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

regex first, fixes #1058

Browse source
This commit is contained in:
j 2012-10-01 23:29:57 +02:00
parent 102365eb8e
commit 7fe62b5ce3
1 changed files with 22 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
ox/web/imdb.py
View file

@ -288,6 +288,7 @@ class Imdb(SiteParser):
isinstance(self['alternativeTitles'][0], basestring): isinstance(self['alternativeTitles'][0], basestring):
self['alternativeTitles'] = [self['alternativeTitles']] self['alternativeTitles'] = [self['alternativeTitles']]
types = {}
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()
@ -304,8 +305,9 @@ class Imdb(SiteParser):
if key in type: if key in type:
stop_word = True stop_word = True
break break
if stop_word: if not stop_word:
continue types[type] = t[0]
for regexp in ( for regexp in (
"^.+ \(imdb display title\) \(English title\)$", "^.+ \(imdb display title\) \(English title\)$",
"^International \(English title\)$", "^International \(English title\)$",
@ -321,10 +323,9 @@ class Imdb(SiteParser):
"^Australia \(.+\)$", "^Australia \(.+\)$",
"^International \(.+ title\)$", "^International \(.+ title\)$",
): ):
for type in types:
if re.compile(regexp).findall(type): if re.compile(regexp).findall(type):
self['internationalTitle'] = t[0] self['internationalTitle'] = types[type]
break
if 'internationalTitle' in self:
break break
if 'internationalTitle' in self: if 'internationalTitle' in self:
break break