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

use geo.normalize_country_name for normalize imdb names

Browse source
This commit is contained in:
j 2013-07-13 15:48:26 +02:00
parent ad7e21e7a8
commit adfe642547
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

@ -16,6 +16,7 @@ from siteparser import SiteParser
import duckduckgo import duckduckgo
from ..utils import datetime from ..utils import datetime
from ..geo import normalize_country_name
def read_url(url, data=None, headers=ox.cache.DEFAULT_HEADERS, timeout=ox.cache.cache_timeout, valid=None, unicode=False): def read_url(url, data=None, headers=ox.cache.DEFAULT_HEADERS, timeout=ox.cache.cache_timeout, valid=None, unicode=False):
headers = headers.copy() headers = headers.copy()
@ -328,6 +329,10 @@ class Imdb(SiteParser):
isinstance(self['alternativeTitles'][0], basestring): isinstance(self['alternativeTitles'][0], basestring):
self['alternativeTitles'] = [self['alternativeTitles']] self['alternativeTitles'] = [self['alternativeTitles']]
#normalize country names
if 'country' in self:
self['country'] = [normalize_country_name(c) or c for c in self['country']]
types = {} types = {}
stop_words = [ stop_words = [
'alternative spelling', 'alternative spelling',
@ -378,7 +383,10 @@ class Imdb(SiteParser):
regexps += [ regexps += [
"Hong Kong \(English title\)" "Hong Kong \(English title\)"
] ]
english_countries = ('USA', 'UK', 'Australia', 'New Zealand') english_countries = (
'USA', 'UK', 'United States', 'United Kingdom',
'Australia', 'New Zealand'
)
if not filter(lambda c: c in english_countries, self.get('country', [])): if not filter(lambda c: c in english_countries, self.get('country', [])):
regexps += [ regexps += [
"^[^(]+ \(English title\)$", "^[^(]+ \(English title\)$",