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

title refinement

Browse source
This commit is contained in:
j 2007-06-28 11:00:12 +00:00
parent 3d8fb83063
commit 8cf1f86184
1 changed files with 5 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
scrapeit/imdb.py
View file

@ -159,9 +159,9 @@ class IMDb:
html_title = str(html_title[0]) html_title = str(html_title[0])
title = stripTags(html_title) title = stripTags(html_title)
title = re.sub('\(\d\d\d\d\)', '', title) title = re.sub('\(\d\d\d\d\)', '', title)
title = re.sub('\(TV\)', '', title) title = re.sub('\(\d\d\d\d\/I)', '', title)
title = re.sub('\(V\)', '', title) for t in ('TV-Series', '(mini)', '(VG)', '(V)', '(TV)')
title = re.sub('\(VG\)', '', title) title = title.replace(t, '')
return title.strip() return title.strip()
def parseYear(self): def parseYear(self):
@ -174,6 +174,8 @@ class IMDb:
if html_title: if html_title:
html_title = str(html_title[0]) html_title = str(html_title[0])
year = re.compile('(\d\d\d\d)').findall(html_title) year = re.compile('(\d\d\d\d)').findall(html_title)
if not year:
year = re.compile('(\d\d\d\d/I)').findall(html_title)
if year: if year:
year = year[0] year = year[0]
else: year = '' else: year = ''