google.find(google_query, timeout=timeout)
results = duckduckgo.find(google_query, timeout=timeout) results = duckduckgo.find(google_query, timeout=timeout)
if results: if results: