diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-01-11 00:40:46 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-01-11 00:40:46 +0600 |
commit | ed3958d714d8e68b3b48697333c72ff6438002f4 (patch) | |
tree | 8a33b3c4bca2712da2e6953d09aae1684d23a0b4 /youtube_dl/extractor | |
parent | 6ce08764a1faba3eeecbd2a04643f3266c8c5111 (diff) |
[collegerama] Add extractor (#4540)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/collegerama.py | 92 |
2 files changed, 93 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 647e0a8c2..2f3a322a7 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -70,6 +70,7 @@ from .cnn import ( CNNArticleIE, ) from .collegehumor import CollegeHumorIE +from .collegerama import CollegeRamaIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE from .comcarcoff import ComCarCoffIE from .commonmistakes import CommonMistakesIE diff --git a/youtube_dl/extractor/collegerama.py b/youtube_dl/extractor/collegerama.py new file mode 100644 index 000000000..fedd48490 --- /dev/null +++ b/youtube_dl/extractor/collegerama.py @@ -0,0 +1,92 @@ +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..compat import compat_urllib_request +from ..utils import ( + float_or_none, + int_or_none, +) + + +class CollegeRamaIE(InfoExtractor): + _VALID_URL = r'https?://collegerama\.tudelft\.nl/Mediasite/Play/(?P<id>[\da-f]+)' + _TESTS = [ + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d', + 'md5': '481fda1c11f67588c0d9d8fbdced4e39', + 'info_dict': { + 'id': '585a43626e544bdd97aeb71a0ec907a01d', + 'ext': 'mp4', + 'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.', + 'description': '', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 7713.088, + 'timestamp': 1413309600, + 'upload_date': '20141014', + }, + }, + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4', + 'md5': 'ef1fdded95bdf19b12c5999949419c92', + 'info_dict': { + 'id': '86a9ea9f53e149079fbdb4202b521ed21d', + 'ext': 'wmv', + 'title': '64ste Vakantiecursus: Afvalwater', + 'description': 'md5:7fd774865cc69d972f542b157c328305', + 'duration': 10853, + 'timestamp': 1326446400, + 'upload_date': '20120113', + }, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + player_options_request = { + "getPlayerOptionsRequest": { + "ResourceId": video_id, + "QueryString": "", + } + } + + request = compat_urllib_request.Request( + 'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions', + json.dumps(player_options_request)) + request.add_header('Content-Type', 'application/json') + + player_options = self._download_json(request, video_id) + + presentation = player_options['d']['Presentation'] + title = presentation['Title'] + description = presentation.get('Description') + thumbnail = None + duration = float_or_none(presentation.get('Duration'), 1000) + timestamp = int_or_none(presentation.get('UnixTime'), 1000) + + formats = [] + for stream in presentation['Streams']: + for video in stream['VideoUrls']: + thumbnail_url = stream.get('ThumbnailUrl') + if thumbnail_url: + thumbnail = 'http://collegerama.tudelft.nl' + thumbnail_url + format_id = video['MediaType'] + if format_id == 'SS': + continue + formats.append({ + 'url': video['Location'], + 'format_id': format_id, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + } |