0x2620/openmedialibrary_platform
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

update Shared

Browse source
This commit is contained in:
j 2015-11-04 13:01:55 +01:00
commit 6881f3471a
184 changed files with 13080 additions and 13691 deletions
Download patch file Download diff file Expand all files Collapse all files

17
Shared/lib/python3.4/site-packages/ox/web/imdb.py
View file

@ -6,7 +6,7 @@ import re
import time
import unicodedata
from six.moves import urllib
from six.moves.urllib.parse import urlencode
from six import string_types
from .. import find_re, strip_tags, decode_html
@ -37,7 +37,7 @@ class Imdb(SiteParser):
'alternativeTitles': {
'page': 'releaseinfo',
're': [
'name="akas".*?<table.*?>(.*?)</table>',
'<table[^>]*?id="akas"[^>]*?>(.*?)</table>',
"td>(.*?)</td>.*?<td>(.*?)</td>"
],
'type': 'list'
@ -74,7 +74,7 @@ class Imdb(SiteParser):
'type': 'list'
},
'connections': {
'page': 'trivia?tab=mc',
'page': 'movieconnections',
're': '<h4 class="li_group">(.*?)</h4>(.*?)(<\/div>\n <a|<script)',
'type': 'list'
},
@ -476,9 +476,8 @@ class Imdb(SiteParser):
alt[title].append(c)
self['alternativeTitles'] = []
for t in sorted(alt, key=lambda a: sorted(alt[a])):
if alt[t]:
countries = sorted([normalize_country_name(c) or c for c in alt[t]])
self['alternativeTitles'].append((t, countries))
countries = sorted([normalize_country_name(c) or c for c in alt[t]])
self['alternativeTitles'].append((t, countries))
if not self['alternativeTitles']:
del self['alternativeTitles']
@ -521,7 +520,7 @@ class Imdb(SiteParser):
if len(description) == 2 and description[-1].strip() != '-':
r['description'] = description[-1].strip()
return r
cc[rel] = list(map(get_conn, re.compile('<a href="/title/tt(\d{7})/">(.*?)</a>(.*?)<\/div', re.DOTALL).findall(data)))
cc[rel] = list(map(get_conn, re.compile('<a href="/title/tt(\d{7})/?">(.*?)</a>(.*?)<\/div', re.DOTALL).findall(data)))
self['connections'] = cc
@ -665,7 +664,7 @@ def get_movie_by_title(title, timeout=-1):
params['q'] = unicodedata.normalize('NFKC', params['q']).encode('latin-1')
except:
params['q'] = params['q'].encode('utf-8')
params = urllib.urlencode(params)
params = urlencode(params)
url = "http://akas.imdb.com/find?" + params
data = read_url(url, timeout=timeout, unicode=True)
#if search results in redirect, get id of current page
@ -741,7 +740,7 @@ def get_movie_id(title, director='', year='', timeout=-1):
params['q'] = unicodedata.normalize('NFKC', params['q']).encode('latin-1')
except:
params['q'] = params['q'].encode('utf-8')
params = urllib.urlencode(params)
params = urlencode(params)
url = "http://akas.imdb.com/find?" + params
#print url