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

fix stop words

Browse source
This commit is contained in:
j 2012-09-22 22:56:10 +02:00
parent 6df54b5ca2
commit a79b2a6134
1 changed files with 5 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
ox/web/imdb.py
View file

@ -291,6 +291,7 @@ 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()
stop_word = False
for key in ( for key in (
'complete title', 'complete title',
'recut version', 'recut version',
@ -298,7 +299,10 @@ class Imdb(SiteParser):
'working title', 'working title',
): ):
if key in type: if key in type:
continue stop_word = True
break
if stop_word:
continue
for regexp in ( for regexp in (
"^.+ \(imdb display title\) \(English title\)$", "^.+ \(imdb display title\) \(English title\)$",
"^International \(English title\)$", "^International \(English title\)$",