diff options
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/azubu.py | 40 | ||||
-rw-r--r-- | youtube_dl/extractor/common.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/cspan.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/espn.py | 4 | ||||
-rw-r--r-- | youtube_dl/extractor/youtube.py | 2 |
6 files changed, 45 insertions, 7 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 532be7e4c..5e0d7d3dc 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -50,7 +50,7 @@ from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE from .audimedia import AudiMediaIE from .audiomack import AudiomackIE, AudiomackAlbumIE -from .azubu import AzubuIE +from .azubu import AzubuIE, AzubuLiveIE from .baidu import BaiduVideoIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE diff --git a/youtube_dl/extractor/azubu.py b/youtube_dl/extractor/azubu.py index 0961d339f..011edf128 100644 --- a/youtube_dl/extractor/azubu.py +++ b/youtube_dl/extractor/azubu.py @@ -3,7 +3,11 @@ from __future__ import unicode_literals import json from .common import InfoExtractor -from ..utils import float_or_none +from ..utils import ( + ExtractorError, + float_or_none, + sanitized_Request, +) class AzubuIE(InfoExtractor): @@ -91,3 +95,37 @@ class AzubuIE(InfoExtractor): 'view_count': view_count, 'formats': formats, } + + +class AzubuLiveIE(InfoExtractor): + _VALID_URL = r'http://www.azubu.tv/(?P<id>[^/]+)$' + + _TEST = { + 'url': 'http://www.azubu.tv/MarsTVMDLen', + 'only_matching': True, + } + + def _real_extract(self, url): + user = self._match_id(url) + + info = self._download_json( + 'http://api.azubu.tv/public/modules/last-video/{0}/info'.format(user), + user)['data'] + if info['type'] != 'STREAM': + raise ExtractorError('{0} is not streaming live'.format(user), expected=True) + + req = sanitized_Request( + 'https://edge-elb.api.brightcove.com/playback/v1/accounts/3361910549001/videos/ref:' + info['reference_id']) + req.add_header('Accept', 'application/json;pk=BCpkADawqM1gvI0oGWg8dxQHlgT8HkdE2LnAlWAZkOlznO39bSZX726u4JqnDsK3MDXcO01JxXK2tZtJbgQChxgaFzEVdHRjaDoxaOu8hHOO8NYhwdxw9BzvgkvLUlpbDNUuDoc4E4wxDToV') + bc_info = self._download_json(req, user) + m3u8_url = next(source['src'] for source in bc_info['sources'] if source['container'] == 'M2TS') + formats = self._extract_m3u8_formats(m3u8_url, user, ext='mp4') + + return { + 'id': info['id'], + 'title': self._live_title(info['title']), + 'uploader_id': user, + 'formats': formats, + 'is_live': True, + 'thumbnail': bc_info['poster'], + } diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 33290fd74..b3d57dfce 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -828,7 +828,7 @@ class InfoExtractor(object): for f in formats: # Automatically determine tbr when missing based on abr and vbr (improves # formats sorting in some cases) - if 'tbr' not in f and 'abr' in f and 'vbr' in f: + if 'tbr' not in f and f.get('abr') is not None and f.get('vbr') is not None: f['tbr'] = f['abr'] + f['vbr'] def _formats_key(f): diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index b78edf729..b8b9d058d 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -113,7 +113,7 @@ class CSpanIE(InfoExtractor): 'tbr': int_or_none(get_text_attr(quality, 'bitrate')), }) if not formats: - path = get_text_attr(f, 'path') + path = unescapeHTML(get_text_attr(f, 'path')) if not path: continue formats = self._extract_m3u8_formats( diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index 3762d8748..db4b263bc 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -53,8 +53,8 @@ class ESPNIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_id = self._search_regex( - r'class="video-play-button"[^>]+data-id="(\d+)', - webpage, 'video id') + r'class=(["\']).*?video-play-button.*?\1[^>]+data-id=["\'](?P<id>\d+)', + webpage, 'video id', group='id') cms = 'espn' if 'data-source="intl"' in webpage: diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 92b9f3ae4..a24c73584 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1846,7 +1846,7 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): class YoutubeUserIE(YoutubeChannelIE): IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' + _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos' IE_NAME = 'youtube:user' |