mirror of
https://github.com/yt-dlp/yt-dlp
synced 2025-12-16 06:05:41 +07:00
Compare commits
2 Commits
854fded114
...
2021.05.20
| Author | SHA1 | Date | |
|---|---|---|---|
|
65075de35b | ||
|
50755db160 |
@@ -44,3 +44,7 @@ Lamieur
|
||||
tsukumijima
|
||||
Hadi0609
|
||||
b5eff52
|
||||
craftingmod
|
||||
tpikonen
|
||||
tripulse
|
||||
king-millez
|
||||
|
||||
36
Changelog.md
36
Changelog.md
@@ -19,6 +19,42 @@ # Instuctions for creating release
|
||||
-->
|
||||
|
||||
|
||||
### 2021.05.20
|
||||
|
||||
**Youtube improvements**:
|
||||
* Support youtube music `MP`, `VL` and `browse` pages
|
||||
* Extract more formats for youtube music by @craftingmod, @colethedj, @pukkandan
|
||||
* Extract multiple subtitles in same language by @pukkandan and @tpikonen
|
||||
* Redirect channels that doesn't have a `videos` tab to their `UU` playlists
|
||||
* Support in-channel search
|
||||
* Sort audio-only formats correctly
|
||||
* Always extract `maxresdefault` thumbnail
|
||||
* Extract audio language
|
||||
* Add subtitle language names by @nixxo and @tpikonen
|
||||
* Show alerts only from the final webpage
|
||||
* Add `html5=1` param to `get_video_info` page requests by @colethedj
|
||||
* Better message when login required
|
||||
**Add option `--print`**: to print any field/template
|
||||
Deprecates: `--get-description`, `--get-duration`, `--get-filename`, `--get-format`, `--get-id`, `--get-thumbnail`, `--get-title`, `--get-url`
|
||||
* Field `additional_urls` to download additional videos from metadata using [`--parse-metadata`](https://github.com/yt-dlp/yt-dlp#modifying-metadata)
|
||||
* Merge youtube-dl: Upto [commit/dfbbe29](https://github.com/ytdl-org/youtube-dl/commit/dfbbe2902fc67f0f93ee47a8077c148055c67a9b)
|
||||
* Write thumbnail of playlist and add `pl_thumbnail` outtmpl key
|
||||
* [embedthumbnail] Add `flac` support and refactor `mutagen` code by @pukkandan and @tripulse
|
||||
* [audius:artist] Add extractor by @king-millez
|
||||
* [parlview] Add extractor by @king-millez
|
||||
* [tenplay] Fix extractor by @king-millez
|
||||
* [rmcdecouverte] Generalize `_VALID_URL`
|
||||
* Add compat-option `no-attach-infojson`
|
||||
* Add field `name` for subtitles
|
||||
* Ensure `post_extract` and `pre_process` only run once
|
||||
* Fix `--check-formats` when there is network error
|
||||
* Standardize `write_debug` and `get_param`
|
||||
* [options] Alias `--write-comments`, `--no-write-comments`
|
||||
* [options] Refactor callbacks
|
||||
* [test:download] Only extract enough videos for `playlist_mincount`
|
||||
* [extractor] bugfix for when `compat_opts` is not given
|
||||
* [cleanup] code formatting, youtube tests and readme
|
||||
|
||||
### 2021.05.11
|
||||
* **Deprecate support for python versions < 3.6**
|
||||
* **Subtitle extraction from manifests** by [fstirlitz](https://github.com/fstirlitz). See [be6202f](https://github.com/yt-dlp/yt-dlp/commit/be6202f12b97858b9d716e608394b51065d0419f) for details
|
||||
|
||||
16
README.md
16
README.md
@@ -66,15 +66,17 @@ # NEW FEATURES
|
||||
|
||||
* **[Format Sorting](#sorting-formats)**: The default format sorting options have been changed so that higher resolution and better codecs will be now preferred instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection that what is possible by simply using `--format` ([examples](#format-selection-examples))
|
||||
|
||||
* **Merged with youtube-dl [commit/a726009](https://github.com/ytdl-org/youtube-dl/commit/a7260099873acc6dc7d76cafad2f6b139087afd0)**: (v2021.04.26) You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
|
||||
* **Merged with youtube-dl [commit/dfbbe29](https://github.com/ytdl-org/youtube-dl/commit/dfbbe2902fc67f0f93ee47a8077c148055c67a9b)**: (v2021.05.16) You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
|
||||
|
||||
* **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--get-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, playlist infojson etc. Note that the NicoNico improvements are not available. See [#31](https://github.com/yt-dlp/yt-dlp/pull/31) for details.
|
||||
* **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--write-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, playlist infojson etc. Note that the NicoNico improvements are not available. See [#31](https://github.com/yt-dlp/yt-dlp/pull/31) for details.
|
||||
|
||||
* **Youtube improvements**:
|
||||
* All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works and supports downloading multiple pages of content
|
||||
* Youtube search (`ytsearch:`, `ytsearchdate:`) along with Search URLs work
|
||||
* Youtube mixes supports downloading multiple pages of content
|
||||
* All Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) supports downloading multiple pages of content
|
||||
* Search (`ytsearch:`, `ytsearchdate:`), search URLs and in-channel search works
|
||||
* Mixes supports downloading multiple pages of content
|
||||
* Redirect channel's home URL automatically to `/video` to preserve the old behaviour
|
||||
* `255kbps` audio is extracted from youtube music if premium cookies are given
|
||||
* Youtube music Albums, channels etc can be downloaded
|
||||
|
||||
* **Split video by chapters**: Videos can be split into multiple files based on chapters using `--split-chapters`
|
||||
|
||||
@@ -82,9 +84,9 @@ # NEW FEATURES
|
||||
|
||||
* **Aria2c with HLS/DASH**: You can use `aria2c` as the external downloader for DASH(mpd) and HLS(m3u8) formats
|
||||
|
||||
* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius, zee5, mtv.it, wimtv, pluto.tv, niconico users, discoveryplus.in, mediathek, NFHSNetwork, nebula, ukcolumn, whowatch, MxplayerShow
|
||||
* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius, zee5, mtv.it, wimtv, pluto.tv, niconico users, discoveryplus.in, mediathek, NFHSNetwork, nebula, ukcolumn, whowatch, MxplayerShow, parlview (au)
|
||||
|
||||
* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, akamai, ina, rumble, tennistv, amcnetworks, la7 podcasts, linuxacadamy, nitter, twitcasting, viu, crackle, curiositystream, mediasite, rmcdecouverte, sonyliv, tubi
|
||||
* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, akamai, ina, rumble, tennistv, amcnetworks, la7 podcasts, linuxacadamy, nitter, twitcasting, viu, crackle, curiositystream, mediasite, rmcdecouverte, sonyliv, tubi, tenplay
|
||||
|
||||
* **Subtitle extraction from manifests**: Subtitles can be extracted from streaming media manifests. See [be6202f12b97858b9d716e608394b51065d0419f](https://github.com/yt-dlp/yt-dlp/commit/be6202f12b97858b9d716e608394b51065d0419f) for details
|
||||
|
||||
|
||||
@@ -82,6 +82,7 @@ # Supported sites
|
||||
- **audiomack**
|
||||
- **audiomack:album**
|
||||
- **Audius**: Audius.co
|
||||
- **audius:artist**: Audius.co profile/artist pages
|
||||
- **audius:playlist**: Audius.co playlists
|
||||
- **audius:track**: Audius track ID or API link. Prepend with "audius:"
|
||||
- **AWAAN**
|
||||
@@ -725,6 +726,7 @@ # Supported sites
|
||||
- **pandora.tv**: 판도라TV
|
||||
- **ParamountNetwork**
|
||||
- **parliamentlive.tv**: UK parliament videos
|
||||
- **Parlview**
|
||||
- **Patreon**
|
||||
- **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
|
||||
- **PearVideo**
|
||||
@@ -748,6 +750,7 @@ # Supported sites
|
||||
- **play.fm**
|
||||
- **player.sky.it**
|
||||
- **PlayPlusTV**
|
||||
- **PlayStuff**
|
||||
- **PlaysTV**
|
||||
- **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
|
||||
- **Playvid**
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
from ..compat import compat_urllib_parse_urlencode
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
unescapeHTML
|
||||
merge_dicts,
|
||||
)
|
||||
|
||||
|
||||
@@ -24,7 +24,8 @@ class EroProfileIE(InfoExtractor):
|
||||
'title': 'sexy babe softcore',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'age_limit': 18,
|
||||
}
|
||||
},
|
||||
'skip': 'Video not found',
|
||||
}, {
|
||||
'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
|
||||
'md5': '1baa9602ede46ce904c431f5418d8916',
|
||||
@@ -77,19 +78,15 @@ def _real_extract(self, url):
|
||||
[r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
|
||||
webpage, 'video id', default=None)
|
||||
|
||||
video_url = unescapeHTML(self._search_regex(
|
||||
r'<source src="([^"]+)', webpage, 'video url'))
|
||||
title = self._html_search_regex(
|
||||
r'Title:</th><td>([^<]+)</td>', webpage, 'title')
|
||||
thumbnail = self._search_regex(
|
||||
r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
|
||||
webpage, 'thumbnail', fatal=False)
|
||||
(r'Title:</th><td>([^<]+)</td>', r'<h1[^>]*>(.+?)</h1>'),
|
||||
webpage, 'title')
|
||||
|
||||
return {
|
||||
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
|
||||
|
||||
return merge_dicts(info, {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'age_limit': 18,
|
||||
}
|
||||
})
|
||||
|
||||
@@ -985,6 +985,7 @@
|
||||
from .playfm import PlayFMIE
|
||||
from .playplustv import PlayPlusTVIE
|
||||
from .plays import PlaysTVIE
|
||||
from .playstuff import PlayStuffIE
|
||||
from .playtvak import PlaytvakIE
|
||||
from .playvid import PlayvidIE
|
||||
from .playwire import PlaywireIE
|
||||
|
||||
@@ -126,6 +126,7 @@
|
||||
from .expressen import ExpressenIE
|
||||
from .zype import ZypeIE
|
||||
from .odnoklassniki import OdnoklassnikiIE
|
||||
from .vk import VKIE
|
||||
from .kinja import KinjaEmbedIE
|
||||
from .gedidigital import GediDigitalIE
|
||||
from .rcs import RCSEmbedsIE
|
||||
@@ -2252,6 +2253,10 @@ class GenericIE(InfoExtractor):
|
||||
'playlist_mincount': 52,
|
||||
},
|
||||
{
|
||||
# Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
|
||||
'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# WimTv embed player
|
||||
'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
|
||||
'info_dict': {
|
||||
@@ -2803,6 +2808,11 @@ def _real_extract(self, url):
|
||||
if odnoklassniki_url:
|
||||
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
|
||||
|
||||
# Look for sibnet embedded player
|
||||
sibnet_urls = VKIE._extract_sibnet_urls(webpage)
|
||||
if sibnet_urls:
|
||||
return self.playlist_from_matches(sibnet_urls, video_id, video_title)
|
||||
|
||||
# Look for embedded ivi player
|
||||
mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
|
||||
if mobj is not None:
|
||||
@@ -3454,6 +3464,9 @@ def _real_extract(self, url):
|
||||
'url': src,
|
||||
'ext': (mimetype2ext(src_type)
|
||||
or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
|
||||
'http_headers': {
|
||||
'Referer': full_response.geturl(),
|
||||
},
|
||||
})
|
||||
if formats:
|
||||
self._sort_formats(formats)
|
||||
@@ -3522,7 +3535,7 @@ def filter_video(urls):
|
||||
m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
|
||||
# We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
|
||||
if m_video_type is not None:
|
||||
found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
|
||||
found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
|
||||
if not found:
|
||||
REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
|
||||
found = re.search(
|
||||
|
||||
@@ -182,7 +182,7 @@ def _real_extract(self, url):
|
||||
duration = end - start if end and start else None
|
||||
entries.append({
|
||||
'id': loop_stream_id.replace('.mp3', ''),
|
||||
'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
|
||||
'url': 'https://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
|
||||
'title': title,
|
||||
'description': clean_html(data.get('subtitle')),
|
||||
'duration': duration,
|
||||
|
||||
@@ -9,8 +9,9 @@
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
xpath_text,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
@@ -27,10 +28,11 @@ class PhoenixIE(ZDFBaseIE):
|
||||
'title': 'Wohin führt der Protest in der Pandemie?',
|
||||
'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
|
||||
'duration': 1691,
|
||||
'timestamp': 1613906100,
|
||||
'timestamp': 1613902500,
|
||||
'upload_date': '20210221',
|
||||
'uploader': 'Phoenix',
|
||||
'channel': 'corona nachgehakt',
|
||||
'series': 'corona nachgehakt',
|
||||
'episode': 'Wohin führt der Protest in der Pandemie?',
|
||||
},
|
||||
}, {
|
||||
# Youtube embed
|
||||
@@ -79,50 +81,53 @@ def _real_extract(self, url):
|
||||
|
||||
video_id = compat_str(video.get('basename') or video.get('content'))
|
||||
|
||||
details = self._download_xml(
|
||||
details = self._download_json(
|
||||
'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
|
||||
video_id, 'Downloading details XML', query={
|
||||
video_id, 'Downloading details JSON', query={
|
||||
'ak': 'web',
|
||||
'ptmd': 'true',
|
||||
'id': video_id,
|
||||
'profile': 'player2',
|
||||
})
|
||||
|
||||
title = title or xpath_text(
|
||||
details, './/information/title', 'title', fatal=True)
|
||||
content_id = xpath_text(
|
||||
details, './/video/details/basename', 'content id', fatal=True)
|
||||
title = title or details['title']
|
||||
content_id = details['tracking']['nielsen']['content']['assetid']
|
||||
|
||||
info = self._extract_ptmd(
|
||||
'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
|
||||
content_id, None, url)
|
||||
|
||||
timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
|
||||
duration = int_or_none(try_get(
|
||||
details, lambda x: x['tracking']['nielsen']['content']['length']))
|
||||
timestamp = unified_timestamp(details.get('editorialDate'))
|
||||
series = try_get(
|
||||
details, lambda x: x['tracking']['nielsen']['content']['program'],
|
||||
compat_str)
|
||||
episode = title if details.get('contentType') == 'episode' else None
|
||||
|
||||
thumbnails = []
|
||||
for node in details.findall('.//teaserimages/teaserimage'):
|
||||
thumbnail_url = node.text
|
||||
teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
|
||||
for thumbnail_key, thumbnail_url in teaser_images.items():
|
||||
thumbnail_url = urljoin(url, thumbnail_url)
|
||||
if not thumbnail_url:
|
||||
continue
|
||||
thumbnail = {
|
||||
'url': thumbnail_url,
|
||||
}
|
||||
thumbnail_key = node.get('key')
|
||||
if thumbnail_key:
|
||||
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
|
||||
if m:
|
||||
thumbnail['width'] = int(m.group(1))
|
||||
thumbnail['height'] = int(m.group(2))
|
||||
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
|
||||
if m:
|
||||
thumbnail['width'] = int(m.group(1))
|
||||
thumbnail['height'] = int(m.group(2))
|
||||
thumbnails.append(thumbnail)
|
||||
|
||||
return merge_dicts(info, {
|
||||
'id': content_id,
|
||||
'title': title,
|
||||
'description': xpath_text(details, './/information/detail'),
|
||||
'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
|
||||
'description': details.get('leadParagraph'),
|
||||
'duration': duration,
|
||||
'thumbnails': thumbnails,
|
||||
'timestamp': timestamp,
|
||||
'uploader': xpath_text(details, './/details/channel'),
|
||||
'uploader_id': xpath_text(details, './/details/originChannelId'),
|
||||
'channel': xpath_text(details, './/details/originChannelTitle'),
|
||||
'uploader': details.get('tvService'),
|
||||
'series': series,
|
||||
'episode': episode,
|
||||
})
|
||||
|
||||
65
yt_dlp/extractor/playstuff.py
Normal file
65
yt_dlp/extractor/playstuff.py
Normal file
@@ -0,0 +1,65 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
smuggle_url,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class PlayStuffIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?play\.stuff\.co\.nz/details/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://play.stuff.co.nz/details/608778ac1de1c4001a3fa09a',
|
||||
'md5': 'c82d3669e5247c64bc382577843e5bd0',
|
||||
'info_dict': {
|
||||
'id': '6250584958001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Episode 1: Rotorua/Mt Maunganui/Tauranga',
|
||||
'description': 'md5:c154bafb9f0dd02d01fd4100fb1c1913',
|
||||
'uploader_id': '6005208634001',
|
||||
'timestamp': 1619491027,
|
||||
'upload_date': '20210427',
|
||||
},
|
||||
'add_ie': ['BrightcoveNew'],
|
||||
}, {
|
||||
# geo restricted, bypassable
|
||||
'url': 'https://play.stuff.co.nz/details/_6155660351001',
|
||||
'only_matching': True,
|
||||
}]
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
state = self._parse_json(
|
||||
self._search_regex(
|
||||
r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'state'),
|
||||
video_id)
|
||||
|
||||
account_id = try_get(
|
||||
state, lambda x: x['configurations']['accountId'],
|
||||
compat_str) or '6005208634001'
|
||||
player_id = try_get(
|
||||
state, lambda x: x['configurations']['playerId'],
|
||||
compat_str) or 'default'
|
||||
|
||||
entries = []
|
||||
for item_id, video in state['items'].items():
|
||||
if not isinstance(video, dict):
|
||||
continue
|
||||
asset_id = try_get(
|
||||
video, lambda x: x['content']['attributes']['assetId'],
|
||||
compat_str)
|
||||
if not asset_id:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
smuggle_url(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, asset_id),
|
||||
{'geo_countries': ['NZ']}),
|
||||
'BrightcoveNew', video_id))
|
||||
|
||||
return self.playlist_result(entries, video_id)
|
||||
@@ -133,8 +133,10 @@ def _real_extract(self, url):
|
||||
rrn_id = self._match_id(url)
|
||||
asset_id = self._download_json(
|
||||
'https://edge-graphql.crepo-production.redbullaws.com/v1/graphql',
|
||||
rrn_id, headers={'API-KEY': 'e90a1ff11335423998b100c929ecc866'},
|
||||
query={
|
||||
rrn_id, headers={
|
||||
'Accept': 'application/json',
|
||||
'API-KEY': 'e90a1ff11335423998b100c929ecc866',
|
||||
}, query={
|
||||
'query': '''{
|
||||
resource(id: "%s", enforceGeoBlocking: false) {
|
||||
%s
|
||||
|
||||
@@ -21,6 +21,7 @@
|
||||
class ShahidBaseIE(AWSIE):
|
||||
_AWS_PROXY_HOST = 'api2.shahid.net'
|
||||
_AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
|
||||
_VALID_URL_BASE = r'https?://shahid\.mbc\.net/[a-z]{2}/'
|
||||
|
||||
def _handle_error(self, e):
|
||||
fail_data = self._parse_json(
|
||||
@@ -49,7 +50,7 @@ def _call_api(self, path, video_id, request=None):
|
||||
|
||||
class ShahidIE(ShahidBaseIE):
|
||||
_NETRC_MACHINE = 'shahid'
|
||||
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
|
||||
_VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
|
||||
'info_dict': {
|
||||
@@ -73,6 +74,9 @@ class ShahidIE(ShahidBaseIE):
|
||||
# shahid plus subscriber only
|
||||
'url': 'https://shahid.mbc.net/ar/series/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/episode-90511',
|
||||
'only_matching': True
|
||||
}, {
|
||||
'url': 'https://shahid.mbc.net/en/shows/Ramez-Fi-Al-Shallal-season-1-episode-1/episode-359319',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
@@ -168,7 +172,7 @@ def _real_extract(self, url):
|
||||
|
||||
|
||||
class ShahidShowIE(ShahidBaseIE):
|
||||
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
|
||||
_VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
|
||||
'info_dict': {
|
||||
|
||||
@@ -86,10 +86,10 @@ def _extract_video_url(self, webpage, video_id, url):
|
||||
|
||||
class VivoIE(SharedBaseIE):
|
||||
IE_DESC = 'vivo.sx'
|
||||
_VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
|
||||
_VALID_URL = r'https?://vivo\.s[xt]/(?P<id>[\da-z]{10})'
|
||||
_FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://vivo.sx/d7ddda0e78',
|
||||
'md5': '15b3af41be0b4fe01f4df075c2678b2c',
|
||||
'info_dict': {
|
||||
@@ -98,7 +98,10 @@ class VivoIE(SharedBaseIE):
|
||||
'title': 'Chicken',
|
||||
'filesize': 515659,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'http://vivo.st/d7ddda0e78',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_title(self, webpage):
|
||||
title = self._html_search_regex(
|
||||
|
||||
@@ -300,6 +300,13 @@ class VKIE(VKBaseIE):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_sibnet_urls(webpage):
|
||||
# https://help.sibnet.ru/?sibnet_video_embed
|
||||
return [unescapeHTML(mobj.group('url')) for mobj in re.finditer(
|
||||
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.sibnet\.ru/shell\.php\?.*?\bvideoid=\d+.*?)\1',
|
||||
webpage)]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('videoid')
|
||||
@@ -408,6 +415,10 @@ def _real_extract(self, url):
|
||||
if odnoklassniki_url:
|
||||
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
|
||||
|
||||
sibnet_urls = self._extract_sibnet_urls(info_page)
|
||||
if sibnet_urls:
|
||||
return self.url_result(sibnet_urls[0])
|
||||
|
||||
m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
|
||||
if m_opts:
|
||||
m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
|
||||
|
||||
Reference in New Issue
Block a user