1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-27 19:04:32 +01:00
youtube-dl/youtube_dl/extractor/spankwire.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

183 lines
6.3 KiB
Python

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
merge_dicts,
str_or_none,
str_to_int,
url_or_none,
)
class SpankwireIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:www\.)?spankwire\.com/
(?:
[^/]+/video|
EmbedPlayer\.aspx/?\?.*?\bArticleId=
)
(?P<id>\d+)
'''
_TESTS = [{
# download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
'md5': '5aa0e4feef20aad82cbcae3aed7ab7cd',
'info_dict': {
'id': '103545',
'ext': 'mp4',
'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
'description': 'Crazy Bitch X rated music video.',
'duration': 222,
'uploader': 'oreusz',
'uploader_id': '124697',
'timestamp': 1178587885,
'upload_date': '20070508',
'average_rating': float,
'view_count': int,
'comment_count': int,
'age_limit': 18,
'categories': list,
'tags': list,
},
}, {
# download URL pattern: */mp4_<format_id>_<video_id>.mp4
'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
'md5': '09b3c20833308b736ae8902db2f8d7e6',
'info_dict': {
'id': '1921551',
'ext': 'mp4',
'title': 'Titcums Compiloation I',
'description': 'cum on tits',
'uploader': 'dannyh78999',
'uploader_id': '3056053',
'upload_date': '20150822',
'age_limit': 18,
},
'params': {
'proxy': '127.0.0.1:8118'
},
'skip': 'removed',
}, {
'url': 'https://www.spankwire.com/EmbedPlayer.aspx/?ArticleId=156156&autostart=true',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?spankwire\.com/EmbedPlayer\.aspx/?\?.*?\bArticleId=\d+)',
webpage)
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'https://www.spankwire.com/api/video/%s.json' % video_id, video_id)
title = video['title']
formats = []
videos = video.get('videos')
if isinstance(videos, dict):
for format_id, format_url in videos.items():
video_url = url_or_none(format_url)
if not format_url:
continue
height = int_or_none(self._search_regex(
r'(\d+)[pP]', format_id, 'height', default=None))
m = re.search(
r'/(?P<height>\d+)[pP]_(?P<tbr>\d+)[kK]', video_url)
if m:
tbr = int(m.group('tbr'))
height = height or int(m.group('height'))
else:
tbr = None
formats.append({
'url': video_url,
'format_id': '%dp' % height if height else format_id,
'height': height,
'tbr': tbr,
})
m3u8_url = url_or_none(video.get('HLS'))
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
self._sort_formats(formats, ('height', 'tbr', 'width', 'format_id'))
view_count = str_to_int(video.get('viewed'))
thumbnails = []
for preference, t in enumerate(('', '2x'), start=0):
thumbnail_url = url_or_none(video.get('poster%s' % t))
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
'preference': preference,
})
def extract_names(key):
entries_list = video.get(key)
if not isinstance(entries_list, list):
return
entries = []
for entry in entries_list:
name = str_or_none(entry.get('name'))
if name:
entries.append(name)
return entries
categories = extract_names('categories')
tags = extract_names('tags')
uploader = None
info = {}
webpage = self._download_webpage(
'https://www.spankwire.com/_/video%s/' % video_id, video_id,
fatal=False)
if webpage:
info = self._search_json_ld(webpage, video_id, default={})
thumbnail_url = None
if 'thumbnail' in info:
thumbnail_url = url_or_none(info['thumbnail'])
del info['thumbnail']
if not thumbnail_url:
thumbnail_url = self._og_search_thumbnail(webpage)
if thumbnail_url:
thumbnails.append({
'url': thumbnail_url,
'preference': 10,
})
uploader = self._html_search_regex(
r'(?s)by\s*<a[^>]+\bclass=["\']uploaded__by[^>]*>(.+?)</a>',
webpage, 'uploader', fatal=False)
if not view_count:
view_count = str_to_int(self._search_regex(
r'data-views=["\']([\d,.]+)', webpage, 'view count',
fatal=False))
return merge_dicts({
'id': video_id,
'title': title,
'description': video.get('description'),
'duration': int_or_none(video.get('duration')),
'thumbnails': thumbnails,
'uploader': uploader,
'uploader_id': str_or_none(video.get('userId')),
'timestamp': int_or_none(video.get('time_approved_on')),
'average_rating': float_or_none(video.get('rating')),
'view_count': view_count,
'comment_count': int_or_none(video.get('comments')),
'age_limit': 18,
'categories': categories,
'tags': tags,
'formats': formats,
}, info)