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

some more special cases

Browse source
This commit is contained in:
j 2012-11-11 17:15:40 +01:00
parent 43a54740bd
commit 6529e5f1c1
1 changed files with 29 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
ox/web/imdb.py
View file

@ -289,23 +289,33 @@ class Imdb(SiteParser):
self['alternativeTitles'] = [self['alternativeTitles']] self['alternativeTitles'] = [self['alternativeTitles']]
types = {} types = {}
stop_words = [
'alternative spelling',
'alternative title',
'alternative transliteration',
'complete title',
'IMAX version',
'informal short title',
'longer version',
'new title',
'recut version',
'reissue title',
'restored version',
'script title',
'TV title',
'working title',
]
#ignore english japanese titles
#for movies that are not only from japan
if ['Japan'] != self.get('country', []):
stop_words += [
'Japan (English title)'
]
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 stop_word = False
for key in ( for key in stop_words:
'alternative title',
'complete title',
'recut version',
'script title',
'working title',
'reissue title',
'IMAX version',
'alternative spelling',
'informal short title',
'alternative transliteration',
'restored version'
):
if key in type: if key in type:
stop_word = True stop_word = True
break break
@ -318,7 +328,12 @@ class Imdb(SiteParser):
"^International \(English title\)$", "^International \(English title\)$",
"^International \(.+\) \(English title\)$", "^International \(.+\) \(English title\)$",
] ]
if not filter(lambda c: c in ('USA', 'UK', 'Australia', 'New Zealand'), self.get('country', [])): if 'Hong Kong' in self.get('country', []):
regexps += [
"Hong Kong \(English title\)"
]
english_countries = ('USA', 'UK', 'Australia', 'New Zealand')
if not filter(lambda c: c in english_countries, self.get('country', [])):
regexps += [ regexps += [
"^[^(]+ \(English title\)$", "^[^(]+ \(English title\)$",
"^.+ \(.+\) \(English title\)$", "^.+ \(.+\) \(English title\)$",