X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Finfoq.py;h=65f0b76cb0e2a413e82005405b012b4a93fae107;hb=7560096db5ce0002b3cf3f3bcbbb53ef05e6fb13;hp=7c208b85d21d58fb47c1be5d2db16598c10d1757;hpb=d882161d5a25b658c3be7f6c6c86f4c707d58bb3;p=youtube-dl diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index 7c208b85d..65f0b76cb 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -10,46 +10,49 @@ from ..utils import ( class InfoQIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' + _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P[^/]+)$' + _TEST = { - "name": "InfoQ", - "url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things", - "file": "12-jan-pythonthings.mp4", - "info_dict": { - "description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.", - "title": "A Few of My Favorite [Python] Things", - }, - "params": { - "skip_download": True, + u'name': u'InfoQ', + u'url': u'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things', + u'md5': u'fcaa3d995e04080dcb9465d86b5eef62', + u'info_dict': { + u'id': u'12-jan-pythonthings', + u'ext': u'mp4', + u'description': u'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.', + u'title': u'A Few of My Favorite [Python] Things', }, } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + self.report_extraction(video_id) - webpage = self._download_webpage(url, video_id=url) - self.report_extraction(url) + video_title = self._html_search_regex(r'(.*?)', webpage, 'title') + video_description = self._html_search_meta('description', webpage, 'description') + + # The server URL is hardcoded + video_url = 'rtmpe://video.infoq.com/cfx/st/' # Extract video URL encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id') real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8')) - video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id - - # Extract title - video_title = self._search_regex(r'contentTitle = "(.*?)";', - webpage, 'title') - - # Extract description - video_description = self._html_search_regex(r'', - webpage, 'description', fatal=False) + playpath = 'mp4:' + real_id - video_filename = video_url.split('/')[-1] + video_filename = playpath.split('/')[-1] video_id, extension = video_filename.split('.') - return { + return [{ 'id': video_id, - 'url': video_url, 'title': video_title, - 'ext': extension, # Extension is always(?) mp4, but seems to be flv 'description': video_description, - } + 'formats': [{ + 'url': video_url, + 'ext': extension, + 'play_path': playpath, + }], + }]