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

add title stop words again

Browse source
This commit is contained in:
j 2012-09-22 22:52:18 +02:00
parent b5b480e3f2
commit 6df54b5ca2
1 changed files with 9 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
ox/web/imdb.py
View file

@ -291,6 +291,14 @@ class Imdb(SiteParser):
for t in self.get('alternativeTitles', []): for t in self.get('alternativeTitles', []):
for type in t[1].split('/'): for type in t[1].split('/'):
type = type.strip() type = type.strip()
for key in (
'complete title',
'recut version',
'script title',
'working title',
):
if key in type:
continue
for regexp in ( for regexp in (
"^.+ \(imdb display title\) \(English title\)$", "^.+ \(imdb display title\) \(English title\)$",
"^International \(English title\)$", "^International \(English title\)$",
@ -325,7 +333,7 @@ class Imdb(SiteParser):
self[t] = cleanup_title(self[t]) self[t] = cleanup_title(self[t])
if 'internationalTitle' in self and \ if 'internationalTitle' in self and \
self.get('title') == self['internationalTitle']: self.get('title', '').lower() == self['internationalTitle'].lower():
del self['internationalTitle'] del self['internationalTitle']
if 'alternativeTitles' in self: if 'alternativeTitles' in self: