1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-27 19:04:32 +01:00
youtube-dl/youtube_dl/extractor/peertube.py
Aakash Gajjar b827ee921f
pull changes from remote master (#190)
* [scrippsnetworks] Add new extractor(closes #19857)(closes #22981)

* [teachable] Improve locked lessons detection (#23528)

* [teachable] Fail with error message if no video URL found

* [extractors] add missing import for ScrippsNetworksIE

* [brightcove] cache brightcove player policy keys

* [prosiebensat1] improve geo restriction handling(closes #23571)

* [soundcloud] automatically update client id on failing requests

* [spankbang] Fix extraction (closes #23307, closes #23423, closes #23444)

* [spankbang] Improve removed video detection (#23423)

* [brightcove] update policy key on failing requests

* [pornhub] Fix extraction and add support for m3u8 formats (closes #22749, closes #23082)

* [pornhub] Improve locked videos detection (closes #22449, closes #22780)

* [brightcove] invalidate policy key cache on failing requests

* [soundcloud] fix client id extraction for non fatal requests

* [ChangeLog] Actualize
[ci skip]

* [devscripts/create-github-release] Switch to using PAT for authentication

Basic authentication will be deprecated soon

* release 2020.01.01

* [redtube] Detect private videos (#23518)

* [vice] improve extraction(closes #23631)

* [devscripts/create-github-release] Remove unused import

* [wistia] improve format extraction and extract subtitles(closes #22590)

* [nrktv:seriebase] Fix extraction (closes #23625) (#23537)

* [discovery] fix anonymous token extraction(closes #23650)

* [scrippsnetworks] add support for www.discovery.com videos

* [scrippsnetworks] correct test case URL

* [dctp] fix format extraction(closes #23656)

* [pandatv] Remove extractor (#23630)

* [naver] improve extraction

- improve geo-restriction handling
- extract automatic captions
- extract uploader metadata
- extract VLive HLS formats

* [naver] improve metadata extraction

* [cloudflarestream] improve extraction

- add support for bytehighway.net domain
- add support for signed URLs
- extract thumbnail

* [cloudflarestream] import embed URL extraction

* [lego] fix extraction and extract subtitle(closes #23687)

* [safari] Fix kaltura session extraction (closes #23679) (#23670)

* [orf:fm4] Fix extraction (#23599)

* [orf:radio] Clean description and improve extraction

* [twitter] add support for promo_video_website cards(closes #23711)

* [vodplatform] add support for embed.kwikmotion.com domain

* [ndr:base:embed] Improve thumbnails extraction (closes #23731)

* [canvas] Add support for new API endpoint and update tests (closes #17680, closes #18629)

* [travis] Add flake8 job (#23720)

* [yourporn] Fix extraction (closes #21645, closes #22255, closes #23459)

* [ChangeLog] Actualize
[ci skip]

* release 2020.01.15

* [soundcloud] Restore previews extraction (closes #23739)

* [orf:tvthek] Improve geo restricted videos detection (closes #23741)

* [zype] improve extraction

- extract subtitles(closes #21258)
- support URLs with alternative keys/tokens(#21258)
- extract more metadata

* [americastestkitchen] fix extraction

* [nbc] add support for nbc multi network URLs(closes #23049)

* [ard] improve extraction(closes #23761)

- simplify extraction
- extract age limit and series
- bypass geo-restriction

* [ivi:compilation] Fix entries extraction (closes #23770)

* [24video] Add support for 24video.vip (closes #23753)

* [businessinsider] Fix jwplatform id extraction (closes #22929) (#22954)

* [ard] add a missing condition

* [azmedien] fix extraction(closes #23783)

* [voicerepublic] fix extraction

* [stretchinternet] fix extraction(closes #4319)

* [youtube] Fix sigfunc name extraction (closes #23819)

* [ChangeLog] Actualize
[ci skip]

* release 2020.01.24

* [soundcloud] imporve private playlist/set tracks extraction

https://github.com/ytdl-org/youtube-dl/issues/3707#issuecomment-577873539

* [svt] fix article extraction(closes #22897)(closes #22919)

* [svt] fix series extraction(closes #22297)

* [viewlift] improve extraction

- fix extraction(closes #23851)
- add add support for authentication
- add support for more domains

* [vimeo] fix album extraction(closes #23864)

* [tva] Relax _VALID_URL (closes #23903)

* [tv5mondeplus] Fix extraction (closes #23907, closes #23911)

* [twitch:stream] Lowercase channel id for stream request (closes #23917)

* [sportdeutschland] Update to new sportdeutschland API

They switched to SSL, but under a different host AND path...
Remove the old test cases because these videos have become unavailable.

* [popcorntimes] Add extractor (closes #23949)

* [thisoldhouse] fix extraction(closes #23951)

* [toggle] Add support for mewatch.sg (closes #23895) (#23930)

* [compat] Introduce compat_realpath (refs #23991)

* [update] Fix updating via symlinks (closes #23991)

* [nytimes] improve format sorting(closes #24010)

* [abc:iview] Support 720p (#22907) (#22921)

* [nova:embed] Fix extraction (closes #23672)

* [nova:embed] Improve (closes #23690)

* [nova] Improve extraction (refs #23690)

* [jpopsuki] Remove extractor (closes #23858)

* [YoutubeDL] Fix playlist entry indexing with --playlist-items (closes #10591, closes #10622)

* [test_YoutubeDL] Fix get_ids

* [test_YoutubeDL] Add tests for #10591 (closes #23873)

* [24video] Add support for porn.24video.net (closes #23779, closes #23784)

* [npr] Add support for streams (closes #24042)

* [ChangeLog] Actualize
[ci skip]

* release 2020.02.16

* [tv2dk:bornholm:play] Fix extraction (#24076)

* [imdb] Fix extraction (closes #23443)

* [wistia] Add support for multiple generic embeds (closes #8347, closes #11385)

* [teachable] Add support for multiple videos per lecture (closes #24101)

* [pornhd] Fix extraction (closes #24128)

* [options] Remove duplicate short option -v for --version (#24162)

* [extractor/common] Convert ISM manifest to unicode before processing on python 2 (#24152)

* [YoutubeDL] Force redirect URL to unicode on python 2

* Remove no longer needed compat_str around geturl

* [youjizz] Fix extraction (closes #24181)

* [test_subtitles] Remove obsolete test

* [zdf:channel] Fix tests

* [zapiks] Fix test

* [xtube] Fix metadata extraction (closes #21073, closes #22455)

* [xtube:user] Fix test

* [telecinco] Fix extraction (refs #24195)

* [telecinco] Add support for article opening videos

* [franceculture] Fix extraction (closes #24204)

* [xhamster] Fix extraction (closes #24205)

* [ChangeLog] Actualize
[ci skip]

* release 2020.03.01

* [vimeo] Fix subtitles URLs (#24209)

* [servus] Add support for new URL schema (closes #23475, closes #23583, closes #24142)

* [youtube:playlist] Fix tests (closes #23872) (#23885)

* [peertube] Improve extraction

* [peertube] Fix issues and improve extraction (closes #23657)

* [pornhub] Improve title extraction (closes #24184)

* [vimeo] fix showcase password protected video extraction(closes #24224)

* [youtube] Fix age-gated videos support without login (closes #24248)

* [youtube] Fix tests

* [ChangeLog] Actualize
[ci skip]

* release 2020.03.06

* [nhk] update API version(closes #24270)

* [youtube] Improve extraction in 429 error conditions (closes #24283)

* [youtube] Improve age-gated videos extraction in 429 error conditions (refs #24283)

* [youtube] Remove outdated code

Additional get_video_info requests don't seem to provide any extra itags any longer

* [README.md] Clarify 429 error

* [pornhub] Add support for pornhubpremium.com (#24288)

* [utils] Add support for cookies with spaces used instead of tabs

* [ChangeLog] Actualize
[ci skip]

* release 2020.03.08

* Revert "[utils] Add support for cookies with spaces used instead of tabs"

According to [1] TABs must be used as separators between fields.
Files produces by some tools with spaces as separators are considered
malformed.

1. https://curl.haxx.se/docs/http-cookies.html

This reverts commit cff99c91d1.

* [utils] Add reference to cookie file format

* Revert "[vimeo] fix showcase password protected video extraction(closes #24224)"

This reverts commit 12ee431676.

* [nhk] Relax _VALID_URL (#24329)

* [nhk] Remove obsolete rtmp formats (closes #24329)

* [nhk] Update m3u8 URL and use native hls (#24329)

* [ndr] Fix extraction (closes #24326)

* [xtube] Fix formats extraction (closes #24348)

* [xtube] Fix typo

* [hellporno] Fix extraction (closes #24399)

* [cbc:watch] Add support for authentication

* [cbc:watch] Fix authenticated device token caching (closes #19160)

* [soundcloud] fix download url extraction(closes #24394)

* [limelight] remove disabled API requests(closes #24255)

* [bilibili] Add support for new URL schema with BV ids (closes #24439, closes #24442)

* [bilibili] Add support for player.bilibili.com (closes #24402)

* [teachable] Extract chapter metadata (closes #24421)

* [generic] Look for teachable embeds before wistia

* [teachable] Update upskillcourses domain

New version does not use teachable platform any longer

* [teachable] Update gns3 domain

* [teachable] Update test

* [ChangeLog] Actualize
[ci skip]

* [ChangeLog] Actualize
[ci skip]

* release 2020.03.24

* [spankwire] Fix extraction (closes #18924, closes #20648)

* [spankwire] Add support for generic embeds (refs #24633)

* [youporn] Add support form generic embeds

* [mofosex] Add support for generic embeds (closes #24633)

* [tele5] Fix extraction (closes #24553)

* [extractor/common] Skip malformed ISM manifest XMLs while extracting ISM formats (#24667)

* [tv4] Fix ISM formats extraction (closes #24667)

* [twitch:clips] Extend _VALID_URL (closes #24290) (#24642)

* [motherless] Fix extraction (closes #24699)

* [nova:embed] Fix extraction (closes #24700)

* [youtube] Skip broken multifeed videos (closes #24711)

* [soundcloud] Extract AAC format

* [soundcloud] Improve AAC format extraction (closes #19173, closes #24708)

* [thisoldhouse] Fix video id extraction (closes #24548)

Added support for:
with of without "www."
and either  ".chorus.build" or ".com"

It now validated correctly on older URL's
```
<iframe src="https://thisoldhouse.chorus.build/videos/zype/5e33baec27d2e50001d5f52f
```
and newer ones
```
<iframe src="https://www.thisoldhouse.com/videos/zype/5e2b70e95216cc0001615120
```

* [thisoldhouse] Improve video id extraction (closes #24549)

* [youtube] Fix DRM videos detection (refs #24736)

* [options] Clarify doc on --exec command (closes #19087) (#24883)

* [prosiebensat1] Improve extraction and remove 7tv.de support (#24948)

* [prosiebensat1] Extract series metadata

* [tenplay] Relax _VALID_URL (closes #25001)

* [tvplay] fix Viafree extraction(closes #15189)(closes #24473)(closes #24789)

* [yahoo] fix GYAO Player extraction and relax title URL regex(closes #24178)(closes #24778)

* [youtube] Use redirected video id if any (closes #25063)

* [youtube] Improve player id extraction and add tests

* [extractor/common] Extract multiple JSON-LD entries

* [crunchyroll] Fix and improve extraction (closes #25096, closes #25060)

* [ChangeLog] Actualize
[ci skip]

* release 2020.05.03

* [puhutv] Remove no longer available HTTP formats (closes #25124)

* [utils] Improve cookie files support

+ Add support for UTF-8 in cookie files
* Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)

* [dailymotion] Fix typo

* [compat] Introduce compat_cookiejar_Cookie

* [extractor/common] Use compat_cookiejar_Cookie for _set_cookie (closes #23256, closes #24776)

To always ensure cookie name and value are bytestrings on python 2.

* [orf] Add support for more radio stations (closes #24938) (#24968)

* [uol] fix extraction(closes #22007)

* [downloader/http] Finish downloading once received data length matches expected

Always do this if possible, i.e. if Content-Length or expected length is known, not only in test.
This will save unnecessary last extra loop trying to read 0 bytes.

* [downloader/http] Request last data block of exact remaining size

Always request last data block of exact size remaining to download if possible not the current block size.

* [iprima] Improve extraction (closes #25138)

* [youtube] Improve signature cipher extraction (closes #25188)

* [ChangeLog] Actualize
[ci skip]

* release 2020.05.08

* [spike] fix Bellator mgid extraction(closes #25195)

* [bbccouk] PEP8

* [mailru] Fix extraction (closes #24530) (#25239)

* [README.md] flake8 HTTPS URL (#25230)

* [youtube] Add support for yewtu.be (#25226)

* [soundcloud] reduce API playlist page limit(closes #25274)

* [vimeo] improve format extraction and sorting(closes #25285)

* [redtube] Improve title extraction (#25208)

* [indavideo] Switch to HTTPS for API request (#25191)

* [utils] Fix file permissions in write_json_file (closes #12471) (#25122)

* [redtube] Improve formats extraction and extract m3u8 formats (closes #25311, closes #25321)

* [ard] Improve _VALID_URL (closes #25134) (#25198)

* [giantbomb] Extend _VALID_URL (#25222)

* [postprocessor/ffmpeg] Embed series metadata with --add-metadata

* [youtube] Add support for more invidious instances (#25417)

* [ard:beta] Extend _VALID_URL (closes #25405)

* [ChangeLog] Actualize
[ci skip]

* release 2020.05.29

* [jwplatform] Improve embeds extraction (closes #25467)

* [periscope] Fix untitled broadcasts (#25482)

* [twitter:broadcast] Add untitled periscope broadcast test

* [malltv] Add support for sk.mall.tv (#25445)

* [brightcove] Fix subtitles extraction (closes #25540)

* [brightcove] Sort imports

* [twitch] Pass v5 accept header and fix thumbnails extraction (closes #25531)

* [twitch:stream] Fix extraction (closes #25528)

* [twitch:stream] Expect 400 and 410 HTTP errors from API

* [tele5] Prefer jwplatform over nexx (closes #25533)

* [jwplatform] Add support for bypass geo restriction

* [tele5] Bypass geo restriction

* [ChangeLog] Actualize
[ci skip]

* release 2020.06.06

* [kaltura] Add support for multiple embeds on a webpage (closes #25523)

* [youtube] Extract chapters from JSON (closes #24819)

* [facebook] Support single-video ID links

I stumbled upon this at https://www.facebook.com/bwfbadminton/posts/10157127020046316 . No idea how prevalent it is yet.

* [youtube] Fix playlist and feed extraction (closes #25675)

* [youtube] Fix thumbnails extraction and remove uploader id extraction warning (closes #25676)

* [youtube] Fix upload date extraction

* [youtube] Improve view count extraction

* [youtube] Fix uploader id and uploader URL extraction

* [ChangeLog] Actualize
[ci skip]

* release 2020.06.16

* [youtube] Fix categories and improve tags extraction

* [youtube] Force old layout (closes #25682, closes #25683, closes #25680, closes #25686)

* [ChangeLog] Actualize
[ci skip]

* release 2020.06.16.1

* [brightcove] Improve embed detection (closes #25674)

* [bellmedia] add support for cp24.com clip URLs(closes #25764)

* [youtube:playlists] Extend _VALID_URL (closes #25810)

* [youtube] Prevent excess HTTP 301 (#25786)

* [wistia] Restrict embed regex (closes #25969)

* [youtube] Improve description extraction (closes #25937) (#25980)

* [youtube] Fix sigfunc name extraction (closes #26134, closes #26135, closes #26136, closes #26137)

* [ChangeLog] Actualize
[ci skip]

* release 2020.07.28

* [xhamster] Extend _VALID_URL (closes #25789) (#25804)

* [xhamster] Fix extraction (closes #26157) (#26254)

* [xhamster] Extend _VALID_URL (closes #25927)

Co-authored-by: Remita Amine <remitamine@gmail.com>
Co-authored-by: Sergey M․ <dstftw@gmail.com>
Co-authored-by: nmeum <soeren+github@soeren-tempel.net>
Co-authored-by: Roxedus <me@roxedus.dev>
Co-authored-by: Singwai Chan <c.singwai@gmail.com>
Co-authored-by: cdarlint <cdarlint@users.noreply.github.com>
Co-authored-by: Johannes N <31795504+jonolt@users.noreply.github.com>
Co-authored-by: jnozsc <jnozsc@gmail.com>
Co-authored-by: Moritz Patelscheck <moritz.patelscheck@campus.tu-berlin.de>
Co-authored-by: PB <3854688+uno20001@users.noreply.github.com>
Co-authored-by: Philipp Hagemeister <phihag@phihag.de>
Co-authored-by: Xaver Hellauer <software@hellauer.bayern>
Co-authored-by: d2au <d2au.dev@gmail.com>
Co-authored-by: Jan 'Yenda' Trmal <jtrmal@gmail.com>
Co-authored-by: jxu <7989982+jxu@users.noreply.github.com>
Co-authored-by: Martin Ström <name@my-domain.se>
Co-authored-by: The Hatsune Daishi <nao20010128@gmail.com>
Co-authored-by: tsia <github@tsia.de>
Co-authored-by: 3risian <59593325+3risian@users.noreply.github.com>
Co-authored-by: Tristan Waddington <tristan.waddington@gmail.com>
Co-authored-by: Devon Meunier <devon.meunier@gmail.com>
Co-authored-by: Felix Stupp <felix.stupp@outlook.com>
Co-authored-by: tom <tomster954@gmail.com>
Co-authored-by: AndrewMBL <62922222+AndrewMBL@users.noreply.github.com>
Co-authored-by: willbeaufoy <will@willbeaufoy.net>
Co-authored-by: Philipp Stehle <anderschwiedu@googlemail.com>
Co-authored-by: hh0rva1h <61889859+hh0rva1h@users.noreply.github.com>
Co-authored-by: comsomisha <shmelev1996@mail.ru>
Co-authored-by: TotalCaesar659 <14265316+TotalCaesar659@users.noreply.github.com>
Co-authored-by: Juan Francisco Cantero Hurtado <iam@juanfra.info>
Co-authored-by: Dave Loyall <dave@the-good-guys.net>
Co-authored-by: tlsssl <63866177+tlsssl@users.noreply.github.com>
Co-authored-by: Rob <ankenyr@gmail.com>
Co-authored-by: Michael Klein <github@a98shuttle.de>
Co-authored-by: JordanWeatherby <47519158+JordanWeatherby@users.noreply.github.com>
Co-authored-by: striker.sh <19488257+strikersh@users.noreply.github.com>
Co-authored-by: Matej Dujava <mdujava@gmail.com>
Co-authored-by: Glenn Slayden <5589855+glenn-slayden@users.noreply.github.com>
Co-authored-by: MRWITEK <mrvvitek@gmail.com>
Co-authored-by: JChris246 <43832407+JChris246@users.noreply.github.com>
Co-authored-by: TheRealDude2 <the.real.dude@gmx.de>
2020-08-25 20:23:34 +05:30

601 lines
27 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
parse_resolution,
str_or_none,
try_get,
unified_timestamp,
url_or_none,
urljoin,
)
class PeerTubeIE(InfoExtractor):
_INSTANCES_RE = r'''(?:
# Taken from https://instances.joinpeertube.org/instances
peertube\.rainbowswingers\.net|
tube\.stanisic\.nl|
peer\.suiri\.us|
medias\.libox\.fr|
videomensoif\.ynh\.fr|
peertube\.travelpandas\.eu|
peertube\.rachetjay\.fr|
peertube\.montecsys\.fr|
tube\.eskuero\.me|
peer\.tube|
peertube\.umeahackerspace\.se|
tube\.nx-pod\.de|
video\.monsieurbidouille\.fr|
tube\.openalgeria\.org|
vid\.lelux\.fi|
video\.anormallostpod\.ovh|
tube\.crapaud-fou\.org|
peertube\.stemy\.me|
lostpod\.space|
exode\.me|
peertube\.snargol\.com|
vis\.ion\.ovh|
videosdulib\.re|
v\.mbius\.io|
videos\.judrey\.eu|
peertube\.osureplayviewer\.xyz|
peertube\.mathieufamily\.ovh|
www\.videos-libr\.es|
fightforinfo\.com|
peertube\.fediverse\.ru|
peertube\.oiseauroch\.fr|
video\.nesven\.eu|
v\.bearvideo\.win|
video\.qoto\.org|
justporn\.cc|
video\.vny\.fr|
peervideo\.club|
tube\.taker\.fr|
peertube\.chantierlibre\.org|
tube\.ipfixe\.info|
tube\.kicou\.info|
tube\.dodsorf\.as|
videobit\.cc|
video\.yukari\.moe|
videos\.elbinario\.net|
hkvideo\.live|
pt\.tux\.tf|
www\.hkvideo\.live|
FIGHTFORINFO\.com|
pt\.765racing\.com|
peertube\.gnumeria\.eu\.org|
nordenmedia\.com|
peertube\.co\.uk|
tube\.darfweb\.eu|
tube\.kalah-france\.org|
0ch\.in|
vod\.mochi\.academy|
film\.node9\.org|
peertube\.hatthieves\.es|
video\.fitchfamily\.org|
peertube\.ddns\.net|
video\.ifuncle\.kr|
video\.fdlibre\.eu|
tube\.22decembre\.eu|
peertube\.harmoniescreatives\.com|
tube\.fabrigli\.fr|
video\.thedwyers\.co|
video\.bruitbruit\.com|
peertube\.foxfam\.club|
peer\.philoxweb\.be|
videos\.bugs\.social|
peertube\.malbert\.xyz|
peertube\.bilange\.ca|
libretube\.net|
diytelevision\.com|
peertube\.fedilab\.app|
libre\.video|
video\.mstddntfdn\.online|
us\.tv|
peertube\.sl-network\.fr|
peertube\.dynlinux\.io|
peertube\.david\.durieux\.family|
peertube\.linuxrocks\.online|
peerwatch\.xyz|
v\.kretschmann\.social|
tube\.otter\.sh|
yt\.is\.nota\.live|
tube\.dragonpsi\.xyz|
peertube\.boneheadmedia\.com|
videos\.funkwhale\.audio|
watch\.44con\.com|
peertube\.gcaillaut\.fr|
peertube\.icu|
pony\.tube|
spacepub\.space|
tube\.stbr\.io|
v\.mom-gay\.faith|
tube\.port0\.xyz|
peertube\.simounet\.net|
play\.jergefelt\.se|
peertube\.zeteo\.me|
tube\.danq\.me|
peertube\.kerenon\.com|
tube\.fab-l3\.org|
tube\.calculate\.social|
peertube\.mckillop\.org|
tube\.netzspielplatz\.de|
vod\.ksite\.de|
peertube\.laas\.fr|
tube\.govital\.net|
peertube\.stephenson\.cc|
bistule\.nohost\.me|
peertube\.kajalinifi\.de|
video\.ploud\.jp|
video\.omniatv\.com|
peertube\.ffs2play\.fr|
peertube\.leboulaire\.ovh|
peertube\.tronic-studio\.com|
peertube\.public\.cat|
peertube\.metalbanana\.net|
video\.1000i100\.fr|
peertube\.alter-nativ-voll\.de|
tube\.pasa\.tf|
tube\.worldofhauru\.xyz|
pt\.kamp\.site|
peertube\.teleassist\.fr|
videos\.mleduc\.xyz|
conf\.tube|
media\.privacyinternational\.org|
pt\.forty-two\.nl|
video\.halle-leaks\.de|
video\.grosskopfgames\.de|
peertube\.schaeferit\.de|
peertube\.jackbot\.fr|
tube\.extinctionrebellion\.fr|
peertube\.f-si\.org|
video\.subak\.ovh|
videos\.koweb\.fr|
peertube\.zergy\.net|
peertube\.roflcopter\.fr|
peertube\.floss-marketing-school\.com|
vloggers\.social|
peertube\.iriseden\.eu|
videos\.ubuntu-paris\.org|
peertube\.mastodon\.host|
armstube\.com|
peertube\.s2s\.video|
peertube\.lol|
tube\.open-plug\.eu|
open\.tube|
peertube\.ch|
peertube\.normandie-libre\.fr|
peertube\.slat\.org|
video\.lacaveatonton\.ovh|
peertube\.uno|
peertube\.servebeer\.com|
peertube\.fedi\.quebec|
tube\.h3z\.jp|
tube\.plus200\.com|
peertube\.eric\.ovh|
tube\.metadocs\.cc|
tube\.unmondemeilleur\.eu|
gouttedeau\.space|
video\.antirep\.net|
nrop\.cant\.at|
tube\.ksl-bmx\.de|
tube\.plaf\.fr|
tube\.tchncs\.de|
video\.devinberg\.com|
hitchtube\.fr|
peertube\.kosebamse\.com|
yunopeertube\.myddns\.me|
peertube\.varney\.fr|
peertube\.anon-kenkai\.com|
tube\.maiti\.info|
tubee\.fr|
videos\.dinofly\.com|
toobnix\.org|
videotape\.me|
voca\.tube|
video\.heromuster\.com|
video\.lemediatv\.fr|
video\.up\.edu\.ph|
balafon\.video|
video\.ivel\.fr|
thickrips\.cloud|
pt\.laurentkruger\.fr|
video\.monarch-pass\.net|
peertube\.artica\.center|
video\.alternanet\.fr|
indymotion\.fr|
fanvid\.stopthatimp\.net|
video\.farci\.org|
v\.lesterpig\.com|
video\.okaris\.de|
tube\.pawelko\.net|
peertube\.mablr\.org|
tube\.fede\.re|
pytu\.be|
evertron\.tv|
devtube\.dev-wiki\.de|
raptube\.antipub\.org|
video\.selea\.se|
peertube\.mygaia\.org|
video\.oh14\.de|
peertube\.livingutopia\.org|
peertube\.the-penguin\.de|
tube\.thechangebook\.org|
tube\.anjara\.eu|
pt\.pube\.tk|
video\.samedi\.pm|
mplayer\.demouliere\.eu|
widemus\.de|
peertube\.me|
peertube\.zapashcanon\.fr|
video\.latavernedejohnjohn\.fr|
peertube\.pcservice46\.fr|
peertube\.mazzonetto\.eu|
video\.irem\.univ-paris-diderot\.fr|
video\.livecchi\.cloud|
alttube\.fr|
video\.coop\.tools|
video\.cabane-libre\.org|
peertube\.openstreetmap\.fr|
videos\.alolise\.org|
irrsinn\.video|
video\.antopie\.org|
scitech\.video|
tube2\.nemsia\.org|
video\.amic37\.fr|
peertube\.freeforge\.eu|
video\.arbitrarion\.com|
video\.datsemultimedia\.com|
stoptrackingus\.tv|
peertube\.ricostrongxxx\.com|
docker\.videos\.lecygnenoir\.info|
peertube\.togart\.de|
tube\.postblue\.info|
videos\.domainepublic\.net|
peertube\.cyber-tribal\.com|
video\.gresille\.org|
peertube\.dsmouse\.net|
cinema\.yunohost\.support|
tube\.theocevaer\.fr|
repro\.video|
tube\.4aem\.com|
quaziinc\.com|
peertube\.metawurst\.space|
videos\.wakapo\.com|
video\.ploud\.fr|
video\.freeradical\.zone|
tube\.valinor\.fr|
refuznik\.video|
pt\.kircheneuenburg\.de|
peertube\.asrun\.eu|
peertube\.lagob\.fr|
videos\.side-ways\.net|
91video\.online|
video\.valme\.io|
video\.taboulisme\.com|
videos-libr\.es|
tv\.mooh\.fr|
nuage\.acostey\.fr|
video\.monsieur-a\.fr|
peertube\.librelois\.fr|
videos\.pair2jeux\.tube|
videos\.pueseso\.club|
peer\.mathdacloud\.ovh|
media\.assassinate-you\.net|
vidcommons\.org|
ptube\.rousset\.nom\.fr|
tube\.cyano\.at|
videos\.squat\.net|
video\.iphodase\.fr|
peertube\.makotoworkshop\.org|
peertube\.serveur\.slv-valbonne\.fr|
vault\.mle\.party|
hostyour\.tv|
videos\.hack2g2\.fr|
libre\.tube|
pire\.artisanlogiciel\.net|
videos\.numerique-en-commun\.fr|
video\.netsyms\.com|
video\.die-partei\.social|
video\.writeas\.org|
peertube\.swarm\.solvingmaz\.es|
tube\.pericoloso\.ovh|
watching\.cypherpunk\.observer|
videos\.adhocmusic\.com|
tube\.rfc1149\.net|
peertube\.librelabucm\.org|
videos\.numericoop\.fr|
peertube\.koehn\.com|
peertube\.anarchmusicall\.net|
tube\.kampftoast\.de|
vid\.y-y\.li|
peertube\.xtenz\.xyz|
diode\.zone|
tube\.egf\.mn|
peertube\.nomagic\.uk|
visionon\.tv|
videos\.koumoul\.com|
video\.rastapuls\.com|
video\.mantlepro\.com|
video\.deadsuperhero\.com|
peertube\.musicstudio\.pro|
peertube\.we-keys\.fr|
artitube\.artifaille\.fr|
peertube\.ethernia\.net|
tube\.midov\.pl|
peertube\.fr|
watch\.snoot\.tube|
peertube\.donnadieu\.fr|
argos\.aquilenet\.fr|
tube\.nemsia\.org|
tube\.bruniau\.net|
videos\.darckoune\.moe|
tube\.traydent\.info|
dev\.videos\.lecygnenoir\.info|
peertube\.nayya\.org|
peertube\.live|
peertube\.mofgao\.space|
video\.lequerrec\.eu|
peertube\.amicale\.net|
aperi\.tube|
tube\.ac-lyon\.fr|
video\.lw1\.at|
www\.yiny\.org|
videos\.pofilo\.fr|
tube\.lou\.lt|
choob\.h\.etbus\.ch|
tube\.hoga\.fr|
peertube\.heberge\.fr|
video\.obermui\.de|
videos\.cloudfrancois\.fr|
betamax\.video|
video\.typica\.us|
tube\.piweb\.be|
video\.blender\.org|
peertube\.cat|
tube\.kdy\.ch|
pe\.ertu\.be|
peertube\.social|
videos\.lescommuns\.org|
tv\.datamol\.org|
videonaute\.fr|
dialup\.express|
peertube\.nogafa\.org|
megatube\.lilomoino\.fr|
peertube\.tamanoir\.foucry\.net|
peertube\.devosi\.org|
peertube\.1312\.media|
tube\.bootlicker\.party|
skeptikon\.fr|
video\.blueline\.mg|
tube\.homecomputing\.fr|
tube\.ouahpiti\.info|
video\.tedomum\.net|
video\.g3l\.org|
fontube\.fr|
peertube\.gaialabs\.ch|
tube\.kher\.nl|
peertube\.qtg\.fr|
video\.migennes\.net|
tube\.p2p\.legal|
troll\.tv|
videos\.iut-orsay\.fr|
peertube\.solidev\.net|
videos\.cemea\.org|
video\.passageenseine\.fr|
videos\.festivalparminous\.org|
peertube\.touhoppai\.moe|
sikke\.fi|
peer\.hostux\.social|
share\.tube|
peertube\.walkingmountains\.fr|
videos\.benpro\.fr|
peertube\.parleur\.net|
peertube\.heraut\.eu|
tube\.aquilenet\.fr|
peertube\.gegeweb\.eu|
framatube\.org|
thinkerview\.video|
tube\.conferences-gesticulees\.net|
peertube\.datagueule\.tv|
video\.lqdn\.fr|
tube\.mochi\.academy|
media\.zat\.im|
video\.colibris-outilslibres\.org|
tube\.svnet\.fr|
peertube\.video|
peertube3\.cpy\.re|
peertube2\.cpy\.re|
videos\.tcit\.fr|
peertube\.cpy\.re
)'''
_UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
_API_BASE = 'https://%s/api/v1/videos/%s/%s'
_VALID_URL = r'''(?x)
(?:
peertube:(?P<host>[^:]+):|
https?://(?P<host_2>%s)/(?:videos/(?:watch|embed)|api/v\d/videos)/
)
(?P<id>%s)
''' % (_INSTANCES_RE, _UUID_RE)
_TESTS = [{
'url': 'https://framatube.org/videos/watch/9c9de5e8-0a1e-484a-b099-e80766180a6d',
'md5': '9bed8c0137913e17b86334e5885aacff',
'info_dict': {
'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d',
'ext': 'mp4',
'title': 'What is PeerTube?',
'description': 'md5:3fefb8dde2b189186ce0719fda6f7b10',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
'timestamp': 1538391166,
'upload_date': '20181001',
'uploader': 'Framasoft',
'uploader_id': '3',
'uploader_url': 'https://framatube.org/accounts/framasoft',
'channel': 'Les vidéos de Framasoft',
'channel_id': '2',
'channel_url': 'https://framatube.org/video-channels/bf54d359-cfad-4935-9d45-9d6be93f63e8',
'language': 'en',
'license': 'Attribution - Share Alike',
'duration': 113,
'view_count': int,
'like_count': int,
'dislike_count': int,
'tags': ['framasoft', 'peertube'],
'categories': ['Science & Technology'],
}
}, {
'url': 'https://peertube.tamanoir.foucry.net/videos/watch/0b04f13d-1e18-4f1d-814e-4979aa7c9c44',
'only_matching': True,
}, {
# nsfw
'url': 'https://tube.22decembre.eu/videos/watch/9bb88cd3-9959-46d9-9ab9-33d2bb704c39',
'only_matching': True,
}, {
'url': 'https://tube.22decembre.eu/videos/embed/fed67262-6edb-4d1c-833b-daa9085c71d7',
'only_matching': True,
}, {
'url': 'https://tube.openalgeria.org/api/v1/videos/c1875674-97d0-4c94-a058-3f7e64c962e8',
'only_matching': True,
}, {
'url': 'peertube:video.blender.org:b37a5b9f-e6b5-415c-b700-04a5cd6ec205',
'only_matching': True,
}]
@staticmethod
def _extract_peertube_url(webpage, source_url):
mobj = re.match(
r'https?://(?P<host>[^/]+)/videos/(?:watch|embed)/(?P<id>%s)'
% PeerTubeIE._UUID_RE, source_url)
if mobj and any(p in webpage for p in (
'<title>PeerTube<',
'There will be other non JS-based clients to access PeerTube',
'>We are sorry but it seems that PeerTube is not compatible with your web browser.<')):
return 'peertube:%s:%s' % mobj.group('host', 'id')
@staticmethod
def _extract_urls(webpage, source_url):
entries = re.findall(
r'''(?x)<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//%s/videos/embed/%s)'''
% (PeerTubeIE._INSTANCES_RE, PeerTubeIE._UUID_RE), webpage)
if not entries:
peertube_url = PeerTubeIE._extract_peertube_url(webpage, source_url)
if peertube_url:
entries = [peertube_url]
return entries
def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True):
return self._download_json(
self._API_BASE % (host, video_id, path), video_id,
note=note, errnote=errnote, fatal=fatal)
def _get_subtitles(self, host, video_id):
captions = self._call_api(
host, video_id, 'captions', note='Downloading captions JSON',
fatal=False)
if not isinstance(captions, dict):
return
data = captions.get('data')
if not isinstance(data, list):
return
subtitles = {}
for e in data:
language_id = try_get(e, lambda x: x['language']['id'], compat_str)
caption_url = urljoin('https://%s' % host, e.get('captionPath'))
if not caption_url:
continue
subtitles.setdefault(language_id or 'en', []).append({
'url': caption_url,
})
return subtitles
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host') or mobj.group('host_2')
video_id = mobj.group('id')
video = self._call_api(
host, video_id, '', note='Downloading video JSON')
title = video['name']
formats = []
for file_ in video['files']:
if not isinstance(file_, dict):
continue
file_url = url_or_none(file_.get('fileUrl'))
if not file_url:
continue
file_size = int_or_none(file_.get('size'))
format_id = try_get(
file_, lambda x: x['resolution']['label'], compat_str)
f = parse_resolution(format_id)
f.update({
'url': file_url,
'format_id': format_id,
'filesize': file_size,
})
formats.append(f)
self._sort_formats(formats)
full_description = self._call_api(
host, video_id, 'description', note='Downloading description JSON',
fatal=False)
description = None
if isinstance(full_description, dict):
description = str_or_none(full_description.get('description'))
if not description:
description = video.get('description')
subtitles = self.extract_subtitles(host, video_id)
def data(section, field, type_):
return try_get(video, lambda x: x[section][field], type_)
def account_data(field, type_):
return data('account', field, type_)
def channel_data(field, type_):
return data('channel', field, type_)
category = data('category', 'label', compat_str)
categories = [category] if category else None
nsfw = video.get('nsfw')
if nsfw is bool:
age_limit = 18 if nsfw else 0
else:
age_limit = None
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': urljoin(url, video.get('thumbnailPath')),
'timestamp': unified_timestamp(video.get('publishedAt')),
'uploader': account_data('displayName', compat_str),
'uploader_id': str_or_none(account_data('id', int)),
'uploader_url': url_or_none(account_data('url', compat_str)),
'channel': channel_data('displayName', compat_str),
'channel_id': str_or_none(channel_data('id', int)),
'channel_url': url_or_none(channel_data('url', compat_str)),
'language': data('language', 'id', compat_str),
'license': data('licence', 'label', compat_str),
'duration': int_or_none(video.get('duration')),
'view_count': int_or_none(video.get('views')),
'like_count': int_or_none(video.get('likes')),
'dislike_count': int_or_none(video.get('dislikes')),
'age_limit': age_limit,
'tags': try_get(video, lambda x: x['tags'], list),
'categories': categories,
'formats': formats,
'subtitles': subtitles
}