Merge remote-tracking branch 'refs/remotes/rg3/master' into shoutfactorytv
This commit is contained in:
gkoelln
commit
aa204d3da0
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.10*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.01.10**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.28*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.01.28**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
|
||||
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] youtube-dl version 2017.01.10
|
||||
[debug] youtube-dl version 2017.01.28
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
||||
111
ChangeLog
111
ChangeLog
@ -1,3 +1,114 @@
|
||||
version 2017.01.28
|
||||
|
||||
Core
|
||||
* [utils] Improve parse_duration
|
||||
|
||||
Extractors
|
||||
* [crunchyroll] Improve series and season metadata extraction (#11832)
|
||||
* [soundcloud] Improve formats extraction and extract audio bitrate
|
||||
+ [soundcloud] Extract HLS formats
|
||||
* [soundcloud] Fix track URL extraction (#11852)
|
||||
+ [twitch:vod] Expand URL regular expressions (#11846)
|
||||
* [aenetworks] Fix season episodes extraction (#11669)
|
||||
+ [tva] Add support for videos.tva.ca (#11842)
|
||||
* [jamendo] Improve and extract more metadata (#11836)
|
||||
+ [disney] Add support for Disney sites (#7409, #11801, #4975, #11000)
|
||||
* [vevo] Remove request to old API and catch API v2 errors
|
||||
+ [cmt,mtv,southpark] Add support for episode URLs (#11837)
|
||||
+ [youtube] Add fallback for duration extraction (#11841)
|
||||
|
||||
|
||||
version 2017.01.25
|
||||
|
||||
Extractors
|
||||
+ [openload] Fallback video extension to mp4
|
||||
+ [extractor/generic] Add support for Openload embeds (#11536, #11812)
|
||||
* [srgssr] Fix rts video extraction (#11831)
|
||||
+ [afreecatv:global] Add support for afreeca.tv (#11807)
|
||||
+ [crackle] Extract vtt subtitles
|
||||
+ [crackle] Extract multiple resolutions for thumbnails
|
||||
+ [crackle] Add support for mobile URLs
|
||||
+ [konserthusetplay] Extract subtitles (#11823)
|
||||
+ [konserthusetplay] Add support for HLS videos (#11823)
|
||||
* [vimeo:review] Fix config URL extraction (#11821)
|
||||
|
||||
|
||||
version 2017.01.24
|
||||
|
||||
Extractors
|
||||
* [pluralsight] Fix extraction (#11820)
|
||||
+ [nextmedia] Add support for NextTV (壹電視)
|
||||
* [24video] Fix extraction (#11811)
|
||||
* [youtube:playlist] Fix nonexistent and private playlist detection (#11604)
|
||||
+ [chirbit] Extract uploader (#11809)
|
||||
|
||||
|
||||
version 2017.01.22
|
||||
|
||||
Extractors
|
||||
+ [pornflip] Add support for pornflip.com (#11556, #11795)
|
||||
* [chaturbate] Fix extraction (#11797, #11802)
|
||||
+ [azmedien] Add support for AZ Medien sites (#11784, #11785)
|
||||
+ [nextmedia] Support redirected URLs
|
||||
+ [vimeo:channel] Extract videos' titles for playlist entries (#11796)
|
||||
+ [youtube] Extract episode metadata (#9695, #11774)
|
||||
+ [cspan] Support Ustream embedded videos (#11547)
|
||||
+ [1tv] Add support for HLS videos (#11786)
|
||||
* [uol] Fix extraction (#11770)
|
||||
* [mtv] Relax triforce feed regular expression (#11766)
|
||||
|
||||
|
||||
version 2017.01.18
|
||||
|
||||
Extractors
|
||||
* [bilibili] Fix extraction (#11077)
|
||||
+ [canalplus] Add fallback for video id (#11764)
|
||||
* [20min] Fix extraction (#11683, #11751)
|
||||
* [imdb] Extend URL regular expression (#11744)
|
||||
+ [naver] Add support for tv.naver.com links (#11743)
|
||||
|
||||
|
||||
version 2017.01.16
|
||||
|
||||
Core
|
||||
* [options] Apply custom config to final composite configuration (#11741)
|
||||
* [YoutubeDL] Improve protocol auto determining (#11720)
|
||||
|
||||
Extractors
|
||||
* [xiami] Relax URL regular expressions
|
||||
* [xiami] Improve track metadata extraction (#11699)
|
||||
+ [limelight] Check hand-make direct HTTP links
|
||||
+ [limelight] Add support for direct HTTP links at video.llnw.net (#11737)
|
||||
+ [brightcove] Recognize another player ID pattern (#11688)
|
||||
+ [niconico] Support login via cookies (#7968)
|
||||
* [yourupload] Fix extraction (#11601)
|
||||
+ [beam:live] Add support for beam.pro live streams (#10702, #11596)
|
||||
* [vevo] Improve geo restriction detection
|
||||
+ [dramafever] Add support for URLs with language code (#11714)
|
||||
* [cbc] Improve playlist support (#11704)
|
||||
|
||||
|
||||
version 2017.01.14
|
||||
|
||||
Core
|
||||
+ [common] Add ability to customize akamai manifest host
|
||||
+ [utils] Add more date formats
|
||||
|
||||
Extractors
|
||||
- [mtv] Eliminate _transform_rtmp_url
|
||||
* [mtv] Generalize triforce mgid extraction
|
||||
+ [cmt] Add support for full episodes and video clips (#11623)
|
||||
+ [mitele] Extract DASH formats
|
||||
+ [ooyala] Add support for videos with embedToken (#11684)
|
||||
* [mixcloud] Fix extraction (#11674)
|
||||
* [openload] Fix extraction (#10408)
|
||||
* [tv4] Improve extraction (#11698)
|
||||
* [freesound] Fix and improve extraction (#11602)
|
||||
+ [nick] Add support for beta.nick.com (#11655)
|
||||
* [mtv,cc] Use HLS by default with native HLS downloader (#11641)
|
||||
* [mtv] Fix non-HLS extraction
|
||||
|
||||
|
||||
version 2017.01.10
|
||||
|
||||
Extractors
|
||||
|
||||
@ -374,7 +374,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
|
||||
avprobe)
|
||||
--audio-format FORMAT Specify audio format: "best", "aac",
|
||||
"vorbis", "mp3", "m4a", "opus", or "wav";
|
||||
"best" by default
|
||||
"best" by default; No effect without -x
|
||||
--audio-quality QUALITY Specify ffmpeg/avconv audio quality, insert
|
||||
a value between 0 (better) and 9 (worse)
|
||||
for VBR or a specific bitrate like 128K
|
||||
@ -841,7 +841,7 @@ Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
|
||||
|
||||
In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox).
|
||||
|
||||
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
|
||||
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, Mac OS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
|
||||
|
||||
Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).
|
||||
|
||||
|
||||
@ -33,7 +33,8 @@
|
||||
- **AdobeTVVideo**
|
||||
- **AdultSwim**
|
||||
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
|
||||
- **AfreecaTV**: afreecatv.com
|
||||
- **afreecatv**: afreecatv.com
|
||||
- **afreecatv:global**: afreecatv.com
|
||||
- **AirMozilla**
|
||||
- **AlJazeera**
|
||||
- **Allocine**
|
||||
@ -74,6 +75,8 @@
|
||||
- **awaan:live**
|
||||
- **awaan:season**
|
||||
- **awaan:video**
|
||||
- **AZMedien**: AZ Medien videos
|
||||
- **AZMedienShow**: AZ Medien shows
|
||||
- **Azubu**
|
||||
- **AzubuLive**
|
||||
- **BaiduVideo**: 百度视频
|
||||
@ -86,6 +89,7 @@
|
||||
- **bbc.co.uk:article**: BBC articles
|
||||
- **bbc.co.uk:iplayer:playlist**
|
||||
- **bbc.co.uk:playlist**
|
||||
- **Beam:live**
|
||||
- **Beatport**
|
||||
- **Beeg**
|
||||
- **BehindKink**
|
||||
@ -198,6 +202,7 @@
|
||||
- **Digiteka**
|
||||
- **Discovery**
|
||||
- **DiscoveryGo**
|
||||
- **Disney**
|
||||
- **Dotsub**
|
||||
- **DouyuTV**: 斗鱼
|
||||
- **DPlay**
|
||||
@ -482,6 +487,7 @@
|
||||
- **Newstube**
|
||||
- **NextMedia**: 蘋果日報
|
||||
- **NextMediaActionNews**: 蘋果日報 - 動新聞
|
||||
- **NextTV**: 壹電視
|
||||
- **nfb**: National Film Board of Canada
|
||||
- **nfl.com**
|
||||
- **NhkVod**
|
||||
@ -571,6 +577,7 @@
|
||||
- **PolskieRadio**
|
||||
- **PolskieRadioCategory**
|
||||
- **PornCom**
|
||||
- **PornFlip**
|
||||
- **PornHd**
|
||||
- **PornHub**: PornHub and Thumbzilla
|
||||
- **PornHubPlaylist**
|
||||
@ -779,6 +786,7 @@
|
||||
- **TV2Article**
|
||||
- **TV3**
|
||||
- **TV4**: tv4.se and tv4play.se
|
||||
- **TVA**
|
||||
- **TVANouvelles**
|
||||
- **TVANouvellesArticle**
|
||||
- **TVC**
|
||||
|
||||
@ -510,6 +510,7 @@ class TestUtil(unittest.TestCase):
|
||||
self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
|
||||
self.assertEqual(parse_duration('87 Min.'), 5220)
|
||||
self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
|
||||
self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
|
||||
|
||||
def test_fix_xml_ampersands(self):
|
||||
self.assertEqual(
|
||||
|
||||
@ -1363,7 +1363,7 @@ class YoutubeDL(object):
|
||||
format['ext'] = determine_ext(format['url']).lower()
|
||||
# Automatically determine protocol if missing (useful for format
|
||||
# selection purposes)
|
||||
if 'protocol' not in format:
|
||||
if format.get('protocol') is None:
|
||||
format['protocol'] = determine_protocol(format)
|
||||
# Add HTTP headers, so that external programs can use them from the
|
||||
# json output
|
||||
|
||||
@ -87,7 +87,7 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
self._html_search_meta('aetn:SeriesTitle', webpage))
|
||||
elif url_parts_len == 2:
|
||||
entries = []
|
||||
for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
|
||||
for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
|
||||
episode_attributes = extract_attributes(episode_item)
|
||||
episode_url = compat_urlparse.urljoin(
|
||||
url, episode_attributes['data-canonical'])
|
||||
|
||||
@ -18,6 +18,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class AfreecaTVIE(InfoExtractor):
|
||||
IE_NAME = 'afreecatv'
|
||||
IE_DESC = 'afreecatv.com'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
@ -143,3 +144,94 @@ class AfreecaTVIE(InfoExtractor):
|
||||
expected=True)
|
||||
|
||||
return info
|
||||
|
||||
|
||||
class AfreecaTVGlobalIE(AfreecaTVIE):
|
||||
IE_NAME = 'afreecatv:global'
|
||||
_VALID_URL = r'https?://(?:www\.)?afreeca\.tv/(?P<channel_id>\d+)(?:/v/(?P<video_id>\d+))?'
|
||||
_TESTS = [{
|
||||
'url': 'http://afreeca.tv/36853014/v/58301',
|
||||
'info_dict': {
|
||||
'id': '58301',
|
||||
'title': 'tryhard top100',
|
||||
'uploader_id': '36853014',
|
||||
'uploader': 'makgi Hearthstone Live!',
|
||||
},
|
||||
'playlist_count': 3,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
channel_id, video_id = re.match(self._VALID_URL, url).groups()
|
||||
video_type = 'video' if video_id else 'live'
|
||||
query = {
|
||||
'pt': 'view',
|
||||
'bid': channel_id,
|
||||
}
|
||||
if video_id:
|
||||
query['vno'] = video_id
|
||||
video_data = self._download_json(
|
||||
'http://api.afreeca.tv/%s/view_%s.php' % (video_type, video_type),
|
||||
video_id or channel_id, query=query)['channel']
|
||||
|
||||
if video_data.get('result') != 1:
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, video_data['remsg']))
|
||||
|
||||
title = video_data['title']
|
||||
|
||||
info = {
|
||||
'thumbnail': video_data.get('thumb'),
|
||||
'view_count': int_or_none(video_data.get('vcnt')),
|
||||
'age_limit': int_or_none(video_data.get('grade')),
|
||||
'uploader_id': channel_id,
|
||||
'uploader': video_data.get('cname'),
|
||||
}
|
||||
|
||||
if video_id:
|
||||
entries = []
|
||||
for i, f in enumerate(video_data.get('flist', [])):
|
||||
video_key = self.parse_video_key(f.get('key', ''))
|
||||
f_url = f.get('file')
|
||||
if not video_key or not f_url:
|
||||
continue
|
||||
entries.append({
|
||||
'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
|
||||
'title': title,
|
||||
'upload_date': video_key.get('upload_date'),
|
||||
'duration': int_or_none(f.get('length')),
|
||||
'url': f_url,
|
||||
'protocol': 'm3u8_native',
|
||||
'ext': 'mp4',
|
||||
})
|
||||
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'duration': int_or_none(video_data.get('length')),
|
||||
})
|
||||
if len(entries) > 1:
|
||||
info['_type'] = 'multi_video'
|
||||
info['entries'] = entries
|
||||
elif len(entries) == 1:
|
||||
i = entries[0].copy()
|
||||
i.update(info)
|
||||
info = i
|
||||
else:
|
||||
formats = []
|
||||
for s in video_data.get('strm', []):
|
||||
s_url = s.get('purl')
|
||||
if not s_url:
|
||||
continue
|
||||
# TODO: extract rtmp formats
|
||||
if s.get('stype') == 'HLS':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
s_url, channel_id, 'mp4', fatal=False))
|
||||
self._sort_formats(formats)
|
||||
|
||||
info.update({
|
||||
'id': channel_id,
|
||||
'title': self._live_title(title),
|
||||
'is_live': True,
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
return info
|
||||
|
||||
145
youtube_dl/extractor/azmedien.py
Normal file
145
youtube_dl/extractor/azmedien.py
Normal file
@ -0,0 +1,145 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .kaltura import KalturaIE
|
||||
from ..utils import (
|
||||
get_element_by_class,
|
||||
strip_or_none,
|
||||
)
|
||||
|
||||
|
||||
class AZMedienBaseIE(InfoExtractor):
|
||||
def _kaltura_video(self, partner_id, entry_id):
|
||||
return self.url_result(
|
||||
'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
|
||||
video_id=entry_id)
|
||||
|
||||
|
||||
class AZMedienIE(AZMedienBaseIE):
|
||||
IE_DESC = 'AZ Medien videos'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:www\.)?
|
||||
(?:
|
||||
telezueri\.ch|
|
||||
telebaern\.tv|
|
||||
telem1\.ch
|
||||
)/
|
||||
[0-9]+-show-[^/\#]+
|
||||
(?:
|
||||
/[0-9]+-episode-[^/\#]+
|
||||
(?:
|
||||
/[0-9]+-segment-(?:[^/\#]+\#)?|
|
||||
\#
|
||||
)|
|
||||
\#
|
||||
)
|
||||
(?P<id>[^\#]+)
|
||||
'''
|
||||
|
||||
_TESTS = [{
|
||||
# URL with 'segment'
|
||||
'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
|
||||
'info_dict': {
|
||||
'id': '1_2444peh4',
|
||||
'ext': 'mov',
|
||||
'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
|
||||
'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
|
||||
'uploader_id': 'TeleZ?ri',
|
||||
'upload_date': '20161218',
|
||||
'timestamp': 1482084490,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# URL with 'segment' and fragment:
|
||||
'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
|
||||
'only_matching': True
|
||||
}, {
|
||||
# URL with 'episode' and fragment:
|
||||
'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
|
||||
'only_matching': True
|
||||
}, {
|
||||
# URL with 'show' and fragment:
|
||||
'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
partner_id = self._search_regex(
|
||||
r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
|
||||
webpage, 'kaltura partner id')
|
||||
entry_id = self._html_search_regex(
|
||||
r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
|
||||
% re.escape(video_id), webpage, 'kaltura entry id', group='id')
|
||||
|
||||
return self._kaltura_video(partner_id, entry_id)
|
||||
|
||||
|
||||
class AZMedienShowIE(AZMedienBaseIE):
|
||||
IE_DESC = 'AZ Medien shows'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:www\.)?
|
||||
(?:
|
||||
telezueri\.ch|
|
||||
telebaern\.tv|
|
||||
telem1\.ch
|
||||
)/
|
||||
(?P<id>[0-9]+-show-[^/\#]+
|
||||
(?:
|
||||
/[0-9]+-episode-[^/\#]+
|
||||
)?
|
||||
)$
|
||||
'''
|
||||
|
||||
_TESTS = [{
|
||||
# URL with 'episode'
|
||||
'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
|
||||
'info_dict': {
|
||||
'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
|
||||
'title': 'News - Donnerstag, 15. Dezember 2016',
|
||||
},
|
||||
'playlist_count': 9,
|
||||
}, {
|
||||
# URL with 'show' only
|
||||
'url': 'http://www.telezueri.ch/86-show-talktaeglich',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
show_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, show_id)
|
||||
|
||||
entries = []
|
||||
|
||||
partner_id = self._search_regex(
|
||||
r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
|
||||
webpage, 'kaltura partner id', default=None)
|
||||
|
||||
if partner_id:
|
||||
entries = [
|
||||
self._kaltura_video(partner_id, m.group('id'))
|
||||
for m in re.finditer(
|
||||
r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
|
||||
|
||||
if not entries:
|
||||
entries = [
|
||||
self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
|
||||
for m in re.finditer(
|
||||
r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
|
||||
|
||||
title = self._search_regex(
|
||||
r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
|
||||
webpage, 'title',
|
||||
default=strip_or_none(get_element_by_class(
|
||||
'title-block-cell', webpage)), group='title')
|
||||
|
||||
return self.playlist_result(entries, show_id, title)
|
||||
73
youtube_dl/extractor/beampro.py
Normal file
73
youtube_dl/extractor/beampro.py
Normal file
@ -0,0 +1,73 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
clean_html,
|
||||
compat_str,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class BeamProLiveIE(InfoExtractor):
|
||||
IE_NAME = 'Beam:live'
|
||||
_VALID_URL = r'https?://(?:\w+\.)?beam\.pro/(?P<id>[^/?#&]+)'
|
||||
_RATINGS = {'family': 0, 'teen': 13, '18+': 18}
|
||||
_TEST = {
|
||||
'url': 'http://www.beam.pro/niterhayven',
|
||||
'info_dict': {
|
||||
'id': '261562',
|
||||
'ext': 'mp4',
|
||||
'title': 'Introducing The Witcher 3 // The Grind Starts Now!',
|
||||
'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
|
||||
'thumbnail': r're:https://.*\.jpg$',
|
||||
'timestamp': 1483477281,
|
||||
'upload_date': '20170103',
|
||||
'uploader': 'niterhayven',
|
||||
'uploader_id': '373396',
|
||||
'age_limit': 18,
|
||||
'is_live': True,
|
||||
'view_count': int,
|
||||
},
|
||||
'skip': 'niterhayven is offline',
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
channel_name = self._match_id(url)
|
||||
|
||||
chan = self._download_json(
|
||||
'https://beam.pro/api/v1/channels/%s' % channel_name, channel_name)
|
||||
|
||||
if chan.get('online') is False:
|
||||
raise ExtractorError(
|
||||
'{0} is offline'.format(channel_name), expected=True)
|
||||
|
||||
channel_id = chan['id']
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
'https://beam.pro/api/v1/channels/%s/manifest.m3u8' % channel_id,
|
||||
channel_name, ext='mp4', m3u8_id='hls', fatal=False)
|
||||
self._sort_formats(formats)
|
||||
|
||||
user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
|
||||
|
||||
return {
|
||||
'id': compat_str(chan.get('id') or channel_name),
|
||||
'title': self._live_title(chan.get('name') or channel_name),
|
||||
'description': clean_html(chan.get('description')),
|
||||
'thumbnail': try_get(chan, lambda x: x['thumbnail']['url'], compat_str),
|
||||
'timestamp': parse_iso8601(chan.get('updatedAt')),
|
||||
'uploader': chan.get('token') or try_get(
|
||||
chan, lambda x: x['user']['username'], compat_str),
|
||||
'uploader_id': compat_str(user_id) if user_id else None,
|
||||
'age_limit': self._RATINGS.get(chan.get('audience')),
|
||||
'is_live': True,
|
||||
'view_count': int_or_none(chan.get('viewersTotal')),
|
||||
'formats': formats,
|
||||
}
|
||||
@ -34,8 +34,8 @@ class BiliBiliIE(InfoExtractor):
|
||||
},
|
||||
}
|
||||
|
||||
_APP_KEY = '6f90a59ac58a4123'
|
||||
_BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
|
||||
_APP_KEY = '84956560bc028eb7'
|
||||
_BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
@ -179,7 +179,7 @@ class BrightcoveLegacyIE(InfoExtractor):
|
||||
|
||||
params = {}
|
||||
|
||||
playerID = find_param('playerID')
|
||||
playerID = find_param('playerID') or find_param('playerId')
|
||||
if playerID is None:
|
||||
raise ExtractorError('Cannot find player ID')
|
||||
params['playerID'] = playerID
|
||||
@ -204,7 +204,7 @@ class BrightcoveLegacyIE(InfoExtractor):
|
||||
# // build Brightcove <object /> XML
|
||||
# }
|
||||
m = re.search(
|
||||
r'''(?x)customBC.\createVideo\(
|
||||
r'''(?x)customBC\.createVideo\(
|
||||
.*? # skipping width and height
|
||||
["\'](?P<playerID>\d+)["\']\s*,\s* # playerID
|
||||
["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s* # playerKey begins with AQ and is 50 characters
|
||||
|
||||
@ -107,7 +107,7 @@ class CanalplusIE(InfoExtractor):
|
||||
[r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
|
||||
r'id=["\']canal_video_player(?P<id>\d+)',
|
||||
r'data-video=["\'](?P<id>\d+)'],
|
||||
webpage, 'video id', group='id')
|
||||
webpage, 'video id', default=mobj.group('vid'), group='id')
|
||||
|
||||
info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
|
||||
video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
|
||||
|
||||
@ -90,36 +90,49 @@ class CBCIE(InfoExtractor):
|
||||
},
|
||||
}],
|
||||
'skip': 'Geo-restricted to Canada',
|
||||
}, {
|
||||
# multiple CBC.APP.Caffeine.initInstance(...)
|
||||
'url': 'http://www.cbc.ca/news/canada/calgary/dog-indoor-exercise-winter-1.3928238',
|
||||
'info_dict': {
|
||||
'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
|
||||
'id': 'dog-indoor-exercise-winter-1.3928238',
|
||||
},
|
||||
'playlist_mincount': 6,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url)
|
||||
|
||||
def _extract_player_init(self, player_init, display_id):
|
||||
player_info = self._parse_json(player_init, display_id, js_to_json)
|
||||
media_id = player_info.get('mediaId')
|
||||
if not media_id:
|
||||
clip_id = player_info['clipId']
|
||||
feed = self._download_json(
|
||||
'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
|
||||
clip_id, fatal=False)
|
||||
if feed:
|
||||
media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
|
||||
if not media_id:
|
||||
media_id = self._download_json(
|
||||
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
|
||||
clip_id)['entries'][0]['id'].split('/')[-1]
|
||||
return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
player_init = self._search_regex(
|
||||
r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init',
|
||||
default=None)
|
||||
if player_init:
|
||||
player_info = self._parse_json(player_init, display_id, js_to_json)
|
||||
media_id = player_info.get('mediaId')
|
||||
if not media_id:
|
||||
clip_id = player_info['clipId']
|
||||
feed = self._download_json(
|
||||
'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
|
||||
clip_id, fatal=False)
|
||||
if feed:
|
||||
media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
|
||||
if not media_id:
|
||||
media_id = self._download_json(
|
||||
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
|
||||
clip_id)['entries'][0]['id'].split('/')[-1]
|
||||
return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
|
||||
else:
|
||||
entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
|
||||
return self.playlist_result(entries)
|
||||
entries = [
|
||||
self._extract_player_init(player_init, display_id)
|
||||
for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
|
||||
entries.extend([
|
||||
self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
|
||||
for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)])
|
||||
return self.playlist_result(
|
||||
entries, display_id,
|
||||
self._og_search_title(webpage, fatal=False),
|
||||
self._og_search_description(webpage))
|
||||
|
||||
|
||||
class CBCPlayerIE(InfoExtractor):
|
||||
|
||||
@ -1,5 +1,7 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
@ -31,30 +33,35 @@ class ChaturbateIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
m3u8_url = self._search_regex(
|
||||
r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
|
||||
'playlist', default=None, group='url')
|
||||
m3u8_formats = [(m.group('id').lower(), m.group('url')) for m in re.finditer(
|
||||
r'hlsSource(?P<id>.+?)\s*=\s*(?P<q>["\'])(?P<url>http.+?)(?P=q)', webpage)]
|
||||
|
||||
if not m3u8_url:
|
||||
if not m3u8_formats:
|
||||
error = self._search_regex(
|
||||
[r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
|
||||
r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
|
||||
webpage, 'error', group='error', default=None)
|
||||
if not error:
|
||||
if any(p not in webpage for p in (
|
||||
if any(p in webpage for p in (
|
||||
self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
|
||||
error = self._ROOM_OFFLINE
|
||||
if error:
|
||||
raise ExtractorError(error, expected=True)
|
||||
raise ExtractorError('Unable to find stream URL')
|
||||
|
||||
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
|
||||
formats = []
|
||||
for m3u8_id, m3u8_url in m3u8_formats:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, ext='mp4',
|
||||
# ffmpeg skips segments for fast m3u8
|
||||
preference=-10 if m3u8_id == 'fast' else None,
|
||||
m3u8_id=m3u8_id, fatal=False, live=True))
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._live_title(video_id),
|
||||
'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
|
||||
'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
|
||||
'age_limit': self._rta_search(webpage),
|
||||
'is_live': True,
|
||||
'formats': formats,
|
||||
|
||||
@ -19,6 +19,7 @@ class ChirbitIE(InfoExtractor):
|
||||
'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
|
||||
'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
|
||||
'duration': 306,
|
||||
'uploader': 'Gerryaudio',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
@ -54,6 +55,9 @@ class ChirbitIE(InfoExtractor):
|
||||
duration = parse_duration(self._search_regex(
|
||||
r'class=["\']c-length["\'][^>]*>([^<]+)',
|
||||
webpage, 'duration', fatal=False))
|
||||
uploader = self._search_regex(
|
||||
r'id=["\']chirbit-username["\'][^>]*>([^<]+)',
|
||||
webpage, 'uploader', fatal=False)
|
||||
|
||||
return {
|
||||
'id': audio_id,
|
||||
@ -61,6 +65,7 @@ class ChirbitIE(InfoExtractor):
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'uploader': uploader,
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -1,13 +1,11 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .mtv import MTVIE
|
||||
from ..utils import ExtractorError
|
||||
|
||||
|
||||
class CMTIE(MTVIE):
|
||||
IE_NAME = 'cmt.com'
|
||||
_VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
|
||||
_FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
|
||||
_VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows|(?:full-)?episodes|video-clips)/(?P<id>[^/]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
|
||||
@ -33,17 +31,24 @@ class CMTIE(MTVIE):
|
||||
}, {
|
||||
'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.cmt.com/full-episodes/537qb3/nashville-the-wayfaring-stranger-season-5-ep-501',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.cmt.com/video-clips/t9e4ci/nashville-juliette-in-2-minutes',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def _transform_rtmp_url(cls, rtmp_video_url):
|
||||
if 'error_not_available.swf' in rtmp_video_url:
|
||||
raise ExtractorError(
|
||||
'%s said: video is not available' % cls.IE_NAME, expected=True)
|
||||
|
||||
return super(CMTIE, cls)._transform_rtmp_url(rtmp_video_url)
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
return self._search_regex(
|
||||
mgid = self._search_regex(
|
||||
r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P<mgid>.+?)\1',
|
||||
webpage, 'mgid', group='mgid')
|
||||
webpage, 'mgid', group='mgid', default=None)
|
||||
if not mgid:
|
||||
mgid = self._extract_triforce_mgid(webpage)
|
||||
return mgid
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
mgid = self._extract_mgid(webpage)
|
||||
return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)
|
||||
|
||||
@ -48,17 +48,8 @@ class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
playlist_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
|
||||
feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
|
||||
feed = self._parse_json(feed_json, playlist_id)
|
||||
zones = feed['manifest']['zones']
|
||||
|
||||
video_zone = zones['t2_lc_promo1']
|
||||
feed = self._download_json(video_zone['feed'], playlist_id)
|
||||
mgid = feed['result']['data']['id']
|
||||
|
||||
mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1')
|
||||
videos_info = self._get_videos_info(mgid)
|
||||
|
||||
return videos_info
|
||||
|
||||
|
||||
@ -94,12 +85,6 @@ class ToshIE(MTVServicesInfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def _transform_rtmp_url(cls, rtmp_video_url):
|
||||
new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
|
||||
new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
|
||||
return new_urls
|
||||
|
||||
|
||||
class ComedyCentralTVIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
|
||||
|
||||
@ -6,7 +6,7 @@ from ..utils import int_or_none
|
||||
|
||||
|
||||
class CrackleIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
|
||||
_VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
|
||||
'info_dict': {
|
||||
@ -31,8 +31,32 @@ class CrackleIE(InfoExtractor):
|
||||
}
|
||||
}
|
||||
|
||||
_THUMBNAIL_RES = [
|
||||
(120, 90),
|
||||
(208, 156),
|
||||
(220, 124),
|
||||
(220, 220),
|
||||
(240, 180),
|
||||
(250, 141),
|
||||
(315, 236),
|
||||
(320, 180),
|
||||
(360, 203),
|
||||
(400, 300),
|
||||
(421, 316),
|
||||
(460, 330),
|
||||
(460, 460),
|
||||
(462, 260),
|
||||
(480, 270),
|
||||
(587, 330),
|
||||
(640, 480),
|
||||
(700, 330),
|
||||
(700, 394),
|
||||
(854, 480),
|
||||
(1024, 1024),
|
||||
(1920, 1080),
|
||||
]
|
||||
|
||||
# extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx
|
||||
_THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
|
||||
_MEDIA_FILE_SLOTS = {
|
||||
'c544.flv': {
|
||||
'width': 544,
|
||||
@ -61,17 +85,25 @@ class CrackleIE(InfoExtractor):
|
||||
|
||||
item = self._download_xml(
|
||||
'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
|
||||
video_id).find('i')
|
||||
video_id, headers=self.geo_verification_headers()).find('i')
|
||||
title = item.attrib['t']
|
||||
|
||||
subtitles = {}
|
||||
formats = self._extract_m3u8_formats(
|
||||
'http://content.uplynk.com/ext/%s/%s.m3u8' % (config_doc.attrib['strUplynkOwnerId'], video_id),
|
||||
video_id, 'mp4', m3u8_id='hls', fatal=None)
|
||||
thumbnail = None
|
||||
thumbnails = []
|
||||
path = item.attrib.get('p')
|
||||
if path:
|
||||
thumbnail = self._THUMBNAIL_TEMPLATE % path
|
||||
for width, height in self._THUMBNAIL_RES:
|
||||
res = '%dx%d' % (width, height)
|
||||
thumbnails.append({
|
||||
'id': res,
|
||||
'url': 'http://images-us-am.crackle.com/%stnl_%s.jpg' % (path, res),
|
||||
'width': width,
|
||||
'height': height,
|
||||
'resolution': res,
|
||||
})
|
||||
http_base_url = 'http://ahttp.crackle.com/' + path
|
||||
for mfs_path, mfs_info in self._MEDIA_FILE_SLOTS.items():
|
||||
formats.append({
|
||||
@ -86,10 +118,11 @@ class CrackleIE(InfoExtractor):
|
||||
if locale and v:
|
||||
if locale not in subtitles:
|
||||
subtitles[locale] = []
|
||||
subtitles[locale] = [{
|
||||
'url': '%s/%s%s_%s.xml' % (config_doc.attrib['strSubtitleServer'], path, locale, v),
|
||||
'ext': 'ttml',
|
||||
}]
|
||||
for url_ext, ext in (('vtt', 'vtt'), ('xml', 'tt')):
|
||||
subtitles.setdefault(locale, []).append({
|
||||
'url': '%s/%s%s_%s.%s' % (config_doc.attrib['strSubtitleServer'], path, locale, v, url_ext),
|
||||
'ext': ext,
|
||||
})
|
||||
self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
|
||||
|
||||
return {
|
||||
@ -100,7 +133,7 @@ class CrackleIE(InfoExtractor):
|
||||
'series': item.attrib.get('sn'),
|
||||
'season_number': int_or_none(item.attrib.get('se')),
|
||||
'episode_number': int_or_none(item.attrib.get('ep')),
|
||||
'thumbnail': thumbnail,
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': subtitles,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -166,6 +166,25 @@ class CrunchyrollIE(CrunchyrollBaseIE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
|
||||
'info_dict': {
|
||||
'id': '727589',
|
||||
'ext': 'mp4',
|
||||
'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
|
||||
'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'uploader': 'Kadokawa Pictures Inc.',
|
||||
'upload_date': '20170118',
|
||||
'series': "KONOSUBA -God's blessing on this wonderful world!",
|
||||
'season_number': 2,
|
||||
'episode': 'Give Me Deliverance from this Judicial Injustice!',
|
||||
'episode_number': 1,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
|
||||
'only_matching': True,
|
||||
@ -439,6 +458,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
||||
|
||||
subtitles = self.extract_subtitles(video_id, webpage)
|
||||
|
||||
# webpage provide more accurate data than series_title from XML
|
||||
series = self._html_search_regex(
|
||||
r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
|
||||
webpage, 'series', default=xpath_text(metadata, 'series_title'))
|
||||
|
||||
episode = xpath_text(metadata, 'episode_title')
|
||||
episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
|
||||
|
||||
season_number = int_or_none(self._search_regex(
|
||||
r'(?s)<h4[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h4>\s*<h4>\s*Season (\d+)',
|
||||
webpage, 'season number', default=None))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': video_title,
|
||||
@ -446,9 +477,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
||||
'thumbnail': xpath_text(metadata, 'episode_image_url'),
|
||||
'uploader': video_uploader,
|
||||
'upload_date': video_upload_date,
|
||||
'series': xpath_text(metadata, 'series_title'),
|
||||
'episode': xpath_text(metadata, 'episode_title'),
|
||||
'episode_number': int_or_none(xpath_text(metadata, 'episode_number')),
|
||||
'series': series,
|
||||
'season_number': season_number,
|
||||
'episode': episode,
|
||||
'episode_number': episode_number,
|
||||
'subtitles': subtitles,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -12,6 +12,7 @@ from ..utils import (
|
||||
ExtractorError,
|
||||
)
|
||||
from .senateisvp import SenateISVPIE
|
||||
from .ustream import UstreamIE
|
||||
|
||||
|
||||
class CSpanIE(InfoExtractor):
|
||||
@ -22,14 +23,13 @@ class CSpanIE(InfoExtractor):
|
||||
'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
|
||||
'info_dict': {
|
||||
'id': '315139',
|
||||
'ext': 'mp4',
|
||||
'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
|
||||
'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
'skip': 'Regularly fails on travis, for unknown reasons',
|
||||
}, {
|
||||
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
|
||||
'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
|
||||
# md5 is unstable
|
||||
'info_dict': {
|
||||
'id': 'c4486943',
|
||||
'ext': 'mp4',
|
||||
@ -38,14 +38,11 @@ class CSpanIE(InfoExtractor):
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
|
||||
'md5': '2ae5051559169baadba13fc35345ae74',
|
||||
'info_dict': {
|
||||
'id': '342759',
|
||||
'ext': 'mp4',
|
||||
'title': 'General Motors Ignition Switch Recall',
|
||||
'duration': 14848,
|
||||
'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
|
||||
},
|
||||
'playlist_mincount': 6,
|
||||
}, {
|
||||
# Video from senate.gov
|
||||
'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
|
||||
@ -57,12 +54,30 @@ class CSpanIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True, # m3u8 downloads
|
||||
}
|
||||
}, {
|
||||
# Ustream embedded video
|
||||
'url': 'https://www.c-span.org/video/?114917-1/armed-services',
|
||||
'info_dict': {
|
||||
'id': '58428542',
|
||||
'ext': 'flv',
|
||||
'title': 'USHR07 Armed Services Committee',
|
||||
'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee',
|
||||
'timestamp': 1423060374,
|
||||
'upload_date': '20150204',
|
||||
'uploader': 'HouseCommittee',
|
||||
'uploader_id': '12987475',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_type = None
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
ustream_url = UstreamIE._extract_url(webpage)
|
||||
if ustream_url:
|
||||
return self.url_result(ustream_url, UstreamIE.ie_key())
|
||||
|
||||
# We first look for clipid, because clipprog always appears before
|
||||
patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
|
||||
results = list(filter(None, (re.search(p, webpage) for p in patterns)))
|
||||
|
||||
115
youtube_dl/extractor/disney.py
Normal file
115
youtube_dl/extractor/disney.py
Normal file
@ -0,0 +1,115 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
compat_str,
|
||||
determine_ext,
|
||||
)
|
||||
|
||||
|
||||
class DisneyIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})'''
|
||||
_TESTS = [{
|
||||
'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
|
||||
'info_dict': {
|
||||
'id': '545ed1857afee5a0ec239977',
|
||||
'ext': 'mp4',
|
||||
'title': 'Moana - Trailer',
|
||||
'description': 'A fun adventure for the entire Family! Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
|
||||
'upload_date': '20170112',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
domain, video_id = re.match(self._VALID_URL, url).groups()
|
||||
webpage = self._download_webpage(
|
||||
'http://%s/embed/%s' % (domain, video_id), video_id)
|
||||
video_data = self._parse_json(self._search_regex(
|
||||
r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video']
|
||||
|
||||
for external in video_data.get('externals', []):
|
||||
if external.get('source') == 'vevo':
|
||||
return self.url_result('vevo:' + external['data_id'], 'Vevo')
|
||||
|
||||
title = video_data['title']
|
||||
|
||||
formats = []
|
||||
for flavor in video_data.get('flavors', []):
|
||||
flavor_format = flavor.get('format')
|
||||
flavor_url = flavor.get('url')
|
||||
if not flavor_url or not re.match(r'https?://', flavor_url):
|
||||
continue
|
||||
tbr = int_or_none(flavor.get('bitrate'))
|
||||
if tbr == 99999:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False))
|
||||
continue
|
||||
format_id = []
|
||||
if flavor_format:
|
||||
format_id.append(flavor_format)
|
||||
if tbr:
|
||||
format_id.append(compat_str(tbr))
|
||||
ext = determine_ext(flavor_url)
|
||||
if flavor_format == 'applehttp' or ext == 'm3u8':
|
||||
ext = 'mp4'
|
||||
width = int_or_none(flavor.get('width'))
|
||||
height = int_or_none(flavor.get('height'))
|
||||
formats.append({
|
||||
'format_id': '-'.join(format_id),
|
||||
'url': flavor_url,
|
||||
'width': width,
|
||||
'height': height,
|
||||
'tbr': tbr,
|
||||
'ext': ext,
|
||||
'vcodec': 'none' if (width == 0 and height == 0) else None,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
for caption in video_data.get('captions', []):
|
||||
caption_url = caption.get('url')
|
||||
caption_format = caption.get('format')
|
||||
if not caption_url or caption_format.startswith('unknown'):
|
||||
continue
|
||||
subtitles.setdefault(caption.get('language', 'en'), []).append({
|
||||
'url': caption_url,
|
||||
'ext': {
|
||||
'webvtt': 'vtt',
|
||||
}.get(caption_format, caption_format),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': video_data.get('description') or video_data.get('short_desc'),
|
||||
'thumbnail': video_data.get('thumb') or video_data.get('thumb_secure'),
|
||||
'duration': int_or_none(video_data.get('duration_sec')),
|
||||
'upload_date': unified_strdate(video_data.get('publish_date')),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
@ -66,7 +66,7 @@ class DramaFeverBaseIE(AMPIE):
|
||||
|
||||
class DramaFeverIE(DramaFeverBaseIE):
|
||||
IE_NAME = 'dramafever'
|
||||
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
|
||||
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
|
||||
'info_dict': {
|
||||
@ -103,6 +103,9 @@ class DramaFeverIE(DramaFeverBaseIE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -148,7 +151,7 @@ class DramaFeverIE(DramaFeverBaseIE):
|
||||
|
||||
class DramaFeverSeriesIE(DramaFeverBaseIE):
|
||||
IE_NAME = 'dramafever:series'
|
||||
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
|
||||
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
|
||||
'info_dict': {
|
||||
|
||||
@ -30,7 +30,10 @@ from .aenetworks import (
|
||||
AENetworksIE,
|
||||
HistoryTopicIE,
|
||||
)
|
||||
from .afreecatv import AfreecaTVIE
|
||||
from .afreecatv import (
|
||||
AfreecaTVIE,
|
||||
AfreecaTVGlobalIE,
|
||||
)
|
||||
from .airmozilla import AirMozillaIE
|
||||
from .aljazeera import AlJazeeraIE
|
||||
from .alphaporno import AlphaPornoIE
|
||||
@ -77,6 +80,10 @@ from .awaan import (
|
||||
AWAANLiveIE,
|
||||
AWAANSeasonIE,
|
||||
)
|
||||
from .azmedien import (
|
||||
AZMedienIE,
|
||||
AZMedienShowIE,
|
||||
)
|
||||
from .azubu import AzubuIE, AzubuLiveIE
|
||||
from .baidu import BaiduVideoIE
|
||||
from .bambuser import BambuserIE, BambuserChannelIE
|
||||
@ -88,6 +95,7 @@ from .bbc import (
|
||||
BBCCoUkPlaylistIE,
|
||||
BBCIE,
|
||||
)
|
||||
from .beampro import BeamProLiveIE
|
||||
from .beeg import BeegIE
|
||||
from .behindkink import BehindKinkIE
|
||||
from .bellmedia import BellMediaIE
|
||||
@ -243,6 +251,7 @@ from .dumpert import DumpertIE
|
||||
from .defense import DefenseGouvFrIE
|
||||
from .discovery import DiscoveryIE
|
||||
from .discoverygo import DiscoveryGoIE
|
||||
from .disney import DisneyIE
|
||||
from .dispeak import DigitallySpeakingIE
|
||||
from .dropbox import DropboxIE
|
||||
from .dw import (
|
||||
@ -593,6 +602,7 @@ from .nextmedia import (
|
||||
NextMediaIE,
|
||||
NextMediaActionNewsIE,
|
||||
AppleDailyIE,
|
||||
NextTVIE,
|
||||
)
|
||||
from .nfb import NFBIE
|
||||
from .nfl import NFLIE
|
||||
@ -719,6 +729,7 @@ from .polskieradio import (
|
||||
)
|
||||
from .porn91 import Porn91IE
|
||||
from .porncom import PornComIE
|
||||
from .pornflip import PornFlipIE
|
||||
from .pornhd import PornHdIE
|
||||
from .pornhub import (
|
||||
PornHubIE,
|
||||
@ -975,6 +986,7 @@ from .tv2 import (
|
||||
)
|
||||
from .tv3 import TV3IE
|
||||
from .tv4 import TV4IE
|
||||
from .tva import TVAIE
|
||||
from .tvanouvelles import (
|
||||
TVANouvellesIE,
|
||||
TVANouvellesArticleIE,
|
||||
|
||||
@ -86,18 +86,43 @@ class FirstTVIE(InfoExtractor):
|
||||
title = item['title']
|
||||
quality = qualities(QUALITIES)
|
||||
formats = []
|
||||
path = None
|
||||
for f in item.get('mbr', []):
|
||||
src = f.get('src')
|
||||
if not src or not isinstance(src, compat_str):
|
||||
continue
|
||||
tbr = int_or_none(self._search_regex(
|
||||
r'_(\d{3,})\.mp4', src, 'tbr', default=None))
|
||||
if not path:
|
||||
path = self._search_regex(
|
||||
r'//[^/]+/(.+?)_\d+\.mp4', src,
|
||||
'm3u8 path', default=None)
|
||||
formats.append({
|
||||
'url': src,
|
||||
'format_id': f.get('name'),
|
||||
'tbr': tbr,
|
||||
'quality': quality(f.get('name')),
|
||||
'source_preference': quality(f.get('name')),
|
||||
})
|
||||
# m3u8 URL format is reverse engineered from [1] (search for
|
||||
# master.m3u8). dashEdges (that is currently balancer-vod.1tv.ru)
|
||||
# is taken from [2].
|
||||
# 1. http://static.1tv.ru/player/eump1tv-current/eump-1tv.all.min.js?rnd=9097422834:formatted
|
||||
# 2. http://static.1tv.ru/player/eump1tv-config/config-main.js?rnd=9097422834
|
||||
if not path and len(formats) == 1:
|
||||
path = self._search_regex(
|
||||
r'//[^/]+/(.+?$)', formats[0]['url'],
|
||||
'm3u8 path', default=None)
|
||||
if path:
|
||||
if len(formats) == 1:
|
||||
m3u8_path = ','
|
||||
else:
|
||||
tbrs = [compat_str(t) for t in sorted(f['tbr'] for f in formats)]
|
||||
m3u8_path = '_,%s,%s' % (','.join(tbrs), '.mp4')
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
'http://balancer-vod.1tv.ru/%s%s.urlset/master.m3u8'
|
||||
% (path, m3u8_path),
|
||||
display_id, 'mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)
|
||||
|
||||
@ -81,7 +81,7 @@ class FlipagramIE(InfoExtractor):
|
||||
'filesize': int_or_none(cover.get('size')),
|
||||
} for cover in flipagram.get('covers', []) if cover.get('url')]
|
||||
|
||||
# Note that this only retrieves comments that are initally loaded.
|
||||
# Note that this only retrieves comments that are initially loaded.
|
||||
# For videos with large amounts of comments, most won't be retrieved.
|
||||
comments = []
|
||||
for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []):
|
||||
|
||||
@ -78,6 +78,9 @@ from .vbox7 import Vbox7IE
|
||||
from .dbtv import DBTVIE
|
||||
from .piksel import PikselIE
|
||||
from .videa import VideaIE
|
||||
from .twentymin import TwentyMinutenIE
|
||||
from .ustream import UstreamIE
|
||||
from .openload import OpenloadIE
|
||||
|
||||
|
||||
class GenericIE(InfoExtractor):
|
||||
@ -422,6 +425,26 @@ class GenericIE(InfoExtractor):
|
||||
'skip_download': True, # m3u8 download
|
||||
},
|
||||
},
|
||||
{
|
||||
# Brightcove with alternative playerID key
|
||||
'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
|
||||
'info_dict': {
|
||||
'id': 'nmeth.2062_SV1',
|
||||
'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
|
||||
},
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'id': '2228375078001',
|
||||
'ext': 'mp4',
|
||||
'title': 'nmeth.2062-sv1',
|
||||
'description': 'nmeth.2062-sv1',
|
||||
'timestamp': 1363357591,
|
||||
'upload_date': '20130315',
|
||||
'uploader': 'Nature Publishing Group',
|
||||
'uploader_id': '1964492299001',
|
||||
},
|
||||
}],
|
||||
},
|
||||
# ooyala video
|
||||
{
|
||||
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
|
||||
@ -567,17 +590,6 @@ class GenericIE(InfoExtractor):
|
||||
'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
|
||||
}
|
||||
},
|
||||
# Embedded Ustream video
|
||||
{
|
||||
'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
|
||||
'md5': '27b99cdb639c9b12a79bca876a073417',
|
||||
'info_dict': {
|
||||
'id': '45734260',
|
||||
'ext': 'flv',
|
||||
'uploader': 'AU SPA: The NSA and Privacy',
|
||||
'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
|
||||
}
|
||||
},
|
||||
# nowvideo embed hidden behind percent encoding
|
||||
{
|
||||
'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
|
||||
@ -1448,6 +1460,20 @@ class GenericIE(InfoExtractor):
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
},
|
||||
{
|
||||
# 20 minuten embed
|
||||
'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
|
||||
'info_dict': {
|
||||
'id': '523629',
|
||||
'ext': 'mp4',
|
||||
'title': 'So kommen Sie bei Eis und Schnee sicher an',
|
||||
'description': 'md5:117c212f64b25e3d95747e5276863f7d',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': [TwentyMinutenIE.ie_key()],
|
||||
}
|
||||
# {
|
||||
# # TODO: find another test
|
||||
# # http://schema.org/VideoObject
|
||||
@ -1939,7 +1965,14 @@ class GenericIE(InfoExtractor):
|
||||
re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
|
||||
re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
|
||||
if mobj is not None:
|
||||
return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
|
||||
embed_token = self._search_regex(
|
||||
r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
|
||||
webpage, 'ooyala embed token', default=None)
|
||||
return OoyalaIE._build_url_result(smuggle_url(
|
||||
mobj.group('ec'), {
|
||||
'domain': url,
|
||||
'embed_token': embed_token,
|
||||
}))
|
||||
|
||||
# Look for multiple Ooyala embeds on SBN network websites
|
||||
mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
|
||||
@ -2070,10 +2103,9 @@ class GenericIE(InfoExtractor):
|
||||
return self.url_result(mobj.group('url'), 'TED')
|
||||
|
||||
# Look for embedded Ustream videos
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
|
||||
if mobj is not None:
|
||||
return self.url_result(mobj.group('url'), 'Ustream')
|
||||
ustream_url = UstreamIE._extract_url(webpage)
|
||||
if ustream_url:
|
||||
return self.url_result(ustream_url, UstreamIE.ie_key())
|
||||
|
||||
# Look for embedded arte.tv player
|
||||
mobj = re.search(
|
||||
@ -2394,6 +2426,18 @@ class GenericIE(InfoExtractor):
|
||||
if videa_urls:
|
||||
return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
|
||||
|
||||
# Look for 20 minuten embeds
|
||||
twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
|
||||
if twentymin_urls:
|
||||
return _playlist_from_matches(
|
||||
twentymin_urls, ie=TwentyMinutenIE.ie_key())
|
||||
|
||||
# Look for Openload embeds
|
||||
openload_urls = OpenloadIE._extract_urls(webpage)
|
||||
if openload_urls:
|
||||
return _playlist_from_matches(
|
||||
openload_urls, ie=OpenloadIE.ie_key())
|
||||
|
||||
# Looking for http://schema.org/VideoObject
|
||||
json_ld = self._search_json_ld(
|
||||
webpage, video_id, default={}, expected_type='VideoObject')
|
||||
|
||||
@ -13,7 +13,7 @@ from ..utils import (
|
||||
class ImdbIE(InfoExtractor):
|
||||
IE_NAME = 'imdb'
|
||||
IE_DESC = 'Internet Movie Database trailers'
|
||||
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-)vi(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-|videoplayer/)vi(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
|
||||
@ -32,6 +32,9 @@ class ImdbIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.imdb.com/videoplayer/vi1562949145',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -5,9 +5,27 @@ import re
|
||||
|
||||
from ..compat import compat_urlparse
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_duration
|
||||
|
||||
|
||||
class JamendoIE(InfoExtractor):
|
||||
class JamendoBaseIE(InfoExtractor):
|
||||
def _extract_meta(self, webpage, fatal=True):
|
||||
title = self._og_search_title(
|
||||
webpage, default=None) or self._search_regex(
|
||||
r'<title>([^<]+)', webpage,
|
||||
'title', default=None)
|
||||
if title:
|
||||
title = self._search_regex(
|
||||
r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
|
||||
if not title:
|
||||
title = self._html_search_meta(
|
||||
'name', webpage, 'title', fatal=fatal)
|
||||
mobj = re.search(r'(.+) - (.+)', title or '')
|
||||
artist, second = mobj.groups() if mobj else [None] * 2
|
||||
return title, artist, second
|
||||
|
||||
|
||||
class JamendoIE(JamendoBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
|
||||
@ -16,7 +34,10 @@ class JamendoIE(InfoExtractor):
|
||||
'id': '196219',
|
||||
'display_id': 'stories-from-emona-i',
|
||||
'ext': 'flac',
|
||||
'title': 'Stories from Emona I',
|
||||
'title': 'Maya Filipič - Stories from Emona I',
|
||||
'artist': 'Maya Filipič',
|
||||
'track': 'Stories from Emona I',
|
||||
'duration': 210,
|
||||
'thumbnail': r're:^https?://.*\.jpg'
|
||||
}
|
||||
}
|
||||
@ -28,7 +49,7 @@ class JamendoIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
title = self._html_search_meta('name', webpage, 'title')
|
||||
title, artist, track = self._extract_meta(webpage)
|
||||
|
||||
formats = [{
|
||||
'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
|
||||
@ -46,37 +67,47 @@ class JamendoIE(InfoExtractor):
|
||||
|
||||
thumbnail = self._html_search_meta(
|
||||
'image', webpage, 'thumbnail', fatal=False)
|
||||
duration = parse_duration(self._search_regex(
|
||||
r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
|
||||
webpage, 'duration', fatal=False))
|
||||
|
||||
return {
|
||||
'id': track_id,
|
||||
'display_id': display_id,
|
||||
'thumbnail': thumbnail,
|
||||
'title': title,
|
||||
'duration': duration,
|
||||
'artist': artist,
|
||||
'track': track,
|
||||
'formats': formats
|
||||
}
|
||||
|
||||
|
||||
class JamendoAlbumIE(InfoExtractor):
|
||||
class JamendoAlbumIE(JamendoBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
|
||||
'info_dict': {
|
||||
'id': '121486',
|
||||
'title': 'Duck On Cover'
|
||||
'title': 'Shearer - Duck On Cover'
|
||||
},
|
||||
'playlist': [{
|
||||
'md5': 'e1a2fcb42bda30dfac990212924149a8',
|
||||
'info_dict': {
|
||||
'id': '1032333',
|
||||
'ext': 'flac',
|
||||
'title': 'Warmachine'
|
||||
'title': 'Shearer - Warmachine',
|
||||
'artist': 'Shearer',
|
||||
'track': 'Warmachine',
|
||||
}
|
||||
}, {
|
||||
'md5': '1f358d7b2f98edfe90fd55dac0799d50',
|
||||
'info_dict': {
|
||||
'id': '1032330',
|
||||
'ext': 'flac',
|
||||
'title': 'Without Your Ghost'
|
||||
'title': 'Shearer - Without Your Ghost',
|
||||
'artist': 'Shearer',
|
||||
'track': 'Without Your Ghost',
|
||||
}
|
||||
}],
|
||||
'params': {
|
||||
@ -90,18 +121,18 @@ class JamendoAlbumIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, mobj.group('display_id'))
|
||||
|
||||
title = self._html_search_meta('name', webpage, 'title')
|
||||
title, artist, album = self._extract_meta(webpage, fatal=False)
|
||||
|
||||
entries = [
|
||||
self.url_result(
|
||||
compat_urlparse.urljoin(url, m.group('path')),
|
||||
ie=JamendoIE.ie_key(),
|
||||
video_id=self._search_regex(
|
||||
r'/track/(\d+)', m.group('path'),
|
||||
'track id', default=None))
|
||||
for m in re.finditer(
|
||||
r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
|
||||
webpage)
|
||||
]
|
||||
entries = [{
|
||||
'_type': 'url_transparent',
|
||||
'url': compat_urlparse.urljoin(url, m.group('path')),
|
||||
'ie_key': JamendoIE.ie_key(),
|
||||
'id': self._search_regex(
|
||||
r'/track/(\d+)', m.group('path'), 'track id', default=None),
|
||||
'artist': artist,
|
||||
'album': album,
|
||||
} for m in re.finditer(
|
||||
r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
|
||||
webpage)]
|
||||
|
||||
return self.playlist_result(entries, album_id, title)
|
||||
|
||||
@ -2,29 +2,31 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class KonserthusetPlayIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?konserthusetplay\.se/\?.*\bm=(?P<id>[^&]+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:konserthusetplay|rspoplay)\.se/\?.*\bm=(?P<id>[^&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.konserthusetplay.se/?m=CKDDnlCY-dhWAAqiMERd-A',
|
||||
'md5': 'e3fd47bf44e864bd23c08e487abe1967',
|
||||
'info_dict': {
|
||||
'id': 'CKDDnlCY-dhWAAqiMERd-A',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': 'Orkesterns instrument: Valthornen',
|
||||
'description': 'md5:f10e1f0030202020396a4d712d2fa827',
|
||||
'thumbnail': 're:^https?://.*$',
|
||||
'duration': 398.8,
|
||||
'duration': 398.76,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'http://rspoplay.se/?m=elWuEH34SMKvaO4wO_cHBw',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
@ -42,12 +44,18 @@ class KonserthusetPlayIE(InfoExtractor):
|
||||
player_config = media['playerconfig']
|
||||
playlist = player_config['playlist']
|
||||
|
||||
source = next(f for f in playlist if f.get('bitrates'))
|
||||
source = next(f for f in playlist if f.get('bitrates') or f.get('provider'))
|
||||
|
||||
FORMAT_ID_REGEX = r'_([^_]+)_h264m\.mp4'
|
||||
|
||||
formats = []
|
||||
|
||||
m3u8_url = source.get('url')
|
||||
if m3u8_url and determine_ext(m3u8_url) == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
|
||||
fallback_url = source.get('fallbackUrl')
|
||||
fallback_format_id = None
|
||||
if fallback_url:
|
||||
@ -97,6 +105,13 @@ class KonserthusetPlayIE(InfoExtractor):
|
||||
thumbnail = media.get('image')
|
||||
duration = float_or_none(media.get('duration'), 1000)
|
||||
|
||||
subtitles = {}
|
||||
captions = source.get('captionsAvailableLanguages')
|
||||
if isinstance(captions, dict):
|
||||
for lang, subtitle_url in captions.items():
|
||||
if lang != 'none' and isinstance(subtitle_url, compat_str):
|
||||
subtitles.setdefault(lang, []).append({'url': subtitle_url})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
@ -104,4 +119,5 @@ class KonserthusetPlayIE(InfoExtractor):
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
@ -59,14 +59,26 @@ class LimelightBaseIE(InfoExtractor):
|
||||
format_id = 'rtmp'
|
||||
if stream.get('videoBitRate'):
|
||||
format_id += '-%d' % int_or_none(stream['videoBitRate'])
|
||||
http_url = 'http://cpl.delvenetworks.com/' + rtmp.group('playpath')[4:]
|
||||
urls.append(http_url)
|
||||
http_fmt = fmt.copy()
|
||||
http_fmt.update({
|
||||
'url': http_url,
|
||||
'format_id': format_id.replace('rtmp', 'http'),
|
||||
})
|
||||
formats.append(http_fmt)
|
||||
http_format_id = format_id.replace('rtmp', 'http')
|
||||
|
||||
CDN_HOSTS = (
|
||||
('delvenetworks.com', 'cpl.delvenetworks.com'),
|
||||
('video.llnw.net', 's2.content.video.llnw.net'),
|
||||
)
|
||||
for cdn_host, http_host in CDN_HOSTS:
|
||||
if cdn_host not in rtmp.group('host').lower():
|
||||
continue
|
||||
http_url = 'http://%s/%s' % (http_host, rtmp.group('playpath')[4:])
|
||||
urls.append(http_url)
|
||||
if self._is_valid_url(http_url, video_id, http_format_id):
|
||||
http_fmt = fmt.copy()
|
||||
http_fmt.update({
|
||||
'url': http_url,
|
||||
'format_id': http_format_id,
|
||||
})
|
||||
formats.append(http_fmt)
|
||||
break
|
||||
|
||||
fmt.update({
|
||||
'url': rtmp.group('url'),
|
||||
'play_path': rtmp.group('playpath'),
|
||||
|
||||
@ -190,7 +190,7 @@ class MiTeleIE(InfoExtractor):
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
# for some reason only HLS is supported
|
||||
'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8'}),
|
||||
'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}),
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
|
||||
@ -16,7 +16,6 @@ from ..utils import (
|
||||
clean_html,
|
||||
ExtractorError,
|
||||
OnDemandPagedList,
|
||||
parse_count,
|
||||
str_to_int,
|
||||
)
|
||||
|
||||
@ -36,7 +35,6 @@ class MixcloudIE(InfoExtractor):
|
||||
'uploader_id': 'dholbach',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
|
||||
@ -49,7 +47,6 @@ class MixcloudIE(InfoExtractor):
|
||||
'uploader_id': 'gillespeterson',
|
||||
'thumbnail': 're:https?://.*',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
|
||||
@ -89,26 +86,18 @@ class MixcloudIE(InfoExtractor):
|
||||
|
||||
song_url = play_info['stream_url']
|
||||
|
||||
PREFIX = (
|
||||
r'm-play-on-spacebar[^>]+'
|
||||
r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
|
||||
title = self._html_search_regex(
|
||||
PREFIX + r'm-title="([^"]+)"', webpage, 'title')
|
||||
title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title')
|
||||
thumbnail = self._proto_relative_url(self._html_search_regex(
|
||||
PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
|
||||
fatal=False))
|
||||
r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False))
|
||||
uploader = self._html_search_regex(
|
||||
PREFIX + r'm-owner-name="([^"]+)"',
|
||||
webpage, 'uploader', fatal=False)
|
||||
r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False)
|
||||
uploader_id = self._search_regex(
|
||||
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
|
||||
description = self._og_search_description(webpage)
|
||||
like_count = parse_count(self._search_regex(
|
||||
r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
|
||||
webpage, 'like count', default=None))
|
||||
view_count = str_to_int(self._search_regex(
|
||||
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
|
||||
r'/listeners/?">([0-9,.]+)</a>'],
|
||||
r'/listeners/?">([0-9,.]+)</a>',
|
||||
r'm-tooltip=["\']([\d,.]+) plays'],
|
||||
webpage, 'play count', default=None))
|
||||
|
||||
return {
|
||||
@ -120,7 +109,6 @@ class MixcloudIE(InfoExtractor):
|
||||
'uploader': uploader,
|
||||
'uploader_id': uploader_id,
|
||||
'view_count': view_count,
|
||||
'like_count': like_count,
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -13,11 +13,11 @@ from ..utils import (
|
||||
fix_xml_ampersands,
|
||||
float_or_none,
|
||||
HEADRequest,
|
||||
NO_DEFAULT,
|
||||
RegexNotFoundError,
|
||||
sanitized_Request,
|
||||
strip_or_none,
|
||||
timeconvert,
|
||||
try_get,
|
||||
unescapeHTML,
|
||||
update_url_query,
|
||||
url_basename,
|
||||
@ -42,15 +42,6 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
# Remove the templates, like &device={device}
|
||||
return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
|
||||
|
||||
# This was originally implemented for ComedyCentral, but it also works here
|
||||
@classmethod
|
||||
def _transform_rtmp_url(cls, rtmp_video_url):
|
||||
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
|
||||
if not m:
|
||||
return {'rtmp': rtmp_video_url}
|
||||
base = 'http://viacommtvstrmfs.fplive.net/'
|
||||
return {'http': base + m.group('finalid')}
|
||||
|
||||
def _get_feed_url(self, uri):
|
||||
return self._FEED_URL
|
||||
|
||||
@ -91,22 +82,28 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
if rendition.get('method') == 'hls':
|
||||
hls_url = rendition.find('./src').text
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
hls_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
|
||||
hls_url, video_id, ext='mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls'))
|
||||
else:
|
||||
# fms
|
||||
try:
|
||||
_, _, ext = rendition.attrib['type'].partition('/')
|
||||
rtmp_video_url = rendition.find('./src').text
|
||||
if 'error_not_available.swf' in rtmp_video_url:
|
||||
raise ExtractorError(
|
||||
'%s said: video is not available' % self.IE_NAME,
|
||||
expected=True)
|
||||
if rtmp_video_url.endswith('siteunavail.png'):
|
||||
continue
|
||||
new_urls = self._transform_rtmp_url(rtmp_video_url)
|
||||
formats.extend([{
|
||||
'ext': 'flv' if new_url.startswith('rtmp') else ext,
|
||||
'url': new_url,
|
||||
'format_id': '-'.join(filter(None, [kind, rendition.get('bitrate')])),
|
||||
'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext,
|
||||
'url': rtmp_video_url,
|
||||
'format_id': '-'.join(filter(None, [
|
||||
'rtmp' if rtmp_video_url.startswith('rtmp') else None,
|
||||
rendition.get('bitrate')])),
|
||||
'width': int(rendition.get('width')),
|
||||
'height': int(rendition.get('height')),
|
||||
} for kind, new_url in new_urls.items()])
|
||||
}])
|
||||
except (KeyError, TypeError):
|
||||
raise ExtractorError('Invalid rendition field.')
|
||||
self._sort_formats(formats)
|
||||
@ -212,7 +209,28 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
[self._get_video_info(item, use_hls) for item in idoc.findall('.//item')],
|
||||
playlist_title=title, playlist_description=description)
|
||||
|
||||
def _extract_mgid(self, webpage, default=NO_DEFAULT):
|
||||
def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
|
||||
triforce_feed = self._parse_json(self._search_regex(
|
||||
r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage,
|
||||
'triforce feed', default='{}'), video_id, fatal=False)
|
||||
|
||||
data_zone = self._search_regex(
|
||||
r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage,
|
||||
'data zone', default=data_zone, group='zone')
|
||||
|
||||
feed_url = try_get(
|
||||
triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
|
||||
compat_str)
|
||||
if not feed_url:
|
||||
return
|
||||
|
||||
feed = self._download_json(feed_url, video_id, fatal=False)
|
||||
if not feed:
|
||||
return
|
||||
|
||||
return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
try:
|
||||
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
|
||||
# or http://media.mtvnservices.com/{mgid}
|
||||
@ -232,7 +250,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
sm4_embed = self._html_search_meta(
|
||||
'sm4:video:embed', webpage, 'sm4 embed', default='')
|
||||
mgid = self._search_regex(
|
||||
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=default)
|
||||
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
|
||||
|
||||
if not mgid:
|
||||
mgid = self._extract_triforce_mgid(webpage)
|
||||
|
||||
return mgid
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -282,7 +304,7 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
|
||||
|
||||
class MTVIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'mtv'
|
||||
_VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|full-episodes)/(?P<id>[^/?#.]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
|
||||
_FEED_URL = 'http://www.mtv.com/feeds/mrss/'
|
||||
|
||||
_TESTS = [{
|
||||
@ -299,6 +321,9 @@ class MTVIE(MTVServicesInfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
|
||||
@ -12,10 +12,10 @@ from ..utils import (
|
||||
|
||||
|
||||
class NaverIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/v/(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://tvcast.naver.com/v/81652',
|
||||
'url': 'http://tv.naver.com/v/81652',
|
||||
'info_dict': {
|
||||
'id': '81652',
|
||||
'ext': 'mp4',
|
||||
@ -24,7 +24,7 @@ class NaverIE(InfoExtractor):
|
||||
'upload_date': '20130903',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://tvcast.naver.com/v/395837',
|
||||
'url': 'http://tv.naver.com/v/395837',
|
||||
'md5': '638ed4c12012c458fefcddfd01f173cd',
|
||||
'info_dict': {
|
||||
'id': '395837',
|
||||
@ -34,6 +34,9 @@ class NaverIE(InfoExtractor):
|
||||
'upload_date': '20150519',
|
||||
},
|
||||
'skip': 'Georestricted',
|
||||
}, {
|
||||
'url': 'http://tvcast.naver.com/v/81652',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -2,7 +2,15 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_iso8601
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
get_element_by_class,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
remove_start,
|
||||
unified_timestamp,
|
||||
)
|
||||
|
||||
|
||||
class NextMediaIE(InfoExtractor):
|
||||
@ -30,6 +38,12 @@ class NextMediaIE(InfoExtractor):
|
||||
return self._extract_from_nextmedia_page(news_id, url, page)
|
||||
|
||||
def _extract_from_nextmedia_page(self, news_id, url, page):
|
||||
redirection_url = self._search_regex(
|
||||
r'window\.location\.href\s*=\s*([\'"])(?P<url>(?!\1).+)\1',
|
||||
page, 'redirection URL', default=None, group='url')
|
||||
if redirection_url:
|
||||
return self.url_result(compat_urlparse.urljoin(url, redirection_url))
|
||||
|
||||
title = self._fetch_title(page)
|
||||
video_url = self._search_regex(self._URL_PATTERN, page, 'video url')
|
||||
|
||||
@ -93,7 +107,7 @@ class NextMediaActionNewsIE(NextMediaIE):
|
||||
|
||||
class AppleDailyIE(NextMediaIE):
|
||||
IE_DESC = '臺灣蘋果日報'
|
||||
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews|actionnews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
|
||||
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/[^/]+/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
|
||||
_TESTS = [{
|
||||
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
|
||||
'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
|
||||
@ -157,6 +171,10 @@ class AppleDailyIE(NextMediaIE):
|
||||
}, {
|
||||
'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Redirected from http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694
|
||||
'url': 'http://ent.appledaily.com.tw/section/article/headline/20150128/36354694',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_URL_PATTERN = r'\{url: \'(.+)\'\}'
|
||||
@ -173,3 +191,48 @@ class AppleDailyIE(NextMediaIE):
|
||||
|
||||
def _fetch_description(self, page):
|
||||
return self._html_search_meta('description', page, 'news description')
|
||||
|
||||
|
||||
class NextTVIE(InfoExtractor):
|
||||
IE_DESC = '壹電視'
|
||||
_VALID_URL = r'https?://(?:www\.)?nexttv\.com\.tw/(?:[^/]+/)+(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.nexttv.com.tw/news/realtime/politics/11779671',
|
||||
'info_dict': {
|
||||
'id': '11779671',
|
||||
'ext': 'mp4',
|
||||
'title': '「超收稅」近4千億！ 藍議員籲發消費券',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'timestamp': 1484825400,
|
||||
'upload_date': '20170119',
|
||||
'view_count': int,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<h1[^>]*>([^<]+)</h1>', webpage, 'title')
|
||||
|
||||
data = self._hidden_inputs(webpage)
|
||||
|
||||
video_url = data['ntt-vod-src-detailview']
|
||||
|
||||
date_str = get_element_by_class('date', webpage)
|
||||
timestamp = unified_timestamp(date_str + '+0800') if date_str else None
|
||||
|
||||
view_count = int_or_none(remove_start(
|
||||
clean_html(get_element_by_class('click', webpage)), '點閱：'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'url': video_url,
|
||||
'thumbnail': data.get('ntt-vod-img-src'),
|
||||
'timestamp': timestamp,
|
||||
'view_count': view_count,
|
||||
}
|
||||
|
||||
@ -7,7 +7,6 @@ import datetime
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_urllib_parse_urlencode,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
@ -40,6 +39,7 @@ class NiconicoIE(InfoExtractor):
|
||||
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
|
||||
'duration': 33,
|
||||
},
|
||||
'skip': 'Requires an account',
|
||||
}, {
|
||||
# File downloaded with and without credentials are different, so omit
|
||||
# the md5 field
|
||||
@ -55,6 +55,7 @@ class NiconicoIE(InfoExtractor):
|
||||
'timestamp': 1304065916,
|
||||
'duration': 209,
|
||||
},
|
||||
'skip': 'Requires an account',
|
||||
}, {
|
||||
# 'video exists but is marked as "deleted"
|
||||
# md5 is unstable
|
||||
@ -65,9 +66,10 @@ class NiconicoIE(InfoExtractor):
|
||||
'description': 'deleted',
|
||||
'title': 'ドラえもんエターナル第3話「決戦第3新東京市」＜前編＞',
|
||||
'upload_date': '20071224',
|
||||
'timestamp': 1198527840, # timestamp field has different value if logged in
|
||||
'timestamp': int, # timestamp field has different value if logged in
|
||||
'duration': 304,
|
||||
},
|
||||
'skip': 'Requires an account',
|
||||
}, {
|
||||
'url': 'http://www.nicovideo.jp/watch/so22543406',
|
||||
'info_dict': {
|
||||
@ -79,13 +81,12 @@ class NiconicoIE(InfoExtractor):
|
||||
'upload_date': '20140104',
|
||||
'uploader': 'アニメロチャンネル',
|
||||
'uploader_id': '312',
|
||||
}
|
||||
},
|
||||
'skip': 'The viewing period of the video you were searching for has expired.',
|
||||
}]
|
||||
|
||||
_VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
|
||||
_NETRC_MACHINE = 'niconico'
|
||||
# Determine whether the downloader used authentication to download video
|
||||
_AUTHENTICATED = False
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
@ -109,8 +110,6 @@ class NiconicoIE(InfoExtractor):
|
||||
if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
|
||||
self._downloader.report_warning('unable to log in: bad username or password')
|
||||
return False
|
||||
# Successful login
|
||||
self._AUTHENTICATED = True
|
||||
return True
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -128,35 +127,19 @@ class NiconicoIE(InfoExtractor):
|
||||
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
|
||||
note='Downloading video info page')
|
||||
|
||||
if self._AUTHENTICATED:
|
||||
# Get flv info
|
||||
flv_info_webpage = self._download_webpage(
|
||||
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
|
||||
video_id, 'Downloading flv info')
|
||||
else:
|
||||
# Get external player info
|
||||
ext_player_info = self._download_webpage(
|
||||
'http://ext.nicovideo.jp/thumb_watch/' + video_id, video_id)
|
||||
thumb_play_key = self._search_regex(
|
||||
r'\'thumbPlayKey\'\s*:\s*\'(.*?)\'', ext_player_info, 'thumbPlayKey')
|
||||
|
||||
# Get flv info
|
||||
flv_info_data = compat_urllib_parse_urlencode({
|
||||
'k': thumb_play_key,
|
||||
'v': video_id
|
||||
})
|
||||
flv_info_request = sanitized_Request(
|
||||
'http://ext.nicovideo.jp/thumb_watch', flv_info_data,
|
||||
{'Content-Type': 'application/x-www-form-urlencoded'})
|
||||
flv_info_webpage = self._download_webpage(
|
||||
flv_info_request, video_id,
|
||||
note='Downloading flv info', errnote='Unable to download flv info')
|
||||
# Get flv info
|
||||
flv_info_webpage = self._download_webpage(
|
||||
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
|
||||
video_id, 'Downloading flv info')
|
||||
|
||||
flv_info = compat_urlparse.parse_qs(flv_info_webpage)
|
||||
if 'url' not in flv_info:
|
||||
if 'deleted' in flv_info:
|
||||
raise ExtractorError('The video has been deleted.',
|
||||
expected=True)
|
||||
elif 'closed' in flv_info:
|
||||
raise ExtractorError('Niconico videos now require logging in',
|
||||
expected=True)
|
||||
else:
|
||||
raise ExtractorError('Unable to find video URL')
|
||||
|
||||
|
||||
@ -18,7 +18,7 @@ class OoyalaBaseIE(InfoExtractor):
|
||||
_CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
|
||||
_AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?'
|
||||
|
||||
def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None):
|
||||
def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None, embed_token=None):
|
||||
content_tree = self._download_json(content_tree_url, video_id)['content_tree']
|
||||
metadata = content_tree[list(content_tree)[0]]
|
||||
embed_code = metadata['embed_code']
|
||||
@ -29,7 +29,8 @@ class OoyalaBaseIE(InfoExtractor):
|
||||
self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
|
||||
compat_urllib_parse_urlencode({
|
||||
'domain': domain,
|
||||
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds',
|
||||
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
|
||||
'embedToken': embed_token,
|
||||
}), video_id)
|
||||
|
||||
cur_auth_data = auth_data['authorization_data'][embed_code]
|
||||
@ -52,6 +53,12 @@ class OoyalaBaseIE(InfoExtractor):
|
||||
elif delivery_type == 'hds' or ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
s_url + '?hdcore=3.7.0', embed_code, f4m_id='hds', fatal=False))
|
||||
elif delivery_type == 'dash' or ext == 'mpd':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
s_url, embed_code, mpd_id='dash', fatal=False))
|
||||
elif delivery_type == 'smooth':
|
||||
self._extract_ism_formats(
|
||||
s_url, embed_code, ism_id='mss', fatal=False)
|
||||
elif ext == 'smil':
|
||||
formats.extend(self._extract_smil_formats(
|
||||
s_url, embed_code, fatal=False))
|
||||
@ -146,8 +153,9 @@ class OoyalaIE(OoyalaBaseIE):
|
||||
embed_code = self._match_id(url)
|
||||
domain = smuggled_data.get('domain')
|
||||
supportedformats = smuggled_data.get('supportedformats')
|
||||
embed_token = smuggled_data.get('embed_token')
|
||||
content_tree_url = self._CONTENT_TREE_BASE + 'embed_code/%s/%s' % (embed_code, embed_code)
|
||||
return self._extract(content_tree_url, embed_code, domain, supportedformats)
|
||||
return self._extract(content_tree_url, embed_code, domain, supportedformats, embed_token)
|
||||
|
||||
|
||||
class OoyalaExternalIE(OoyalaBaseIE):
|
||||
|
||||
@ -1,6 +1,8 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_chr
|
||||
from ..utils import (
|
||||
@ -56,6 +58,12 @@ class OpenloadIE(InfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
|
||||
webpage)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
|
||||
@ -64,16 +72,17 @@ class OpenloadIE(InfoExtractor):
|
||||
raise ExtractorError('File not found', expected=True)
|
||||
|
||||
ol_id = self._search_regex(
|
||||
'<span[^>]+id="[a-zA-Z0-9]+x"[^>]*>([0-9]+)</span>',
|
||||
'<span[^>]+id="[^"]+"[^>]*>([0-9]+)</span>',
|
||||
webpage, 'openload ID')
|
||||
|
||||
first_two_chars = int(float(ol_id[0:][:2]))
|
||||
first_three_chars = int(float(ol_id[0:][:3]))
|
||||
fifth_char = int(float(ol_id[3:5]))
|
||||
urlcode = ''
|
||||
num = 2
|
||||
num = 5
|
||||
|
||||
while num < len(ol_id):
|
||||
urlcode += compat_chr(int(float(ol_id[num:][:3])) -
|
||||
first_two_chars * int(float(ol_id[num + 3:][:2])))
|
||||
urlcode += compat_chr(int(float(ol_id[num:][:3])) +
|
||||
first_three_chars - fifth_char * int(float(ol_id[num + 3:][:2])))
|
||||
num += 5
|
||||
|
||||
video_url = 'https://openload.co/stream/' + urlcode
|
||||
@ -92,7 +101,7 @@ class OpenloadIE(InfoExtractor):
|
||||
'thumbnail': self._og_search_thumbnail(webpage, default=None),
|
||||
'url': video_url,
|
||||
# Seems all videos have extensions in their titles
|
||||
'ext': determine_ext(title),
|
||||
'ext': determine_ext(title, 'mp4'),
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
return info_dict
|
||||
|
||||
@ -157,13 +157,10 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
|
||||
display_id = '%s-%s' % (name, clip_id)
|
||||
|
||||
parsed_url = compat_urlparse.urlparse(url)
|
||||
|
||||
payload_url = compat_urlparse.urlunparse(parsed_url._replace(
|
||||
netloc='app.pluralsight.com', path='player/api/v1/payload'))
|
||||
|
||||
course = self._download_json(
|
||||
payload_url, display_id, headers={'Referer': url})['payload']['course']
|
||||
'https://app.pluralsight.com/player/user/api/v1/player/payload',
|
||||
display_id, data=urlencode_postdata({'courseId': course_name}),
|
||||
headers={'Referer': url})
|
||||
|
||||
collection = course['modules']
|
||||
|
||||
|
||||
92
youtube_dl/extractor/pornflip.py
Normal file
92
youtube_dl/extractor/pornflip.py
Normal file
@ -0,0 +1,92 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
)
|
||||
|
||||
|
||||
class PornFlipIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:v|embed)/(?P<id>[0-9A-Za-z]{11})'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
|
||||
'md5': '98c46639849145ae1fd77af532a9278c',
|
||||
'info_dict': {
|
||||
'id': 'wz7DfNhMmep',
|
||||
'ext': 'mp4',
|
||||
'title': '2 Amateurs swallow make his dream cumshots true',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 112,
|
||||
'timestamp': 1481655502,
|
||||
'upload_date': '20161213',
|
||||
'uploader_id': '106786',
|
||||
'uploader': 'figifoto',
|
||||
'view_count': int,
|
||||
'age_limit': 18,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.pornflip.com/embed/wz7DfNhMmep',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'https://www.pornflip.com/v/%s' % video_id, video_id)
|
||||
|
||||
flashvars = compat_parse_qs(self._search_regex(
|
||||
r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
|
||||
webpage, 'flashvars', group='flashvars'))
|
||||
|
||||
title = flashvars['video_vars[title]'][0]
|
||||
|
||||
def flashvar(kind):
|
||||
return try_get(
|
||||
flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
|
||||
|
||||
formats = []
|
||||
for key, value in flashvars.items():
|
||||
if not (value and isinstance(value, list)):
|
||||
continue
|
||||
format_url = value[0]
|
||||
if key == 'video_vars[hds_manifest]':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
format_url, video_id, mpd_id='dash', fatal=False))
|
||||
continue
|
||||
height = self._search_regex(
|
||||
r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
|
||||
if not height:
|
||||
continue
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': 'http-%s' % height,
|
||||
'height': int_or_none(height),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
(r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
|
||||
r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
|
||||
webpage, 'uploader', fatal=False, group='uploader')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'thumbnail': flashvar('big_thumb'),
|
||||
'duration': int_or_none(flashvar('duration')),
|
||||
'timestamp': unified_timestamp(self._html_search_meta(
|
||||
'uploadDate', webpage, 'timestamp')),
|
||||
'uploader_id': flashvar('author_id'),
|
||||
'uploader': uploader,
|
||||
'view_count': int_or_none(flashvar('views')),
|
||||
'age_limit': 18,
|
||||
}
|
||||
@ -173,46 +173,54 @@ class SoundcloudIE(InfoExtractor):
|
||||
})
|
||||
|
||||
# We have to retrieve the url
|
||||
streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?'
|
||||
'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
|
||||
format_dict = self._download_json(
|
||||
streams_url,
|
||||
track_id, 'Downloading track url')
|
||||
'http://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
|
||||
track_id, 'Downloading track url', query={
|
||||
'client_id': self._CLIENT_ID,
|
||||
'secret_token': secret_token,
|
||||
})
|
||||
|
||||
for key, stream_url in format_dict.items():
|
||||
abr = int_or_none(self._search_regex(
|
||||
r'_(\d+)_url', key, 'audio bitrate', default=None))
|
||||
if key.startswith('http'):
|
||||
formats.append({
|
||||
stream_formats = [{
|
||||
'format_id': key,
|
||||
'ext': ext,
|
||||
'url': stream_url,
|
||||
'vcodec': 'none',
|
||||
})
|
||||
}]
|
||||
elif key.startswith('rtmp'):
|
||||
# The url doesn't have an rtmp app, we have to extract the playpath
|
||||
url, path = stream_url.split('mp3:', 1)
|
||||
formats.append({
|
||||
stream_formats = [{
|
||||
'format_id': key,
|
||||
'url': url,
|
||||
'play_path': 'mp3:' + path,
|
||||
'ext': 'flv',
|
||||
'vcodec': 'none',
|
||||
})
|
||||
}]
|
||||
elif key.startswith('hls'):
|
||||
stream_formats = self._extract_m3u8_formats(
|
||||
stream_url, track_id, 'mp3', entry_protocol='m3u8_native',
|
||||
m3u8_id=key, fatal=False)
|
||||
else:
|
||||
continue
|
||||
|
||||
if not formats:
|
||||
# We fallback to the stream_url in the original info, this
|
||||
# cannot be always used, sometimes it can give an HTTP 404 error
|
||||
formats.append({
|
||||
'format_id': 'fallback',
|
||||
'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
|
||||
'ext': ext,
|
||||
'vcodec': 'none',
|
||||
})
|
||||
for f in stream_formats:
|
||||
f['abr'] = abr
|
||||
|
||||
for f in formats:
|
||||
if f['format_id'].startswith('http'):
|
||||
f['protocol'] = 'http'
|
||||
if f['format_id'].startswith('rtmp'):
|
||||
f['protocol'] = 'rtmp'
|
||||
formats.extend(stream_formats)
|
||||
|
||||
if not formats:
|
||||
# We fallback to the stream_url in the original info, this
|
||||
# cannot be always used, sometimes it can give an HTTP 404 error
|
||||
formats.append({
|
||||
'format_id': 'fallback',
|
||||
'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
|
||||
'ext': ext,
|
||||
})
|
||||
|
||||
for f in formats:
|
||||
f['vcodec'] = 'none'
|
||||
|
||||
self._check_formats(formats, track_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
@ -6,7 +6,7 @@ from .mtv import MTVServicesInfoExtractor
|
||||
|
||||
class SouthParkIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'southpark.cc.com'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))'
|
||||
|
||||
_FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
|
||||
|
||||
@ -75,7 +75,7 @@ class SouthParkDeIE(SouthParkIE):
|
||||
|
||||
class SouthParkNlIE(SouthParkIE):
|
||||
IE_NAME = 'southpark.nl'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))'
|
||||
_FEED_URL = 'http://www.southpark.nl/feeds/video-player/mrss/'
|
||||
|
||||
_TESTS = [{
|
||||
|
||||
@ -46,7 +46,7 @@ class SpikeIE(MTVServicesInfoExtractor):
|
||||
_CUSTOM_URL_REGEX = re.compile(r'spikenetworkapp://([^/]+/[-a-fA-F0-9]+)')
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
mgid = super(SpikeIE, self)._extract_mgid(webpage, default=None)
|
||||
mgid = super(SpikeIE, self)._extract_mgid(webpage)
|
||||
if mgid is None:
|
||||
url_parts = self._search_regex(self._CUSTOM_URL_REGEX, webpage, 'episode_id')
|
||||
video_type, episode_id = url_parts.split('/', 1)
|
||||
|
||||
@ -48,9 +48,6 @@ class SRGSSRIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
|
||||
|
||||
if bu == 'rts':
|
||||
return self.url_result('rts:%s' % media_id, 'RTS')
|
||||
|
||||
media_data = self.get_media_data(bu, media_type, media_id)
|
||||
|
||||
metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
|
||||
|
||||
54
youtube_dl/extractor/tva.py
Normal file
54
youtube_dl/extractor/tva.py
Normal file
@ -0,0 +1,54 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
smuggle_url,
|
||||
)
|
||||
|
||||
|
||||
class TVAIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://videos\.tva\.ca/episode/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://videos.tva.ca/episode/85538',
|
||||
'info_dict': {
|
||||
'id': '85538',
|
||||
'ext': 'mp4',
|
||||
'title': 'Épisode du 25 janvier 2017',
|
||||
'description': 'md5:e9e7fb5532ab37984d2dc87229cadf98',
|
||||
'upload_date': '20170126',
|
||||
'timestamp': 1485442329,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_data = self._download_json(
|
||||
"https://d18jmrhziuoi7p.cloudfront.net/isl/api/v1/dataservice/Items('%s')" % video_id,
|
||||
video_id, query={
|
||||
'$expand': 'Metadata,CustomId',
|
||||
'$select': 'Metadata,Id,Title,ShortDescription,LongDescription,CreatedDate,CustomId,AverageUserRating,Categories,ShowName',
|
||||
'$format': 'json',
|
||||
})
|
||||
metadata = video_data.get('Metadata', {})
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'title': video_data['Title'],
|
||||
'url': smuggle_url('ooyala:' + video_data['CustomId'], {'supportedformats': 'm3u8,hds'}),
|
||||
'description': video_data.get('LongDescription') or video_data.get('ShortDescription'),
|
||||
'series': video_data.get('ShowName'),
|
||||
'episode': metadata.get('EpisodeTitle'),
|
||||
'episode_number': int_or_none(metadata.get('EpisodeNumber')),
|
||||
'categories': video_data.get('Categories'),
|
||||
'average_rating': video_data.get('AverageUserRating'),
|
||||
'timestamp': parse_iso8601(video_data.get('CreatedDate')),
|
||||
'ie_key': 'Ooyala',
|
||||
}
|
||||
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
class TwentyFourVideoIE(InfoExtractor):
|
||||
IE_NAME = '24video'
|
||||
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.24video.net/video/view/1044982',
|
||||
@ -43,7 +43,7 @@ class TwentyFourVideoIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'http://www.24video.net/video/view/%s' % video_id, video_id)
|
||||
'http://www.24video.sex/video/view/%s' % video_id, video_id)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._html_search_regex(
|
||||
@ -69,11 +69,11 @@ class TwentyFourVideoIE(InfoExtractor):
|
||||
|
||||
# Sets some cookies
|
||||
self._download_xml(
|
||||
r'http://www.24video.net/video/xml/%s?mode=init' % video_id,
|
||||
r'http://www.24video.sex/video/xml/%s?mode=init' % video_id,
|
||||
video_id, 'Downloading init XML')
|
||||
|
||||
video_xml = self._download_xml(
|
||||
'http://www.24video.net/video/xml/%s?mode=play' % video_id,
|
||||
'http://www.24video.sex/video/xml/%s?mode=play' % video_id,
|
||||
video_id, 'Downloading video XML')
|
||||
|
||||
video = xpath_element(video_xml, './/video', 'video', fatal=True)
|
||||
|
||||
@ -4,91 +4,88 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import remove_end
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class TwentyMinutenIE(InfoExtractor):
|
||||
IE_NAME = '20min'
|
||||
_VALID_URL = r'https?://(?:www\.)?20min\.ch/(?:videotv/*\?.*\bvid=(?P<id>\d+)|(?:[^/]+/)*(?P<display_id>[^/#?]+))'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:www\.)?20min\.ch/
|
||||
(?:
|
||||
videotv/*\?.*?\bvid=|
|
||||
videoplayer/videoplayer\.html\?.*?\bvideoId@
|
||||
)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
# regular video
|
||||
'url': 'http://www.20min.ch/videotv/?vid=469148&cid=2',
|
||||
'md5': 'b52d6bc6ea6398e6a38f12cfd418149c',
|
||||
'md5': 'e7264320db31eed8c38364150c12496e',
|
||||
'info_dict': {
|
||||
'id': '469148',
|
||||
'ext': 'flv',
|
||||
'title': '85 000 Franken für 15 perfekte Minuten',
|
||||
'description': 'Was die Besucher vom Silvesterzauber erwarten können. (Video: Alice Grosjean/Murat Temel)',
|
||||
'thumbnail': 'http://thumbnails.20min-tv.ch/server063/469148/frame-72-469148.jpg'
|
||||
}
|
||||
}, {
|
||||
# news article with video
|
||||
'url': 'http://www.20min.ch/schweiz/news/story/-Wir-muessen-mutig-nach-vorne-schauen--22050469',
|
||||
'md5': 'cd4cbb99b94130cff423e967cd275e5e',
|
||||
'info_dict': {
|
||||
'id': '469408',
|
||||
'display_id': '-Wir-muessen-mutig-nach-vorne-schauen--22050469',
|
||||
'ext': 'flv',
|
||||
'title': '«Wir müssen mutig nach vorne schauen»',
|
||||
'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.',
|
||||
'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg'
|
||||
},
|
||||
'skip': '"This video is no longer available" is shown both on the web page and in the downloaded file.',
|
||||
}, {
|
||||
# YouTube embed
|
||||
'url': 'http://www.20min.ch/ro/sports/football/story/Il-marque-une-bicyclette-de-plus-de-30-metres--21115184',
|
||||
'md5': 'cec64d59aa01c0ed9dbba9cf639dd82f',
|
||||
'info_dict': {
|
||||
'id': 'ivM7A7SpDOs',
|
||||
'ext': 'mp4',
|
||||
'title': 'GOLAZO DE CHILENA DE JAVI GÓMEZ, FINALISTA AL BALÓN DE CLM 2016',
|
||||
'description': 'md5:903c92fbf2b2f66c09de514bc25e9f5a',
|
||||
'upload_date': '20160424',
|
||||
'uploader': 'RTVCM Castilla-La Mancha',
|
||||
'uploader_id': 'RTVCM',
|
||||
'title': '85 000 Franken für 15 perfekte Minuten',
|
||||
'thumbnail': r're:https?://.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.20min.ch/videoplayer/videoplayer.html?params=client@twentyDE|videoId@523629',
|
||||
'info_dict': {
|
||||
'id': '523629',
|
||||
'ext': 'mp4',
|
||||
'title': 'So kommen Sie bei Eis und Schnee sicher an',
|
||||
'description': 'md5:117c212f64b25e3d95747e5276863f7d',
|
||||
'thumbnail': r're:https?://.*\.jpg$',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
}, {
|
||||
'url': 'http://www.20min.ch/videotv/?cid=44&vid=468738',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.20min.ch/ro/sortir/cinema/story/Grandir-au-bahut--c-est-dur-18927411',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return [m.group('url') for m in re.finditer(
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:www\.)?20min\.ch/videoplayer/videoplayer.html\?.*?\bvideoId@\d+.*?)\1',
|
||||
webpage)]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video = self._download_json(
|
||||
'http://api.20min.ch/video/%s/show' % video_id,
|
||||
video_id)['content']
|
||||
|
||||
youtube_url = self._html_search_regex(
|
||||
r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
|
||||
webpage, 'YouTube embed URL', default=None)
|
||||
if youtube_url is not None:
|
||||
return self.url_result(youtube_url, 'Youtube')
|
||||
title = video['title']
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<h1>.*?<span>(.+?)</span></h1>',
|
||||
webpage, 'title', default=None)
|
||||
if not title:
|
||||
title = remove_end(re.sub(
|
||||
r'^20 [Mm]inuten.*? -', '', self._og_search_title(webpage)), ' - News')
|
||||
formats = [{
|
||||
'format_id': format_id,
|
||||
'url': 'http://podcast.20min-tv.ch/podcast/20min/%s%s.mp4' % (video_id, p),
|
||||
'quality': quality,
|
||||
} for quality, (format_id, p) in enumerate([('sd', ''), ('hd', 'h')])]
|
||||
self._sort_formats(formats)
|
||||
|
||||
if not video_id:
|
||||
video_id = self._search_regex(
|
||||
r'"file\d?"\s*,\s*\"(\d+)', webpage, 'video id')
|
||||
description = video.get('lead')
|
||||
thumbnail = video.get('thumbnail')
|
||||
|
||||
description = self._html_search_meta(
|
||||
'description', webpage, 'description')
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
def extract_count(kind):
|
||||
return try_get(
|
||||
video,
|
||||
lambda x: int_or_none(x['communityobject']['thumbs_%s' % kind]))
|
||||
|
||||
like_count = extract_count('up')
|
||||
dislike_count = extract_count('down')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': 'http://speed.20min-tv.ch/%sm.flv' % video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'like_count': like_count,
|
||||
'dislike_count': dislike_count,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -209,7 +209,7 @@ class TwitchVodIE(TwitchItemBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
(?:www\.)?twitch\.tv/[^/]+/v/|
|
||||
(?:www\.)?twitch\.tv/(?:[^/]+/v|videos)/|
|
||||
player\.twitch\.tv/\?.*?\bvideo=v
|
||||
)
|
||||
(?P<id>\d+)
|
||||
@ -259,6 +259,9 @@ class TwitchVodIE(TwitchItemBaseIE):
|
||||
}, {
|
||||
'url': 'http://player.twitch.tv/?t=5m10s&video=v6528877',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.twitch.tv/videos/6528877',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -84,12 +84,27 @@ class UOLIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
if not video_id.isdigit():
|
||||
embed_page = self._download_webpage('https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id, video_id)
|
||||
video_id = self._search_regex(r'mediaId=(\d+)', embed_page, 'media id')
|
||||
media_id = None
|
||||
|
||||
if video_id.isdigit():
|
||||
media_id = video_id
|
||||
|
||||
if not media_id:
|
||||
embed_page = self._download_webpage(
|
||||
'https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id,
|
||||
video_id, 'Downloading embed page', fatal=False)
|
||||
if embed_page:
|
||||
media_id = self._search_regex(
|
||||
(r'uol\.com\.br/(\d+)', r'mediaId=(\d+)'),
|
||||
embed_page, 'media id', default=None)
|
||||
|
||||
if not media_id:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
media_id = self._search_regex(r'mediaId=(\d+)', webpage, 'media id')
|
||||
|
||||
video_data = self._download_json(
|
||||
'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % video_id,
|
||||
video_id)['item']
|
||||
'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % media_id,
|
||||
media_id)['item']
|
||||
title = video_data['title']
|
||||
|
||||
query = {
|
||||
@ -118,7 +133,7 @@ class UOLIE(InfoExtractor):
|
||||
tags.append(tag_description)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'id': media_id,
|
||||
'title': title,
|
||||
'description': clean_html(video_data.get('desMedia')),
|
||||
'thumbnail': video_data.get('thumbnail'),
|
||||
|
||||
@ -69,6 +69,13 @@ class UstreamIE(InfoExtractor):
|
||||
},
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_url(webpage):
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
|
||||
if mobj is not None:
|
||||
return mobj.group('url')
|
||||
|
||||
def _get_stream_info(self, url, video_id, app_id_ver, extra_note=None):
|
||||
def num_to_hex(n):
|
||||
return hex(n)[2:]
|
||||
|
||||
@ -4,9 +4,9 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_etree_fromstring,
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
compat_HTTPError,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
@ -140,21 +140,6 @@ class VevoIE(VevoBaseIE):
|
||||
'url': 'http://www.vevo.com/watch/INS171400764',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_SMIL_BASE_URL = 'http://smil.lvl3.vevo.com'
|
||||
_SOURCE_TYPES = {
|
||||
0: 'youtube',
|
||||
1: 'brightcove',
|
||||
2: 'http',
|
||||
3: 'hls_ios',
|
||||
4: 'hls',
|
||||
5: 'smil', # http
|
||||
7: 'f4m_cc',
|
||||
8: 'f4m_ak',
|
||||
9: 'f4m_l3',
|
||||
10: 'ism',
|
||||
13: 'smil', # rtmp
|
||||
18: 'dash',
|
||||
}
|
||||
_VERSIONS = {
|
||||
0: 'youtube', # only in AuthenticateVideo videoVersions
|
||||
1: 'level3',
|
||||
@ -163,41 +148,6 @@ class VevoIE(VevoBaseIE):
|
||||
4: 'amazon',
|
||||
}
|
||||
|
||||
def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
|
||||
formats = []
|
||||
els = smil.findall('.//{http://www.w3.org/2001/SMIL20/Language}video')
|
||||
for el in els:
|
||||
src = el.attrib['src']
|
||||
m = re.match(r'''(?xi)
|
||||
(?P<ext>[a-z0-9]+):
|
||||
(?P<path>
|
||||
[/a-z0-9]+ # The directory and main part of the URL
|
||||
_(?P<tbr>[0-9]+)k
|
||||
_(?P<width>[0-9]+)x(?P<height>[0-9]+)
|
||||
_(?P<vcodec>[a-z0-9]+)
|
||||
_(?P<vbr>[0-9]+)
|
||||
_(?P<acodec>[a-z0-9]+)
|
||||
_(?P<abr>[0-9]+)
|
||||
\.[a-z0-9]+ # File extension
|
||||
)''', src)
|
||||
if not m:
|
||||
continue
|
||||
|
||||
format_url = self._SMIL_BASE_URL + m.group('path')
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': 'smil_' + m.group('tbr'),
|
||||
'vcodec': m.group('vcodec'),
|
||||
'acodec': m.group('acodec'),
|
||||
'tbr': int(m.group('tbr')),
|
||||
'vbr': int(m.group('vbr')),
|
||||
'abr': int(m.group('abr')),
|
||||
'ext': m.group('ext'),
|
||||
'width': int(m.group('width')),
|
||||
'height': int(m.group('height')),
|
||||
})
|
||||
return formats
|
||||
|
||||
def _initialize_api(self, video_id):
|
||||
req = sanitized_Request(
|
||||
'http://www.vevo.com/auth', data=b'')
|
||||
@ -206,7 +156,7 @@ class VevoIE(VevoBaseIE):
|
||||
note='Retrieving oauth token',
|
||||
errnote='Unable to retrieve oauth token')
|
||||
|
||||
if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage:
|
||||
if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage):
|
||||
self.raise_geo_restricted(
|
||||
'%s said: This page is currently unavailable in your region' % self.IE_NAME)
|
||||
|
||||
@ -214,148 +164,91 @@ class VevoIE(VevoBaseIE):
|
||||
self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['access_token']
|
||||
|
||||
def _call_api(self, path, *args, **kwargs):
|
||||
return self._download_json(self._api_url_template % path, *args, **kwargs)
|
||||
try:
|
||||
data = self._download_json(self._api_url_template % path, *args, **kwargs)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError):
|
||||
errors = self._parse_json(e.cause.read().decode(), None)['errors']
|
||||
error_message = ', '.join([error['message'] for error in errors])
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
raise
|
||||
return data
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
json_url = 'http://api.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
|
||||
response = self._download_json(
|
||||
json_url, video_id, 'Downloading video info',
|
||||
'Unable to download info', fatal=False) or {}
|
||||
video_info = response.get('video') or {}
|
||||
self._initialize_api(video_id)
|
||||
|
||||
video_info = self._call_api(
|
||||
'video/%s' % video_id, video_id, 'Downloading api video info',
|
||||
'Failed to download video info')
|
||||
|
||||
video_versions = self._call_api(
|
||||
'video/%s/streams' % video_id, video_id,
|
||||
'Downloading video versions info',
|
||||
'Failed to download video versions info',
|
||||
fatal=False)
|
||||
|
||||
# Some videos are only available via webpage (e.g.
|
||||
# https://github.com/rg3/youtube-dl/issues/9366)
|
||||
if not video_versions:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
|
||||
|
||||
uploader = None
|
||||
artist = None
|
||||
featured_artist = None
|
||||
uploader = None
|
||||
view_count = None
|
||||
artists = video_info.get('artists')
|
||||
for curr_artist in artists:
|
||||
if curr_artist.get('role') == 'Featured':
|
||||
featured_artist = curr_artist['name']
|
||||
else:
|
||||
artist = uploader = curr_artist['name']
|
||||
|
||||
formats = []
|
||||
for video_version in video_versions:
|
||||
version = self._VERSIONS.get(video_version['version'])
|
||||
version_url = video_version.get('url')
|
||||
if not version_url:
|
||||
continue
|
||||
|
||||
if not video_info:
|
||||
try:
|
||||
self._initialize_api(video_id)
|
||||
except ExtractorError:
|
||||
ytid = response.get('errorInfo', {}).get('ytid')
|
||||
if ytid:
|
||||
self.report_warning(
|
||||
'Video is geoblocked, trying with the YouTube video %s' % ytid)
|
||||
return self.url_result(ytid, 'Youtube', ytid)
|
||||
|
||||
raise
|
||||
|
||||
video_info = self._call_api(
|
||||
'video/%s' % video_id, video_id, 'Downloading api video info',
|
||||
'Failed to download video info')
|
||||
|
||||
video_versions = self._call_api(
|
||||
'video/%s/streams' % video_id, video_id,
|
||||
'Downloading video versions info',
|
||||
'Failed to download video versions info',
|
||||
fatal=False)
|
||||
|
||||
# Some videos are only available via webpage (e.g.
|
||||
# https://github.com/rg3/youtube-dl/issues/9366)
|
||||
if not video_versions:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
|
||||
|
||||
timestamp = parse_iso8601(video_info.get('releaseDate'))
|
||||
artists = video_info.get('artists')
|
||||
for curr_artist in artists:
|
||||
if curr_artist.get('role') == 'Featured':
|
||||
featured_artist = curr_artist['name']
|
||||
else:
|
||||
artist = uploader = curr_artist['name']
|
||||
view_count = int_or_none(video_info.get('views', {}).get('total'))
|
||||
|
||||
for video_version in video_versions:
|
||||
version = self._VERSIONS.get(video_version['version'])
|
||||
version_url = video_version.get('url')
|
||||
if not version_url:
|
||||
if '.ism' in version_url:
|
||||
continue
|
||||
elif '.mpd' in version_url:
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
version_url, video_id, mpd_id='dash-%s' % version,
|
||||
note='Downloading %s MPD information' % version,
|
||||
errnote='Failed to download %s MPD information' % version,
|
||||
fatal=False))
|
||||
elif '.m3u8' in version_url:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
version_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls-%s' % version,
|
||||
note='Downloading %s m3u8 information' % version,
|
||||
errnote='Failed to download %s m3u8 information' % version,
|
||||
fatal=False))
|
||||
else:
|
||||
m = re.search(r'''(?xi)
|
||||
_(?P<width>[0-9]+)x(?P<height>[0-9]+)
|
||||
_(?P<vcodec>[a-z0-9]+)
|
||||
_(?P<vbr>[0-9]+)
|
||||
_(?P<acodec>[a-z0-9]+)
|
||||
_(?P<abr>[0-9]+)
|
||||
\.(?P<ext>[a-z0-9]+)''', version_url)
|
||||
if not m:
|
||||
continue
|
||||
|
||||
if '.ism' in version_url:
|
||||
continue
|
||||
elif '.mpd' in version_url:
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
version_url, video_id, mpd_id='dash-%s' % version,
|
||||
note='Downloading %s MPD information' % version,
|
||||
errnote='Failed to download %s MPD information' % version,
|
||||
fatal=False))
|
||||
elif '.m3u8' in version_url:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
version_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls-%s' % version,
|
||||
note='Downloading %s m3u8 information' % version,
|
||||
errnote='Failed to download %s m3u8 information' % version,
|
||||
fatal=False))
|
||||
else:
|
||||
m = re.search(r'''(?xi)
|
||||
_(?P<width>[0-9]+)x(?P<height>[0-9]+)
|
||||
_(?P<vcodec>[a-z0-9]+)
|
||||
_(?P<vbr>[0-9]+)
|
||||
_(?P<acodec>[a-z0-9]+)
|
||||
_(?P<abr>[0-9]+)
|
||||
\.(?P<ext>[a-z0-9]+)''', version_url)
|
||||
if not m:
|
||||
continue
|
||||
|
||||
formats.append({
|
||||
'url': version_url,
|
||||
'format_id': 'http-%s-%s' % (version, video_version['quality']),
|
||||
'vcodec': m.group('vcodec'),
|
||||
'acodec': m.group('acodec'),
|
||||
'vbr': int(m.group('vbr')),
|
||||
'abr': int(m.group('abr')),
|
||||
'ext': m.group('ext'),
|
||||
'width': int(m.group('width')),
|
||||
'height': int(m.group('height')),
|
||||
})
|
||||
else:
|
||||
timestamp = int_or_none(self._search_regex(
|
||||
r'/Date\((\d+)\)/',
|
||||
video_info['releaseDate'], 'release date', fatal=False),
|
||||
scale=1000)
|
||||
artists = video_info.get('mainArtists')
|
||||
if artists:
|
||||
artist = uploader = artists[0]['artistName']
|
||||
|
||||
featured_artists = video_info.get('featuredArtists')
|
||||
if featured_artists:
|
||||
featured_artist = featured_artists[0]['artistName']
|
||||
|
||||
smil_parsed = False
|
||||
for video_version in video_info['videoVersions']:
|
||||
version = self._VERSIONS.get(video_version['version'])
|
||||
if version == 'youtube':
|
||||
continue
|
||||
else:
|
||||
source_type = self._SOURCE_TYPES.get(video_version['sourceType'])
|
||||
renditions = compat_etree_fromstring(video_version['data'])
|
||||
if source_type == 'http':
|
||||
for rend in renditions.findall('rendition'):
|
||||
attr = rend.attrib
|
||||
formats.append({
|
||||
'url': attr['url'],
|
||||
'format_id': 'http-%s-%s' % (version, attr['name']),
|
||||
'height': int_or_none(attr.get('frameheight')),
|
||||
'width': int_or_none(attr.get('frameWidth')),
|
||||
'tbr': int_or_none(attr.get('totalBitrate')),
|
||||
'vbr': int_or_none(attr.get('videoBitrate')),
|
||||
'abr': int_or_none(attr.get('audioBitrate')),
|
||||
'vcodec': attr.get('videoCodec'),
|
||||
'acodec': attr.get('audioCodec'),
|
||||
})
|
||||
elif source_type == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
renditions.find('rendition').attrib['url'], video_id,
|
||||
'mp4', 'm3u8_native', m3u8_id='hls-%s' % version,
|
||||
note='Downloading %s m3u8 information' % version,
|
||||
errnote='Failed to download %s m3u8 information' % version,
|
||||
fatal=False))
|
||||
elif source_type == 'smil' and version == 'level3' and not smil_parsed:
|
||||
formats.extend(self._extract_smil_formats(
|
||||
renditions.find('rendition').attrib['url'], video_id, False))
|
||||
smil_parsed = True
|
||||
formats.append({
|
||||
'url': version_url,
|
||||
'format_id': 'http-%s-%s' % (version, video_version['quality']),
|
||||
'vcodec': m.group('vcodec'),
|
||||
'acodec': m.group('acodec'),
|
||||
'vbr': int(m.group('vbr')),
|
||||
'abr': int(m.group('abr')),
|
||||
'ext': m.group('ext'),
|
||||
'width': int(m.group('width')),
|
||||
'height': int(m.group('height')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
track = video_info['title']
|
||||
@ -376,17 +269,15 @@ class VevoIE(VevoBaseIE):
|
||||
else:
|
||||
age_limit = None
|
||||
|
||||
duration = video_info.get('duration')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': video_info.get('imageUrl') or video_info.get('thumbnailUrl'),
|
||||
'timestamp': timestamp,
|
||||
'timestamp': parse_iso8601(video_info.get('releaseDate')),
|
||||
'uploader': uploader,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'duration': int_or_none(video_info.get('duration')),
|
||||
'view_count': int_or_none(video_info.get('views', {}).get('total')),
|
||||
'age_limit': age_limit,
|
||||
'track': track,
|
||||
'artist': uploader,
|
||||
|
||||
@ -338,7 +338,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
'expected_warnings': ['Unable to download JSON metadata'],
|
||||
},
|
||||
{
|
||||
# redirects to ondemand extractor and should be passed throught it
|
||||
# redirects to ondemand extractor and should be passed through it
|
||||
# for successful extraction
|
||||
'url': 'https://vimeo.com/73445910',
|
||||
'info_dict': {
|
||||
@ -730,12 +730,12 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
|
||||
# Try extracting href first since not all videos are available via
|
||||
# short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
|
||||
clips = re.findall(
|
||||
r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)', webpage)
|
||||
r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
|
||||
if clips:
|
||||
for video_id, video_url in clips:
|
||||
for video_id, video_url, video_title in clips:
|
||||
yield self.url_result(
|
||||
compat_urlparse.urljoin(base_url, video_url),
|
||||
VimeoIE.ie_key(), video_id=video_id)
|
||||
VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
|
||||
# More relaxed fallback
|
||||
else:
|
||||
for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
|
||||
@ -884,10 +884,14 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
|
||||
|
||||
def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
|
||||
webpage = self._download_webpage(webpage_url, video_id)
|
||||
data = self._parse_json(self._search_regex(
|
||||
r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
|
||||
default=NO_DEFAULT if video_password_verified else '{}'), video_id)
|
||||
config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
|
||||
config_url = self._html_search_regex(
|
||||
r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
|
||||
'config URL', default=None, group='url')
|
||||
if not config_url:
|
||||
data = self._parse_json(self._search_regex(
|
||||
r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
|
||||
default=NO_DEFAULT if video_password_verified else '{}'), video_id)
|
||||
config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
|
||||
if config_url is None:
|
||||
self._verify_video_password(webpage_url, video_id, webpage)
|
||||
config_url = self._get_config_url(
|
||||
|
||||
@ -16,7 +16,9 @@ class XiamiBaseIE(InfoExtractor):
|
||||
return webpage
|
||||
|
||||
def _extract_track(self, track, track_id=None):
|
||||
title = track['title']
|
||||
track_name = track.get('songName') or track.get('name') or track['subName']
|
||||
artist = track.get('artist') or track.get('artist_name') or track.get('singers')
|
||||
title = '%s - %s' % (artist, track_name) if artist else track_name
|
||||
track_url = self._decrypt(track['location'])
|
||||
|
||||
subtitles = {}
|
||||
@ -31,9 +33,10 @@ class XiamiBaseIE(InfoExtractor):
|
||||
'thumbnail': track.get('pic') or track.get('album_pic'),
|
||||
'duration': int_or_none(track.get('length')),
|
||||
'creator': track.get('artist', '').split(';')[0],
|
||||
'track': title,
|
||||
'album': track.get('album_name'),
|
||||
'artist': track.get('artist'),
|
||||
'track': track_name,
|
||||
'track_number': int_or_none(track.get('track')),
|
||||
'album': track.get('album_name') or track.get('title'),
|
||||
'artist': artist,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
@ -68,14 +71,14 @@ class XiamiBaseIE(InfoExtractor):
|
||||
class XiamiSongIE(XiamiBaseIE):
|
||||
IE_NAME = 'xiami:song'
|
||||
IE_DESC = '虾米音乐'
|
||||
_VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.xiami.com/song/1775610518',
|
||||
'md5': '521dd6bea40fd5c9c69f913c232cb57e',
|
||||
'info_dict': {
|
||||
'id': '1775610518',
|
||||
'ext': 'mp3',
|
||||
'title': 'Woman',
|
||||
'title': 'HONNE - Woman',
|
||||
'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
|
||||
'duration': 265,
|
||||
'creator': 'HONNE',
|
||||
@ -95,7 +98,7 @@ class XiamiSongIE(XiamiBaseIE):
|
||||
'info_dict': {
|
||||
'id': '1775256504',
|
||||
'ext': 'mp3',
|
||||
'title': '悟空',
|
||||
'title': '戴荃 - 悟空',
|
||||
'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
|
||||
'duration': 200,
|
||||
'creator': '戴荃',
|
||||
@ -109,6 +112,26 @@ class XiamiSongIE(XiamiBaseIE):
|
||||
},
|
||||
},
|
||||
'skip': 'Georestricted',
|
||||
}, {
|
||||
'url': 'http://www.xiami.com/song/1775953850',
|
||||
'info_dict': {
|
||||
'id': '1775953850',
|
||||
'ext': 'mp3',
|
||||
'title': 'До Скону - Чума Пожирает Землю',
|
||||
'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
|
||||
'duration': 683,
|
||||
'creator': 'До Скону',
|
||||
'track': 'Чума Пожирает Землю',
|
||||
'track_number': 7,
|
||||
'album': 'Ад',
|
||||
'artist': 'До Скону',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.xiami.com/song/xLHGwgd07a1',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -124,7 +147,7 @@ class XiamiPlaylistBaseIE(XiamiBaseIE):
|
||||
class XiamiAlbumIE(XiamiPlaylistBaseIE):
|
||||
IE_NAME = 'xiami:album'
|
||||
IE_DESC = '虾米音乐 - 专辑'
|
||||
_VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[^/?#&]+)'
|
||||
_TYPE = '1'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.xiami.com/album/2100300444',
|
||||
@ -136,28 +159,34 @@ class XiamiAlbumIE(XiamiPlaylistBaseIE):
|
||||
}, {
|
||||
'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.xiami.com/album/URVDji2a506',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class XiamiArtistIE(XiamiPlaylistBaseIE):
|
||||
IE_NAME = 'xiami:artist'
|
||||
IE_DESC = '虾米音乐 - 歌手'
|
||||
_VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[^/?#&]+)'
|
||||
_TYPE = '2'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
|
||||
'info_dict': {
|
||||
'id': '2132',
|
||||
},
|
||||
'playlist_count': 20,
|
||||
'skip': 'Georestricted',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.xiami.com/artist/bC5Tk2K6eb99',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class XiamiCollectionIE(XiamiPlaylistBaseIE):
|
||||
IE_NAME = 'xiami:collection'
|
||||
IE_DESC = '虾米音乐 - 精选集'
|
||||
_VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[^/?#&]+)'
|
||||
_TYPE = '3'
|
||||
_TEST = {
|
||||
'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',
|
||||
|
||||
@ -2,44 +2,37 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import urljoin
|
||||
|
||||
|
||||
class YourUploadIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?
|
||||
(?:yourupload\.com/watch|
|
||||
embed\.yourupload\.com|
|
||||
embed\.yucache\.net
|
||||
)/(?P<id>[A-Za-z0-9]+)
|
||||
'''
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://yourupload.com/watch/14i14h',
|
||||
'md5': '5e2c63385454c557f97c4c4131a393cd',
|
||||
'info_dict': {
|
||||
'id': '14i14h',
|
||||
'ext': 'mp4',
|
||||
'title': 'BigBuckBunny_320x180.mp4',
|
||||
'thumbnail': r're:^https?://.*\.jpe?g',
|
||||
}
|
||||
},
|
||||
{
|
||||
'url': 'http://embed.yourupload.com/14i14h',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'http://embed.yucache.net/14i14h?client_file_id=803349',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:yourupload\.com/(?:watch|embed)|embed\.yourupload\.com)/(?P<id>[A-Za-z0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://yourupload.com/watch/14i14h',
|
||||
'md5': '5e2c63385454c557f97c4c4131a393cd',
|
||||
'info_dict': {
|
||||
'id': '14i14h',
|
||||
'ext': 'mp4',
|
||||
'title': 'BigBuckBunny_320x180.mp4',
|
||||
'thumbnail': r're:^https?://.*\.jpe?g',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.yourupload.com/embed/14i14h',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://embed.yourupload.com/14i14h',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
embed_url = 'http://embed.yucache.net/{0:}'.format(video_id)
|
||||
embed_url = 'http://www.yourupload.com/embed/%s' % video_id
|
||||
|
||||
webpage = self._download_webpage(embed_url, video_id)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
video_url = self._og_search_video_url(webpage)
|
||||
video_url = urljoin(embed_url, self._og_search_video_url(webpage))
|
||||
thumbnail = self._og_search_thumbnail(webpage, default=None)
|
||||
|
||||
return {
|
||||
|
||||
@ -40,6 +40,7 @@ from ..utils import (
|
||||
sanitized_Request,
|
||||
smuggle_url,
|
||||
str_to_int,
|
||||
try_get,
|
||||
unescapeHTML,
|
||||
unified_strdate,
|
||||
unsmuggle_url,
|
||||
@ -383,6 +384,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
|
||||
'categories': ['Science & Technology'],
|
||||
'tags': ['youtube-dl'],
|
||||
'duration': 10,
|
||||
'like_count': int,
|
||||
'dislike_count': int,
|
||||
'start_time': 1,
|
||||
@ -402,6 +404,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
|
||||
'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
|
||||
'iconic ep', 'iconic', 'love', 'it'],
|
||||
'duration': 180,
|
||||
'uploader': 'Icona Pop',
|
||||
'uploader_id': 'IconaPop',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
|
||||
@ -419,6 +422,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
|
||||
'alt_title': 'Tunnel Vision',
|
||||
'description': 'md5:64249768eec3bc4276236606ea996373',
|
||||
'duration': 419,
|
||||
'uploader': 'justintimberlakeVEVO',
|
||||
'uploader_id': 'justintimberlakeVEVO',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
|
||||
@ -458,6 +462,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
|
||||
'categories': ['Science & Technology'],
|
||||
'tags': ['youtube-dl'],
|
||||
'duration': 10,
|
||||
'like_count': int,
|
||||
'dislike_count': int,
|
||||
},
|
||||
@ -493,6 +498,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'm4a',
|
||||
'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
|
||||
'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
|
||||
'duration': 244,
|
||||
'uploader': 'AfrojackVEVO',
|
||||
'uploader_id': 'AfrojackVEVO',
|
||||
'upload_date': '20131011',
|
||||
@ -512,6 +518,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'title': 'Taylor Swift - Shake It Off',
|
||||
'alt_title': 'Shake It Off',
|
||||
'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
|
||||
'duration': 242,
|
||||
'uploader': 'TaylorSwiftVEVO',
|
||||
'uploader_id': 'TaylorSwiftVEVO',
|
||||
'upload_date': '20140818',
|
||||
@ -529,6 +536,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'T4XJQO3qol8',
|
||||
'ext': 'mp4',
|
||||
'duration': 219,
|
||||
'upload_date': '20100909',
|
||||
'uploader': 'The Amazing Atheist',
|
||||
'uploader_id': 'TheAmazingAtheist',
|
||||
@ -546,6 +554,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
|
||||
'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
|
||||
'duration': 142,
|
||||
'uploader': 'The Witcher',
|
||||
'uploader_id': 'WitcherGame',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
|
||||
@ -562,6 +571,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
|
||||
'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
|
||||
'duration': 247,
|
||||
'uploader': 'LloydVEVO',
|
||||
'uploader_id': 'LloydVEVO',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
|
||||
@ -576,6 +586,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '__2ABJjxzNo',
|
||||
'ext': 'mp4',
|
||||
'duration': 266,
|
||||
'upload_date': '20100430',
|
||||
'uploader_id': 'deadmau5',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
|
||||
@ -596,6 +607,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'lqQg6PlCWgI',
|
||||
'ext': 'mp4',
|
||||
'duration': 6085,
|
||||
'upload_date': '20150827',
|
||||
'uploader_id': 'olympic',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
|
||||
@ -615,6 +627,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'id': '_b-2C3KPAM0',
|
||||
'ext': 'mp4',
|
||||
'stretched_ratio': 16 / 9.,
|
||||
'duration': 85,
|
||||
'upload_date': '20110310',
|
||||
'uploader_id': 'AllenMeow',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
|
||||
@ -649,6 +662,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:7b81415841e02ecd4313668cde88737a',
|
||||
'description': 'md5:116377fd2963b81ec4ce64b542173306',
|
||||
'duration': 220,
|
||||
'upload_date': '20150625',
|
||||
'uploader_id': 'dorappi2000',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
|
||||
@ -691,6 +705,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
|
||||
'description': 'md5:dc7872fb300e143831327f1bae3af010',
|
||||
'duration': 7335,
|
||||
'upload_date': '20150721',
|
||||
'uploader': 'Beer Games Beer',
|
||||
'uploader_id': 'beergamesbeer',
|
||||
@ -703,6 +718,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
|
||||
'description': 'md5:dc7872fb300e143831327f1bae3af010',
|
||||
'duration': 7337,
|
||||
'upload_date': '20150721',
|
||||
'uploader': 'Beer Games Beer',
|
||||
'uploader_id': 'beergamesbeer',
|
||||
@ -715,6 +731,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
|
||||
'description': 'md5:dc7872fb300e143831327f1bae3af010',
|
||||
'duration': 7337,
|
||||
'upload_date': '20150721',
|
||||
'uploader': 'Beer Games Beer',
|
||||
'uploader_id': 'beergamesbeer',
|
||||
@ -727,6 +744,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'teamPGP: Rocket League Noob Stream (zim)',
|
||||
'description': 'md5:dc7872fb300e143831327f1bae3af010',
|
||||
'duration': 7334,
|
||||
'upload_date': '20150721',
|
||||
'uploader': 'Beer Games Beer',
|
||||
'uploader_id': 'beergamesbeer',
|
||||
@ -768,6 +786,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
|
||||
'alt_title': 'Dark Walk',
|
||||
'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
|
||||
'duration': 133,
|
||||
'upload_date': '20151119',
|
||||
'uploader_id': 'IronSoulElf',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
|
||||
@ -809,10 +828,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:e41008789470fc2533a3252216f1c1d1',
|
||||
'description': 'md5:a677553cf0840649b731a3024aeff4cc',
|
||||
'duration': 721,
|
||||
'upload_date': '20150127',
|
||||
'uploader_id': 'BerkmanCenter',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
|
||||
'uploader': 'BerkmanCenter',
|
||||
'uploader': 'The Berkman Klein Center for Internet & Society',
|
||||
'license': 'Creative Commons Attribution license (reuse allowed)',
|
||||
},
|
||||
'params': {
|
||||
@ -827,6 +847,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
|
||||
'description': 'md5:dda0d780d5a6e120758d1711d062a867',
|
||||
'duration': 4060,
|
||||
'upload_date': '20151119',
|
||||
'uploader': 'Bernie 2016',
|
||||
'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
|
||||
@ -864,6 +885,31 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
# YouTube Red video with episode data
|
||||
'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
|
||||
'info_dict': {
|
||||
'id': 'iqKdEhx-dD4',
|
||||
'ext': 'mp4',
|
||||
'title': 'Isolation - Mind Field (Ep 1)',
|
||||
'description': 'md5:8013b7ddea787342608f63a13ddc9492',
|
||||
'duration': 2085,
|
||||
'upload_date': '20170118',
|
||||
'uploader': 'Vsauce',
|
||||
'uploader_id': 'Vsauce',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
|
||||
'license': 'Standard YouTube License',
|
||||
'series': 'Mind Field',
|
||||
'season_number': 1,
|
||||
'episode_number': 1,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': [
|
||||
'Skipping DASH manifest',
|
||||
],
|
||||
},
|
||||
{
|
||||
# itag 212
|
||||
'url': '1t24XAntNCY',
|
||||
@ -1454,6 +1500,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
else:
|
||||
video_alt_title = video_creator = None
|
||||
|
||||
m_episode = re.search(
|
||||
r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
|
||||
video_webpage)
|
||||
if m_episode:
|
||||
series = m_episode.group('series')
|
||||
season_number = int(m_episode.group('season'))
|
||||
episode_number = int(m_episode.group('episode'))
|
||||
else:
|
||||
series = season_number = episode_number = None
|
||||
|
||||
m_cat_container = self._search_regex(
|
||||
r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
|
||||
video_webpage, 'categories', default=None)
|
||||
@ -1482,11 +1538,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
video_subtitles = self.extract_subtitles(video_id, video_webpage)
|
||||
automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
|
||||
|
||||
if 'length_seconds' not in video_info:
|
||||
self._downloader.report_warning('unable to extract video duration')
|
||||
video_duration = None
|
||||
else:
|
||||
video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0]))
|
||||
video_duration = try_get(
|
||||
video_info, lambda x: int_or_none(x['length_seconds'][0]))
|
||||
if not video_duration:
|
||||
video_duration = parse_duration(self._html_search_meta(
|
||||
'duration', video_webpage, 'video duration'))
|
||||
|
||||
# annotations
|
||||
video_annotations = None
|
||||
@ -1743,6 +1799,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'is_live': is_live,
|
||||
'start_time': start_time,
|
||||
'end_time': end_time,
|
||||
'series': series,
|
||||
'season_number': season_number,
|
||||
'episode_number': episode_number,
|
||||
}
|
||||
|
||||
|
||||
@ -1819,6 +1878,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
|
||||
'title': 'YDL_Empty_List',
|
||||
},
|
||||
'playlist_count': 0,
|
||||
'skip': 'This playlist is private',
|
||||
}, {
|
||||
'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
|
||||
'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
|
||||
@ -1850,6 +1910,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
|
||||
'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
'skip': 'This playlist is private',
|
||||
}, {
|
||||
'note': 'embedded',
|
||||
'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
|
||||
@ -1961,14 +2022,18 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
|
||||
url = self._TEMPLATE_URL % playlist_id
|
||||
page = self._download_webpage(url, playlist_id)
|
||||
|
||||
for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
|
||||
# the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
|
||||
for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
|
||||
match = match.strip()
|
||||
# Check if the playlist exists or is private
|
||||
if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match):
|
||||
raise ExtractorError(
|
||||
'The playlist doesn\'t exist or is private, use --username or '
|
||||
'--netrc to access it.',
|
||||
expected=True)
|
||||
mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
|
||||
if mobj:
|
||||
reason = mobj.group('reason')
|
||||
message = 'This playlist %s' % reason
|
||||
if 'private' in reason:
|
||||
message += ', use --username or --netrc to access it'
|
||||
message += '.'
|
||||
raise ExtractorError(message, expected=True)
|
||||
elif re.match(r'[^<]*Invalid parameters[^<]*', match):
|
||||
raise ExtractorError(
|
||||
'Invalid parameters. Maybe URL is incorrect.',
|
||||
|
||||
@ -751,7 +751,7 @@ def parseOpts(overrideArguments=None):
|
||||
help='Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
|
||||
postproc.add_option(
|
||||
'--audio-format', metavar='FORMAT', dest='audioformat', default='best',
|
||||
help='Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default')
|
||||
help='Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default; No effect without -x')
|
||||
postproc.add_option(
|
||||
'--audio-quality', metavar='QUALITY',
|
||||
dest='audioquality', default='5',
|
||||
@ -867,7 +867,7 @@ def parseOpts(overrideArguments=None):
|
||||
if '--ignore-config' not in system_conf:
|
||||
user_conf = _readUserConf()
|
||||
|
||||
argv = system_conf + user_conf + command_line_conf
|
||||
argv = system_conf + user_conf + custom_conf + command_line_conf
|
||||
opts, args = parser.parse_args(argv)
|
||||
if opts.verbose:
|
||||
for conf_label, conf in (
|
||||
|
||||
@ -143,6 +143,7 @@ DATE_FORMATS = (
|
||||
'%Y/%m/%d',
|
||||
'%Y/%m/%d %H:%M',
|
||||
'%Y/%m/%d %H:%M:%S',
|
||||
'%Y-%m-%d %H:%M',
|
||||
'%Y-%m-%d %H:%M:%S',
|
||||
'%Y-%m-%d %H:%M:%S.%f',
|
||||
'%d.%m.%Y %H:%M',
|
||||
@ -1772,7 +1773,7 @@ def parse_duration(s):
|
||||
s = s.strip()
|
||||
|
||||
days, hours, mins, secs, ms = [None] * 5
|
||||
m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?$', s)
|
||||
m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?Z?$', s)
|
||||
if m:
|
||||
days, hours, mins, secs, ms = m.groups()
|
||||
else:
|
||||
@ -1789,11 +1790,11 @@ def parse_duration(s):
|
||||
)?
|
||||
(?:
|
||||
(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*s(?:ec(?:ond)?s?)?\s*
|
||||
)?$''', s)
|
||||
)?Z?$''', s)
|
||||
if m:
|
||||
days, hours, mins, secs, ms = m.groups()
|
||||
else:
|
||||
m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)$', s)
|
||||
m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)Z?$', s)
|
||||
if m:
|
||||
hours, mins = m.groups()
|
||||
else:
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2017.01.10'
|
||||
__version__ = '2017.01.28'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user