diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/kaltura.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/lynda.py | 11 | ||||
| -rw-r--r-- | youtube_dl/extractor/odnoklassniki.py | 85 |
4 files changed, 98 insertions, 5 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d137e1104..ffcc7d9ab 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -346,6 +346,7 @@ from .ntvde import NTVDeIE from .ntvru import NTVRuIE from .nytimes import NYTimesIE from .nuvid import NuvidIE +from .odnoklassniki import OdnoklassnikiIE from .oktoberfesttv import OktoberfestTVIE from .ooyala import OoyalaIE from .openfilm import OpenFilmIE diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 2aff410c5..d28730492 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -14,7 +14,7 @@ from ..utils import ( class KalturaIE(InfoExtractor): _VALID_URL = r'''(?x) (?:kaltura:| - https?://(:?www\.)?kaltura\.com/index\.php/kwidget/(?:[^/]+/)*?wid/_ + https?://(:?(?:www|cdnapisec)\.)?kaltura\.com/index\.php/kwidget/(?:[^/]+/)*?wid/_ )(?P<partner_id>\d+) (?::| /(?:[^/]+/)*?entry_id/ @@ -39,6 +39,10 @@ class KalturaIE(InfoExtractor): 'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4', 'only_matching': True, }, + { + 'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3', + 'only_matching': True, + }, ] def _kaltura_api_call(self, video_id, actions, *args, **kwargs): diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 109055e72..5dc22da22 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -18,7 +18,7 @@ from ..utils import ( class LyndaIE(InfoExtractor): IE_NAME = 'lynda' IE_DESC = 'lynda.com videos' - _VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html' + _VALID_URL = r'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(\d+)' _LOGIN_URL = 'https://www.lynda.com/login/login.aspx' _NETRC_MACHINE = 'lynda' @@ -27,7 +27,7 @@ class LyndaIE(InfoExtractor): ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.' - _TEST = { + _TESTS = [{ 'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html', 'md5': 'ecfc6862da89489161fb9cd5f5a6fac1', 'info_dict': { @@ -36,7 +36,10 @@ class LyndaIE(InfoExtractor): 'title': 'Using the exercise files', 'duration': 68 } - } + }, { + 'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0', + 'only_matching': True, + }] def _real_initialize(self): self._login() @@ -152,7 +155,7 @@ class LyndaIE(InfoExtractor): continue appear_time = m_current.group('timecode') disappear_time = m_next.group('timecode') - text = seq_current['Caption'] + text = seq_current['Caption'].lstrip() srt += '%s\r\n%s --> %s\r\n%s' % (str(pos), appear_time, disappear_time, text) if srt: return srt diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py new file mode 100644 index 000000000..155d0ee6a --- /dev/null +++ b/youtube_dl/extractor/odnoklassniki.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, + int_or_none, + qualities, +) + + +class OdnoklassnikiIE(InfoExtractor): + _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://ok.ru/video/20079905452', + 'md5': '8e24ad2da6f387948e7a7d44eb8668fe', + 'info_dict': { + 'id': '20079905452', + 'ext': 'mp4', + 'title': 'Культура меняет нас (прекрасный ролик!))', + 'duration': 100, + 'upload_date': '20141207', + 'uploader_id': '330537914540', + 'uploader': 'Виталий Добровольский', + 'like_count': int, + 'age_limit': 0, + }, + }, { + 'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + player = self._parse_json( + self._search_regex( + r"OKVideo\.start\(({.+?})\s*,\s*'VideoAutoplay_player'", webpage, 'player'), + video_id) + + metadata = self._parse_json(player['flashvars']['metadata'], video_id) + + movie = metadata['movie'] + title = movie['title'] + thumbnail = movie.get('poster') + duration = int_or_none(movie.get('duration')) + + author = metadata.get('author', {}) + uploader_id = author.get('id') + uploader = author.get('name') + + upload_date = unified_strdate(self._html_search_meta( + 'ya:ovs:upload_date', webpage, 'upload date')) + + age_limit = None + adult = self._html_search_meta( + 'ya:ovs:adult', webpage, 'age limit') + if adult: + age_limit = 18 if adult == 'true' else 0 + + like_count = int_or_none(metadata.get('likeCount')) + + quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd')) + + formats = [{ + 'url': f['url'], + 'ext': 'mp4', + 'format_id': f['name'], + 'quality': quality(f['name']), + } for f in metadata['videos']] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'upload_date': upload_date, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'like_count': like_count, + 'age_limit': age_limit, + 'formats': formats, + } |