X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Finfoq.py;h=71cfd12c56549d0be540c9daee6a2732959039de;hb=720334659ac13d7f5bc0759662ba0534f48a1ce4;hp=65f0b76cb0e2a413e82005405b012b4a93fae107;hpb=117a7d194432788435d9a2e697378c8bfc9a640d;p=youtube-dl diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index 65f0b76cb..71cfd12c5 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -1,37 +1,35 @@ from __future__ import unicode_literals import base64 -import re from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse, +from ..compat import ( + compat_urllib_parse_unquote, + compat_urlparse, ) class InfoQIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P[^/]+)$' - - _TEST = { - 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', + _VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P[^/]+)' + + _TESTS = [{ + 'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things', + 'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2', + 'info_dict': { + 'id': '12-jan-pythonthings', + 'ext': 'mp4', + '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', }, - } + }, { + 'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) - video_title = self._html_search_regex(r'(.*?)', webpage, 'title') video_description = self._html_search_meta('description', webpage, 'description') @@ -39,20 +37,32 @@ class InfoQIE(InfoExtractor): 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')) + encoded_id = self._search_regex( + r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id') + real_id = compat_urllib_parse_unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8')) playpath = 'mp4:' + real_id video_filename = playpath.split('/')[-1] video_id, extension = video_filename.split('.') - return [{ + http_base = self._search_regex( + r'EXPRESSINSTALL_SWF\s*=\s*[^"]*"((?:https?:)?//[^/"]+/)', webpage, + 'HTTP base URL') + + formats = [{ + 'format_id': 'rtmp', + 'url': video_url, + 'ext': extension, + 'play_path': playpath, + }, { + 'format_id': 'http', + 'url': compat_urlparse.urljoin(url, http_base) + real_id, + }] + self._sort_formats(formats) + + return { 'id': video_id, 'title': video_title, 'description': video_description, - 'formats': [{ - 'url': video_url, - 'ext': extension, - 'play_path': playpath, - }], - }] + 'formats': formats, + }