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

title have special space too, good to cut out year etc

Browse source
This commit is contained in:
j 2007-07-24 12:17:05 +00:00
parent 3730587937
commit 547353e484
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
scrapeit/imdb.py
View file

@ -173,6 +173,8 @@ class IMDb:
title = re.sub('\(\d\d\d\d/I\)', '', title) title = re.sub('\(\d\d\d\d/I\)', '', title)
for t in ('TV-Series', '(mini)', '(VG)', '(V)', '(TV)'): for t in ('TV-Series', '(mini)', '(VG)', '(V)', '(TV)'):
title = title.replace(t, '') title = title.replace(t, '')
if title.find(u'\xa0') > -1:
title = title[:title.find(u'\xa0')]
title = title.strip() title = title.strip()
if title.startswith('"') and title.endswith('"'): if title.startswith('"') and title.endswith('"'):
title = title[1:-1] title = title[1:-1]