Merge remote-tracking branch 'rg3/master'
This commit is contained in:
renalid
commit
04167e247c
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 *2016.08.31*. 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 Issues with outdated version will be rejected.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 **2016.08.31**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.11.1*. 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 Issues with outdated version will be rejected.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 **2016.09.11.1**
|
||||
|
||||
### 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 2016.08.31
|
||||
[debug] youtube-dl version 2016.09.11.1
|
||||
[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: {}
|
||||
|
||||
2
.github/ISSUE_TEMPLATE_tmpl.md
vendored
2
.github/ISSUE_TEMPLATE_tmpl.md
vendored
@ -55,4 +55,4 @@ $ youtube-dl -v <your command line>
|
||||
### Description of your *issue*, suggested solution and other information
|
||||
|
||||
Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
|
||||
If work on your *issue* required an account credentials please provide them or explain how one can obtain them.
|
||||
If work on your *issue* requires account credentials please provide them or explain how one can obtain them.
|
||||
|
||||
3
AUTHORS
3
AUTHORS
@ -182,3 +182,6 @@ Rob van Bekkum
|
||||
Petr Zvoníček
|
||||
Pratyush Singh
|
||||
Aleksander Nitecki
|
||||
Sebastian Blunt
|
||||
Matěj Cepl
|
||||
Xie Yanbo
|
||||
|
||||
104
ChangeLog
104
ChangeLog
@ -1,8 +1,112 @@
|
||||
version <unreleased>
|
||||
|
||||
Extractors
|
||||
* [kwuo] Improve error detection (#10650)
|
||||
* [bilibili] Fix extraction for specific videos (#10647)
|
||||
+ [nbc] Add support for NBC Olympics (#10361)
|
||||
|
||||
|
||||
version 2016.09.11.1
|
||||
|
||||
Extractors
|
||||
+ [tube8] Extract categories and tags (#10579)
|
||||
+ [pornhub] Extract categories and tags (#10499)
|
||||
* [openload] Temporary fix (#10408)
|
||||
+ [foxnews] Add support Fox News articles (#10598)
|
||||
* [viafree] Improve video id extraction (#10615)
|
||||
* [iwara] Fix extraction after relaunch (#10462, #3215)
|
||||
+ [tfo] Add extractor for tfo.org
|
||||
* [lrt] Fix audio extraction (#10566)
|
||||
* [9now] Fix extraction (#10561)
|
||||
+ [canalplus] Add support for c8.fr (#10577)
|
||||
* [newgrounds] Fix uploader extraction (#10584)
|
||||
+ [polskieradio:category] Add support for category lists (#10576)
|
||||
+ [ketnet] Add extractor for ketnet.be (#10343)
|
||||
+ [canvas] Add support for een.be (#10605)
|
||||
+ [telequebec] Add extractor for telequebec.tv (#1999)
|
||||
* [parliamentliveuk] Fix extraction (#9137)
|
||||
|
||||
|
||||
version 2016.09.08
|
||||
|
||||
Extractors
|
||||
+ [jwplatform] Extract height from format label
|
||||
+ [yahoo] Extract Brightcove Legacy Studio embeds (#9345)
|
||||
* [videomore] Fix extraction (#10592)
|
||||
* [foxgay] Fix extraction (#10480)
|
||||
+ [rmcdecouverte] Add extractor for rmcdecouverte.bfmtv.com (#9709)
|
||||
* [gamestar] Fix metadata extraction (#10479)
|
||||
* [puls4] Fix extraction (#10583)
|
||||
+ [cctv] Add extractor for CCTV and CNTV (#8153)
|
||||
+ [lci] Add extractor for lci.fr (#10573)
|
||||
+ [wat] Extract DASH formats
|
||||
+ [viafree] Improve video id detection (#10569)
|
||||
+ [trutv] Add extractor for trutv.com (#10519)
|
||||
+ [nick] Add support for nickelodeon.nl (#10559)
|
||||
+ [abcotvs:clips] Add support for clips.abcotvs.com
|
||||
+ [abcotvs] Add support for ABC Owned Television Stations sites (#9551)
|
||||
+ [miaopai] Add extractor for miaopai.com (#10556)
|
||||
* [gamestar] Fix metadata extraction (#10479)
|
||||
+ [bilibili] Add support for episodes (#10190)
|
||||
+ [tvnoe] Add extractor for tvnoe.cz (#10524)
|
||||
|
||||
|
||||
version 2016.09.04.1
|
||||
|
||||
Core
|
||||
* In DASH downloader if the first segment fails, abort the whole download
|
||||
process to prevent throttling (#10497)
|
||||
+ Add support for --skip-unavailable-fragments and --fragment retries in
|
||||
hlsnative downloader (#10165, #10448).
|
||||
+ Add support for --skip-unavailable-fragments in DASH downloader
|
||||
+ Introduce --skip-unavailable-fragments option for fragment based downloaders
|
||||
that allows to skip fragments unavailable due to a HTTP error
|
||||
* Fix extraction of video/audio entries with src attribute in
|
||||
_parse_html5_media_entries (#10540)
|
||||
|
||||
Extractors
|
||||
* [theplatform] Relax URL regular expression (#10546)
|
||||
* [youtube:playlist] Extend URL regular expression
|
||||
* [rottentomatoes] Delegate extraction to internetvideoarchive extractor
|
||||
* [internetvideoarchive] Extract all formats
|
||||
* [pornvoisines] Fix extraction (#10469)
|
||||
* [rottentomatoes] Fix extraction (#10467)
|
||||
* [espn] Extend URL regular expression (#10549)
|
||||
* [vimple] Extend URL regular expression (#10547)
|
||||
* [youtube:watchlater] Fix extraction (#10544)
|
||||
* [youjizz] Fix extraction (#10437)
|
||||
+ [foxnews] Add support for FoxNews Insider (#10445)
|
||||
+ [fc2] Recognize Flash player URLs (#10512)
|
||||
|
||||
|
||||
version 2016.09.03
|
||||
|
||||
Core
|
||||
* Restore usage of NAME attribute from EXT-X-MEDIA tag for formats codes in
|
||||
_extract_m3u8_formats (#10522)
|
||||
* Handle semicolon in mimetype2ext
|
||||
|
||||
Extractors
|
||||
+ [youtube] Add support for rental videos' previews (#10532)
|
||||
* [youtube:playlist] Fallback to video extraction for video/playlist URLs when
|
||||
no playlist is actually served (#10537)
|
||||
+ [drtv] Add support for dr.dk/nyheder (#10536)
|
||||
+ [facebook:plugins:video] Add extractor (#10530)
|
||||
+ [go] Add extractor for *.go.com sites
|
||||
* [adobepass] Check for authz_token expiration (#10527)
|
||||
* [nytimes] improve extraction
|
||||
* [thestar] Fix extraction (#10465)
|
||||
* [glide] Fix extraction (#10478)
|
||||
- [exfm] Remove extractor (#10482)
|
||||
* [youporn] Fix categories and tags extraction (#10521)
|
||||
+ [curiositystream] Add extractor for app.curiositystream.com
|
||||
- [thvideo] Remove extractor (#10464)
|
||||
* [movingimage] Fix for the new site name (#10466)
|
||||
+ [cbs] Add support for once formats (#10515)
|
||||
* [limelight] Skip ism snd duplicate manifests
|
||||
+ [porncom] Extract categories and tags (#10510)
|
||||
+ [facebook] Extract timestamp (#10508)
|
||||
+ [yahoo] Extract more formats
|
||||
|
||||
|
||||
version 2016.08.31
|
||||
|
||||
17
README.md
17
README.md
@ -89,6 +89,8 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--mark-watched Mark videos watched (YouTube only)
|
||||
--no-mark-watched Do not mark videos watched (YouTube only)
|
||||
--no-color Do not emit color codes in output
|
||||
--abort-on-unavailable-fragment Abort downloading when some fragment is not
|
||||
available
|
||||
|
||||
## Network Options:
|
||||
--proxy URL Use the specified HTTP/HTTPS/SOCKS proxy.
|
||||
@ -173,7 +175,10 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
-R, --retries RETRIES Number of retries (default is 10), or
|
||||
"infinite".
|
||||
--fragment-retries RETRIES Number of retries for a fragment (default
|
||||
is 10), or "infinite" (DASH only)
|
||||
is 10), or "infinite" (DASH and hlsnative
|
||||
only)
|
||||
--skip-unavailable-fragments Skip unavailable fragments (DASH and
|
||||
hlsnative only)
|
||||
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K)
|
||||
(default is 1024)
|
||||
--no-resize-buffer Do not automatically adjust the buffer
|
||||
@ -846,6 +851,16 @@ will download the complete `PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re` playlist and cre
|
||||
|
||||
youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
|
||||
|
||||
### Should I add `--hls-prefer-native` into my config?
|
||||
|
||||
When youtube-dl detects an HLS video, it can download it either with the built-in downloader or ffmpeg. Since many HLS streams are slightly invalid and ffmpeg/youtube-dl each handle some invalid cases better than the other, there is an option to switch the downloader if needed.
|
||||
|
||||
When youtube-dl knows that one particular downloader works better for a given website, that downloader will be picked. Otherwise, youtube-dl will pick the best downloader for general compatibility, which at the moment happens to be ffmpeg. This choice may change in future versions of youtube-dl, with improvements of the built-in downloader and/or ffmpeg.
|
||||
|
||||
In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](http://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
|
||||
|
||||
If you put either `--hls-prefer-native` or `--hls-prefer-ffmpeg` into your configuration, a different subset of videos will fail to download correctly. Instead, it is much better to [file an issue](https://yt-dl.org/bug) or a pull request which details why the native or the ffmpeg HLS downloader is a better choice for your use case.
|
||||
|
||||
### Can you add support for this anime video site, or site which shows current movies for free?
|
||||
|
||||
As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
|
||||
|
||||
@ -60,6 +60,9 @@ if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; e
|
||||
if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
|
||||
if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi
|
||||
|
||||
read -p "Is ChangeLog up to date? (y/n) " -n 1
|
||||
if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
|
||||
|
||||
/bin/echo -e "\n### First of all, testing..."
|
||||
make clean
|
||||
if $skip_tests ; then
|
||||
|
||||
@ -19,9 +19,10 @@
|
||||
- **9now.com.au**
|
||||
- **abc.net.au**
|
||||
- **abc.net.au:iview**
|
||||
- **Abc7News**
|
||||
- **abcnews**
|
||||
- **abcnews:video**
|
||||
- **abcotvs**: ABC Owned Television Stations
|
||||
- **abcotvs:clips**
|
||||
- **AcademicEarth:Course**
|
||||
- **acast**
|
||||
- **acast:channel**
|
||||
@ -128,6 +129,7 @@
|
||||
- **CBSNews**: CBS News
|
||||
- **CBSNewsLiveVideo**: CBS News Live Videos
|
||||
- **CBSSports**
|
||||
- **CCTV**
|
||||
- **CDA**
|
||||
- **CeskaTelevize**
|
||||
- **channel9**: Channel 9
|
||||
@ -171,6 +173,8 @@
|
||||
- **CTVNews**
|
||||
- **culturebox.francetvinfo.fr**
|
||||
- **CultureUnplugged**
|
||||
- **curiositystream**
|
||||
- **curiositystream:collection**
|
||||
- **CWTV**
|
||||
- **DailyMail**
|
||||
- **dailymotion**
|
||||
@ -223,13 +227,14 @@
|
||||
- **EsriVideo**
|
||||
- **Europa**
|
||||
- **EveryonesMixtape**
|
||||
- **exfm**: ex.fm
|
||||
- **ExpoTV**
|
||||
- **ExtremeTube**
|
||||
- **EyedoTV**
|
||||
- **facebook**
|
||||
- **FacebookPluginsVideo**
|
||||
- **faz.net**
|
||||
- **fc2**
|
||||
- **fc2:embed**
|
||||
- **Fczenit**
|
||||
- **features.aol.com**
|
||||
- **fernsehkritik.tv**
|
||||
@ -242,7 +247,9 @@
|
||||
- **Formula1**
|
||||
- **FOX**
|
||||
- **Foxgay**
|
||||
- **FoxNews**: Fox News and Fox Business Video
|
||||
- **foxnews**: Fox News and Fox Business Video
|
||||
- **foxnews:article**
|
||||
- **foxnews:insider**
|
||||
- **FoxSports**
|
||||
- **france2.fr:generation-quoi**
|
||||
- **FranceCulture**
|
||||
@ -271,6 +278,7 @@
|
||||
- **Glide**: Glide mobile video messages (glide.me)
|
||||
- **Globo**
|
||||
- **GloboArticle**
|
||||
- **Go**
|
||||
- **GodTube**
|
||||
- **GodTV**
|
||||
- **Golem**
|
||||
@ -319,6 +327,7 @@
|
||||
- **ivi**: ivi.ru
|
||||
- **ivi:compilation**: ivi.ru compilations
|
||||
- **ivideon**: Ivideon TV
|
||||
- **Iwara**
|
||||
- **Izlesene**
|
||||
- **JeuxVideo**
|
||||
- **Jove**
|
||||
@ -332,6 +341,7 @@
|
||||
- **KarriereVideos**
|
||||
- **keek**
|
||||
- **KeezMovies**
|
||||
- **Ketnet**
|
||||
- **KhanAcademy**
|
||||
- **KickStarter**
|
||||
- **KonserthusetPlay**
|
||||
@ -347,6 +357,7 @@
|
||||
- **kuwo:song**: 酷我音乐
|
||||
- **la7.it**
|
||||
- **Laola1Tv**
|
||||
- **LCI**
|
||||
- **Lcp**
|
||||
- **LcpPlay**
|
||||
- **Le**: 乐视网
|
||||
@ -385,6 +396,7 @@
|
||||
- **Metacritic**
|
||||
- **Mgoon**
|
||||
- **MGTV**: 芒果TV
|
||||
- **MiaoPai**
|
||||
- **Minhateca**
|
||||
- **MinistryGrid**
|
||||
- **Minoto**
|
||||
@ -406,6 +418,7 @@
|
||||
- **MovieClips**
|
||||
- **MovieFap**
|
||||
- **Moviezine**
|
||||
- **MovingImage**
|
||||
- **MPORA**
|
||||
- **MSN**
|
||||
- **mtg**: MTG services
|
||||
@ -530,6 +543,7 @@
|
||||
- **podomatic**
|
||||
- **Pokemon**
|
||||
- **PolskieRadio**
|
||||
- **PolskieRadioCategory**
|
||||
- **PornCom**
|
||||
- **PornHd**
|
||||
- **PornHub**: PornHub and Thumbzilla
|
||||
@ -570,6 +584,7 @@
|
||||
- **revision3:embed**
|
||||
- **RICE**
|
||||
- **RingTV**
|
||||
- **RMCDecouverte**
|
||||
- **RockstarGames**
|
||||
- **RoosterTeeth**
|
||||
- **RottenTomatoes**
|
||||
@ -659,7 +674,6 @@
|
||||
- **sr:mediathek**: Saarländischer Rundfunk
|
||||
- **SRGSSR**
|
||||
- **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
|
||||
- **SSA**
|
||||
- **stanfordoc**: Stanford Open ClassRoom
|
||||
- **Steam**
|
||||
- **Stitcher**
|
||||
@ -691,9 +705,11 @@
|
||||
- **Telecinco**: telecinco.es, cuatro.com and mediaset.es
|
||||
- **Telegraaf**
|
||||
- **TeleMB**
|
||||
- **TeleQuebec**
|
||||
- **TeleTask**
|
||||
- **Telewebion**
|
||||
- **TF1**
|
||||
- **TFO**
|
||||
- **TheIntercept**
|
||||
- **ThePlatform**
|
||||
- **ThePlatformFeed**
|
||||
@ -702,8 +718,6 @@
|
||||
- **TheStar**
|
||||
- **ThisAmericanLife**
|
||||
- **ThisAV**
|
||||
- **THVideo**
|
||||
- **THVideoPlaylist**
|
||||
- **tinypic**: tinypic.com videos
|
||||
- **tlc.de**
|
||||
- **TMZ**
|
||||
@ -717,7 +731,7 @@
|
||||
- **ToypicsUser**: Toypics user profile
|
||||
- **TrailerAddict** (Currently broken)
|
||||
- **Trilulilu**
|
||||
- **trollvids**
|
||||
- **TruTV**
|
||||
- **Tube8**
|
||||
- **TubiTv**
|
||||
- **tudou**
|
||||
@ -739,6 +753,7 @@
|
||||
- **TVCArticle**
|
||||
- **tvigle**: Интернет-телевидение Tvigle.ru
|
||||
- **tvland.com**
|
||||
- **TVNoe**
|
||||
- **tvp**: Telewizja Polska
|
||||
- **tvp:embed**: Telewizja Polska
|
||||
- **tvp:series**
|
||||
|
||||
@ -39,6 +39,8 @@ from youtube_dl.utils import (
|
||||
is_html,
|
||||
js_to_json,
|
||||
limit_length,
|
||||
mimetype2ext,
|
||||
month_by_name,
|
||||
ohdave_rsa_encrypt,
|
||||
OnDemandPagedList,
|
||||
orderedSet,
|
||||
@ -625,6 +627,22 @@ class TestUtil(unittest.TestCase):
|
||||
limit_length('foo bar baz asd', 12).startswith('foo bar'))
|
||||
self.assertTrue('...' in limit_length('foo bar baz asd', 12))
|
||||
|
||||
def test_mimetype2ext(self):
|
||||
self.assertEqual(mimetype2ext(None), None)
|
||||
self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
|
||||
self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
|
||||
self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
|
||||
self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
|
||||
self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
|
||||
|
||||
def test_month_by_name(self):
|
||||
self.assertEqual(month_by_name(None), None)
|
||||
self.assertEqual(month_by_name('December', 'en'), 12)
|
||||
self.assertEqual(month_by_name('décembre', 'fr'), 12)
|
||||
self.assertEqual(month_by_name('December'), 12)
|
||||
self.assertEqual(month_by_name('décembre'), None)
|
||||
self.assertEqual(month_by_name('Unknown', 'unknown'), None)
|
||||
|
||||
def test_parse_codecs(self):
|
||||
self.assertEqual(parse_codecs(''), {})
|
||||
self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
|
||||
|
||||
@ -131,6 +131,9 @@ class YoutubeDL(object):
|
||||
username: Username for authentication purposes.
|
||||
password: Password for authentication purposes.
|
||||
videopassword: Password for accessing a video.
|
||||
ap_mso: Adobe Pass Multiple-system operator Identifier.
|
||||
ap_username: TV Provider username for authentication purposes.
|
||||
ap_password: TV Provider password for authentication purposes.
|
||||
usenetrc: Use netrc for authentication instead.
|
||||
verbose: Print additional info to stdout.
|
||||
quiet: Do not print messages to stdout.
|
||||
|
||||
@ -34,12 +34,14 @@ from .utils import (
|
||||
setproctitle,
|
||||
std_headers,
|
||||
write_string,
|
||||
render_table,
|
||||
)
|
||||
from .update import update_self
|
||||
from .downloader import (
|
||||
FileDownloader,
|
||||
)
|
||||
from .extractor import gen_extractors, list_extractors
|
||||
from .extractor.adobepass import MSO_INFO
|
||||
from .YoutubeDL import YoutubeDL
|
||||
|
||||
|
||||
@ -118,18 +120,26 @@ def _real_main(argv=None):
|
||||
desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
|
||||
write_string(desc + '\n', out=sys.stdout)
|
||||
sys.exit(0)
|
||||
if opts.ap_list_mso:
|
||||
table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
|
||||
write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
|
||||
sys.exit(0)
|
||||
|
||||
# Conflicting, missing and erroneous options
|
||||
if opts.usenetrc and (opts.username is not None or opts.password is not None):
|
||||
parser.error('using .netrc conflicts with giving username/password')
|
||||
if opts.password is not None and opts.username is None:
|
||||
parser.error('account username missing\n')
|
||||
if opts.ap_password is not None and opts.ap_username is None:
|
||||
parser.error('TV Provider account username missing\n')
|
||||
if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
|
||||
parser.error('using output template conflicts with using title, video ID or auto number')
|
||||
if opts.usetitle and opts.useid:
|
||||
parser.error('using title conflicts with using video ID')
|
||||
if opts.username is not None and opts.password is None:
|
||||
opts.password = compat_getpass('Type account password and press [Return]: ')
|
||||
if opts.ap_username is not None and opts.ap_password is None:
|
||||
opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
|
||||
if opts.ratelimit is not None:
|
||||
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
|
||||
if numeric_limit is None:
|
||||
@ -155,6 +165,8 @@ def _real_main(argv=None):
|
||||
parser.error('max sleep interval must be greater than or equal to min sleep interval')
|
||||
else:
|
||||
opts.max_sleep_interval = opts.sleep_interval
|
||||
if opts.ap_mso and opts.ap_mso not in MSO_INFO:
|
||||
parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
|
||||
|
||||
def parse_retries(retries):
|
||||
if retries in ('inf', 'infinite'):
|
||||
@ -293,6 +305,9 @@ def _real_main(argv=None):
|
||||
'password': opts.password,
|
||||
'twofactor': opts.twofactor,
|
||||
'videopassword': opts.videopassword,
|
||||
'ap_mso': opts.ap_mso,
|
||||
'ap_username': opts.ap_username,
|
||||
'ap_password': opts.ap_password,
|
||||
'quiet': (opts.quiet or any_getting or any_printing),
|
||||
'no_warnings': opts.no_warnings,
|
||||
'forceurl': opts.geturl,
|
||||
@ -318,6 +333,7 @@ def _real_main(argv=None):
|
||||
'nooverwrites': opts.nooverwrites,
|
||||
'retries': opts.retries,
|
||||
'fragment_retries': opts.fragment_retries,
|
||||
'skip_unavailable_fragments': opts.skip_unavailable_fragments,
|
||||
'buffersize': opts.buffersize,
|
||||
'noresizebuffer': opts.noresizebuffer,
|
||||
'continuedl': opts.continue_dl,
|
||||
|
||||
@ -38,8 +38,10 @@ class DashSegmentsFD(FragmentFD):
|
||||
segments_filenames = []
|
||||
|
||||
fragment_retries = self.params.get('fragment_retries', 0)
|
||||
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
|
||||
|
||||
def append_url_to_file(target_url, tmp_filename, segment_name):
|
||||
def process_segment(segment, tmp_filename, fatal):
|
||||
target_url, segment_name = segment
|
||||
target_filename = '%s-%s' % (tmp_filename, segment_name)
|
||||
count = 0
|
||||
while count <= fragment_retries:
|
||||
@ -52,26 +54,35 @@ class DashSegmentsFD(FragmentFD):
|
||||
down.close()
|
||||
segments_filenames.append(target_sanitized)
|
||||
break
|
||||
except (compat_urllib_error.HTTPError, ) as err:
|
||||
except compat_urllib_error.HTTPError as err:
|
||||
# YouTube may often return 404 HTTP error for a fragment causing the
|
||||
# whole download to fail. However if the same fragment is immediately
|
||||
# retried with the same request data this usually succeeds (1-2 attemps
|
||||
# is usually enough) thus allowing to download the whole file successfully.
|
||||
# So, we will retry all fragments that fail with 404 HTTP error for now.
|
||||
if err.code != 404:
|
||||
raise
|
||||
# Retry fragment
|
||||
# To be future-proof we will retry all fragments that fail with any
|
||||
# HTTP error.
|
||||
count += 1
|
||||
if count <= fragment_retries:
|
||||
self.report_retry_fragment(segment_name, count, fragment_retries)
|
||||
self.report_retry_fragment(err, segment_name, count, fragment_retries)
|
||||
if count > fragment_retries:
|
||||
if not fatal:
|
||||
self.report_skip_fragment(segment_name)
|
||||
return True
|
||||
self.report_error('giving up after %s fragment retries' % fragment_retries)
|
||||
return False
|
||||
return True
|
||||
|
||||
if initialization_url:
|
||||
append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init')
|
||||
for i, segment_url in enumerate(segment_urls):
|
||||
append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i)
|
||||
segments_to_download = [(initialization_url, 'Init')] if initialization_url else []
|
||||
segments_to_download.extend([
|
||||
(segment_url, 'Seg%d' % i)
|
||||
for i, segment_url in enumerate(segment_urls)])
|
||||
|
||||
for i, segment in enumerate(segments_to_download):
|
||||
# In DASH, the first segment contains necessary headers to
|
||||
# generate a valid MP4 file, so always abort for the first segment
|
||||
fatal = i == 0 or not skip_unavailable_fragments
|
||||
if not process_segment(segment, ctx['tmpfilename'], fatal):
|
||||
return False
|
||||
|
||||
self._finish_frag_download(ctx)
|
||||
|
||||
|
||||
@ -6,6 +6,7 @@ import time
|
||||
from .common import FileDownloader
|
||||
from .http import HttpFD
|
||||
from ..utils import (
|
||||
error_to_compat_str,
|
||||
encodeFilename,
|
||||
sanitize_open,
|
||||
)
|
||||
@ -22,13 +23,19 @@ class FragmentFD(FileDownloader):
|
||||
|
||||
Available options:
|
||||
|
||||
fragment_retries: Number of times to retry a fragment for HTTP error (DASH only)
|
||||
fragment_retries: Number of times to retry a fragment for HTTP error (DASH
|
||||
and hlsnative only)
|
||||
skip_unavailable_fragments:
|
||||
Skip unavailable fragments (DASH and hlsnative only)
|
||||
"""
|
||||
|
||||
def report_retry_fragment(self, fragment_name, count, retries):
|
||||
def report_retry_fragment(self, err, fragment_name, count, retries):
|
||||
self.to_screen(
|
||||
'[download] Got server HTTP error. Retrying fragment %s (attempt %d of %s)...'
|
||||
% (fragment_name, count, self.format_retries(retries)))
|
||||
'[download] Got server HTTP error: %s. Retrying fragment %s (attempt %d of %s)...'
|
||||
% (error_to_compat_str(err), fragment_name, count, self.format_retries(retries)))
|
||||
|
||||
def report_skip_fragment(self, fragment_name):
|
||||
self.to_screen('[download] Skipping fragment %s...' % fragment_name)
|
||||
|
||||
def _prepare_and_start_frag_download(self, ctx):
|
||||
self._prepare_frag_download(ctx)
|
||||
|
||||
@ -13,6 +13,7 @@ from .fragment import FragmentFD
|
||||
from .external import FFmpegFD
|
||||
|
||||
from ..compat import (
|
||||
compat_urllib_error,
|
||||
compat_urlparse,
|
||||
compat_struct_pack,
|
||||
)
|
||||
@ -83,6 +84,10 @@ class HlsFD(FragmentFD):
|
||||
|
||||
self._prepare_and_start_frag_download(ctx)
|
||||
|
||||
fragment_retries = self.params.get('fragment_retries', 0)
|
||||
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
|
||||
test = self.params.get('test', False)
|
||||
|
||||
extra_query = None
|
||||
extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
|
||||
if extra_param_to_segment_url:
|
||||
@ -99,15 +104,37 @@ class HlsFD(FragmentFD):
|
||||
line
|
||||
if re.match(r'^https?://', line)
|
||||
else compat_urlparse.urljoin(man_url, line))
|
||||
frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
|
||||
frag_name = 'Frag%d' % i
|
||||
frag_filename = '%s-%s' % (ctx['tmpfilename'], frag_name)
|
||||
if extra_query:
|
||||
frag_url = update_url_query(frag_url, extra_query)
|
||||
success = ctx['dl'].download(frag_filename, {'url': frag_url})
|
||||
if not success:
|
||||
count = 0
|
||||
while count <= fragment_retries:
|
||||
try:
|
||||
success = ctx['dl'].download(frag_filename, {'url': frag_url})
|
||||
if not success:
|
||||
return False
|
||||
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
|
||||
frag_content = down.read()
|
||||
down.close()
|
||||
break
|
||||
except compat_urllib_error.HTTPError as err:
|
||||
# Unavailable (possibly temporary) fragments may be served.
|
||||
# First we try to retry then either skip or abort.
|
||||
# See https://github.com/rg3/youtube-dl/issues/10165,
|
||||
# https://github.com/rg3/youtube-dl/issues/10448).
|
||||
count += 1
|
||||
if count <= fragment_retries:
|
||||
self.report_retry_fragment(err, frag_name, count, fragment_retries)
|
||||
if count > fragment_retries:
|
||||
if skip_unavailable_fragments:
|
||||
i += 1
|
||||
media_sequence += 1
|
||||
self.report_skip_fragment(frag_name)
|
||||
continue
|
||||
self.report_error(
|
||||
'giving up after %s fragment retries' % fragment_retries)
|
||||
return False
|
||||
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
|
||||
frag_content = down.read()
|
||||
down.close()
|
||||
if decrypt_info['METHOD'] == 'AES-128':
|
||||
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
|
||||
frag_content = AES.new(
|
||||
@ -115,7 +142,7 @@ class HlsFD(FragmentFD):
|
||||
ctx['dest_stream'].write(frag_content)
|
||||
frags_filenames.append(frag_sanitized)
|
||||
# We only download the first fragment during the test
|
||||
if self.params.get('test', False):
|
||||
if test:
|
||||
break
|
||||
i += 1
|
||||
media_sequence += 1
|
||||
|
||||
@ -13,7 +13,7 @@ from ..utils import (
|
||||
|
||||
class ABCIE(InfoExtractor):
|
||||
IE_NAME = 'abc.net.au'
|
||||
_VALID_URL = r'https?://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
|
||||
@ -100,6 +100,7 @@ class ABCIViewIE(InfoExtractor):
|
||||
IE_NAME = 'abc.net.au:iview'
|
||||
_VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
|
||||
|
||||
# ABC iview programs are normally available for 14 days only.
|
||||
_TESTS = [{
|
||||
'url': 'http://iview.abc.net.au/programs/gardening-australia/FA1505V024S00',
|
||||
'md5': '979d10b2939101f0d27a06b79edad536',
|
||||
@ -112,6 +113,7 @@ class ABCIViewIE(InfoExtractor):
|
||||
'uploader_id': 'abc1',
|
||||
'timestamp': 1471719600,
|
||||
},
|
||||
'skip': 'Video gone',
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -12,7 +12,7 @@ from ..compat import compat_urlparse
|
||||
|
||||
class AbcNewsVideoIE(AMPIE):
|
||||
IE_NAME = 'abcnews:video'
|
||||
_VALID_URL = 'http://abcnews.go.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://abcnews\.go\.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
|
||||
@ -49,7 +49,7 @@ class AbcNewsVideoIE(AMPIE):
|
||||
|
||||
class AbcNewsIE(InfoExtractor):
|
||||
IE_NAME = 'abcnews'
|
||||
_VALID_URL = 'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
|
||||
|
||||
@ -1,13 +1,19 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_iso8601
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
class Abc7NewsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
|
||||
class ABCOTVSIE(InfoExtractor):
|
||||
IE_NAME = 'abcotvs'
|
||||
IE_DESC = 'ABC Owned Television Stations'
|
||||
_VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
|
||||
@ -15,7 +21,7 @@ class Abc7NewsIE(InfoExtractor):
|
||||
'id': '472581',
|
||||
'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
|
||||
'ext': 'mp4',
|
||||
'title': 'East Bay museum celebrates history of synthesized music',
|
||||
'title': 'East Bay museum celebrates vintage synthesizers',
|
||||
'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'timestamp': 1421123075,
|
||||
@ -41,7 +47,7 @@ class Abc7NewsIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
m3u8 = self._html_search_meta(
|
||||
'contentURL', webpage, 'm3u8 url', fatal=True)
|
||||
'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
|
||||
|
||||
formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
@ -66,3 +72,41 @@ class Abc7NewsIE(InfoExtractor):
|
||||
'uploader': uploader,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class ABCOTVSClipsIE(InfoExtractor):
|
||||
IE_NAME = 'abcotvs:clips'
|
||||
_VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'https://clips.abcotvs.com/kabc/video/214814',
|
||||
'info_dict': {
|
||||
'id': '214814',
|
||||
'ext': 'mp4',
|
||||
'title': 'SpaceX launch pad explosion destroys rocket, satellite',
|
||||
'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
|
||||
'upload_date': '20160901',
|
||||
'timestamp': 1472756695,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
|
||||
title = video_data['title']
|
||||
formats = self._extract_m3u8_formats(
|
||||
video_data['videoURL'].split('?')[0], video_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': video_data.get('description'),
|
||||
'thumbnail': video_data.get('thumbnailURL'),
|
||||
'duration': int_or_none(video_data.get('duration')),
|
||||
'timestamp': int_or_none(video_data.get('pubDate')),
|
||||
'formats': formats,
|
||||
}
|
||||
@ -6,13 +6,29 @@ import time
|
||||
import xml.etree.ElementTree as etree
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import (
|
||||
unescapeHTML,
|
||||
urlencode_postdata,
|
||||
unified_timestamp,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
MSO_INFO = {
|
||||
'DTV': {
|
||||
'name': 'DirecTV',
|
||||
'username_field': 'username',
|
||||
'password_field': 'password',
|
||||
},
|
||||
'Rogers': {
|
||||
'name': 'Rogers Cable',
|
||||
'username_field': 'UserName',
|
||||
'password_field': 'UserPassword',
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
class AdobePassIE(InfoExtractor):
|
||||
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
|
||||
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
|
||||
@ -41,6 +57,24 @@ class AdobePassIE(InfoExtractor):
|
||||
token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele)))
|
||||
return token_expires and token_expires <= int(time.time())
|
||||
|
||||
def post_form(form_page_res, note, data={}):
|
||||
form_page, urlh = form_page_res
|
||||
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
|
||||
if not re.match(r'https?://', post_url):
|
||||
post_url = compat_urlparse.urljoin(urlh.geturl(), post_url)
|
||||
form_data = self._hidden_inputs(form_page)
|
||||
form_data.update(data)
|
||||
return self._download_webpage_handle(
|
||||
post_url, video_id, note, data=urlencode_postdata(form_data), headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded',
|
||||
})
|
||||
|
||||
def raise_mvpd_required():
|
||||
raise ExtractorError(
|
||||
'This video is only available for users of participating TV providers. '
|
||||
'Use --ap-mso to specify Adobe Pass Multiple-system operator Identifier '
|
||||
'and --ap-username and --ap-password or --netrc to provide account credentials.', expected=True)
|
||||
|
||||
mvpd_headers = {
|
||||
'ap_42': 'anonymous',
|
||||
'ap_11': 'Linux i686',
|
||||
@ -49,89 +83,91 @@ class AdobePassIE(InfoExtractor):
|
||||
}
|
||||
|
||||
guid = xml_text(resource, 'guid')
|
||||
requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {}
|
||||
authn_token = requestor_info.get('authn_token')
|
||||
if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
|
||||
authn_token = None
|
||||
if not authn_token:
|
||||
# TODO add support for other TV Providers
|
||||
mso_id = 'DTV'
|
||||
username, password = self._get_netrc_login_info(mso_id)
|
||||
if not username or not password:
|
||||
return ''
|
||||
count = 0
|
||||
while count < 2:
|
||||
requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {}
|
||||
authn_token = requestor_info.get('authn_token')
|
||||
if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
|
||||
authn_token = None
|
||||
if not authn_token:
|
||||
# TODO add support for other TV Providers
|
||||
mso_id = self._downloader.params.get('ap_mso')
|
||||
if not mso_id:
|
||||
raise_mvpd_required()
|
||||
username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
|
||||
if not username or not password:
|
||||
raise_mvpd_required()
|
||||
mso_info = MSO_INFO[mso_id]
|
||||
|
||||
def post_form(form_page, note, data={}):
|
||||
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
|
||||
return self._download_webpage(
|
||||
post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded',
|
||||
provider_redirect_page_res = self._download_webpage_handle(
|
||||
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
|
||||
'Downloading Provider Redirect Page', query={
|
||||
'noflash': 'true',
|
||||
'mso_id': mso_id,
|
||||
'requestor_id': requestor_id,
|
||||
'no_iframe': 'false',
|
||||
'domain_name': 'adobe.com',
|
||||
'redirect_url': url,
|
||||
})
|
||||
|
||||
provider_redirect_page = self._download_webpage(
|
||||
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
|
||||
'Downloading Provider Redirect Page', query={
|
||||
'noflash': 'true',
|
||||
'mso_id': mso_id,
|
||||
'requestor_id': requestor_id,
|
||||
'no_iframe': 'false',
|
||||
'domain_name': 'adobe.com',
|
||||
'redirect_url': url,
|
||||
provider_login_page_res = post_form(
|
||||
provider_redirect_page_res, 'Downloading Provider Login Page')
|
||||
mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', {
|
||||
mso_info['username_field']: username,
|
||||
mso_info['password_field']: password,
|
||||
})
|
||||
provider_login_page = post_form(
|
||||
provider_redirect_page, 'Downloading Provider Login Page')
|
||||
mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
|
||||
'username': username,
|
||||
'password': password,
|
||||
if mso_id == 'DTV':
|
||||
post_form(mvpd_confirm_page_res, 'Confirming Login')
|
||||
|
||||
session = self._download_webpage(
|
||||
self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
|
||||
'Retrieving Session', data=urlencode_postdata({
|
||||
'_method': 'GET',
|
||||
'requestor_id': requestor_id,
|
||||
}), headers=mvpd_headers)
|
||||
if '<pendingLogout' in session:
|
||||
self._downloader.cache.store('mvpd', requestor_id, {})
|
||||
count += 1
|
||||
continue
|
||||
authn_token = unescapeHTML(xml_text(session, 'authnToken'))
|
||||
requestor_info['authn_token'] = authn_token
|
||||
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
|
||||
|
||||
authz_token = requestor_info.get(guid)
|
||||
if authz_token and is_expired(authz_token, 'simpleTokenTTL'):
|
||||
authz_token = None
|
||||
if not authz_token:
|
||||
authorize = self._download_webpage(
|
||||
self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
|
||||
'Retrieving Authorization Token', data=urlencode_postdata({
|
||||
'resource_id': resource,
|
||||
'requestor_id': requestor_id,
|
||||
'authentication_token': authn_token,
|
||||
'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
|
||||
'userMeta': '1',
|
||||
}), headers=mvpd_headers)
|
||||
if '<pendingLogout' in authorize:
|
||||
self._downloader.cache.store('mvpd', requestor_id, {})
|
||||
count += 1
|
||||
continue
|
||||
authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
|
||||
requestor_info[guid] = authz_token
|
||||
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
|
||||
|
||||
mvpd_headers.update({
|
||||
'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
|
||||
'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
|
||||
})
|
||||
post_form(mvpd_confirm_page, 'Confirming Login')
|
||||
|
||||
session = self._download_webpage(
|
||||
self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
|
||||
'Retrieving Session', data=urlencode_postdata({
|
||||
'_method': 'GET',
|
||||
short_authorize = self._download_webpage(
|
||||
self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
|
||||
video_id, 'Retrieving Media Token', data=urlencode_postdata({
|
||||
'authz_token': authz_token,
|
||||
'requestor_id': requestor_id,
|
||||
'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
|
||||
'hashed_guid': 'false',
|
||||
}), headers=mvpd_headers)
|
||||
if '<pendingLogout' in session:
|
||||
if '<pendingLogout' in short_authorize:
|
||||
self._downloader.cache.store('mvpd', requestor_id, {})
|
||||
return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
|
||||
authn_token = unescapeHTML(xml_text(session, 'authnToken'))
|
||||
requestor_info['authn_token'] = authn_token
|
||||
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
|
||||
|
||||
authz_token = requestor_info.get(guid)
|
||||
if authz_token and is_expired(authz_token, 'simpleTokenTTL'):
|
||||
authz_token = None
|
||||
if not authz_token:
|
||||
authorize = self._download_webpage(
|
||||
self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
|
||||
'Retrieving Authorization Token', data=urlencode_postdata({
|
||||
'resource_id': resource,
|
||||
'requestor_id': requestor_id,
|
||||
'authentication_token': authn_token,
|
||||
'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
|
||||
'userMeta': '1',
|
||||
}), headers=mvpd_headers)
|
||||
if '<pendingLogout' in authorize:
|
||||
self._downloader.cache.store('mvpd', requestor_id, {})
|
||||
return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
|
||||
authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
|
||||
requestor_info[guid] = authz_token
|
||||
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
|
||||
|
||||
mvpd_headers.update({
|
||||
'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
|
||||
'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
|
||||
})
|
||||
|
||||
short_authorize = self._download_webpage(
|
||||
self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
|
||||
video_id, 'Retrieving Media Token', data=urlencode_postdata({
|
||||
'authz_token': authz_token,
|
||||
'requestor_id': requestor_id,
|
||||
'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
|
||||
'hashed_guid': 'false',
|
||||
}), headers=mvpd_headers)
|
||||
if '<pendingLogout' in short_authorize:
|
||||
self._downloader.cache.store('mvpd', requestor_id, {})
|
||||
return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
|
||||
return short_authorize
|
||||
count += 1
|
||||
continue
|
||||
return short_authorize
|
||||
|
||||
@ -4,7 +4,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class AlJazeeraIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
|
||||
|
||||
@ -238,7 +238,7 @@ class ARDMediathekIE(InfoExtractor):
|
||||
|
||||
|
||||
class ARDIE(InfoExtractor):
|
||||
_VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
|
||||
_VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
|
||||
_TEST = {
|
||||
'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
|
||||
'md5': 'd216c3a86493f9322545e045ddc3eb35',
|
||||
|
||||
@ -103,7 +103,7 @@ class AzubuIE(InfoExtractor):
|
||||
|
||||
|
||||
class AzubuLiveIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www.azubu.tv/(?P<id>[^/]+)$'
|
||||
_VALID_URL = r'https?://(?:www\.)?azubu\.tv/(?P<id>[^/]+)$'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.azubu.tv/MarsTVMDLen',
|
||||
|
||||
@ -1028,7 +1028,7 @@ class BBCIE(BBCCoUkIE):
|
||||
|
||||
|
||||
class BBCCoUkArticleIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
|
||||
IE_NAME = 'bbc.co.uk:article'
|
||||
IE_DESC = 'BBC articles'
|
||||
|
||||
|
||||
@ -6,8 +6,25 @@ import re
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class CTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<domain>ctv|tsn|bnn|thecomedynetwork)\.ca/.*?(?:\bvid=|-vid|~|%7E)(?P<id>[0-9.]+)'
|
||||
class BellMediaIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?
|
||||
(?P<domain>
|
||||
(?:
|
||||
ctv|
|
||||
tsn|
|
||||
bnn|
|
||||
thecomedynetwork|
|
||||
discovery|
|
||||
discoveryvelocity|
|
||||
sciencechannel|
|
||||
investigationdiscovery|
|
||||
animalplanet|
|
||||
bravo|
|
||||
mtv|
|
||||
space
|
||||
)\.ca|
|
||||
much\.com
|
||||
)/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6})'''
|
||||
_TESTS = [{
|
||||
'url': 'http://www.ctv.ca/video/player?vid=706966',
|
||||
'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
|
||||
@ -32,15 +49,27 @@ class CTVIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_DOMAINS = {
|
||||
'thecomedynetwork': 'comedy',
|
||||
'discoveryvelocity': 'discvel',
|
||||
'sciencechannel': 'discsci',
|
||||
'investigationdiscovery': 'invdisc',
|
||||
'animalplanet': 'aniplan',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
domain, video_id = re.match(self._VALID_URL, url).groups()
|
||||
if domain == 'thecomedynetwork':
|
||||
domain = 'comedy'
|
||||
domain = domain.split('.')[0]
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'url': '9c9media:%s_web:%s' % (domain, video_id),
|
||||
'url': '9c9media:%s_web:%s' % (self._DOMAINS.get(domain, domain), video_id),
|
||||
'ie_key': 'NineCNineMedia',
|
||||
}
|
||||
@ -10,13 +10,14 @@ from ..utils import (
|
||||
int_or_none,
|
||||
float_or_none,
|
||||
unified_timestamp,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class BiliBiliIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/v/)(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
_TEST = {
|
||||
'url': 'http://www.bilibili.tv/video/av1074402/',
|
||||
'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
|
||||
'info_dict': {
|
||||
@ -31,66 +32,26 @@ class BiliBiliIE(InfoExtractor):
|
||||
'uploader': '菊子桑',
|
||||
'uploader_id': '156160',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.bilibili.com/video/av1041170/',
|
||||
'info_dict': {
|
||||
'id': '1041170',
|
||||
'ext': 'mp4',
|
||||
'title': '【BD1080P】刀语【诸神&异域】',
|
||||
'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
|
||||
'duration': 3382.259,
|
||||
'timestamp': 1396530060,
|
||||
'upload_date': '20140403',
|
||||
'thumbnail': 're:^https?://.+\.jpg',
|
||||
'uploader': '枫叶逝去',
|
||||
'uploader_id': '520116',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.bilibili.com/video/av4808130/',
|
||||
'info_dict': {
|
||||
'id': '4808130',
|
||||
'ext': 'mp4',
|
||||
'title': '【长篇】哆啦A梦443【钉铛】',
|
||||
'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929',
|
||||
'duration': 1493.995,
|
||||
'timestamp': 1464564180,
|
||||
'upload_date': '20160529',
|
||||
'thumbnail': 're:^https?://.+\.jpg',
|
||||
'uploader': '喜欢拉面',
|
||||
'uploader_id': '151066',
|
||||
},
|
||||
}, {
|
||||
# Missing upload time
|
||||
'url': 'http://www.bilibili.com/video/av1867637/',
|
||||
'info_dict': {
|
||||
'id': '1867637',
|
||||
'ext': 'mp4',
|
||||
'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】',
|
||||
'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
|
||||
'duration': 5760.0,
|
||||
'uploader': '黑夜为猫',
|
||||
'uploader_id': '610729',
|
||||
'thumbnail': 're:^https?://.+\.jpg',
|
||||
},
|
||||
'params': {
|
||||
# Just to test metadata extraction
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['upload time'],
|
||||
}]
|
||||
}
|
||||
|
||||
_APP_KEY = '6f90a59ac58a4123'
|
||||
_BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
cid = compat_parse_qs(self._search_regex(
|
||||
[r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
|
||||
r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
|
||||
webpage, 'player parameters'))['cid'][0]
|
||||
if 'anime/v' not in url:
|
||||
cid = compat_parse_qs(self._search_regex(
|
||||
[r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
|
||||
r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
|
||||
webpage, 'player parameters'))['cid'][0]
|
||||
else:
|
||||
js = self._download_json(
|
||||
'http://bangumi.bilibili.com/web_api/get_source', video_id,
|
||||
data=urlencode_postdata({'episode_id': video_id}),
|
||||
headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'})
|
||||
cid = js['result']['cid']
|
||||
|
||||
payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
|
||||
sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
|
||||
@ -106,7 +67,7 @@ class BiliBiliIE(InfoExtractor):
|
||||
'url': durl['url'],
|
||||
'filesize': int_or_none(durl['size']),
|
||||
}]
|
||||
for backup_url in durl['backup_url']:
|
||||
for backup_url in durl.get('backup_url', []):
|
||||
formats.append({
|
||||
'url': backup_url,
|
||||
# backup URLs have lower priorities
|
||||
@ -125,6 +86,7 @@ class BiliBiliIE(InfoExtractor):
|
||||
description = self._html_search_meta('description', webpage)
|
||||
timestamp = unified_timestamp(self._html_search_regex(
|
||||
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
|
||||
thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
|
||||
|
||||
# TODO 'view_count' requires deobfuscating Javascript
|
||||
info = {
|
||||
@ -132,7 +94,7 @@ class BiliBiliIE(InfoExtractor):
|
||||
'title': title,
|
||||
'description': description,
|
||||
'timestamp': timestamp,
|
||||
'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
|
||||
'thumbnail': thumbnail,
|
||||
'duration': float_or_none(video_info.get('timelength'), scale=1000),
|
||||
}
|
||||
|
||||
|
||||
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
class BpbIE(InfoExtractor):
|
||||
IE_DESC = 'Bundeszentrale für politische Bildung'
|
||||
_VALID_URL = r'https?://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
|
||||
_VALID_URL = r'https?://(?:www\.)?bpb\.de/mediathek/(?P<id>[0-9]+)/'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
|
||||
|
||||
@ -112,7 +112,7 @@ class CamdemyIE(InfoExtractor):
|
||||
|
||||
|
||||
class CamdemyFolderIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?camdemy\.com/folder/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
# links with trailing slash
|
||||
'url': 'http://www.camdemy.com/folder/450',
|
||||
|
||||
@ -23,6 +23,7 @@ class CanalplusIE(InfoExtractor):
|
||||
(?:(?:www|m)\.)?canalplus\.fr|
|
||||
(?:www\.)?piwiplus\.fr|
|
||||
(?:www\.)?d8\.tv|
|
||||
(?:www\.)?c8\.fr|
|
||||
(?:www\.)?d17\.tv|
|
||||
(?:www\.)?itele\.fr
|
||||
)/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
|
||||
@ -35,6 +36,7 @@ class CanalplusIE(InfoExtractor):
|
||||
'canalplus': 'cplus',
|
||||
'piwiplus': 'teletoon',
|
||||
'd8': 'd8',
|
||||
'c8': 'd8',
|
||||
'd17': 'd17',
|
||||
'itele': 'itele',
|
||||
}
|
||||
|
||||
@ -1,11 +1,13 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import float_or_none
|
||||
|
||||
|
||||
class CanvasIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
|
||||
'md5': 'ea838375a547ac787d4064d8c7860a6c',
|
||||
@ -38,22 +40,42 @@ class CanvasIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles',
|
||||
'info_dict': {
|
||||
'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f',
|
||||
'display_id': 'herbekijk-sorry-voor-alles',
|
||||
'ext': 'mp4',
|
||||
'title': 'Herbekijk Sorry voor alles',
|
||||
'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'duration': 3788.06,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
site_id, display_id = mobj.group('site_id'), mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
title = self._search_regex(
|
||||
title = (self._search_regex(
|
||||
r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
|
||||
webpage, 'title', default=None) or self._og_search_title(webpage)
|
||||
webpage, 'title', default=None) or self._og_search_title(
|
||||
webpage)).strip()
|
||||
|
||||
video_id = self._html_search_regex(
|
||||
r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id')
|
||||
|
||||
data = self._download_json(
|
||||
'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id)
|
||||
'https://mediazone.vrt.be/api/v1/%s/assets/%s'
|
||||
% (site_id, video_id), display_id)
|
||||
|
||||
formats = []
|
||||
for target in data['targetUrls']:
|
||||
|
||||
@ -30,7 +30,7 @@ class CartoonNetworkIE(TurnerBaseIE):
|
||||
return self._extract_cvp_info(
|
||||
'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
|
||||
'secure': {
|
||||
'media_src': 'http://apple-secure.cdn.turner.com/toon/big',
|
||||
'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
|
||||
'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
|
||||
},
|
||||
})
|
||||
|
||||
@ -4,7 +4,7 @@ from .cbs import CBSBaseIE
|
||||
|
||||
|
||||
class CBSSportsIE(CBSBaseIE):
|
||||
_VALID_URL = r'https?://www\.cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast',
|
||||
|
||||
53
youtube_dl/extractor/cctv.py
Normal file
53
youtube_dl/extractor/cctv.py
Normal file
@ -0,0 +1,53 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import float_or_none
|
||||
|
||||
|
||||
class CCTVIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:.+?\.)?
|
||||
(?:
|
||||
cctv\.(?:com|cn)|
|
||||
cntv\.cn
|
||||
)/
|
||||
(?:
|
||||
video/[^/]+/(?P<id>[0-9a-f]{32})|
|
||||
\d{4}/\d{2}/\d{2}/(?P<display_id>VID[0-9A-Za-z]+)
|
||||
)'''
|
||||
_TESTS = [{
|
||||
'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
|
||||
'md5': '819c7b49fc3927d529fb4cd555621823',
|
||||
'info_dict': {
|
||||
'id': '454368eb19ad44a1925bf1eb96140a61',
|
||||
'ext': 'mp4',
|
||||
'title': 'Portrait of Real Current Life 09/03/2016 Modern Inventors Part 1',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
if not video_id:
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._search_regex(
|
||||
r'(?:fo\.addVariable\("videoCenterId",\s*|guid\s*=\s*)"([0-9a-f]{32})',
|
||||
webpage, 'video_id')
|
||||
api_data = self._download_json(
|
||||
'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + video_id, video_id)
|
||||
m3u8_url = re.sub(r'maxbr=\d+&?', '', api_data['hls_url'])
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': api_data['title'],
|
||||
'formats': self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False),
|
||||
'duration': float_or_none(api_data.get('video', {}).get('totalLength')),
|
||||
}
|
||||
@ -17,7 +17,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class CeskaTelevizeIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
|
||||
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
|
||||
'info_dict': {
|
||||
|
||||
@ -65,7 +65,7 @@ class ChirbitIE(InfoExtractor):
|
||||
|
||||
class ChirbitProfileIE(InfoExtractor):
|
||||
IE_NAME = 'chirbit:profile'
|
||||
_VALID_URL = r'https?://(?:www\.)?chirbit.com/(?:rss/)?(?P<id>[^/]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?chirbit\.com/(?:rss/)?(?P<id>[^/]+)'
|
||||
_TEST = {
|
||||
'url': 'http://chirbit.com/ScarletBeauty',
|
||||
'info_dict': {
|
||||
|
||||
@ -6,7 +6,7 @@ from ..utils import ExtractorError
|
||||
|
||||
class CMTIE(MTVIE):
|
||||
IE_NAME = 'cmt.com'
|
||||
_VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
|
||||
_FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
|
||||
|
||||
_TESTS = [{
|
||||
|
||||
@ -680,7 +680,7 @@ class InfoExtractor(object):
|
||||
|
||||
return (username, password)
|
||||
|
||||
def _get_login_info(self):
|
||||
def _get_login_info(self, username_option='username', password_option='password', netrc_machine=None):
|
||||
"""
|
||||
Get the login info as (username, password)
|
||||
It will look in the netrc file using the _NETRC_MACHINE value
|
||||
@ -694,11 +694,11 @@ class InfoExtractor(object):
|
||||
downloader_params = self._downloader.params
|
||||
|
||||
# Attempt to use provided username and password or .netrc data
|
||||
if downloader_params.get('username') is not None:
|
||||
username = downloader_params['username']
|
||||
password = downloader_params['password']
|
||||
if downloader_params.get(username_option) is not None:
|
||||
username = downloader_params[username_option]
|
||||
password = downloader_params[password_option]
|
||||
else:
|
||||
username, password = self._get_netrc_login_info()
|
||||
username, password = self._get_netrc_login_info(netrc_machine)
|
||||
|
||||
return (username, password)
|
||||
|
||||
@ -1163,13 +1163,6 @@ class InfoExtractor(object):
|
||||
m3u8_id=None, note=None, errnote=None,
|
||||
fatal=True, live=False):
|
||||
|
||||
formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
|
||||
|
||||
format_url = lambda u: (
|
||||
u
|
||||
if re.match(r'^https?://', u)
|
||||
else compat_urlparse.urljoin(m3u8_url, u))
|
||||
|
||||
res = self._download_webpage_handle(
|
||||
m3u8_url, video_id,
|
||||
note=note or 'Downloading m3u8 information',
|
||||
@ -1180,6 +1173,13 @@ class InfoExtractor(object):
|
||||
m3u8_doc, urlh = res
|
||||
m3u8_url = urlh.geturl()
|
||||
|
||||
formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
|
||||
|
||||
format_url = lambda u: (
|
||||
u
|
||||
if re.match(r'^https?://', u)
|
||||
else compat_urlparse.urljoin(m3u8_url, u))
|
||||
|
||||
# We should try extracting formats only from master playlists [1], i.e.
|
||||
# playlists that describe available qualities. On the other hand media
|
||||
# playlists [2] should be returned as is since they contain just the media
|
||||
@ -1749,7 +1749,7 @@ class InfoExtractor(object):
|
||||
media_attributes = extract_attributes(media_tag)
|
||||
src = media_attributes.get('src')
|
||||
if src:
|
||||
_, formats = _media_formats(src)
|
||||
_, formats = _media_formats(src, media_type)
|
||||
media_info['formats'].extend(formats)
|
||||
media_info['thumbnail'] = media_attributes.get('poster')
|
||||
if media_content:
|
||||
|
||||
@ -7,7 +7,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class CriterionIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
|
||||
_VALID_URL = r'https?://(?:www\.)?criterion\.com/films/(?P<id>[0-9]+)-.+'
|
||||
_TEST = {
|
||||
'url': 'http://www.criterion.com/films/184-le-samourai',
|
||||
'md5': 'bc51beba55685509883a9a7830919ec3',
|
||||
|
||||
@ -394,7 +394,7 @@ class DailymotionUserIE(DailymotionPlaylistIE):
|
||||
|
||||
|
||||
class DailymotionCloudIE(DailymotionBaseInfoExtractor):
|
||||
_VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
|
||||
_VALID_URL_PREFIX = r'https?://api\.dmcloud\.net/(?:player/)?embed/'
|
||||
_VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
|
||||
_VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
|
||||
|
||||
|
||||
@ -6,7 +6,7 @@ from ..compat import compat_str
|
||||
|
||||
|
||||
class DctpTvIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
|
||||
_VALID_URL = r'https?://(?:www\.)?dctp\.tv/(#/)?filme/(?P<id>.+?)/$'
|
||||
_TEST = {
|
||||
'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
|
||||
'info_dict': {
|
||||
|
||||
@ -13,7 +13,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class DemocracynowIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
|
||||
_VALID_URL = r'https?://(?:www\.)?democracynow\.org/(?P<id>[^\?]*)'
|
||||
IE_NAME = 'democracynow'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.democracynow.org/shows/2015/7/3',
|
||||
|
||||
@ -4,26 +4,45 @@ from __future__ import unicode_literals
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
float_or_none,
|
||||
mimetype2ext,
|
||||
parse_iso8601,
|
||||
remove_end,
|
||||
)
|
||||
|
||||
|
||||
class DRTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
|
||||
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
|
||||
'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
|
||||
_TESTS = [{
|
||||
'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
|
||||
'md5': '25e659cccc9a2ed956110a299fdf5983',
|
||||
'info_dict': {
|
||||
'id': 'panisk-paske-5',
|
||||
'id': 'klassen-darlig-taber-10',
|
||||
'ext': 'mp4',
|
||||
'title': 'Panisk Påske (5)',
|
||||
'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
|
||||
'timestamp': 1426984612,
|
||||
'upload_date': '20150322',
|
||||
'duration': 1455,
|
||||
'title': 'Klassen - Dårlig taber (10)',
|
||||
'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
|
||||
'timestamp': 1471991907,
|
||||
'upload_date': '20160823',
|
||||
'duration': 606.84,
|
||||
},
|
||||
}
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
|
||||
'md5': '2c37175c718155930f939ef59952474a',
|
||||
'info_dict': {
|
||||
'id': 'christiania-pusher-street-ryddes-drdkrjpo',
|
||||
'ext': 'mp4',
|
||||
'title': 'LIVE Christianias rydning af Pusher Street er i gang',
|
||||
'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
|
||||
'timestamp': 1472800279,
|
||||
'upload_date': '20160902',
|
||||
'duration': 131.4,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
@ -35,7 +54,8 @@ class DRTVIE(InfoExtractor):
|
||||
'Video %s is not available' % video_id, expected=True)
|
||||
|
||||
video_id = self._search_regex(
|
||||
r'data-(?:material-identifier|episode-slug)="([^"]+)"',
|
||||
(r'data-(?:material-identifier|episode-slug)="([^"]+)"',
|
||||
r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
|
||||
webpage, 'video id')
|
||||
|
||||
programcard = self._download_json(
|
||||
@ -43,9 +63,12 @@ class DRTVIE(InfoExtractor):
|
||||
video_id, 'Downloading video JSON')
|
||||
data = programcard['Data'][0]
|
||||
|
||||
title = data['Title']
|
||||
description = data['Description']
|
||||
timestamp = parse_iso8601(data['CreatedTime'])
|
||||
title = remove_end(self._og_search_title(
|
||||
webpage, default=None), ' | TV | DR') or data['Title']
|
||||
description = self._og_search_description(
|
||||
webpage, default=None) or data.get('Description')
|
||||
|
||||
timestamp = parse_iso8601(data.get('CreatedTime'))
|
||||
|
||||
thumbnail = None
|
||||
duration = None
|
||||
@ -56,16 +79,18 @@ class DRTVIE(InfoExtractor):
|
||||
subtitles = {}
|
||||
|
||||
for asset in data['Assets']:
|
||||
if asset['Kind'] == 'Image':
|
||||
thumbnail = asset['Uri']
|
||||
elif asset['Kind'] == 'VideoResource':
|
||||
duration = asset['DurationInMilliseconds'] / 1000.0
|
||||
restricted_to_denmark = asset['RestrictedToDenmark']
|
||||
spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
|
||||
for link in asset['Links']:
|
||||
uri = link['Uri']
|
||||
target = link['Target']
|
||||
format_id = target
|
||||
if asset.get('Kind') == 'Image':
|
||||
thumbnail = asset.get('Uri')
|
||||
elif asset.get('Kind') == 'VideoResource':
|
||||
duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
|
||||
restricted_to_denmark = asset.get('RestrictedToDenmark')
|
||||
spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
|
||||
for link in asset.get('Links', []):
|
||||
uri = link.get('Uri')
|
||||
if not uri:
|
||||
continue
|
||||
target = link.get('Target')
|
||||
format_id = target or ''
|
||||
preference = None
|
||||
if spoken_subtitles:
|
||||
preference = -1
|
||||
@ -76,8 +101,8 @@ class DRTVIE(InfoExtractor):
|
||||
video_id, preference, f4m_id=format_id))
|
||||
elif target == 'HLS':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
uri, video_id, 'mp4', preference=preference,
|
||||
m3u8_id=format_id))
|
||||
uri, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
preference=preference, m3u8_id=format_id))
|
||||
else:
|
||||
bitrate = link.get('Bitrate')
|
||||
if bitrate:
|
||||
@ -85,7 +110,7 @@ class DRTVIE(InfoExtractor):
|
||||
formats.append({
|
||||
'url': uri,
|
||||
'format_id': format_id,
|
||||
'tbr': bitrate,
|
||||
'tbr': int_or_none(bitrate),
|
||||
'ext': link.get('FileFormat'),
|
||||
})
|
||||
subtitles_list = asset.get('SubtitlesList')
|
||||
@ -94,12 +119,18 @@ class DRTVIE(InfoExtractor):
|
||||
'Danish': 'da',
|
||||
}
|
||||
for subs in subtitles_list:
|
||||
lang = subs['Language']
|
||||
subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
|
||||
if not subs.get('Uri'):
|
||||
continue
|
||||
lang = subs.get('Language') or 'da'
|
||||
subtitles.setdefault(LANGS.get(lang, lang), []).append({
|
||||
'url': subs['Uri'],
|
||||
'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
|
||||
})
|
||||
|
||||
if not formats and restricted_to_denmark:
|
||||
raise ExtractorError(
|
||||
'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
|
||||
self.raise_geo_restricted(
|
||||
'Unfortunately, DR is not allowed to show this program outside Denmark.',
|
||||
expected=True)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
||||
@ -4,7 +4,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class EngadgetIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www.engadget.com/video/(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?engadget\.com/video/(?P<id>[^/?#]+)'
|
||||
|
||||
_TESTS = [{
|
||||
# video with 5min ID
|
||||
|
||||
@ -5,7 +5,7 @@ from ..utils import remove_end
|
||||
|
||||
|
||||
class ESPNIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)'
|
||||
_VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://espn.go.com/video/clip?id=10365079',
|
||||
'md5': '60e5d097a523e767d06479335d1bdc58',
|
||||
@ -47,6 +47,9 @@ class ESPNIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.espn.com/video/clip?id=10365079',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -8,7 +8,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class ExpoTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
|
||||
_VALID_URL = r'https?://(?:www\.)?expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
|
||||
_TEST = {
|
||||
'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916',
|
||||
'md5': 'fe1d728c3a813ff78f595bc8b7a707a8',
|
||||
|
||||
@ -5,11 +5,14 @@ from .abc import (
|
||||
ABCIE,
|
||||
ABCIViewIE,
|
||||
)
|
||||
from .abc7news import Abc7NewsIE
|
||||
from .abcnews import (
|
||||
AbcNewsIE,
|
||||
AbcNewsVideoIE,
|
||||
)
|
||||
from .abcotvs import (
|
||||
ABCOTVSIE,
|
||||
ABCOTVSClipsIE,
|
||||
)
|
||||
from .academicearth import AcademicEarthCourseIE
|
||||
from .acast import (
|
||||
ACastIE,
|
||||
@ -90,6 +93,7 @@ from .bbc import (
|
||||
)
|
||||
from .beeg import BeegIE
|
||||
from .behindkink import BehindKinkIE
|
||||
from .bellmedia import BellMediaIE
|
||||
from .beatportpro import BeatportProIE
|
||||
from .bet import BetIE
|
||||
from .bigflix import BigflixIE
|
||||
@ -143,6 +147,7 @@ from .cbsnews import (
|
||||
)
|
||||
from .cbssports import CBSSportsIE
|
||||
from .ccc import CCCIE
|
||||
from .cctv import CCTVIE
|
||||
from .cda import CDAIE
|
||||
from .ceskatelevize import CeskaTelevizeIE
|
||||
from .channel9 import Channel9IE
|
||||
@ -191,7 +196,6 @@ from .crunchyroll import (
|
||||
)
|
||||
from .cspan import CSpanIE
|
||||
from .ctsnews import CtsNewsIE
|
||||
from .ctv import CTVIE
|
||||
from .ctvnews import CTVNewsIE
|
||||
from .cultureunplugged import CultureUnpluggedIE
|
||||
from .curiositystream import (
|
||||
@ -264,9 +268,15 @@ from .everyonesmixtape import EveryonesMixtapeIE
|
||||
from .expotv import ExpoTVIE
|
||||
from .extremetube import ExtremeTubeIE
|
||||
from .eyedotv import EyedoTVIE
|
||||
from .facebook import FacebookIE
|
||||
from .facebook import (
|
||||
FacebookIE,
|
||||
FacebookPluginsVideoIE,
|
||||
)
|
||||
from .faz import FazIE
|
||||
from .fc2 import FC2IE
|
||||
from .fc2 import (
|
||||
FC2IE,
|
||||
FC2EmbedIE,
|
||||
)
|
||||
from .fczenit import FczenitIE
|
||||
from .firstpost import FirstpostIE
|
||||
from .firsttv import FirstTVIE
|
||||
@ -281,7 +291,11 @@ from .formula1 import Formula1IE
|
||||
from .fourtube import FourTubeIE
|
||||
from .fox import FOXIE
|
||||
from .foxgay import FoxgayIE
|
||||
from .foxnews import FoxNewsIE
|
||||
from .foxnews import (
|
||||
FoxNewsIE,
|
||||
FoxNewsArticleIE,
|
||||
FoxNewsInsiderIE,
|
||||
)
|
||||
from .foxsports import FoxSportsIE
|
||||
from .franceculture import FranceCultureIE
|
||||
from .franceinter import FranceInterIE
|
||||
@ -382,6 +396,7 @@ from .ivi import (
|
||||
IviCompilationIE
|
||||
)
|
||||
from .ivideon import IvideonIE
|
||||
from .iwara import IwaraIE
|
||||
from .izlesene import IzleseneIE
|
||||
from .jeuxvideo import JeuxVideoIE
|
||||
from .jove import JoveIE
|
||||
@ -394,6 +409,7 @@ from .kankan import KankanIE
|
||||
from .karaoketv import KaraoketvIE
|
||||
from .karrierevideos import KarriereVideosIE
|
||||
from .keezmovies import KeezMoviesIE
|
||||
from .ketnet import KetnetIE
|
||||
from .khanacademy import KhanAcademyIE
|
||||
from .kickstarter import KickStarterIE
|
||||
from .keek import KeekIE
|
||||
@ -412,6 +428,7 @@ from .kuwo import (
|
||||
)
|
||||
from .la7 import LA7IE
|
||||
from .laola1tv import Laola1TvIE
|
||||
from .lci import LCIIE
|
||||
from .lcp import (
|
||||
LcpPlayIE,
|
||||
LcpIE,
|
||||
@ -462,6 +479,7 @@ from .metacafe import MetacafeIE
|
||||
from .metacritic import MetacriticIE
|
||||
from .mgoon import MgoonIE
|
||||
from .mgtv import MGTVIE
|
||||
from .miaopai import MiaoPaiIE
|
||||
from .microsoftvirtualacademy import (
|
||||
MicrosoftVirtualAcademyIE,
|
||||
MicrosoftVirtualAcademyCourseIE,
|
||||
@ -516,6 +534,7 @@ from .nbc import (
|
||||
CSNNEIE,
|
||||
NBCIE,
|
||||
NBCNewsIE,
|
||||
NBCOlympicsIE,
|
||||
NBCSportsIE,
|
||||
NBCSportsVPlayerIE,
|
||||
)
|
||||
@ -655,7 +674,10 @@ from .pluralsight import (
|
||||
)
|
||||
from .podomatic import PodomaticIE
|
||||
from .pokemon import PokemonIE
|
||||
from .polskieradio import PolskieRadioIE
|
||||
from .polskieradio import (
|
||||
PolskieRadioIE,
|
||||
PolskieRadioCategoryIE,
|
||||
)
|
||||
from .porn91 import Porn91IE
|
||||
from .porncom import PornComIE
|
||||
from .pornhd import PornHdIE
|
||||
@ -709,6 +731,7 @@ from .revision3 import (
|
||||
)
|
||||
from .rice import RICEIE
|
||||
from .ringtv import RingTVIE
|
||||
from .rmcdecouverte import RMCDecouverteIE
|
||||
from .ro220 import Ro220IE
|
||||
from .rockstargames import RockstarGamesIE
|
||||
from .roosterteeth import RoosterTeethIE
|
||||
@ -845,10 +868,12 @@ from .telebruxelles import TeleBruxellesIE
|
||||
from .telecinco import TelecincoIE
|
||||
from .telegraaf import TelegraafIE
|
||||
from .telemb import TeleMBIE
|
||||
from .telequebec import TeleQuebecIE
|
||||
from .teletask import TeleTaskIE
|
||||
from .telewebion import TelewebionIE
|
||||
from .testurl import TestURLIE
|
||||
from .tf1 import TF1IE
|
||||
from .tfo import TFOIE
|
||||
from .theintercept import TheInterceptIE
|
||||
from .theplatform import (
|
||||
ThePlatformIE,
|
||||
@ -877,7 +902,7 @@ from .toutv import TouTvIE
|
||||
from .toypics import ToypicsUserIE, ToypicsIE
|
||||
from .traileraddict import TrailerAddictIE
|
||||
from .trilulilu import TriluliluIE
|
||||
from .trollvids import TrollvidsIE
|
||||
from .trutv import TruTVIE
|
||||
from .tube8 import Tube8IE
|
||||
from .tubitv import TubiTvIE
|
||||
from .tudou import (
|
||||
@ -907,6 +932,7 @@ from .tvc import (
|
||||
)
|
||||
from .tvigle import TvigleIE
|
||||
from .tvland import TVLandIE
|
||||
from .tvnoe import TVNoeIE
|
||||
from .tvp import (
|
||||
TVPEmbedIE,
|
||||
TVPIE,
|
||||
|
||||
@ -351,3 +351,32 @@ class FacebookIE(InfoExtractor):
|
||||
self._VIDEO_PAGE_TEMPLATE % video_id,
|
||||
video_id, fatal_if_no_video=True)
|
||||
return info_dict
|
||||
|
||||
|
||||
class FacebookPluginsVideoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560',
|
||||
'md5': '5954e92cdfe51fe5782ae9bda7058a07',
|
||||
'info_dict': {
|
||||
'id': '10154383743583686',
|
||||
'ext': 'mp4',
|
||||
'title': 'What to do during the haze?',
|
||||
'uploader': 'Gov.sg',
|
||||
'upload_date': '20160826',
|
||||
'timestamp': 1472184808,
|
||||
},
|
||||
'add_ie': [FacebookIE.ie_key()],
|
||||
}, {
|
||||
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.facebook.com/plugins/video.php?href=https://www.facebook.com/gov.sg/videos/10154383743583686/&show_text=0&width=560',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
return self.url_result(
|
||||
compat_urllib_parse_unquote(self._match_id(url)),
|
||||
FacebookIE.ie_key())
|
||||
|
||||
@ -1,10 +1,12 @@
|
||||
#! -*- coding: utf-8 -*-
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import hashlib
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urllib_request,
|
||||
compat_urlparse,
|
||||
)
|
||||
@ -16,7 +18,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class FC2IE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
|
||||
_VALID_URL = r'^(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
|
||||
IE_NAME = 'fc2'
|
||||
_NETRC_MACHINE = 'fc2'
|
||||
_TESTS = [{
|
||||
@ -75,12 +77,17 @@ class FC2IE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
self._login()
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
self._downloader.cookiejar.clear_session_cookies() # must clear
|
||||
self._login()
|
||||
webpage = None
|
||||
if not url.startswith('fc2:'):
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
self._downloader.cookiejar.clear_session_cookies() # must clear
|
||||
self._login()
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
title = 'FC2 video %s' % video_id
|
||||
thumbnail = None
|
||||
if webpage is not None:
|
||||
title = self._og_search_title(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
refer = url.replace('/content/', '/a/content/') if '/a/content/' not in url else url
|
||||
|
||||
mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
|
||||
@ -113,3 +120,41 @@ class FC2IE(InfoExtractor):
|
||||
'ext': 'flv',
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
||||
|
||||
class FC2EmbedIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://video\.fc2\.com/flv2\.swf\?(?P<query>.+)'
|
||||
IE_NAME = 'fc2:embed'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://video.fc2.com/flv2.swf?t=201404182936758512407645&i=20130316kwishtfitaknmcgd76kjd864hso93htfjcnaogz629mcgfs6rbfk0hsycma7shkf85937cbchfygd74&i=201403223kCqB3Ez&d=2625&sj=11&lang=ja&rel=1&from=11&cmt=1&tk=TlRBM09EQTNNekU9&tl=プリズン･ブレイク%20S1-01%20マイケル%20【吹替】',
|
||||
'md5': 'b8aae5334cb691bdb1193a88a6ab5d5a',
|
||||
'info_dict': {
|
||||
'id': '201403223kCqB3Ez',
|
||||
'ext': 'flv',
|
||||
'title': 'プリズン･ブレイク S1-01 マイケル 【吹替】',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
query = compat_parse_qs(mobj.group('query'))
|
||||
|
||||
video_id = query['i'][-1]
|
||||
title = query.get('tl', ['FC2 video %s' % video_id])[0]
|
||||
|
||||
sj = query.get('sj', [None])[0]
|
||||
thumbnail = None
|
||||
if sj:
|
||||
# See thumbnailImagePath() in ServerConst.as of flv2.swf
|
||||
thumbnail = 'http://video%s-thumbnail.fc2.com/up/pic/%s.jpg' % (
|
||||
sj, '/'.join((video_id[:6], video_id[6:8], video_id[-2], video_id[-1], video_id)))
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': FC2IE.ie_key(),
|
||||
'url': 'fc2:%s' % video_id,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
||||
@ -1,18 +1,24 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
get_element_by_id,
|
||||
remove_end,
|
||||
)
|
||||
|
||||
|
||||
class FoxgayIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
|
||||
_TEST = {
|
||||
'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
|
||||
'md5': '80d72beab5d04e1655a56ad37afe6841',
|
||||
'md5': '344558ccfea74d33b7adbce22e577f54',
|
||||
'info_dict': {
|
||||
'id': '2582',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a',
|
||||
'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf',
|
||||
'title': 'Fuck Turkish-style',
|
||||
'description': 'md5:6ae2d9486921891efe89231ace13ffdf',
|
||||
'age_limit': 18,
|
||||
'thumbnail': 're:https?://.*\.jpg$',
|
||||
},
|
||||
@ -22,27 +28,35 @@ class FoxgayIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<title>(?P<title>.*?)</title>',
|
||||
webpage, 'title', fatal=False)
|
||||
description = self._html_search_regex(
|
||||
r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>',
|
||||
webpage, 'description', fatal=False)
|
||||
title = remove_end(self._html_search_regex(
|
||||
r'<title>([^<]+)</title>', webpage, 'title'), ' - Foxgay.com')
|
||||
description = get_element_by_id('inf_tit', webpage)
|
||||
|
||||
# The default user-agent with foxgay cookies leads to pages without videos
|
||||
self._downloader.cookiejar.clear('.foxgay.com')
|
||||
# Find the URL for the iFrame which contains the actual video.
|
||||
iframe_url = self._html_search_regex(
|
||||
r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1', webpage,
|
||||
'video frame', group='url')
|
||||
iframe = self._download_webpage(
|
||||
self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'),
|
||||
video_id)
|
||||
video_url = self._html_search_regex(
|
||||
r"v_path = '(?P<vid>http://.*?)'", iframe, 'url')
|
||||
thumb_url = self._html_search_regex(
|
||||
r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False)
|
||||
iframe_url, video_id, headers={'User-Agent': 'curl/7.50.1'},
|
||||
note='Downloading video frame')
|
||||
video_data = self._parse_json(self._search_regex(
|
||||
r'video_data\s*=\s*([^;]+);', iframe, 'video data'), video_id)
|
||||
|
||||
formats = [{
|
||||
'url': source,
|
||||
'height': resolution,
|
||||
} for source, resolution in zip(
|
||||
video_data['sources'], video_data.get('resolutions', itertools.repeat(None)))]
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'url': video_url,
|
||||
'formats': formats,
|
||||
'description': description,
|
||||
'thumbnail': thumb_url,
|
||||
'thumbnail': video_data.get('act_vid', {}).get('thumb'),
|
||||
'age_limit': 18,
|
||||
}
|
||||
|
||||
@ -3,11 +3,13 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .amp import AMPIE
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class FoxNewsIE(AMPIE):
|
||||
IE_NAME = 'foxnews'
|
||||
IE_DESC = 'Fox News and Fox Business Video'
|
||||
_VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
|
||||
@ -49,6 +51,11 @@ class FoxNewsIE(AMPIE):
|
||||
'url': 'http://video.foxbusiness.com/v/4442309889001',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
|
||||
'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -58,3 +65,76 @@ class FoxNewsIE(AMPIE):
|
||||
'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
|
||||
info['id'] = video_id
|
||||
return info
|
||||
|
||||
|
||||
class FoxNewsArticleIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
|
||||
IE_NAME = 'foxnews:article'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html',
|
||||
'md5': '62aa5a781b308fdee212ebb6f33ae7ef',
|
||||
'info_dict': {
|
||||
'id': '5116295019001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Trump and Clinton asked to defend positions on Iraq War',
|
||||
'description': 'Veterans react on \'The Kelly File\'',
|
||||
'timestamp': 1473299755,
|
||||
'upload_date': '20160908',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
video_id = self._html_search_regex(
|
||||
r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
|
||||
webpage, 'video ID', group='id')
|
||||
return self.url_result(
|
||||
'http://video.foxnews.com/v/' + video_id,
|
||||
FoxNewsIE.ie_key())
|
||||
|
||||
|
||||
class FoxNewsInsiderIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
|
||||
IE_NAME = 'foxnews:insider'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
|
||||
'md5': 'a10c755e582d28120c62749b4feb4c0c',
|
||||
'info_dict': {
|
||||
'id': '5099377331001',
|
||||
'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words',
|
||||
'ext': 'mp4',
|
||||
'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive',
|
||||
'description': 'Is campus censorship getting out of control?',
|
||||
'timestamp': 1472168725,
|
||||
'upload_date': '20160825',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': [FoxNewsIE.ie_key()],
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL')
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': FoxNewsIE.ie_key(),
|
||||
'url': embed_url,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
}
|
||||
|
||||
@ -2,20 +2,21 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
from ..compat import compat_str
|
||||
from ..utils import month_by_name
|
||||
|
||||
|
||||
class FranceInterIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
|
||||
'url': 'https://www.franceinter.fr/emissions/la-marche-de-l-histoire/la-marche-de-l-histoire-18-decembre-2013',
|
||||
'md5': '4764932e466e6f6c79c317d2e74f6884',
|
||||
'info_dict': {
|
||||
'id': '793962',
|
||||
'id': 'la-marche-de-l-histoire/la-marche-de-l-histoire-18-decembre-2013',
|
||||
'ext': 'mp3',
|
||||
'title': 'L’Histoire dans les jeux vidéo',
|
||||
'description': 'md5:7e93ddb4451e7530022792240a3049c7',
|
||||
'timestamp': 1387369800,
|
||||
'title': 'L’Histoire dans les jeux vidéo du 18 décembre 2013 - France Inter',
|
||||
'description': 'md5:7f2ce449894d1e585932273080fb410d',
|
||||
'upload_date': '20131218',
|
||||
},
|
||||
}
|
||||
@ -25,23 +26,29 @@ class FranceInterIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
path = self._search_regex(
|
||||
r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
|
||||
video_url = 'http://www.franceinter.fr/' + path
|
||||
video_url = self._search_regex(
|
||||
r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
webpage, 'video url', group='url')
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<span class="title-diffusion">(.+?)</span>', webpage, 'title')
|
||||
description = self._html_search_regex(
|
||||
r'<span class="description">(.*?)</span>',
|
||||
webpage, 'description', fatal=False)
|
||||
timestamp = int_or_none(self._search_regex(
|
||||
r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
|
||||
upload_date_str = self._search_regex(
|
||||
r'class=["\']cover-emission-period["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
|
||||
webpage, 'upload date', fatal=False)
|
||||
if upload_date_str:
|
||||
upload_date_list = upload_date_str.split()
|
||||
upload_date_list.reverse()
|
||||
upload_date_list[1] = compat_str(month_by_name(upload_date_list[1], lang='fr'))
|
||||
upload_date = ''.join(upload_date_list)
|
||||
else:
|
||||
upload_date = None
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'timestamp': timestamp,
|
||||
'upload_date': upload_date,
|
||||
'formats': [{
|
||||
'url': video_url,
|
||||
'vcodec': 'none',
|
||||
|
||||
@ -8,7 +8,7 @@ from .common import InfoExtractor
|
||||
|
||||
class FreespeechIE(InfoExtractor):
|
||||
IE_NAME = 'freespeech.org'
|
||||
_VALID_URL = r'https://www\.freespeech\.org/video/(?P<title>.+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?freespeech\.org/video/(?P<title>.+)'
|
||||
_TEST = {
|
||||
'add_ie': ['Youtube'],
|
||||
'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0',
|
||||
|
||||
@ -1,19 +1,15 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
str_to_int,
|
||||
unified_strdate,
|
||||
remove_end,
|
||||
)
|
||||
|
||||
|
||||
class GameStarIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
|
||||
_TEST = {
|
||||
'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
|
||||
'md5': '96974ecbb7fd8d0d20fca5a00810cea7',
|
||||
@ -21,8 +17,9 @@ class GameStarIE(InfoExtractor):
|
||||
'id': '76110',
|
||||
'ext': 'mp4',
|
||||
'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
|
||||
'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den vollständigen Trailer an.',
|
||||
'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg',
|
||||
'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'timestamp': 1406542020,
|
||||
'upload_date': '20140728',
|
||||
'duration': 17
|
||||
}
|
||||
@ -32,41 +29,27 @@ class GameStarIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
og_title = self._og_search_title(webpage)
|
||||
title = re.sub(r'\s*- Video (bei|-) GameStar\.de$', '', og_title)
|
||||
|
||||
url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
|
||||
|
||||
description = self._og_search_description(webpage).strip()
|
||||
|
||||
thumbnail = self._proto_relative_url(
|
||||
self._og_search_thumbnail(webpage), scheme='http:')
|
||||
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+) ',
|
||||
webpage, 'upload_date', fatal=False))
|
||||
|
||||
duration = parse_duration(self._html_search_regex(
|
||||
r' Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration',
|
||||
fatal=False))
|
||||
|
||||
view_count = str_to_int(self._html_search_regex(
|
||||
r' Zuschauer: ([0-9\.]+) ', webpage,
|
||||
'view_count', fatal=False))
|
||||
# TODO: there are multiple ld+json objects in the webpage,
|
||||
# while _search_json_ld finds only the first one
|
||||
json_ld = self._parse_json(self._search_regex(
|
||||
r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>',
|
||||
webpage, 'JSON-LD', group='json_ld'), video_id)
|
||||
info_dict = self._json_ld(json_ld, video_id)
|
||||
info_dict['title'] = remove_end(info_dict['title'], ' - GameStar')
|
||||
|
||||
view_count = json_ld.get('interactionCount')
|
||||
comment_count = int_or_none(self._html_search_regex(
|
||||
r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count',
|
||||
r'([0-9]+) Kommentare</span>', webpage, 'comment_count',
|
||||
fatal=False))
|
||||
|
||||
return {
|
||||
info_dict.update({
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'url': url,
|
||||
'ext': 'mp4',
|
||||
'thumbnail': thumbnail,
|
||||
'description': description,
|
||||
'upload_date': upload_date,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'comment_count': comment_count
|
||||
}
|
||||
})
|
||||
|
||||
return info_dict
|
||||
|
||||
@ -1369,6 +1369,11 @@ class GenericIE(InfoExtractor):
|
||||
},
|
||||
'add_ie': ['Vimeo'],
|
||||
},
|
||||
{
|
||||
# generic vimeo embed that requires original URL passed as Referer
|
||||
'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
|
||||
'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
|
||||
|
||||
@ -19,7 +19,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class GloboIE(InfoExtractor):
|
||||
_VALID_URL = '(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
|
||||
_VALID_URL = r'(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
|
||||
|
||||
_API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist'
|
||||
_SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s'
|
||||
@ -396,7 +396,7 @@ class GloboIE(InfoExtractor):
|
||||
|
||||
|
||||
class GloboArticleIE(InfoExtractor):
|
||||
_VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
|
||||
_VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
|
||||
|
||||
_VIDEOID_REGEXES = [
|
||||
r'\bdata-video-id=["\'](\d{7,})',
|
||||
|
||||
@ -8,6 +8,8 @@ from ..utils import (
|
||||
int_or_none,
|
||||
determine_ext,
|
||||
parse_age_limit,
|
||||
urlencode_postdata,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
@ -19,7 +21,7 @@ class GoIE(InfoExtractor):
|
||||
'watchdisneyjunior': '008',
|
||||
'watchdisneyxd': '009',
|
||||
}
|
||||
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/.*?vdka(?P<id>\w+)' % '|'.join(_BRANDS.keys())
|
||||
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_BRANDS.keys())
|
||||
_TESTS = [{
|
||||
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
|
||||
'info_dict': {
|
||||
@ -38,9 +40,13 @@ class GoIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
sub_domain, video_id = re.match(self._VALID_URL, url).groups()
|
||||
sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
if not video_id:
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._search_regex(r'data-video-id=["\']VDKA(\w+)', webpage, 'video id')
|
||||
brand = self._BRANDS[sub_domain]
|
||||
video_data = self._download_json(
|
||||
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (self._BRANDS[sub_domain], video_id),
|
||||
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
|
||||
video_id)['video'][0]
|
||||
title = video_data['title']
|
||||
|
||||
@ -52,6 +58,21 @@ class GoIE(InfoExtractor):
|
||||
format_id = asset.get('format')
|
||||
ext = determine_ext(asset_url)
|
||||
if ext == 'm3u8':
|
||||
video_type = video_data.get('type')
|
||||
if video_type == 'lf':
|
||||
entitlement = self._download_json(
|
||||
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
|
||||
video_id, data=urlencode_postdata({
|
||||
'video_id': video_data['id'],
|
||||
'video_type': video_type,
|
||||
'brand': brand,
|
||||
'device': '001',
|
||||
}))
|
||||
errors = entitlement.get('errors', {}).get('errors', [])
|
||||
if errors:
|
||||
error_message = ', '.join([error['message'] for error in errors])
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
asset_url += '?' + entitlement['uplynkData']['sessionKey']
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
|
||||
else:
|
||||
|
||||
@ -10,7 +10,7 @@ from ..utils import unified_strdate
|
||||
|
||||
class GooglePlusIE(InfoExtractor):
|
||||
IE_DESC = 'Google Plus'
|
||||
_VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
|
||||
_VALID_URL = r'https?://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
|
||||
IE_NAME = 'plus.google'
|
||||
_TEST = {
|
||||
'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',
|
||||
|
||||
@ -11,7 +11,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class GoshgayIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)'
|
||||
_VALID_URL = r'https?://(?:www\.)?goshgay\.com/video(?P<id>\d+?)($|/)'
|
||||
_TEST = {
|
||||
'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
|
||||
'md5': '4b6db9a0a333142eb9f15913142b0ed1',
|
||||
|
||||
@ -5,7 +5,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class HarkIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.hark\.com/clips/(?P<id>.+?)-.+'
|
||||
_VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P<id>.+?)-.+'
|
||||
_TEST = {
|
||||
'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
|
||||
'md5': '6783a58491b47b92c7c1af5a77d4cbee',
|
||||
|
||||
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class HotNewHipHopIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
|
||||
_TEST = {
|
||||
'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
|
||||
'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
|
||||
|
||||
@ -94,7 +94,7 @@ class ImdbIE(InfoExtractor):
|
||||
class ImdbListIE(InfoExtractor):
|
||||
IE_NAME = 'imdb:list'
|
||||
IE_DESC = 'Internet Movie Database lists'
|
||||
_VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
|
||||
_VALID_URL = r'https?://(?:www\.)?imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
|
||||
_TEST = {
|
||||
'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
|
||||
'info_dict': {
|
||||
|
||||
@ -48,13 +48,23 @@ class InternetVideoArchiveIE(InfoExtractor):
|
||||
# There are multiple videos in the playlist whlie only the first one
|
||||
# matches the video played in browsers
|
||||
video_info = configuration['playlist'][0]
|
||||
title = video_info['title']
|
||||
|
||||
formats = []
|
||||
for source in video_info['sources']:
|
||||
file_url = source['file']
|
||||
if determine_ext(file_url) == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
file_url, video_id, ext='mp4', m3u8_id='hls'))
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
|
||||
if m3u8_formats:
|
||||
formats.extend(m3u8_formats)
|
||||
file_url = m3u8_formats[0]['url']
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
file_url.replace('.m3u8', '.f4m'),
|
||||
video_id, f4m_id='hds', fatal=False))
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
file_url.replace('.m3u8', '.mpd'),
|
||||
video_id, mpd_id='dash', fatal=False))
|
||||
else:
|
||||
a_format = {
|
||||
'url': file_url,
|
||||
@ -70,7 +80,6 @@ class InternetVideoArchiveIE(InfoExtractor):
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = video_info['title']
|
||||
description = video_info.get('description')
|
||||
thumbnail = video_info.get('image')
|
||||
else:
|
||||
|
||||
77
youtube_dl/extractor/iwara.py
Normal file
77
youtube_dl/extractor/iwara.py
Normal file
@ -0,0 +1,77 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_urlparse
|
||||
from ..utils import remove_end
|
||||
|
||||
|
||||
class IwaraIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
|
||||
'md5': '1d53866b2c514b23ed69e4352fdc9839',
|
||||
'info_dict': {
|
||||
'id': 'amVwUl1EHpAD9RD',
|
||||
'ext': 'mp4',
|
||||
'title': '【MMD R-18】ガールフレンド carry_me_off',
|
||||
'age_limit': 18,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO',
|
||||
'md5': '7e5f1f359cd51a027ba4a7b7710a50f0',
|
||||
'info_dict': {
|
||||
'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
|
||||
'ext': 'mp4',
|
||||
'title': '[3D Hentai] Kyonyu Ã\x97 Genkai Ã\x97 Emaki Shinobi Girls.mp4',
|
||||
'age_limit': 18,
|
||||
},
|
||||
'add_ie': ['GoogleDrive'],
|
||||
}, {
|
||||
'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
|
||||
'md5': '1d85f1e5217d2791626cff5ec83bb189',
|
||||
'info_dict': {
|
||||
'id': '6liAP9s2Ojc',
|
||||
'ext': 'mp4',
|
||||
'age_limit': 0,
|
||||
'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
|
||||
'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
|
||||
'upload_date': '20160910',
|
||||
'uploader': 'aMMDsork',
|
||||
'uploader_id': 'UCVOFyOSCyFkXTYYHITtqB7A',
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage, urlh = self._download_webpage_handle(url, video_id)
|
||||
|
||||
hostname = compat_urllib_parse_urlparse(urlh.geturl()).hostname
|
||||
# ecchi is 'sexy' in Japanese
|
||||
age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
|
||||
|
||||
entries = self._parse_html5_media_entries(url, webpage, video_id)
|
||||
|
||||
if not entries:
|
||||
iframe_url = self._html_search_regex(
|
||||
r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
|
||||
webpage, 'iframe URL', group='url')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': iframe_url,
|
||||
'age_limit': age_limit,
|
||||
}
|
||||
|
||||
title = remove_end(self._html_search_regex(
|
||||
r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
|
||||
|
||||
info_dict = entries[0]
|
||||
info_dict.update({
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'age_limit': age_limit,
|
||||
})
|
||||
|
||||
return info_dict
|
||||
@ -63,10 +63,17 @@ class JWPlatformBaseIE(InfoExtractor):
|
||||
'ext': ext,
|
||||
})
|
||||
else:
|
||||
height = int_or_none(source.get('height'))
|
||||
if height is None:
|
||||
# Often no height is provided but there is a label in
|
||||
# format like 1080p.
|
||||
height = int_or_none(self._search_regex(
|
||||
r'^(\d{3,})[pP]$', source.get('label') or '',
|
||||
'height', default=None))
|
||||
a_format = {
|
||||
'url': source_url,
|
||||
'width': int_or_none(source.get('width')),
|
||||
'height': int_or_none(source.get('height')),
|
||||
'height': height,
|
||||
'ext': ext,
|
||||
}
|
||||
if source_url.startswith('rtmp'):
|
||||
|
||||
@ -262,8 +262,16 @@ class KalturaIE(InfoExtractor):
|
||||
# Continue if asset is not ready
|
||||
if f.get('status') != 2:
|
||||
continue
|
||||
# Original format that's not available (e.g. kaltura:1926081:0_c03e1b5g)
|
||||
# skip for now.
|
||||
if f.get('fileExt') == 'chun':
|
||||
continue
|
||||
video_url = sign_url(
|
||||
'%s/flavorId/%s' % (data_url, f['id']))
|
||||
# audio-only has no videoCodecId (e.g. kaltura:1926081:0_c03e1b5g
|
||||
# -f mp4-56)
|
||||
vcodec = 'none' if 'videoCodecId' not in f and f.get(
|
||||
'frameRate') == 0 else f.get('videoCodecId')
|
||||
formats.append({
|
||||
'format_id': '%(fileExt)s-%(bitrate)s' % f,
|
||||
'ext': f.get('fileExt'),
|
||||
@ -271,7 +279,7 @@ class KalturaIE(InfoExtractor):
|
||||
'fps': int_or_none(f.get('frameRate')),
|
||||
'filesize_approx': int_or_none(f.get('size'), invscale=1024),
|
||||
'container': f.get('containerFormat'),
|
||||
'vcodec': f.get('videoCodecId'),
|
||||
'vcodec': vcodec,
|
||||
'height': int_or_none(f.get('height')),
|
||||
'width': int_or_none(f.get('width')),
|
||||
'url': video_url,
|
||||
|
||||
@ -5,7 +5,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class KaraoketvIE(InfoExtractor):
|
||||
_VALID_URL = r'http://www.karaoketv.co.il/[^/]+/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?karaoketv\.co\.il/[^/]+/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.karaoketv.co.il/%D7%A9%D7%99%D7%A8%D7%99_%D7%A7%D7%A8%D7%99%D7%95%D7%A7%D7%99/58356/%D7%90%D7%99%D7%96%D7%95%D7%9F',
|
||||
'info_dict': {
|
||||
|
||||
52
youtube_dl/extractor/ketnet.py
Normal file
52
youtube_dl/extractor/ketnet.py
Normal file
@ -0,0 +1,52 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class KetnetIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.ketnet.be/kijken/zomerse-filmpjes',
|
||||
'md5': 'd907f7b1814ef0fa285c0475d9994ed7',
|
||||
'info_dict': {
|
||||
'id': 'zomerse-filmpjes',
|
||||
'ext': 'mp4',
|
||||
'title': 'Gluur mee op de filmset en op Pennenzakkenrock',
|
||||
'description': 'Gluur mee met Ghost Rockers op de filmset',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.ketnet.be/kijken/karrewiet/uitzending-8-september-2016',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.ketnet.be/achter-de-schermen/sien-repeteert-voor-stars-for-life',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
config = self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?s)playerConfig\s*=\s*({.+?})\s*;', webpage,
|
||||
'player config'),
|
||||
video_id)
|
||||
|
||||
title = config['title']
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
config['source']['hls'], video_id, 'mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id='hls')
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': config.get('description'),
|
||||
'thumbnail': config.get('image'),
|
||||
'series': config.get('program'),
|
||||
'episode': config.get('episode'),
|
||||
'formats': formats,
|
||||
}
|
||||
@ -6,7 +6,7 @@ from ..utils import smuggle_url
|
||||
|
||||
|
||||
class KickStarterIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*'
|
||||
_VALID_URL = r'https?://(?:www\.)?kickstarter\.com/projects/(?P<id>[^/]*)/.*'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant/description',
|
||||
'md5': 'c81addca81327ffa66c642b5d8b08cab',
|
||||
|
||||
@ -59,7 +59,7 @@ class KuwoBaseIE(InfoExtractor):
|
||||
class KuwoIE(KuwoBaseIE):
|
||||
IE_NAME = 'kuwo:song'
|
||||
IE_DESC = '酷我音乐'
|
||||
_VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.kuwo.cn/yinyue/635632/',
|
||||
'info_dict': {
|
||||
@ -82,7 +82,7 @@ class KuwoIE(KuwoBaseIE):
|
||||
'upload_date': '20150518',
|
||||
},
|
||||
'params': {
|
||||
'format': 'mp3-320'
|
||||
'format': 'mp3-320',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
|
||||
@ -91,10 +91,10 @@ class KuwoIE(KuwoBaseIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
song_id = self._match_id(url)
|
||||
webpage = self._download_webpage(
|
||||
webpage, urlh = self._download_webpage_handle(
|
||||
url, song_id, note='Download song detail info',
|
||||
errnote='Unable to get song detail info')
|
||||
if '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
|
||||
if song_id not in urlh.geturl() or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
|
||||
raise ExtractorError('this song has been offline because of copyright issues', expected=True)
|
||||
|
||||
song_name = self._html_search_regex(
|
||||
@ -139,7 +139,7 @@ class KuwoIE(KuwoBaseIE):
|
||||
class KuwoAlbumIE(InfoExtractor):
|
||||
IE_NAME = 'kuwo:album'
|
||||
IE_DESC = '酷我音乐 - 专辑'
|
||||
_VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
|
||||
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'
|
||||
_TEST = {
|
||||
'url': 'http://www.kuwo.cn/album/502294/',
|
||||
'info_dict': {
|
||||
@ -181,7 +181,7 @@ class KuwoChartIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '香港中文龙虎榜',
|
||||
},
|
||||
'playlist_mincount': 10,
|
||||
'playlist_mincount': 7,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -200,7 +200,7 @@ class KuwoChartIE(InfoExtractor):
|
||||
class KuwoSingerIE(InfoExtractor):
|
||||
IE_NAME = 'kuwo:singer'
|
||||
IE_DESC = '酷我音乐 - 歌手'
|
||||
_VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
|
||||
'info_dict': {
|
||||
@ -296,14 +296,14 @@ class KuwoCategoryIE(InfoExtractor):
|
||||
class KuwoMvIE(KuwoBaseIE):
|
||||
IE_NAME = 'kuwo:mv'
|
||||
IE_DESC = '酷我音乐 - MV'
|
||||
_VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
|
||||
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'
|
||||
_TEST = {
|
||||
'url': 'http://www.kuwo.cn/mv/6480076/',
|
||||
'info_dict': {
|
||||
'id': '6480076',
|
||||
'ext': 'mp4',
|
||||
'title': 'My HouseMV',
|
||||
'creator': 'PM02:00',
|
||||
'creator': '2PM',
|
||||
},
|
||||
# In this video, music URLs (anti.s) are blocked outside China and
|
||||
# USA, while the MV URL (mvurl) is available globally, so force the MV
|
||||
|
||||
24
youtube_dl/extractor/lci.py
Normal file
24
youtube_dl/extractor/lci.py
Normal file
@ -0,0 +1,24 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class LCIIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?lci\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html'
|
||||
_TEST = {
|
||||
'url': 'http://www.lci.fr/international/etats-unis-a-j-62-hillary-clinton-reste-sans-voix-2001679.html',
|
||||
'md5': '2fdb2538b884d4d695f9bd2bde137e6c',
|
||||
'info_dict': {
|
||||
'id': '13244802',
|
||||
'ext': 'mp4',
|
||||
'title': 'Hillary Clinton et sa quinte de toux, en plein meeting',
|
||||
'description': 'md5:a4363e3a960860132f8124b62f4a01c9',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
wat_id = self._search_regex(r'data-watid=[\'"](\d+)', webpage, 'wat id')
|
||||
return self.url_result('wat:' + wat_id, 'Wat', wat_id)
|
||||
@ -14,7 +14,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class LiTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
|
||||
|
||||
_URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?id=%s'
|
||||
|
||||
|
||||
@ -1,8 +1,11 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
remove_end,
|
||||
@ -12,8 +15,10 @@ from ..utils import (
|
||||
class LRTIE(InfoExtractor):
|
||||
IE_NAME = 'lrt.lt'
|
||||
_VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
# m3u8 download
|
||||
'url': 'http://www.lrt.lt/mediateka/irasas/54391/',
|
||||
'md5': 'fe44cf7e4ab3198055f2c598fc175cb0',
|
||||
'info_dict': {
|
||||
'id': '54391',
|
||||
'ext': 'mp4',
|
||||
@ -23,20 +28,45 @@ class LRTIE(InfoExtractor):
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # m3u8 download
|
||||
}, {
|
||||
# direct mp3 download
|
||||
'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/',
|
||||
'md5': '389da8ca3cad0f51d12bed0c844f6a0a',
|
||||
'info_dict': {
|
||||
'id': '1013074524',
|
||||
'ext': 'mp3',
|
||||
'title': 'Kita tema 2016-09-05 15:05',
|
||||
'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5',
|
||||
'duration': 3008,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
},
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = remove_end(self._og_search_title(webpage), ' - LRT')
|
||||
m3u8_url = self._search_regex(
|
||||
r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*location\.hash\.substring\(1\)',
|
||||
webpage, 'm3u8 url', group='url')
|
||||
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
|
||||
|
||||
formats = []
|
||||
for _, file_url in re.findall(
|
||||
r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
|
||||
ext = determine_ext(file_url)
|
||||
if ext not in ('m3u8', 'mp3'):
|
||||
continue
|
||||
# mp3 served as m3u8 produces stuttered media file
|
||||
if ext == 'm3u8' and '.mp3' in file_url:
|
||||
continue
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
fatal=False))
|
||||
elif ext == 'mp3':
|
||||
formats.append({
|
||||
'url': file_url,
|
||||
'vcodec': 'none',
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
@ -94,7 +94,7 @@ class LyndaBaseIE(InfoExtractor):
|
||||
class LyndaIE(LyndaBaseIE):
|
||||
IE_NAME = 'lynda'
|
||||
IE_DESC = 'lynda.com videos'
|
||||
_VALID_URL = r'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
|
||||
|
||||
_TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
|
||||
|
||||
|
||||
@ -7,7 +7,7 @@ from ..utils import ExtractorError
|
||||
class MacGameStoreIE(InfoExtractor):
|
||||
IE_NAME = 'macgamestore'
|
||||
IE_DESC = 'MacGameStore trailers'
|
||||
_VALID_URL = r'https?://www\.macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',
|
||||
|
||||
@ -9,7 +9,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class MetacriticIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.metacritic\.com/.+?/trailers/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?metacritic\.com/.+?/trailers/(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222',
|
||||
|
||||
@ -6,7 +6,7 @@ from ..utils import int_or_none
|
||||
|
||||
|
||||
class MGTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
IE_DESC = '芒果TV'
|
||||
|
||||
_TESTS = [{
|
||||
|
||||
40
youtube_dl/extractor/miaopai.py
Normal file
40
youtube_dl/extractor/miaopai.py
Normal file
@ -0,0 +1,40 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class MiaoPaiIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
|
||||
'md5': '095ed3f1cd96b821add957bdc29f845b',
|
||||
'info_dict': {
|
||||
'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
|
||||
'ext': 'mp4',
|
||||
'title': '西游记音乐会的秒拍视频',
|
||||
'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
|
||||
}
|
||||
}
|
||||
|
||||
_USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(
|
||||
url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<title>([^<]+)</title>', webpage, 'title')
|
||||
thumbnail = self._html_search_regex(
|
||||
r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
|
||||
webpage, 'thumbnail', fatal=False, group='url')
|
||||
videos = self._parse_html5_media_entries(url, webpage, video_id)
|
||||
info = videos[0]
|
||||
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
})
|
||||
return info
|
||||
@ -8,7 +8,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class MinistryGridIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.ministrygrid.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
|
||||
_VALID_URL = r'https?://(?:www\.)?ministrygrid\.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers',
|
||||
|
||||
@ -74,7 +74,7 @@ class MiTeleBaseIE(InfoExtractor):
|
||||
|
||||
class MiTeleIE(MiTeleBaseIE):
|
||||
IE_DESC = 'mitele.es'
|
||||
_VALID_URL = r'https?://www\.mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
|
||||
_VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
|
||||
|
||||
@ -35,7 +35,8 @@ class MoeVideoIE(InfoExtractor):
|
||||
'height': 360,
|
||||
'duration': 179,
|
||||
'filesize': 17822500,
|
||||
}
|
||||
},
|
||||
'skip': 'Video has been removed',
|
||||
},
|
||||
{
|
||||
'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
|
||||
|
||||
@ -9,7 +9,7 @@ from ..compat import (
|
||||
|
||||
class MotorsportIE(InfoExtractor):
|
||||
IE_DESC = 'motorsport.com'
|
||||
_VALID_URL = r'https?://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
|
||||
_VALID_URL = r'https?://(?:www\.)?motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
|
||||
_TEST = {
|
||||
'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
|
||||
'info_dict': {
|
||||
|
||||
@ -7,7 +7,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class MoviezineIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.moviezine\.se/video/(?P<id>[^?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?moviezine\.se/video/(?P<id>[^?#]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.moviezine.se/video/205866',
|
||||
|
||||
@ -11,7 +11,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class MySpassIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.myspass\.de/.*'
|
||||
_VALID_URL = r'https?://(?:www\.)?myspass\.de/.*'
|
||||
_TEST = {
|
||||
'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
|
||||
'md5': '0b49f4844a068f8b33f4b7c88405862b',
|
||||
|
||||
@ -13,7 +13,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class NBCIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
@ -138,7 +138,7 @@ class NBCSportsVPlayerIE(InfoExtractor):
|
||||
|
||||
class NBCSportsIE(InfoExtractor):
|
||||
# Does not include https because its certificate is invalid
|
||||
_VALID_URL = r'https?://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
|
||||
@ -161,7 +161,7 @@ class NBCSportsIE(InfoExtractor):
|
||||
|
||||
|
||||
class CSNNEIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.csnne\.com/video/(?P<id>[0-9a-z-]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
|
||||
@ -335,3 +335,43 @@ class NBCNewsIE(ThePlatformIE):
|
||||
'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byId=%s' % video_id,
|
||||
'ie_key': 'ThePlatformFeed',
|
||||
}
|
||||
|
||||
|
||||
class NBCOlympicsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
|
||||
|
||||
_TEST = {
|
||||
# Geo-restricted to US
|
||||
'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
|
||||
'md5': '54fecf846d05429fbaa18af557ee523a',
|
||||
'info_dict': {
|
||||
'id': 'WjTBzDXx5AUq',
|
||||
'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
|
||||
'ext': 'mp4',
|
||||
'title': 'Rose\'s son Leo was in tears after his dad won gold',
|
||||
'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
|
||||
'timestamp': 1471274964,
|
||||
'upload_date': '20160815',
|
||||
'uploader': 'NBCU-SPORTS',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
drupal_settings = self._parse_json(self._search_regex(
|
||||
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
|
||||
webpage, 'drupal settings'), display_id)
|
||||
|
||||
iframe_url = drupal_settings['vod']['iframe_url']
|
||||
theplatform_url = iframe_url.replace(
|
||||
'vplayer.nbcolympics.com', 'player.theplatform.com')
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': theplatform_url,
|
||||
'ie_key': ThePlatformIE.ie_key(),
|
||||
'display_id': display_id,
|
||||
}
|
||||
|
||||
@ -23,7 +23,7 @@ class NDRBaseIE(InfoExtractor):
|
||||
class NDRIE(NDRBaseIE):
|
||||
IE_NAME = 'ndr'
|
||||
IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
|
||||
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
|
||||
_TESTS = [{
|
||||
# httpVideo, same content id
|
||||
'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
|
||||
@ -105,7 +105,7 @@ class NDRIE(NDRBaseIE):
|
||||
class NJoyIE(NDRBaseIE):
|
||||
IE_NAME = 'njoy'
|
||||
IE_DESC = 'N-JOY'
|
||||
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
|
||||
_TESTS = [{
|
||||
# httpVideo, same content id
|
||||
'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
|
||||
@ -238,7 +238,7 @@ class NDREmbedBaseIE(InfoExtractor):
|
||||
|
||||
class NDREmbedIE(NDREmbedBaseIE):
|
||||
IE_NAME = 'ndr:embed'
|
||||
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
|
||||
'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
|
||||
@ -332,7 +332,7 @@ class NDREmbedIE(NDREmbedBaseIE):
|
||||
|
||||
class NJoyEmbedIE(NDREmbedBaseIE):
|
||||
IE_NAME = 'njoy:embed'
|
||||
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
|
||||
_TESTS = [{
|
||||
# httpVideo
|
||||
'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',
|
||||
|
||||
@ -1,15 +1,12 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class NewgroundsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.newgrounds.com/audio/listen/549479',
|
||||
'url': 'https://www.newgrounds.com/audio/listen/549479',
|
||||
'md5': 'fe6033d297591288fa1c1f780386f07a',
|
||||
'info_dict': {
|
||||
'id': '549479',
|
||||
@ -18,7 +15,7 @@ class NewgroundsIE(InfoExtractor):
|
||||
'uploader': 'Burn7',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.newgrounds.com/portal/view/673111',
|
||||
'url': 'https://www.newgrounds.com/portal/view/673111',
|
||||
'md5': '3394735822aab2478c31b1004fe5e5bc',
|
||||
'info_dict': {
|
||||
'id': '673111',
|
||||
@ -29,24 +26,20 @@ class NewgroundsIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
music_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, music_id)
|
||||
media_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, media_id)
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<title>([^>]+)</title>', webpage, 'title')
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
[r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'],
|
||||
webpage, 'uploader')
|
||||
r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
|
||||
|
||||
music_url_json_string = self._html_search_regex(
|
||||
r'({"url":"[^"]+"),', webpage, 'music url') + '}'
|
||||
music_url_json = json.loads(music_url_json_string)
|
||||
music_url = music_url_json['url']
|
||||
music_url = self._parse_json(self._search_regex(
|
||||
r'"url":("[^"]+"),', webpage, ''), media_id)
|
||||
|
||||
return {
|
||||
'id': music_id,
|
||||
'id': media_id,
|
||||
'title': title,
|
||||
'url': music_url,
|
||||
'uploader': uploader,
|
||||
|
||||
@ -7,7 +7,7 @@ from ..utils import parse_iso8601
|
||||
|
||||
class NextMediaIE(InfoExtractor):
|
||||
IE_DESC = '蘋果日報'
|
||||
_VALID_URL = r'https?://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://hk\.apple\.nextmedia\.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
|
||||
'md5': 'dff9fad7009311c421176d1ac90bfe4f',
|
||||
@ -68,7 +68,7 @@ class NextMediaIE(InfoExtractor):
|
||||
|
||||
class NextMediaActionNewsIE(NextMediaIE):
|
||||
IE_DESC = '蘋果日報 - 動新聞'
|
||||
_VALID_URL = r'https?://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
|
||||
_VALID_URL = r'https?://hk\.dv\.nextmedia\.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
|
||||
_TESTS = [{
|
||||
'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
|
||||
'md5': '05fce8ffeed7a5e00665d4b7cf0f9201',
|
||||
@ -93,7 +93,7 @@ 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)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
|
||||
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
|
||||
_TESTS = [{
|
||||
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
|
||||
'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
|
||||
|
||||
@ -1,14 +1,15 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
|
||||
class NhkVodIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>.+?)\.html'
|
||||
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)'
|
||||
_TEST = {
|
||||
# Videos available only for a limited period of time. Visit
|
||||
# http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
|
||||
'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815.html',
|
||||
'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815',
|
||||
'info_dict': {
|
||||
'id': 'A1bnNiNTE6nY3jLllS-BIISfcC_PpvF5',
|
||||
'ext': 'flv',
|
||||
@ -19,25 +20,25 @@ class NhkVodIE(InfoExtractor):
|
||||
},
|
||||
'skip': 'Videos available only for a limited period of time',
|
||||
}
|
||||
_API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
data = self._download_json(self._API_URL, video_id)
|
||||
|
||||
embed_code = self._search_regex(
|
||||
r'nw_vod_ooplayer\([^,]+,\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
|
||||
webpage, 'ooyala embed code', group='id')
|
||||
try:
|
||||
episode = next(
|
||||
e for e in data['data']['episodes']
|
||||
if e.get('url') and video_id in e['url'])
|
||||
except StopIteration:
|
||||
raise ExtractorError('Unable to find episode')
|
||||
|
||||
title = self._search_regex(
|
||||
r'<div[^>]+class=["\']episode-detail["\']>\s*<h\d+>([^<]+)',
|
||||
webpage, 'title', default=None)
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<p[^>]+class=["\']description["\'][^>]*>(.+?)</p>',
|
||||
webpage, 'description', default=None)
|
||||
series = self._search_regex(
|
||||
r'<h2[^>]+class=["\']detail-top-player-title[^>]+><a[^>]+>([^<]+)',
|
||||
webpage, 'series', default=None)
|
||||
embed_code = episode['vod_id']
|
||||
|
||||
title = episode.get('sub_title_clean') or episode['sub_title']
|
||||
description = episode.get('description_clean') or episode.get('description')
|
||||
series = episode.get('title_clean') or episode.get('title')
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
|
||||
@ -69,13 +69,16 @@ class NickIE(MTVServicesInfoExtractor):
|
||||
|
||||
class NickDeIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'nick.de'
|
||||
_VALID_URL = r'https?://(?:www\.)?nick\.de/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:nick\.de|nickelodeon\.nl)/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.nick.de/shows/342-icarly',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.nickelodeon.nl/shows/474-spongebob/videos/17403-een-kijkje-in-de-keuken-met-sandy-van-binnenuit',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -252,7 +252,7 @@ class NiconicoIE(InfoExtractor):
|
||||
|
||||
|
||||
class NiconicoPlaylistIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/mylist/(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.nicovideo.jp/mylist/27411728',
|
||||
|
||||
@ -44,7 +44,20 @@ class NineNowIE(InfoExtractor):
|
||||
page_data = self._parse_json(self._search_regex(
|
||||
r'window\.__data\s*=\s*({.*?});', webpage,
|
||||
'page data'), display_id)
|
||||
common_data = page_data.get('episode', {}).get('episode') or page_data.get('clip', {}).get('clip')
|
||||
|
||||
for kind in ('episode', 'clip'):
|
||||
current_key = page_data.get(kind, {}).get(
|
||||
'current%sKey' % kind.capitalize())
|
||||
if not current_key:
|
||||
continue
|
||||
cache = page_data.get(kind, {}).get('%sCache' % kind, {})
|
||||
if not cache:
|
||||
continue
|
||||
common_data = (cache.get(current_key) or list(cache.values())[0])[kind]
|
||||
break
|
||||
else:
|
||||
raise ExtractorError('Unable to find video data')
|
||||
|
||||
video_data = common_data['video']
|
||||
|
||||
if video_data.get('drm'):
|
||||
|
||||
@ -5,7 +5,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class OktoberfestTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P<id>[^/?#]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.oktoberfest-tv.de/de/kameras/video/hb-zelt',
|
||||
|
||||
@ -90,7 +90,7 @@ class OnetBaseIE(InfoExtractor):
|
||||
|
||||
|
||||
class OnetIE(OnetBaseIE):
|
||||
_VALID_URL = 'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
|
||||
IE_NAME = 'onet.tv'
|
||||
|
||||
_TEST = {
|
||||
|
||||
@ -13,7 +13,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class OpenloadIE(InfoExtractor):
|
||||
_VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
|
||||
_VALID_URL = r'https?://openload\.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://openload.co/f/kUEfGclsU9o',
|
||||
@ -60,7 +60,7 @@ class OpenloadIE(InfoExtractor):
|
||||
if j >= 33 and j <= 126:
|
||||
j = ((j + 14) % 94) + 33
|
||||
if idx == len(enc_data) - 1:
|
||||
j += 1
|
||||
j += 3
|
||||
video_url_chars += compat_chr(j)
|
||||
|
||||
video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)
|
||||
|
||||
@ -1,53 +1,40 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class ParliamentLiveUKIE(InfoExtractor):
|
||||
IE_NAME = 'parliamentlive.tv'
|
||||
IE_DESC = 'UK parliament videos'
|
||||
_VALID_URL = r'https?://www\.parliamentlive\.tv/Main/Player\.aspx\?(?:[^&]+&)*?meetingId=(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?parliamentlive\.tv/Event/Index/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.parliamentlive.tv/Main/Player.aspx?meetingId=15121&player=windowsmedia',
|
||||
'url': 'http://parliamentlive.tv/Event/Index/c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
|
||||
'info_dict': {
|
||||
'id': '15121',
|
||||
'ext': 'asf',
|
||||
'title': 'hoc home affairs committee, 18 mar 2014.pm',
|
||||
'description': 'md5:033b3acdf83304cd43946b2d5e5798d1',
|
||||
'id': 'c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
|
||||
'ext': 'mp4',
|
||||
'title': 'Home Affairs Committee',
|
||||
'uploader_id': 'FFMPEG-01',
|
||||
'timestamp': 1422696664,
|
||||
'upload_date': '20150131',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # Requires mplayer (mms)
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
asx_url = self._html_search_regex(
|
||||
r'embed.*?src="([^"]+)" name="MediaPlayer"', webpage,
|
||||
'metadata URL')
|
||||
asx = self._download_xml(asx_url, video_id, 'Downloading ASX metadata')
|
||||
video_url = asx.find('.//REF').attrib['HREF']
|
||||
|
||||
title = self._search_regex(
|
||||
r'''(?x)player\.setClipDetails\(
|
||||
(?:(?:[0-9]+|"[^"]+"),\s*){2}
|
||||
"([^"]+",\s*"[^"]+)"
|
||||
''',
|
||||
webpage, 'title').replace('", "', ', ')
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<span id="MainContentPlaceHolder_CaptionsBlock_WitnessInfo">(.*?)</span>',
|
||||
webpage, 'description')
|
||||
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(
|
||||
'http://vodplayer.parliamentlive.tv/?mid=' + video_id, video_id)
|
||||
widget_config = self._parse_json(self._search_regex(
|
||||
r'kWidgetConfig\s*=\s*({.+});',
|
||||
webpage, 'kaltura widget config'), video_id)
|
||||
kaltura_url = 'kaltura:%s:%s' % (widget_config['wid'][1:], widget_config['entry_id'])
|
||||
event_title = self._download_json(
|
||||
'http://parliamentlive.tv/Event/GetShareVideo/' + video_id, video_id)['event']['title']
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'ext': 'asf',
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'title': event_title,
|
||||
'description': '',
|
||||
'url': kaltura_url,
|
||||
'ie_key': 'Kaltura',
|
||||
}
|
||||
|
||||
@ -94,7 +94,7 @@ class PeriscopeIE(PeriscopeBaseIE):
|
||||
|
||||
|
||||
class PeriscopeUserIE(PeriscopeBaseIE):
|
||||
_VALID_URL = r'https?://www\.periscope\.tv/(?P<id>[^/]+)/?$'
|
||||
_VALID_URL = r'https?://(?:www\.)?periscope\.tv/(?P<id>[^/]+)/?$'
|
||||
IE_DESC = 'Periscope user videos'
|
||||
IE_NAME = 'periscope:user'
|
||||
|
||||
|
||||
@ -14,7 +14,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class PlayvidIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
|
||||
_VALID_URL = r'https?://(?:www\.)?playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
|
||||
'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
|
||||
|
||||
@ -1,14 +1,17 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_urlparse
|
||||
)
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
int_or_none,
|
||||
strip_or_none,
|
||||
unified_timestamp,
|
||||
@ -97,3 +100,81 @@ class PolskieRadioIE(InfoExtractor):
|
||||
description = strip_or_none(self._og_search_description(webpage))
|
||||
|
||||
return self.playlist_result(entries, playlist_id, title, description)
|
||||
|
||||
|
||||
class PolskieRadioCategoryIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+(?:,[^/]+)?/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.polskieradio.pl/7/5102,HISTORIA-ZYWA',
|
||||
'info_dict': {
|
||||
'id': '5102',
|
||||
'title': 'HISTORIA ŻYWA',
|
||||
},
|
||||
'playlist_mincount': 38,
|
||||
}, {
|
||||
'url': 'http://www.polskieradio.pl/7/4807',
|
||||
'info_dict': {
|
||||
'id': '4807',
|
||||
'title': 'Vademecum 1050. rocznicy Chrztu Polski'
|
||||
},
|
||||
'playlist_mincount': 5
|
||||
}, {
|
||||
'url': 'http://www.polskieradio.pl/7/129,Sygnaly-dnia?ref=source',
|
||||
'only_matching': True
|
||||
}, {
|
||||
'url': 'http://www.polskieradio.pl/37,RedakcjaKatolicka/4143,Kierunek-Krakow',
|
||||
'info_dict': {
|
||||
'id': '4143',
|
||||
'title': 'Kierunek Kraków',
|
||||
},
|
||||
'playlist_mincount': 61
|
||||
}, {
|
||||
'url': 'http://www.polskieradio.pl/10,czworka/214,muzyka',
|
||||
'info_dict': {
|
||||
'id': '214',
|
||||
'title': 'Muzyka',
|
||||
},
|
||||
'playlist_mincount': 61
|
||||
}, {
|
||||
'url': 'http://www.polskieradio.pl/7,Jedynka/5102,HISTORIA-ZYWA',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.polskieradio.pl/8,Dwojka/196,Publicystyka',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if PolskieRadioIE.suitable(url) else super(PolskieRadioCategoryIE, cls).suitable(url)
|
||||
|
||||
def _entries(self, url, page, category_id):
|
||||
content = page
|
||||
for page_num in itertools.count(2):
|
||||
for a_entry, entry_id in re.findall(
|
||||
r'(?s)<article[^>]+>.*?(<a[^>]+href=["\']/\d+/\d+/Artykul/(\d+)[^>]+>).*?</article>',
|
||||
content):
|
||||
entry = extract_attributes(a_entry)
|
||||
href = entry.get('href')
|
||||
if not href:
|
||||
continue
|
||||
yield self.url_result(
|
||||
compat_urlparse.urljoin(url, href), PolskieRadioIE.ie_key(),
|
||||
entry_id, entry.get('title'))
|
||||
mobj = re.search(
|
||||
r'<div[^>]+class=["\']next["\'][^>]*>\s*<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
content)
|
||||
if not mobj:
|
||||
break
|
||||
next_url = compat_urlparse.urljoin(url, mobj.group('url'))
|
||||
content = self._download_webpage(
|
||||
next_url, category_id, 'Downloading page %s' % page_num)
|
||||
|
||||
def _real_extract(self, url):
|
||||
category_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, category_id)
|
||||
title = self._html_search_regex(
|
||||
r'<title>([^<]+) - [^<]+ - [^<]+</title>',
|
||||
webpage, 'title', fatal=False)
|
||||
return self.playlist_result(
|
||||
self._entries(url, webpage, category_id),
|
||||
category_id, title)
|
||||
|
||||
@ -15,6 +15,7 @@ from ..compat import (
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
orderedSet,
|
||||
sanitized_Request,
|
||||
str_to_int,
|
||||
@ -48,6 +49,8 @@ class PornHubIE(InfoExtractor):
|
||||
'dislike_count': int,
|
||||
'comment_count': int,
|
||||
'age_limit': 18,
|
||||
'tags': list,
|
||||
'categories': list,
|
||||
},
|
||||
}, {
|
||||
# non-ASCII title
|
||||
@ -63,6 +66,8 @@ class PornHubIE(InfoExtractor):
|
||||
'dislike_count': int,
|
||||
'comment_count': int,
|
||||
'age_limit': 18,
|
||||
'tags': list,
|
||||
'categories': list,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
@ -183,6 +188,15 @@ class PornHubIE(InfoExtractor):
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
page_params = self._parse_json(self._search_regex(
|
||||
r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
|
||||
webpage, 'page parameters', group='data', default='{}'),
|
||||
video_id, transform_source=js_to_json, fatal=False)
|
||||
tags = categories = None
|
||||
if page_params:
|
||||
tags = page_params.get('tags', '').split(',')
|
||||
categories = page_params.get('categories', '').split(',')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'uploader': video_uploader,
|
||||
@ -195,6 +209,8 @@ class PornHubIE(InfoExtractor):
|
||||
'comment_count': comment_count,
|
||||
'formats': formats,
|
||||
'age_limit': 18,
|
||||
'tags': tags,
|
||||
'categories': categories,
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -2,7 +2,6 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import random
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
@ -13,61 +12,69 @@ from ..utils import (
|
||||
|
||||
|
||||
class PornoVoisinesIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
|
||||
|
||||
_VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
|
||||
'/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
|
||||
|
||||
_SERVER_NUMBERS = (1, 2)
|
||||
_VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/videos/show/(?P<id>\d+)/(?P<display_id>[^/.]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
|
||||
'md5': '5ac670803bc12e9e7f9f662ce64cf1d1',
|
||||
'url': 'http://www.pornovoisines.com/videos/show/919/recherche-appartement.html',
|
||||
'md5': '6f8aca6a058592ab49fe701c8ba8317b',
|
||||
'info_dict': {
|
||||
'id': '1285',
|
||||
'id': '919',
|
||||
'display_id': 'recherche-appartement',
|
||||
'ext': 'mp4',
|
||||
'title': 'Recherche appartement',
|
||||
'description': 'md5:819ea0b785e2a04667a1a01cdc89594e',
|
||||
'description': 'md5:fe10cb92ae2dd3ed94bb4080d11ff493',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'upload_date': '20140925',
|
||||
'duration': 120,
|
||||
'view_count': int,
|
||||
'average_rating': float,
|
||||
'categories': ['Débutantes', 'Scénario', 'Sodomie'],
|
||||
'categories': ['Débutante', 'Débutantes', 'Scénario', 'Sodomie'],
|
||||
'age_limit': 18,
|
||||
'subtitles': {
|
||||
'fr': [{
|
||||
'ext': 'vtt',
|
||||
}]
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def build_video_url(cls, num):
|
||||
return cls._VIDEO_URL_TEMPLATE % (random.choice(cls._SERVER_NUMBERS), num)
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id')
|
||||
|
||||
settings_url = self._download_json(
|
||||
'http://www.pornovoisines.com/api/video/%s/getsettingsurl/' % video_id,
|
||||
video_id, note='Getting settings URL')['video_settings_url']
|
||||
settings = self._download_json(settings_url, video_id)['data']
|
||||
|
||||
formats = []
|
||||
for kind, data in settings['variants'].items():
|
||||
if kind == 'HLS':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
data, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
|
||||
elif kind == 'MP4':
|
||||
for item in data:
|
||||
formats.append({
|
||||
'url': item['url'],
|
||||
'height': item.get('height'),
|
||||
'bitrate': item.get('bitrate'),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_url = self.build_video_url(video_id)
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<h1>(.+?)</h1>', webpage, 'title', flags=re.DOTALL)
|
||||
description = self._html_search_regex(
|
||||
r'<article id="descriptif">(.+?)</article>',
|
||||
webpage, 'description', fatal=False, flags=re.DOTALL)
|
||||
|
||||
thumbnail = self._search_regex(
|
||||
r'<div id="mediaspace%s">\s*<img src="/?([^"]+)"' % video_id,
|
||||
webpage, 'thumbnail', fatal=False)
|
||||
if thumbnail:
|
||||
thumbnail = 'http://www.pornovoisines.com/%s' % thumbnail
|
||||
# The webpage has a bug - there's no space between "thumb" and src=
|
||||
thumbnail = self._html_search_regex(
|
||||
r'<img[^>]+class=([\'"])thumb\1[^>]*src=([\'"])(?P<url>[^"]+)\2',
|
||||
webpage, 'thumbnail', fatal=False, group='url')
|
||||
|
||||
upload_date = unified_strdate(self._search_regex(
|
||||
r'Publié le ([\d-]+)', webpage, 'upload date', fatal=False))
|
||||
duration = int_or_none(self._search_regex(
|
||||
'Durée (\d+)', webpage, 'duration', fatal=False))
|
||||
r'Le\s*<b>([\d/]+)', webpage, 'upload date', fatal=False))
|
||||
duration = settings.get('main', {}).get('duration')
|
||||
view_count = int_or_none(self._search_regex(
|
||||
r'(\d+) vues', webpage, 'view count', fatal=False))
|
||||
average_rating = self._search_regex(
|
||||
@ -75,15 +82,19 @@ class PornoVoisinesIE(InfoExtractor):
|
||||
if average_rating:
|
||||
average_rating = float_or_none(average_rating.replace(',', '.'))
|
||||
|
||||
categories = self._html_search_meta(
|
||||
'keywords', webpage, 'categories', fatal=False)
|
||||
categories = self._html_search_regex(
|
||||
r'(?s)Catégories\s*:\s*<b>(.+?)</b>', webpage, 'categories', fatal=False)
|
||||
if categories:
|
||||
categories = [category.strip() for category in categories.split(',')]
|
||||
|
||||
subtitles = {'fr': [{
|
||||
'url': subtitle,
|
||||
} for subtitle in settings.get('main', {}).get('vtt_tracks', {}).values()]}
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': video_url,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
@ -93,4 +104,5 @@ class PornoVoisinesIE(InfoExtractor):
|
||||
'average_rating': average_rating,
|
||||
'categories': categories,
|
||||
'age_limit': 18,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
@ -15,7 +15,111 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class ProSiebenSat1IE(InfoExtractor):
|
||||
class ProSiebenSat1BaseIE(InfoExtractor):
|
||||
def _extract_video_info(self, url, clip_id):
|
||||
client_location = url
|
||||
|
||||
video = self._download_json(
|
||||
'http://vas.sim-technik.de/vas/live/v2/videos',
|
||||
clip_id, 'Downloading videos JSON', query={
|
||||
'access_token': self._TOKEN,
|
||||
'client_location': client_location,
|
||||
'client_name': self._CLIENT_NAME,
|
||||
'ids': clip_id,
|
||||
})[0]
|
||||
|
||||
if video.get('is_protected') is True:
|
||||
raise ExtractorError('This video is DRM protected.', expected=True)
|
||||
|
||||
duration = float_or_none(video.get('duration'))
|
||||
source_ids = [compat_str(source['id']) for source in video['sources']]
|
||||
|
||||
client_id = self._SALT[:2] + sha1(''.join([clip_id, self._SALT, self._TOKEN, client_location, self._SALT, self._CLIENT_NAME]).encode('utf-8')).hexdigest()
|
||||
|
||||
sources = self._download_json(
|
||||
'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id,
|
||||
clip_id, 'Downloading sources JSON', query={
|
||||
'access_token': self._TOKEN,
|
||||
'client_id': client_id,
|
||||
'client_location': client_location,
|
||||
'client_name': self._CLIENT_NAME,
|
||||
})
|
||||
server_id = sources['server_id']
|
||||
|
||||
def fix_bitrate(bitrate):
|
||||
bitrate = int_or_none(bitrate)
|
||||
if not bitrate:
|
||||
return None
|
||||
return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
|
||||
|
||||
formats = []
|
||||
for source_id in source_ids:
|
||||
client_id = self._SALT[:2] + sha1(''.join([self._SALT, clip_id, self._TOKEN, server_id, client_location, source_id, self._SALT, self._CLIENT_NAME]).encode('utf-8')).hexdigest()
|
||||
urls = self._download_json(
|
||||
'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id,
|
||||
clip_id, 'Downloading urls JSON', fatal=False, query={
|
||||
'access_token': self._TOKEN,
|
||||
'client_id': client_id,
|
||||
'client_location': client_location,
|
||||
'client_name': self._CLIENT_NAME,
|
||||
'server_id': server_id,
|
||||
'source_ids': source_id,
|
||||
})
|
||||
if not urls:
|
||||
continue
|
||||
if urls.get('status_code') != 0:
|
||||
raise ExtractorError('This video is unavailable', expected=True)
|
||||
urls_sources = urls['sources']
|
||||
if isinstance(urls_sources, dict):
|
||||
urls_sources = urls_sources.values()
|
||||
for source in urls_sources:
|
||||
source_url = source.get('url')
|
||||
if not source_url:
|
||||
continue
|
||||
protocol = source.get('protocol')
|
||||
mimetype = source.get('mimetype')
|
||||
if mimetype == 'application/f4m+xml' or 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
source_url, clip_id, f4m_id='hds', fatal=False))
|
||||
elif mimetype == 'application/x-mpegURL':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
source_url, clip_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
tbr = fix_bitrate(source['bitrate'])
|
||||
if protocol in ('rtmp', 'rtmpe'):
|
||||
mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
|
||||
if not mobj:
|
||||
continue
|
||||
path = mobj.group('path')
|
||||
mp4colon_index = path.rfind('mp4:')
|
||||
app = path[:mp4colon_index]
|
||||
play_path = path[mp4colon_index:]
|
||||
formats.append({
|
||||
'url': '%s/%s' % (mobj.group('url'), app),
|
||||
'app': app,
|
||||
'play_path': play_path,
|
||||
'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
|
||||
'page_url': 'http://www.prosieben.de',
|
||||
'tbr': tbr,
|
||||
'ext': 'flv',
|
||||
'format_id': 'rtmp%s' % ('-%d' % tbr if tbr else ''),
|
||||
})
|
||||
else:
|
||||
formats.append({
|
||||
'url': source_url,
|
||||
'tbr': tbr,
|
||||
'format_id': 'http%s' % ('-%d' % tbr if tbr else ''),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'duration': duration,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class ProSiebenSat1IE(ProSiebenSat1BaseIE):
|
||||
IE_NAME = 'prosiebensat1'
|
||||
IE_DESC = 'ProSiebenSat.1 Digital'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany|7tv)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
|
||||
@ -188,6 +292,9 @@ class ProSiebenSat1IE(InfoExtractor):
|
||||
},
|
||||
]
|
||||
|
||||
_TOKEN = 'prosieben'
|
||||
_SALT = '01!8d8F_)r9]4s[qeuXfP%'
|
||||
_CLIENT_NAME = 'kolibri-2.0.19-splec4'
|
||||
_CLIPID_REGEXES = [
|
||||
r'"clip_id"\s*:\s+"(\d+)"',
|
||||
r'clipid: "(\d+)"',
|
||||
@ -234,123 +341,22 @@ class ProSiebenSat1IE(InfoExtractor):
|
||||
def _extract_clip(self, url, webpage):
|
||||
clip_id = self._html_search_regex(
|
||||
self._CLIPID_REGEXES, webpage, 'clip id')
|
||||
|
||||
access_token = 'prosieben'
|
||||
client_name = 'kolibri-2.0.19-splec4'
|
||||
client_location = url
|
||||
|
||||
video = self._download_json(
|
||||
'http://vas.sim-technik.de/vas/live/v2/videos',
|
||||
clip_id, 'Downloading videos JSON', query={
|
||||
'access_token': access_token,
|
||||
'client_location': client_location,
|
||||
'client_name': client_name,
|
||||
'ids': clip_id,
|
||||
})[0]
|
||||
|
||||
if video.get('is_protected') is True:
|
||||
raise ExtractorError('This video is DRM protected.', expected=True)
|
||||
|
||||
duration = float_or_none(video.get('duration'))
|
||||
source_ids = [compat_str(source['id']) for source in video['sources']]
|
||||
|
||||
g = '01!8d8F_)r9]4s[qeuXfP%'
|
||||
client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name]).encode('utf-8')).hexdigest()
|
||||
|
||||
sources = self._download_json(
|
||||
'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id,
|
||||
clip_id, 'Downloading sources JSON', query={
|
||||
'access_token': access_token,
|
||||
'client_id': client_id,
|
||||
'client_location': client_location,
|
||||
'client_name': client_name,
|
||||
})
|
||||
server_id = sources['server_id']
|
||||
|
||||
title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
|
||||
|
||||
def fix_bitrate(bitrate):
|
||||
bitrate = int_or_none(bitrate)
|
||||
if not bitrate:
|
||||
return None
|
||||
return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
|
||||
|
||||
formats = []
|
||||
for source_id in source_ids:
|
||||
client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id, client_location, source_id, g, client_name]).encode('utf-8')).hexdigest()
|
||||
urls = self._download_json(
|
||||
'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id,
|
||||
clip_id, 'Downloading urls JSON', fatal=False, query={
|
||||
'access_token': access_token,
|
||||
'client_id': client_id,
|
||||
'client_location': client_location,
|
||||
'client_name': client_name,
|
||||
'server_id': server_id,
|
||||
'source_ids': source_id,
|
||||
})
|
||||
if not urls:
|
||||
continue
|
||||
if urls.get('status_code') != 0:
|
||||
raise ExtractorError('This video is unavailable', expected=True)
|
||||
urls_sources = urls['sources']
|
||||
if isinstance(urls_sources, dict):
|
||||
urls_sources = urls_sources.values()
|
||||
for source in urls_sources:
|
||||
source_url = source.get('url')
|
||||
if not source_url:
|
||||
continue
|
||||
protocol = source.get('protocol')
|
||||
mimetype = source.get('mimetype')
|
||||
if mimetype == 'application/f4m+xml' or 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
source_url, clip_id, f4m_id='hds', fatal=False))
|
||||
elif mimetype == 'application/x-mpegURL':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
source_url, clip_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
tbr = fix_bitrate(source['bitrate'])
|
||||
if protocol in ('rtmp', 'rtmpe'):
|
||||
mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
|
||||
if not mobj:
|
||||
continue
|
||||
path = mobj.group('path')
|
||||
mp4colon_index = path.rfind('mp4:')
|
||||
app = path[:mp4colon_index]
|
||||
play_path = path[mp4colon_index:]
|
||||
formats.append({
|
||||
'url': '%s/%s' % (mobj.group('url'), app),
|
||||
'app': app,
|
||||
'play_path': play_path,
|
||||
'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
|
||||
'page_url': 'http://www.prosieben.de',
|
||||
'tbr': tbr,
|
||||
'ext': 'flv',
|
||||
'format_id': 'rtmp%s' % ('-%d' % tbr if tbr else ''),
|
||||
})
|
||||
else:
|
||||
formats.append({
|
||||
'url': source_url,
|
||||
'tbr': tbr,
|
||||
'format_id': 'http%s' % ('-%d' % tbr if tbr else ''),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
info = self._extract_video_info(url, clip_id)
|
||||
description = self._html_search_regex(
|
||||
self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))
|
||||
|
||||
return {
|
||||
info.update({
|
||||
'id': clip_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'upload_date': upload_date,
|
||||
'duration': duration,
|
||||
'formats': formats,
|
||||
}
|
||||
})
|
||||
return info
|
||||
|
||||
def _extract_playlist(self, url, webpage):
|
||||
playlist_id = self._html_search_regex(
|
||||
|
||||
@ -1,88 +1,51 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .prosiebensat1 import ProSiebenSat1BaseIE
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
unified_strdate,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
compat_str,
|
||||
)
|
||||
|
||||
|
||||
class Puls4IE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?puls4\.com/video/[^/]+/play/(?P<id>[0-9]+)'
|
||||
class Puls4IE(ProSiebenSat1BaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>(?:[^/]+/)*?videos/[^?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.puls4.com/video/pro-und-contra/play/2716816',
|
||||
'md5': '49f6a6629747eeec43cef6a46b5df81d',
|
||||
'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
|
||||
'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
|
||||
'info_dict': {
|
||||
'id': '2716816',
|
||||
'ext': 'mp4',
|
||||
'title': 'Pro und Contra vom 23.02.2015',
|
||||
'description': 'md5:293e44634d9477a67122489994675db6',
|
||||
'duration': 2989,
|
||||
'upload_date': '20150224',
|
||||
'id': '118118',
|
||||
'ext': 'flv',
|
||||
'title': 'Tobias Homberger von myclubs im #2min2miotalk',
|
||||
'description': 'md5:f9def7c5e8745d6026d8885487d91955',
|
||||
'upload_date': '20160830',
|
||||
'uploader': 'PULS_4',
|
||||
},
|
||||
'skip': 'Only works from Germany',
|
||||
}, {
|
||||
'url': 'http://www.puls4.com/video/kult-spielfilme/play/1298106',
|
||||
'md5': '6a48316c8903ece8dab9b9a7bf7a59ec',
|
||||
'info_dict': {
|
||||
'id': '1298106',
|
||||
'ext': 'mp4',
|
||||
'title': 'Lucky Fritz',
|
||||
},
|
||||
'skip': 'Only works from Germany',
|
||||
}]
|
||||
_TOKEN = 'puls4'
|
||||
_SALT = '01!kaNgaiNgah1Ie4AeSha'
|
||||
_CLIENT_NAME = ''
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
error_message = self._html_search_regex(
|
||||
r'<div[^>]+class="message-error"[^>]*>(.+?)</div>',
|
||||
webpage, 'error message', default=None)
|
||||
if error_message:
|
||||
raise ExtractorError(
|
||||
'%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
|
||||
real_url = self._html_search_regex(
|
||||
r'\"fsk-button\".+?href=\"([^"]+)',
|
||||
webpage, 'fsk_button', default=None)
|
||||
if real_url:
|
||||
webpage = self._download_webpage(real_url, video_id)
|
||||
|
||||
player = self._search_regex(
|
||||
r'p4_video_player(?:_iframe)?\("video_\d+_container"\s*,(.+?)\);\s*\}',
|
||||
webpage, 'player')
|
||||
|
||||
player_json = self._parse_json(
|
||||
'[%s]' % player, video_id,
|
||||
transform_source=lambda s: s.replace('undefined,', ''))
|
||||
|
||||
formats = None
|
||||
result = None
|
||||
|
||||
for v in player_json:
|
||||
if isinstance(v, list) and not formats:
|
||||
formats = [{
|
||||
'url': f['url'],
|
||||
'format': 'hd' if f.get('hd') else 'sd',
|
||||
'width': int_or_none(f.get('size_x')),
|
||||
'height': int_or_none(f.get('size_y')),
|
||||
'tbr': int_or_none(f.get('bitrate')),
|
||||
} for f in v]
|
||||
self._sort_formats(formats)
|
||||
elif isinstance(v, dict) and not result:
|
||||
result = {
|
||||
'id': video_id,
|
||||
'title': v['videopartname'].strip(),
|
||||
'description': v.get('videotitle'),
|
||||
'duration': int_or_none(v.get('videoduration') or v.get('episodeduration')),
|
||||
'upload_date': unified_strdate(v.get('clipreleasetime')),
|
||||
'uploader': v.get('channel'),
|
||||
}
|
||||
|
||||
result['formats'] = formats
|
||||
|
||||
return result
|
||||
path = self._match_id(url)
|
||||
content_path = self._download_json(
|
||||
'http://www.puls4.com/api/json-fe/page/' + path, path)['content'][0]['url']
|
||||
media = self._download_json(
|
||||
'http://www.puls4.com' + content_path,
|
||||
content_path)['mediaCurrent']
|
||||
player_content = media['playerContent']
|
||||
info = self._extract_video_info(url, player_content['id'])
|
||||
info.update({
|
||||
'id': compat_str(media['objectId']),
|
||||
'title': player_content['title'],
|
||||
'description': media.get('description'),
|
||||
'thumbnail': media.get('previewLink'),
|
||||
'upload_date': unified_strdate(media.get('date')),
|
||||
'duration': parse_duration(player_content.get('duration')),
|
||||
'episode': player_content.get('episodePartName'),
|
||||
'show': media.get('channel'),
|
||||
'season_id': player_content.get('seasonId'),
|
||||
'uploader': player_content.get('sourceCompany'),
|
||||
})
|
||||
return info
|
||||
|
||||
@ -18,7 +18,7 @@ from ..utils import (
|
||||
class QQMusicIE(InfoExtractor):
|
||||
IE_NAME = 'qqmusic'
|
||||
IE_DESC = 'QQ音乐'
|
||||
_VALID_URL = r'https?://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
|
||||
_VALID_URL = r'https?://y\.qq\.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
|
||||
'md5': '9ce1c1c8445f561506d2e3cfb0255705',
|
||||
@ -172,7 +172,7 @@ class QQPlaylistBaseIE(InfoExtractor):
|
||||
class QQMusicSingerIE(QQPlaylistBaseIE):
|
||||
IE_NAME = 'qqmusic:singer'
|
||||
IE_DESC = 'QQ音乐 - 歌手'
|
||||
_VALID_URL = r'https?://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
|
||||
_VALID_URL = r'https?://y\.qq\.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
|
||||
_TEST = {
|
||||
'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
|
||||
'info_dict': {
|
||||
@ -217,7 +217,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
|
||||
class QQMusicAlbumIE(QQPlaylistBaseIE):
|
||||
IE_NAME = 'qqmusic:album'
|
||||
IE_DESC = 'QQ音乐 - 专辑'
|
||||
_VALID_URL = r'https?://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
|
||||
_VALID_URL = r'https?://y\.qq\.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
x
Reference in New Issue
Block a user