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

titles without countries

Browse source
This commit is contained in:
j 2015-05-04 10:53:17 +02:00
parent b147c61f5c
commit 5bf53ba463
2 changed files with 4 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
ox/web/imdb.py
View file

@ -476,7 +476,6 @@ class Imdb(SiteParser):
alt[title].append(c) alt[title].append(c)
self['alternativeTitles'] = [] self['alternativeTitles'] = []
for t in sorted(alt, key=lambda a: sorted(alt[a])): for t in sorted(alt, key=lambda a: sorted(alt[a])):
if alt[t]:
countries = sorted([normalize_country_name(c) or c for c in alt[t]]) countries = sorted([normalize_country_name(c) or c for c in alt[t]])
self['alternativeTitles'].append((t, countries)) self['alternativeTitles'].append((t, countries))
if not self['alternativeTitles']: if not self['alternativeTitles']:

4
ox/web/ubu.py
View file

@ -44,9 +44,9 @@ def get_data(url):
if match: if match:
m['title'] = strip_tags(decode_html(match[0])).strip() m['title'] = strip_tags(decode_html(match[0])).strip()
if not 'title' in m: if not 'title' in m:
match = re.compile("<title>.*?&amp;(.*?)</title>").findall(data) match = re.compile("<title>.*?&amp;(.*?)</title>", re.DOTALL).findall(data)
if match: if match:
m['title'] = match[0].strip() m['title'] = re.sub('\s+', ' ', match[0]).strip()
if ' - ' in m['title']: if ' - ' in m['title']:
m['title'] = m['title'].split(' - ', 1)[-1] m['title'] = m['title'].split(' - ', 1)[-1]
if 'title' in m: if 'title' in m: