diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-05-05 19:02:49 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-05-05 19:02:49 +0700 |
commit | fcf5b017469e40b06848a0faeb31853e45794538 (patch) | |
tree | cc07194d01b351ef7be87fe51aafa97105eb4b55 /youtube_dl/extractor | |
parent | 4de9e9a6db00853c8a809b08422b1ccddc3c446f (diff) |
[prosiebensat1] Simplify
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/prosiebensat1.py | 22 |
1 files changed, 5 insertions, 17 deletions
diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 1e84b175f..e4c4ad714 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -8,8 +8,6 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, unified_strdate, - clean_html, - RegexNotFoundError, ) @@ -188,16 +186,7 @@ class ProSiebenSat1IE(InfoExtractor): 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' @@ -246,13 +235,12 @@ class ProSiebenSat1IE(InfoExtractor): 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 = [] |