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

use cookie to get us titles from imdb

Browse source
This commit is contained in:
j 2010-10-08 18:07:39 +02:00
commit 2da500d26e
2 changed files with 16 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ox/web/siteparser.py
View file

@ -30,10 +30,13 @@ class SiteParser(dict):
def getUrl(self, page):
return "%s%s" % (self.baseUrl, page)
def readUrlUnicode(self, url, timeout):
return readUrlUnicode(url, timeout=timeout)
def __init__(self, timeout=-1):
for key in self.regex:
url = self.getUrl(self.regex[key]['page'])
data = readUrlUnicode(url)
data = self.readUrlUnicode(url, timeout)
if isinstance(self.regex[key]['re'], basestring):
data = re.compile(self.regex[key]['re'], re.DOTALL).findall(data)
data = cleanup(key, data, self.regex[key]['type'])