mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-12-22 20:20:09 +09:00
Compare commits
7 Commits
3234272818
...
01c92973dd
Author | SHA1 | Date | |
---|---|---|---|
|
01c92973dd | ||
|
f4415faa46 | ||
|
a86ce9d7a1 | ||
|
37258c644f | ||
|
d0512ac4c5 | ||
|
da4eaa15a2 | ||
|
191286265d |
6
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
6
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
@ -18,7 +18,7 @@ title: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.21.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
|
||||
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a broken site support
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
|
||||
- [ ] I've searched the bugtracker for similar issues including closed ones
|
||||
@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
|
||||
[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 2020.11.21.1
|
||||
[debug] youtube-dl version 2020.11.24
|
||||
[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: {}
|
||||
|
@ -19,7 +19,7 @@ labels: 'site-support-request'
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.21.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
|
||||
- Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a new site support request
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that none of provided URLs violate any copyrights
|
||||
- [ ] I've searched the bugtracker for similar site support requests including closed ones
|
||||
|
@ -18,13 +18,13 @@ title: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.21.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes (like this [x])
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a site feature request
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
|
||||
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
|
||||
|
||||
|
||||
|
6
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
6
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
@ -18,7 +18,7 @@ title: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.21.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
|
||||
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a broken site support issue
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
|
||||
- [ ] I've searched the bugtracker for similar bug reports including closed ones
|
||||
@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
|
||||
[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 2020.11.21.1
|
||||
[debug] youtube-dl version 2020.11.24
|
||||
[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: {}
|
||||
|
4
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
4
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
@ -19,13 +19,13 @@ labels: 'request'
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.21.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes (like this [x])
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a feature request
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
|
||||
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
||||
|
||||
|
||||
|
19
ChangeLog
19
ChangeLog
@ -1,3 +1,22 @@
|
||||
version 2020.11.24
|
||||
|
||||
Core
|
||||
+ [extractor/common] Add generic support for akamai HTTP format extraction
|
||||
|
||||
Extractors
|
||||
* [youtube:tab] Fix feeds extraction (#25695, #26452)
|
||||
* [youtube:favorites] Restore extractor
|
||||
* [youtube:tab] Fix some weird typo (#27157)
|
||||
+ [pinterest] Add support for large collections (more than 25 pins)
|
||||
+ [franceinter] Extract thumbnail (#27153)
|
||||
+ [box] Add support for box.com (#5949)
|
||||
+ [nytimes] Add support for cooking.nytimes.com (#27112, #27143)
|
||||
* [lbry] Relax URL regular expression (#27144)
|
||||
+ [rumble] Add support for embed pages (#10785)
|
||||
+ [skyit] Add support for multiple Sky Italia websites (#26629)
|
||||
+ [pinterest] Add support for pinterest.com (#25747)
|
||||
|
||||
|
||||
version 2020.11.21.1
|
||||
|
||||
Core
|
||||
|
@ -59,6 +59,7 @@
|
||||
- **ARD:mediathek**
|
||||
- **ARDBetaMediathek**
|
||||
- **Arkena**
|
||||
- **arte.sky.it**
|
||||
- **ArteTV**
|
||||
- **ArteTVEmbed**
|
||||
- **ArteTVPlaylist**
|
||||
@ -110,6 +111,7 @@
|
||||
- **Bloomberg**
|
||||
- **BokeCC**
|
||||
- **BostonGlobe**
|
||||
- **Box**
|
||||
- **Bpb**: Bundeszentrale für politische Bildung
|
||||
- **BR**: Bayerischer Rundfunk
|
||||
- **BravoTV**
|
||||
@ -157,6 +159,7 @@
|
||||
- **Chilloutzone**
|
||||
- **chirbit**
|
||||
- **chirbit:profile**
|
||||
- **cielotv.it**
|
||||
- **Cinchcast**
|
||||
- **Cinemax**
|
||||
- **CiscoLiveSearch**
|
||||
@ -608,6 +611,7 @@
|
||||
- **Nuvid**
|
||||
- **NYTimes**
|
||||
- **NYTimesArticle**
|
||||
- **NYTimesCooking**
|
||||
- **NZZ**
|
||||
- **ocw.mit.edu**
|
||||
- **OdaTV**
|
||||
@ -660,10 +664,13 @@
|
||||
- **PicartoVod**
|
||||
- **Piksel**
|
||||
- **Pinkbike**
|
||||
- **Pinterest**
|
||||
- **PinterestCollection**
|
||||
- **Pladform**
|
||||
- **Platzi**
|
||||
- **PlatziCourse**
|
||||
- **play.fm**
|
||||
- **player.sky.it**
|
||||
- **PlayPlusTV**
|
||||
- **PlaysTV**
|
||||
- **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
|
||||
@ -755,6 +762,7 @@
|
||||
- **RTVNH**
|
||||
- **RTVS**
|
||||
- **RUHD**
|
||||
- **RumbleEmbed**
|
||||
- **rutube**: Rutube videos
|
||||
- **rutube:channel**: Rutube channels
|
||||
- **rutube:embed**: Rutube embedded videos
|
||||
@ -792,6 +800,8 @@
|
||||
- **Shared**: shared.sx
|
||||
- **ShowRoomLive**
|
||||
- **Sina**
|
||||
- **sky.it**
|
||||
- **skyacademy.it**
|
||||
- **SkylineWebcams**
|
||||
- **SkyNews**
|
||||
- **skynewsarabia:article**
|
||||
@ -930,6 +940,7 @@
|
||||
- **TV2DKBornholmPlay**
|
||||
- **TV4**: tv4.se and tv4play.se
|
||||
- **TV5MondePlus**: TV5MONDE+
|
||||
- **tv8.it**
|
||||
- **TVA**
|
||||
- **TVANouvelles**
|
||||
- **TVANouvellesArticle**
|
||||
@ -1001,6 +1012,8 @@
|
||||
- **Viddler**
|
||||
- **Videa**
|
||||
- **video.google:search**: Google Video search
|
||||
- **video.sky.it**
|
||||
- **video.sky.it:live**
|
||||
- **VideoDetective**
|
||||
- **videofy.me**
|
||||
- **videomore**
|
||||
@ -1130,6 +1143,7 @@
|
||||
- **YourPorn**
|
||||
- **YourUpload**
|
||||
- **youtube**: YouTube.com
|
||||
- **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
|
||||
- **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
|
||||
- **youtube:playlist**: YouTube.com playlists
|
||||
- **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
|
||||
|
@ -61,9 +61,10 @@ class TestAllURLsMatching(unittest.TestCase):
|
||||
# self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:tab'])
|
||||
|
||||
def test_youtube_feeds(self):
|
||||
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
|
||||
self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
|
||||
self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
|
||||
self.assertMatch('https://www.youtube.com/feed/library', ['youtube:tab'])
|
||||
self.assertMatch('https://www.youtube.com/feed/history', ['youtube:tab'])
|
||||
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:tab'])
|
||||
self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:tab'])
|
||||
|
||||
# def test_youtube_search_matching(self):
|
||||
# self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
|
||||
|
@ -97,12 +97,15 @@ class FragmentFD(FileDownloader):
|
||||
|
||||
def _download_fragment(self, ctx, frag_url, info_dict, headers=None):
|
||||
fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], ctx['fragment_index'])
|
||||
success = ctx['dl'].download(fragment_filename, {
|
||||
fragment_info_dict = {
|
||||
'url': frag_url,
|
||||
'http_headers': headers or info_dict.get('http_headers'),
|
||||
})
|
||||
}
|
||||
success = ctx['dl'].download(fragment_filename, fragment_info_dict)
|
||||
if not success:
|
||||
return False, None
|
||||
if fragment_info_dict.get('filetime'):
|
||||
ctx['fragment_filetime'] = fragment_info_dict.get('filetime')
|
||||
down, frag_sanitized = sanitize_open(fragment_filename, 'rb')
|
||||
ctx['fragment_filename_sanitized'] = frag_sanitized
|
||||
frag_content = down.read()
|
||||
@ -258,6 +261,13 @@ class FragmentFD(FileDownloader):
|
||||
downloaded_bytes = ctx['complete_frags_downloaded_bytes']
|
||||
else:
|
||||
self.try_rename(ctx['tmpfilename'], ctx['filename'])
|
||||
if self.params.get('updatetime', True):
|
||||
filetime = ctx.get('fragment_filetime')
|
||||
if filetime:
|
||||
try:
|
||||
os.utime(ctx['filename'], (time.time(), filetime))
|
||||
except Exception:
|
||||
pass
|
||||
downloaded_bytes = os.path.getsize(encodeFilename(ctx['filename']))
|
||||
|
||||
self._hook_progress({
|
||||
|
@ -5,10 +5,16 @@ import codecs
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_chr,
|
||||
compat_ord,
|
||||
compat_urllib_parse_unquote,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
multipart_encode,
|
||||
parse_duration,
|
||||
random_birthday,
|
||||
@ -107,8 +113,9 @@ class CDAIE(InfoExtractor):
|
||||
r'Odsłony:(?:\s| )*([0-9]+)', webpage,
|
||||
'view_count', default=None)
|
||||
average_rating = self._search_regex(
|
||||
r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
|
||||
webpage, 'rating', fatal=False, group='rating_value')
|
||||
(r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
|
||||
r'<span[^>]+\bclass=["\']rating["\'][^>]*>(?P<rating_value>[0-9.]+)'), webpage, 'rating', fatal=False,
|
||||
group='rating_value')
|
||||
|
||||
info_dict = {
|
||||
'id': video_id,
|
||||
@ -123,6 +130,24 @@ class CDAIE(InfoExtractor):
|
||||
'age_limit': 18 if need_confirm_age else 0,
|
||||
}
|
||||
|
||||
# Source: https://www.cda.pl/js/player.js?t=1606154898
|
||||
def decrypt_file(a):
|
||||
for p in ('_XDDD', '_CDA', '_ADC', '_CXD', '_QWE', '_Q5', '_IKSDE'):
|
||||
a = a.replace(p, '')
|
||||
a = compat_urllib_parse_unquote(a)
|
||||
b = []
|
||||
for c in a:
|
||||
f = compat_ord(c)
|
||||
b.append(compat_chr(33 + (f + 14) % 94) if 33 <= f and 126 >= f else compat_chr(f))
|
||||
a = ''.join(b)
|
||||
a = a.replace('.cda.mp4', '')
|
||||
for p in ('.2cda.pl', '.3cda.pl'):
|
||||
a = a.replace(p, '.cda.pl')
|
||||
if '/upstream' in a:
|
||||
a = a.replace('/upstream', '.mp4/upstream')
|
||||
return 'https://' + a
|
||||
return 'https://' + a + '.mp4'
|
||||
|
||||
def extract_format(page, version):
|
||||
json_str = self._html_search_regex(
|
||||
r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
|
||||
@ -141,6 +166,8 @@ class CDAIE(InfoExtractor):
|
||||
video['file'] = codecs.decode(video['file'], 'rot_13')
|
||||
if video['file'].endswith('adc.mp4'):
|
||||
video['file'] = video['file'].replace('adc.mp4', '.mp4')
|
||||
elif not video['file'].startswith('http'):
|
||||
video['file'] = decrypt_file(video['file'])
|
||||
f = {
|
||||
'url': video['file'],
|
||||
}
|
||||
@ -179,4 +206,6 @@ class CDAIE(InfoExtractor):
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return info_dict
|
||||
info = self._search_json_ld(webpage, video_id, default={})
|
||||
|
||||
return merge_dicts(info_dict, info)
|
||||
|
@ -9,6 +9,7 @@ from ..compat import (
|
||||
compat_urllib_parse_unquote,
|
||||
)
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
@ -16,17 +17,269 @@ from ..utils import (
|
||||
parse_age_limit,
|
||||
parse_duration,
|
||||
try_get,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class NRKBaseIE(InfoExtractor):
|
||||
_GEO_COUNTRIES = ['NO']
|
||||
|
||||
_api_host = None
|
||||
|
||||
class NRKIE(NRKBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
nrk:|
|
||||
https?://
|
||||
(?:
|
||||
(?:www\.)?nrk\.no/video/(?:PS\*|[^_]+_)|
|
||||
v8[-.]psapi\.nrk\.no/mediaelement/
|
||||
)
|
||||
)
|
||||
(?P<id>[^?\#&]+)
|
||||
'''
|
||||
|
||||
_TESTS = [{
|
||||
# video
|
||||
'url': 'http://www.nrk.no/video/PS*150533',
|
||||
'md5': '706f34cdf1322577589e369e522b50ef',
|
||||
'info_dict': {
|
||||
'id': '150533',
|
||||
'ext': 'mp4',
|
||||
'title': 'Dompap og andre fugler i Piip-Show',
|
||||
'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
|
||||
'duration': 262,
|
||||
}
|
||||
}, {
|
||||
# audio
|
||||
'url': 'http://www.nrk.no/video/PS*154915',
|
||||
# MD5 is unstable
|
||||
'info_dict': {
|
||||
'id': '154915',
|
||||
'ext': 'flv',
|
||||
'title': 'Slik høres internett ut når du er blind',
|
||||
'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
|
||||
'duration': 20,
|
||||
}
|
||||
}, {
|
||||
'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.nrk.no/video/dompap-og-andre-fugler-i-piip-show_150533',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.nrk.no/video/humor/kommentatorboksen-reiser-til-sjos_d1fda11f-a4ad-437a-a374-0398bc84e999',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_from_playback(self, video_id):
|
||||
manifest = self._download_json(
|
||||
'http://psapi.nrk.no/playback/manifest/%s' % video_id,
|
||||
video_id, 'Downloading manifest JSON')
|
||||
|
||||
playable = manifest['playable']
|
||||
|
||||
formats = []
|
||||
for asset in playable['assets']:
|
||||
if not isinstance(asset, dict):
|
||||
continue
|
||||
if asset.get('encrypted'):
|
||||
continue
|
||||
format_url = url_or_none(asset.get('url'))
|
||||
if not format_url:
|
||||
continue
|
||||
if asset.get('format') == 'HLS' or determine_ext(format_url) == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
self._sort_formats(formats)
|
||||
|
||||
data = self._download_json(
|
||||
'http://psapi.nrk.no/playback/metadata/%s' % video_id,
|
||||
video_id, 'Downloading metadata JSON')
|
||||
|
||||
preplay = data['preplay']
|
||||
titles = preplay['titles']
|
||||
title = titles['title']
|
||||
alt_title = titles.get('subtitle')
|
||||
|
||||
description = preplay.get('description')
|
||||
duration = parse_duration(playable.get('duration')) or parse_duration(data.get('duration'))
|
||||
|
||||
thumbnails = []
|
||||
for image in try_get(
|
||||
preplay, lambda x: x['poster']['images'], list) or []:
|
||||
if not isinstance(image, dict):
|
||||
continue
|
||||
image_url = url_or_none(image.get('url'))
|
||||
if not image_url:
|
||||
continue
|
||||
thumbnails.append({
|
||||
'url': image_url,
|
||||
'width': int_or_none(image.get('pixelWidth')),
|
||||
'height': int_or_none(image.get('pixelHeight')),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'alt_title': alt_title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'thumbnails': thumbnails,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
return self._extract_from_playback(video_id)
|
||||
|
||||
|
||||
class NRKTVIE(NRKBaseIE):
|
||||
IE_DESC = 'NRK TV and NRK Radio'
|
||||
_EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:tv|radio)\.nrk(?:super)?\.no/
|
||||
(?:serie(?:/[^/]+){1,2}|program)/
|
||||
(?![Ee]pisodes)%s
|
||||
(?:/\d{2}-\d{2}-\d{4})?
|
||||
(?:\#del=(?P<part_id>\d+))?
|
||||
''' % _EPISODE_RE
|
||||
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
|
||||
_TESTS = [{
|
||||
'url': 'https://tv.nrk.no/program/MDDP12000117',
|
||||
'md5': '8270824df46ec629b66aeaa5796b36fb',
|
||||
'info_dict': {
|
||||
'id': 'MDDP12000117AA',
|
||||
'ext': 'mp4',
|
||||
'title': 'Alarm Trolltunga',
|
||||
'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
|
||||
'duration': 2223,
|
||||
'age_limit': 6,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
|
||||
'md5': '9a167e54d04671eb6317a37b7bc8a280',
|
||||
'info_dict': {
|
||||
'id': 'MUHH48000314AA',
|
||||
'ext': 'mp4',
|
||||
'title': '20 spørsmål 23.05.2014',
|
||||
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
|
||||
'duration': 1741,
|
||||
'series': '20 spørsmål',
|
||||
'episode': '23.05.2014',
|
||||
},
|
||||
'skip': 'NoProgramRights',
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/program/mdfp15000514',
|
||||
'info_dict': {
|
||||
'id': 'MDFP15000514CA',
|
||||
'ext': 'mp4',
|
||||
'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
|
||||
'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
|
||||
'duration': 4605,
|
||||
'series': 'Kunnskapskanalen',
|
||||
'episode': '24.05.2014',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# single playlist video
|
||||
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515-part2',
|
||||
'ext': 'flv',
|
||||
'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
|
||||
'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['Video is geo restricted'],
|
||||
'skip': 'particular part is not supported currently',
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515AH',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
'duration': 772,
|
||||
'series': 'Tour de Ski',
|
||||
'episode': '06.01.2015',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515BH',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
'duration': 6175,
|
||||
'series': 'Tour de Ski',
|
||||
'episode': '06.01.2015',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}],
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
},
|
||||
'expected_warnings': ['Video is geo restricted'],
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
|
||||
'info_dict': {
|
||||
'id': 'KMTE50001317AA',
|
||||
'ext': 'mp4',
|
||||
'title': 'Anno 13:30',
|
||||
'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
|
||||
'duration': 2340,
|
||||
'series': 'Anno',
|
||||
'episode': '13:30',
|
||||
'season_number': 3,
|
||||
'episode_number': 13,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
|
||||
'info_dict': {
|
||||
'id': 'MUHH46000317AA',
|
||||
'ext': 'mp4',
|
||||
'title': 'Nytt på Nytt 27.01.2017',
|
||||
'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
|
||||
'duration': 1796,
|
||||
'series': 'Nytt på nytt',
|
||||
'episode': '27.01.2017',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_api_host = None
|
||||
|
||||
def _extract_from_mediaelement(self, video_id):
|
||||
api_hosts = (self._api_host, ) if self._api_host else self._API_HOSTS
|
||||
|
||||
for api_host in api_hosts:
|
||||
@ -195,190 +448,9 @@ class NRKBaseIE(InfoExtractor):
|
||||
|
||||
return self.playlist_result(entries, video_id, title, description)
|
||||
|
||||
|
||||
class NRKIE(NRKBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
nrk:|
|
||||
https?://
|
||||
(?:
|
||||
(?:www\.)?nrk\.no/video/PS\*|
|
||||
v8[-.]psapi\.nrk\.no/mediaelement/
|
||||
)
|
||||
)
|
||||
(?P<id>[^?#&]+)
|
||||
'''
|
||||
_API_HOSTS = ('psapi.nrk.no', 'v8-psapi.nrk.no')
|
||||
_TESTS = [{
|
||||
# video
|
||||
'url': 'http://www.nrk.no/video/PS*150533',
|
||||
'md5': '706f34cdf1322577589e369e522b50ef',
|
||||
'info_dict': {
|
||||
'id': '150533',
|
||||
'ext': 'mp4',
|
||||
'title': 'Dompap og andre fugler i Piip-Show',
|
||||
'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
|
||||
'duration': 262,
|
||||
}
|
||||
}, {
|
||||
# audio
|
||||
'url': 'http://www.nrk.no/video/PS*154915',
|
||||
# MD5 is unstable
|
||||
'info_dict': {
|
||||
'id': '154915',
|
||||
'ext': 'flv',
|
||||
'title': 'Slik høres internett ut når du er blind',
|
||||
'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
|
||||
'duration': 20,
|
||||
}
|
||||
}, {
|
||||
'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class NRKTVIE(NRKBaseIE):
|
||||
IE_DESC = 'NRK TV and NRK Radio'
|
||||
_EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:tv|radio)\.nrk(?:super)?\.no/
|
||||
(?:serie(?:/[^/]+){1,2}|program)/
|
||||
(?![Ee]pisodes)%s
|
||||
(?:/\d{2}-\d{2}-\d{4})?
|
||||
(?:\#del=(?P<part_id>\d+))?
|
||||
''' % _EPISODE_RE
|
||||
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
|
||||
_TESTS = [{
|
||||
'url': 'https://tv.nrk.no/program/MDDP12000117',
|
||||
'md5': '8270824df46ec629b66aeaa5796b36fb',
|
||||
'info_dict': {
|
||||
'id': 'MDDP12000117AA',
|
||||
'ext': 'mp4',
|
||||
'title': 'Alarm Trolltunga',
|
||||
'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
|
||||
'duration': 2223,
|
||||
'age_limit': 6,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
|
||||
'md5': '9a167e54d04671eb6317a37b7bc8a280',
|
||||
'info_dict': {
|
||||
'id': 'MUHH48000314AA',
|
||||
'ext': 'mp4',
|
||||
'title': '20 spørsmål 23.05.2014',
|
||||
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
|
||||
'duration': 1741,
|
||||
'series': '20 spørsmål',
|
||||
'episode': '23.05.2014',
|
||||
},
|
||||
'skip': 'NoProgramRights',
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/program/mdfp15000514',
|
||||
'info_dict': {
|
||||
'id': 'MDFP15000514CA',
|
||||
'ext': 'mp4',
|
||||
'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
|
||||
'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
|
||||
'duration': 4605,
|
||||
'series': 'Kunnskapskanalen',
|
||||
'episode': '24.05.2014',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# single playlist video
|
||||
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515-part2',
|
||||
'ext': 'flv',
|
||||
'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
|
||||
'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['Video is geo restricted'],
|
||||
'skip': 'particular part is not supported currently',
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515AH',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
'duration': 772,
|
||||
'series': 'Tour de Ski',
|
||||
'episode': '06.01.2015',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515BH',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
'duration': 6175,
|
||||
'series': 'Tour de Ski',
|
||||
'episode': '06.01.2015',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}],
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
},
|
||||
'expected_warnings': ['Video is geo restricted'],
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
|
||||
'info_dict': {
|
||||
'id': 'KMTE50001317AA',
|
||||
'ext': 'mp4',
|
||||
'title': 'Anno 13:30',
|
||||
'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
|
||||
'duration': 2340,
|
||||
'series': 'Anno',
|
||||
'episode': '13:30',
|
||||
'season_number': 3,
|
||||
'episode_number': 13,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
|
||||
'info_dict': {
|
||||
'id': 'MUHH46000317AA',
|
||||
'ext': 'mp4',
|
||||
'title': 'Nytt på Nytt 27.01.2017',
|
||||
'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
|
||||
'duration': 1796,
|
||||
'series': 'Nytt på nytt',
|
||||
'episode': '27.01.2017',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
|
||||
'only_matching': True,
|
||||
}]
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
return self._extract_from_mediaelement(video_id)
|
||||
|
||||
|
||||
class NRKTVEpisodeIE(InfoExtractor):
|
||||
|
@ -33,7 +33,6 @@ from ..utils import (
|
||||
get_element_by_id,
|
||||
int_or_none,
|
||||
mimetype2ext,
|
||||
orderedSet,
|
||||
parse_codecs,
|
||||
parse_duration,
|
||||
remove_quotes,
|
||||
@ -2163,7 +2162,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
# Youtube Music Auto-generated description
|
||||
release_date = release_year = None
|
||||
if video_description:
|
||||
mobj = re.search(r'(?s)Provided to YouTube by [^\n]+\n+(?P<track>[^·]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?', video_description)
|
||||
mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
|
||||
if mobj:
|
||||
if not track:
|
||||
track = mobj.group('track').strip()
|
||||
@ -2180,6 +2179,34 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
if release_year:
|
||||
release_year = int(release_year)
|
||||
|
||||
yt_initial_data = self._extract_yt_initial_data(video_id, video_webpage)
|
||||
contents = try_get(yt_initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
|
||||
for content in contents:
|
||||
rows = try_get(content, lambda x: x['videoSecondaryInfoRenderer']['metadataRowContainer']['metadataRowContainerRenderer']['rows'], list) or []
|
||||
multiple_songs = False
|
||||
for row in rows:
|
||||
if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
|
||||
multiple_songs = True
|
||||
break
|
||||
for row in rows:
|
||||
mrr = row.get('metadataRowRenderer') or {}
|
||||
mrr_title = try_get(
|
||||
mrr, lambda x: x['title']['simpleText'], compat_str)
|
||||
mrr_contents = try_get(
|
||||
mrr, lambda x: x['contents'][0], dict) or {}
|
||||
mrr_contents_text = try_get(mrr_contents, [lambda x: x['simpleText'], lambda x: x['runs'][0]['text']], compat_str)
|
||||
if not (mrr_title and mrr_contents_text):
|
||||
continue
|
||||
if mrr_title == 'License':
|
||||
video_license = mrr_contents_text
|
||||
elif not multiple_songs:
|
||||
if mrr_title == 'Album':
|
||||
album = mrr_contents_text
|
||||
elif mrr_title == 'Artist':
|
||||
artist = mrr_contents_text
|
||||
elif mrr_title == 'Song':
|
||||
track = mrr_contents_text
|
||||
|
||||
m_episode = re.search(
|
||||
r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
|
||||
video_webpage)
|
||||
@ -2381,7 +2408,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
|
||||
class YoutubeTabIE(YoutubeBaseInfoExtractor):
|
||||
IE_DESC = 'YouTube.com tab'
|
||||
_VALID_URL = r'https?://(?:\w+\.)?(?:youtube(?:kids)?\.com|invidio\.us)/(?:(?:channel|c|user)/|(?:playlist|watch)\?.*?\blist=)(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:\w+\.)?
|
||||
(?:
|
||||
youtube(?:kids)?\.com|
|
||||
invidio\.us
|
||||
)/
|
||||
(?:
|
||||
(?:channel|c|user|feed)/|
|
||||
(?:playlist|watch)\?.*?\blist=
|
||||
)
|
||||
(?P<id>[^/?\#&]+)
|
||||
'''
|
||||
IE_NAME = 'youtube:tab'
|
||||
|
||||
_TESTS = [{
|
||||
@ -2620,7 +2659,30 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
|
||||
}, {
|
||||
'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
|
||||
'only_matching': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.youtube.com/feed/trending',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# needs auth
|
||||
'url': 'https://www.youtube.com/feed/library',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# needs auth
|
||||
'url': 'https://www.youtube.com/feed/history',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# needs auth
|
||||
'url': 'https://www.youtube.com/feed/subscriptions',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# needs auth
|
||||
'url': 'https://www.youtube.com/feed/watch_later',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# no longer available?
|
||||
'url': 'https://www.youtube.com/feed/recommended',
|
||||
'only_matching': True,
|
||||
}
|
||||
# TODO
|
||||
# {
|
||||
# 'url': 'https://www.youtube.com/TheYoungTurks/live',
|
||||
@ -2707,27 +2769,34 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
|
||||
'https://www.youtube.com/channel/%s' % channel_id,
|
||||
ie=YoutubeTabIE.ie_key(), video_title=title)
|
||||
|
||||
def _shelf_entries_trimmed(self, shelf_renderer):
|
||||
renderer = try_get(
|
||||
shelf_renderer, lambda x: x['content']['horizontalListRenderer'], dict)
|
||||
if not renderer:
|
||||
def _shelf_entries_from_content(self, shelf_renderer):
|
||||
content = shelf_renderer.get('content')
|
||||
if not isinstance(content, dict):
|
||||
return
|
||||
renderer = content.get('gridRenderer')
|
||||
if renderer:
|
||||
# TODO: add support for nested playlists so each shelf is processed
|
||||
# as separate playlist
|
||||
# TODO: this includes only first N items
|
||||
for entry in self._grid_entries(renderer):
|
||||
yield entry
|
||||
renderer = content.get('horizontalListRenderer')
|
||||
if renderer:
|
||||
# TODO
|
||||
pass
|
||||
|
||||
def _shelf_entries(self, shelf_renderer):
|
||||
ep = try_get(
|
||||
shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
|
||||
compat_str)
|
||||
shelf_url = urljoin('https://www.youtube.com', ep)
|
||||
if not shelf_url:
|
||||
return
|
||||
if shelf_url:
|
||||
title = try_get(
|
||||
shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
|
||||
yield self.url_result(shelf_url, video_title=title)
|
||||
# Shelf may not contain shelf URL, fallback to extraction from content
|
||||
for entry in self._shelf_entries_from_content(shelf_renderer):
|
||||
yield entry
|
||||
|
||||
def _playlist_entries(self, video_list_renderer):
|
||||
for content in video_list_renderer['contents']:
|
||||
@ -2832,8 +2901,11 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
|
||||
}
|
||||
|
||||
def _entries(self, tab, identity_token):
|
||||
slr_renderer = try_get(tab, lambda x: x['sectionListRenderer'], dict)
|
||||
if not slr_renderer:
|
||||
return
|
||||
continuation = None
|
||||
slr_contents = try_get(tab, lambda x: x['sectionListRenderer']['contents'], list) or []
|
||||
slr_contents = try_get(slr_renderer, lambda x: x['contents'], list) or []
|
||||
for slr_content in slr_contents:
|
||||
if not isinstance(slr_content, dict):
|
||||
continue
|
||||
@ -2876,6 +2948,9 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
|
||||
if not continuation:
|
||||
continuation = self._extract_continuation(is_renderer)
|
||||
|
||||
if not continuation:
|
||||
continuation = self._extract_continuation(slr_renderer)
|
||||
|
||||
headers = {
|
||||
'x-youtube-client-name': '1',
|
||||
'x-youtube-client-version': '2.20201112.04.01',
|
||||
@ -2924,7 +2999,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
|
||||
continuation_item = continuation_items[0]
|
||||
if not isinstance(continuation_item, dict):
|
||||
continue
|
||||
renderer = continuation_item.get('playlistVideoRenderer')
|
||||
renderer = continuation_item.get('playlistVideoRenderer') or continuation_item.get('itemSectionRenderer')
|
||||
if renderer:
|
||||
video_list_renderer = {'contents': continuation_items}
|
||||
for entry in self._playlist_entries(video_list_renderer):
|
||||
@ -2969,6 +3044,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
|
||||
selected_tab = self._extract_selected_tab(tabs)
|
||||
renderer = try_get(
|
||||
data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
|
||||
playlist_id = title = description = None
|
||||
if renderer:
|
||||
channel_title = renderer.get('title') or item_id
|
||||
tab_title = selected_tab.get('title')
|
||||
@ -3289,10 +3365,10 @@ class YoutubeSearchURLIE(YoutubeSearchIE):
|
||||
"""
|
||||
|
||||
|
||||
class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
|
||||
class YoutubeFeedsInfoExtractor(YoutubeTabIE):
|
||||
"""
|
||||
Base class for feed extractors
|
||||
Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
|
||||
Subclasses must define the _FEED_NAME property.
|
||||
"""
|
||||
_LOGIN_REQUIRED = True
|
||||
|
||||
@ -3303,55 +3379,17 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
def _entries(self, page):
|
||||
# The extraction process is the same as for playlists, but the regex
|
||||
# for the video ids doesn't contain an index
|
||||
ids = []
|
||||
more_widget_html = content_html = page
|
||||
for page_num in itertools.count(1):
|
||||
matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
|
||||
|
||||
# 'recommended' feed has infinite 'load more' and each new portion spins
|
||||
# the same videos in (sometimes) slightly different order, so we'll check
|
||||
# for unicity and break when portion has no new videos
|
||||
new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
|
||||
if not new_ids:
|
||||
break
|
||||
|
||||
ids.extend(new_ids)
|
||||
|
||||
for entry in self._ids_to_results(new_ids):
|
||||
yield entry
|
||||
|
||||
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
|
||||
if not mobj:
|
||||
break
|
||||
|
||||
more = self._download_json(
|
||||
'https://www.youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
|
||||
'Downloading page #%s' % page_num,
|
||||
transform_source=uppercase_escape,
|
||||
headers=self._YOUTUBE_CLIENT_HEADERS)
|
||||
content_html = more['content_html']
|
||||
more_widget_html = more['load_more_widget_html']
|
||||
|
||||
def _real_extract(self, url):
|
||||
page = self._download_webpage(
|
||||
return self.url_result(
|
||||
'https://www.youtube.com/feed/%s' % self._FEED_NAME,
|
||||
self._PLAYLIST_TITLE)
|
||||
return self.playlist_result(
|
||||
self._entries(page), playlist_title=self._PLAYLIST_TITLE)
|
||||
ie=YoutubeTabIE.ie_key())
|
||||
|
||||
|
||||
class YoutubeWatchLaterIE(InfoExtractor):
|
||||
IE_NAME = 'youtube:watchlater'
|
||||
IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
|
||||
_VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/watch_later|:ytwatchlater'
|
||||
|
||||
_VALID_URL = r':ytwatchlater'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.youtube.com/feed/watch_later',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': ':ytwatchlater',
|
||||
'only_matching': True,
|
||||
}]
|
||||
@ -3363,23 +3401,38 @@ class YoutubeWatchLaterIE(InfoExtractor):
|
||||
|
||||
class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
|
||||
IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
|
||||
_VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
|
||||
_VALID_URL = r':ytrec(?:ommended)?'
|
||||
_FEED_NAME = 'recommended'
|
||||
_PLAYLIST_TITLE = 'Youtube Recommended videos'
|
||||
_TESTS = [{
|
||||
'url': ':ytrec',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': ':ytrecommended',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
|
||||
IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
|
||||
_VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
|
||||
_VALID_URL = r':ytsubs(?:criptions)?'
|
||||
_FEED_NAME = 'subscriptions'
|
||||
_PLAYLIST_TITLE = 'Youtube Subscriptions'
|
||||
_TESTS = [{
|
||||
'url': ':ytsubs',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': ':ytsubscriptions',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
|
||||
IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
|
||||
_VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
|
||||
_VALID_URL = r':ythistory'
|
||||
_FEED_NAME = 'history'
|
||||
_PLAYLIST_TITLE = 'Youtube History'
|
||||
_TESTS = [{
|
||||
'url': ':ythistory',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class YoutubeTruncatedURLIE(InfoExtractor):
|
||||
|
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2020.11.21.1'
|
||||
__version__ = '2020.11.24'
|
||||
|
Loading…
Reference in New Issue
Block a user