Improved feedsportal url recognition.

master
pictuga 2013-04-28 10:10:58 +02:00
parent fa7cd957df
commit 93f971896b
1 changed files with 2 additions and 2 deletions

View File

@ -290,8 +290,8 @@ def Fill(rss, cache):
match = re.search('/([0-9a-zA-Z]{20,})/story01.htm$', item.link) match = re.search('/([0-9a-zA-Z]{20,})/story01.htm$', item.link)
if match: if match:
url = match.groups()[0].split('0') url = match.groups()[0].split('0')
t = {'A':'0', 'B':'.', 'C':'/', 'D':'?', 'E':'-', 'I':'_', 'L':'ww', 'S':'w.', 'N':'.com', 'O':'.co.uk'} t = {'A':'0', 'B':'.', 'C':'/', 'D':'?', 'E':'-', 'I':'_', 'L':'http://', 'S':'www.', 'N':'.com', 'O':'.co.uk'}
item.link = 'http://' + "".join([(t[s[0]] if s[0] in t else "=") + s[1:] for s in url[1:]]) item.link = "".join([(t[s[0]] if s[0] in t else "=") + s[1:] for s in url[1:]])
log(item.link) log(item.link)
if '{http://rssnamespace.org/feedburner/ext/1.0}origLink' in item: if '{http://rssnamespace.org/feedburner/ext/1.0}origLink' in item:
item.link = item['{http://rssnamespace.org/feedburner/ext/1.0}origLink'] item.link = item['{http://rssnamespace.org/feedburner/ext/1.0}origLink']