never update imdb cache for now
This commit is contained in:
parent
9fab130d81
commit
10d3783673
1 changed files with 7 additions and 2 deletions
|
@ -10,12 +10,17 @@ from BeautifulSoup import BeautifulSoup
|
|||
import chardet
|
||||
import oxlib
|
||||
from oxlib import stripTags, decodeHtml, findRe, findString
|
||||
from oxlib.cache import getUrl, getUrlUnicode
|
||||
import oxlib.cache
|
||||
from oxlib.normalize import normalizeTitle, normalizeImdbId
|
||||
from oxlib import *
|
||||
|
||||
import google
|
||||
|
||||
'''
|
||||
never timeout imdb data, to update cache remove data from cache folder
|
||||
'''
|
||||
def getUrlUnicode(url, data=None, headers=oxlib.cache.DEFAULT_HEADERS, timeout=-1):
|
||||
return oxlib.cache.getUrlUnicode(url, data, headers, timeout)
|
||||
|
||||
def getMovieId(title, director='', year=''):
|
||||
'''
|
||||
|
@ -330,7 +335,7 @@ def getMovieTrivia(imdbId):
|
|||
|
||||
def getMovieConnections(imdbId):
|
||||
url = "%s/movieconnections" % getUrlBase(imdbId)
|
||||
data = getUrl(url)
|
||||
data = getUrlUnicode(url)
|
||||
connections={}
|
||||
for c in re.compile('''<h5>(.*?)</h5>(.*?)\n\n''', re.DOTALL).findall(data):
|
||||
connections[unicode(c[0])] = re.compile('''<a href="/title/tt(\d{7})/">''').findall(c[1])
|
||||
|
|
Loading…
Reference in a new issue