aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/videolecturesnet.py
diff options
context:
space:
mode:
authorremitamine <remitamine@gmail.com>2015-11-06 21:23:41 +0100
committerSergey M․ <dstftw@gmail.com>2015-11-08 06:55:50 +0600
commita06bf87a2c6009d82ec28afe566f653b3deb11bf (patch)
treeb0a4b959b8d76b0183c0476fcd68e8106bc7144d /youtube_dl/extractor/videolecturesnet.py
parentee4337d100f68bbb2ae795101d4c391b522ec753 (diff)
[viidea] add support for sites using viidea service
Diffstat (limited to 'youtube_dl/extractor/videolecturesnet.py')
-rw-r--r--youtube_dl/extractor/videolecturesnet.py127
1 files changed, 0 insertions, 127 deletions
diff --git a/youtube_dl/extractor/videolecturesnet.py b/youtube_dl/extractor/videolecturesnet.py
deleted file mode 100644
index 351706362..000000000
--- a/youtube_dl/extractor/videolecturesnet.py
+++ /dev/null
@@ -1,127 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import (
- compat_HTTPError,
- compat_urlparse,
-)
-from ..utils import (
- ExtractorError,
- parse_duration,
- js_to_json,
- parse_iso8601,
-)
-
-
-class VideoLecturesNetIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/]+)(?:/video/(?P<part>\d+))?'
- IE_NAME = 'videolectures.net'
-
- _TESTS = [{
- 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
- 'info_dict': {
- 'id': '20171_part1',
- 'ext': 'mp4',
- 'title': 'Automatics, robotics and biocybernetics',
- 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
- 'upload_date': '20130627',
- 'duration': 565,
- 'thumbnail': 're:http://.*\.jpg',
- },
- }, {
- # video with invalid direct format links (HTTP 403)
- 'url': 'http://videolectures.net/russir2010_filippova_nlp/',
- 'info_dict': {
- 'id': '14891_part1',
- 'ext': 'flv',
- 'title': 'NLP at Google',
- 'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
- 'duration': 5352,
- 'thumbnail': 're:http://.*\.jpg',
- },
- 'params': {
- # rtmp download
- 'skip_download': True,
- },
- }, {
- 'url': 'http://videolectures.net/deeplearning2015_montreal/',
- 'info_dict': {
- 'id': '23181',
- 'title': 'Deep Learning Summer School, Montreal 2015',
- 'description': 'md5:0533a85e4bd918df52a01f0e1ebe87b7',
- 'timestamp': 1438560000,
- },
- 'playlist_count': 30,
- }, {
- # multi part lecture
- 'url': 'http://videolectures.net/mlss09uk_bishop_ibi/',
- 'info_dict': {
- 'id': '9737',
- 'title': 'Introduction To Bayesian Inference',
- 'timestamp': 1251622800,
- },
- 'playlist': [{
- 'info_dict': {
- 'id': '9737_part1',
- 'ext': 'wmv',
- 'title': 'Introduction To Bayesian Inference',
- },
- }, {
- 'info_dict': {
- 'id': '9737_part2',
- 'ext': 'wmv',
- 'title': 'Introduction To Bayesian Inference',
- },
- }],
- 'playlist_count': 2,
- }]
-
- def _real_extract(self, url):
- lecture_slug, part = re.match(self._VALID_URL, url).groups()
-
- webpage = self._download_webpage(url, lecture_slug)
-
- cfg = self._parse_json(self._search_regex(r'cfg\s*:\s*({[^}]+})', webpage, 'cfg'), lecture_slug, js_to_json)
-
- lecture_id = str(cfg['obj_id'])
-
- lecture_data = self._download_json('%s/site/api/lecture/%s?format=json' % (self._proto_relative_url(cfg['livepipe'], 'http:'), lecture_id), lecture_id)['lecture'][0]
-
- lecture_info = {
- 'id': lecture_id,
- 'display_id': lecture_slug,
- 'title': lecture_data['title'],
- 'timestamp': parse_iso8601(lecture_data.get('time')),
- 'description': lecture_data.get('description_wiki'),
- 'thumbnail': lecture_data.get('thumb'),
- }
-
- entries = []
- parts = cfg.get('videos')
- if parts:
- if len(parts) == 1:
- part = str(parts[0])
- if part:
- smil_url = 'http://videolectures.net/%s/video/%s/smil.xml' % (lecture_slug, part)
- smil = self._download_smil(smil_url, lecture_id)
- info = self._parse_smil(smil, smil_url, lecture_id)
- info['id'] = '%s_part%s' % (lecture_id, part)
- switch = smil.find('.//switch')
- if switch is not None:
- info['duration'] = parse_duration(switch.attrib.get('dur'))
- return info
- else:
- for part in parts:
- entries.append(self.url_result('http://videolectures.net/%s/video/%s' % (lecture_slug, part), 'VideoLecturesNet'))
- lecture_info['_type'] = 'multi_video'
- else:
- # Probably a playlist
- entries = [
- self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
- for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
- lecture_info['_type'] = 'playlist'
-
- lecture_info['entries'] = entries
- return lecture_info