from ..utils import (
compat_urllib_parse,
unified_strdate,
- clean_html,
- RegexNotFoundError,
)
page = self._download_webpage(url, video_id, 'Downloading page')
- def extract(patterns, name, page, fatal=False):
- for pattern in patterns:
- mobj = re.search(pattern, page)
- if mobj:
- return clean_html(mobj.group(1))
- if fatal:
- raise RegexNotFoundError(u'Unable to extract %s' % name)
- return None
-
- clip_id = extract(self._CLIPID_REGEXES, 'clip id', page, fatal=True)
+ clip_id = self._html_search_regex(self._CLIPID_REGEXES, page, 'clip id')
access_token = 'testclient'
client_name = 'kolibri-1.2.5'
urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON')
- title = extract(self._TITLE_REGEXES, 'title', page, fatal=True)
- description = extract(self._DESCRIPTION_REGEXES, 'description', page)
+ title = self._html_search_regex(self._TITLE_REGEXES, page, 'title')
+ description = self._html_search_regex(self._DESCRIPTION_REGEXES, page, 'description', fatal=False)
thumbnail = self._og_search_thumbnail(page)
- upload_date = extract(self._UPLOAD_DATE_REGEXES, 'upload date', page)
- if upload_date:
- upload_date = unified_strdate(upload_date)
+ upload_date = unified_strdate(self._html_search_regex(
+ self._UPLOAD_DATE_REGEXES, page, 'upload date', fatal=False))
formats = []