diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2015-02-02 23:04:39 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2015-02-02 23:04:39 +0100 |
commit | 531572578e542fcee26f1a30fd9f87ad158e6594 (patch) | |
tree | ccb5487578b2d7e7a39677f37aa69bd96acc24b8 | |
parent | 3a4cca687f674fd5b93fafbe80453b23ef7ea748 (diff) |
[normalboots] Modernize
-rw-r--r-- | youtube_dl/extractor/normalboots.py | 25 |
1 files changed, 14 insertions, 11 deletions
diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py index c13ff0d65..78e75266f 100644 --- a/youtube_dl/extractor/normalboots.py +++ b/youtube_dl/extractor/normalboots.py @@ -11,7 +11,7 @@ from ..utils import ( class NormalbootsIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$' + _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$' _TEST = { 'url': 'http://normalboots.com/video/home-alone-games-jontron/', 'md5': '8bf6de238915dd501105b44ef5f1e0f6', @@ -30,19 +30,22 @@ class NormalbootsIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>', - webpage, 'uploader') - raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', - webpage, 'date') - video_upload_date = unified_strdate(raw_upload_date) - player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url') + video_uploader = self._html_search_regex( + r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>', + webpage, 'uploader', fatal=False) + video_upload_date = unified_strdate(self._html_search_regex( + r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', + webpage, 'date', fatal=False)) + + player_url = self._html_search_regex( + r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', + webpage, 'player url') player_page = self._download_webpage(player_url, video_id) - video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file') + video_url = self._html_search_regex( + r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file') return { 'id': video_id, |