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

reduce choice of alternative titles for english films, fixes #1084

Browse source
This commit is contained in:
j 2012-10-10 13:27:19 +02:00
parent 13a55763d3
commit 639b74eac3
1 changed files with 12 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
ox/web/imdb.py
View file

@ -307,23 +307,28 @@ class Imdb(SiteParser):
break break
if not stop_word and not type in types: if not stop_word and not type in types:
types[type] = t[0] types[type] = t[0]
for regexp in ( regexps = [
"^.+ \(imdb display title\) \(English title\)$", "^.+ \(imdb display title\) \(English title\)$",
"^International \(English title\)$", "^International \(English title\)$",
"^.+ \(English title\)$",
"^International \(.+\) \(English title\)$", "^International \(.+\) \(English title\)$",
"^.+ \(.+\) \(English title\)$", "^.+ \(.+\) \(English title\)$",
"^USA$", "^USA$",
"^UK$", "^UK$",
"^USA \(imdb display title\)$", "^USA \(imdb display title\)$",
"^UK \(imdb display title\)$", "^UK \(imdb display title\)$",
]
if not filter(lambda c: c in ('USA', 'UK', 'Australia'), self.get('country', [])):
regexps.insert(2, "^.+ \(English title\)$")
regexps += [
"^USA \(.+\)$", "^USA \(.+\)$",
"^UK \(.+\)$", "^UK \(.+\)$",
"^Australia \(.+\)$", "^Australia \(.+\)$",
"^International \(.+ title\)$", "^International \(.+ title\)$",
): ]
for regexp in regexps:
for type in types: for type in types:
if re.compile(regexp).findall(type): if re.compile(regexp).findall(type):
#print types[type], type
self['internationalTitle'] = types[type] self['internationalTitle'] = types[type]
break break
if 'internationalTitle' in self: if 'internationalTitle' in self: