1
0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-16 14:36:47 +00:00

Compare commits

..

7 Commits

Author SHA1 Message Date
Sergey M․
d0512ac4c5
release 2020.11.24 2020-11-24 00:23:14 +07:00
Sergey M․
da4eaa15a2
[ChangeLog] Actualize
[ci skip]
2020-11-24 00:20:42 +07:00
Sergey M․
191286265d
[youtube:tab] Fix feeds extraction (closes #25695, closes #26452) 2020-11-24 00:10:25 +07:00
Sergey M․
3234272818
[youtube:tab] PEP 8 2020-11-23 22:34:27 +07:00
Sergey M․
9d2c90354f
[youtube:favorites] Restore extractor 2020-11-23 22:33:21 +07:00
Sergey M․
316b10855a
[youtube:tab] Fix some weird typo (closes #27157) 2020-11-23 22:19:25 +07:00
Remita Amine
484fe78737 [pinterest] Add support for large collections(more than 25 pins) 2020-11-23 14:16:38 +01:00
12 changed files with 225 additions and 121 deletions

View File

@ -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 Issues with outdated version will be REJECTED.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 Issues with outdated version will be REJECTED.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: {}

View File

@ -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

View File

@ -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

View File

@ -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: {}

View File

@ -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

View File

@ -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

View File

@ -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)

View File

@ -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'])

View File

@ -1491,6 +1491,7 @@ from .yourporn import YourPornIE
from .yourupload import YourUploadIE
from .youtube import (
YoutubeIE,
YoutubeFavouritesIE,
YoutubeHistoryIE,
YoutubeTabIE,
YoutubePlaylistIE,

View File

@ -1,6 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
@ -16,12 +19,12 @@ from ..utils import (
class PinterestBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:[^/]+\.)?pinterest\.(?:com|fr|de|ch|jp|cl|ca|it|co\.uk|nz|ru|com\.au|at|pt|co\.kr|es|com\.mx|dk|ph|th|com\.uy|co|nl|info|kr|ie|vn|com\.vn|ec|mx|in|pe|co\.at|hu|co\.in|co\.nz|id|com\.ec|com\.py|tw|be|uk|com\.bo|com\.pe)'
def _extract_resource(self, webpage, video_id):
return self._parse_json(
self._search_regex(
r'<script[^>]+\bid=["\']initial-state["\'][^>]*>({.+?})</script>',
webpage, 'application json'),
video_id)['resourceResponses']
def _call_api(self, resource, video_id, options):
return self._download_json(
'https://www.pinterest.com/resource/%sResource/get/' % resource,
video_id, 'Download %s JSON metadata' % resource, query={
'data': json.dumps({'options': options})
})['resource_response']
def _extract_video(self, data, extract_formats=True):
video_id = data['id']
@ -128,13 +131,16 @@ class PinterestIE(PinterestBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data = self._extract_resource(webpage, video_id)[0]['response']['data']
data = self._call_api(
'Pin', video_id, {
'field_set_key': 'unauth_react_main_pin',
'id': video_id,
})['data']
return self._extract_video(data)
class PinterestCollectionIE(PinterestBaseIE):
_VALID_URL = r'%s/[^/]+/(?P<id>[^/?#&]+)' % PinterestBaseIE._VALID_URL_BASE
_VALID_URL = r'%s/(?P<username>[^/]+)/(?P<id>[^/?#&]+)' % PinterestBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'https://www.pinterest.ca/mashal0407/cool-diys/',
'info_dict': {
@ -142,6 +148,14 @@ class PinterestCollectionIE(PinterestBaseIE):
'title': 'cool diys',
},
'playlist_count': 8,
}, {
'url': 'https://www.pinterest.ca/fudohub/videos/',
'info_dict': {
'id': '682858430939307450',
'title': 'VIDEOS',
},
'playlist_mincount': 365,
'skip': 'Test with extract_formats=False',
}]
@classmethod
@ -150,27 +164,38 @@ class PinterestCollectionIE(PinterestBaseIE):
PinterestCollectionIE, cls).suitable(url)
def _real_extract(self, url):
collection_name = self._match_id(url)
webpage = self._download_webpage(url, collection_name)
resource = self._extract_resource(webpage, collection_name)[1]
username, slug = re.match(self._VALID_URL, url).groups()
board = self._call_api(
'Board', slug, {
'slug': slug,
'username': username
})['data']
board_id = board['id']
options = {
'board_id': board_id,
'page_size': 250,
}
bookmark = None
entries = []
for item in resource['response']['data']:
if not isinstance(item, dict) or item.get('type') != 'pin':
continue
video_id = item.get('id')
if video_id:
# Some pins may not be available anonymously via pin URL
# video = self._extract_video(item, extract_formats=False)
# video.update({
# '_type': 'url_transparent',
# 'url': 'https://www.pinterest.com/pin/%s/' % video_id,
# })
# entries.append(video)
entries.append(self._extract_video(item))
title = try_get(
resource, lambda x: x['options']['board_title'], compat_str)
collection_id = try_get(
resource, lambda x: x['options']['board_id'],
compat_str) or collection_name
while True:
if bookmark:
options['bookmarks'] = [bookmark]
board_feed = self._call_api('BoardFeed', board_id, options)
for item in (board_feed.get('data') or []):
if not isinstance(item, dict) or item.get('type') != 'pin':
continue
video_id = item.get('id')
if video_id:
# Some pins may not be available anonymously via pin URL
# video = self._extract_video(item, extract_formats=False)
# video.update({
# '_type': 'url_transparent',
# 'url': 'https://www.pinterest.com/pin/%s/' % video_id,
# })
# entries.append(video)
entries.append(self._extract_video(item))
bookmark = board_feed.get('bookmark')
if not bookmark:
break
return self.playlist_result(
entries, playlist_id=collection_id, playlist_title=title)
entries, playlist_id=board_id, playlist_title=board.get('name'))

View File

@ -33,7 +33,6 @@ from ..utils import (
get_element_by_id,
int_or_none,
mimetype2ext,
orderedSet,
parse_codecs,
parse_duration,
remove_quotes,
@ -2381,7 +2380,19 @@ 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 = [{
@ -2620,12 +2631,35 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
}, {
'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
'only_matching': True,
},
# TODO
# {
# 'url': 'https://www.youtube.com/TheYoungTurks/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',
# 'only_matching': True,
# }
]
def _extract_channel_id(self, webpage):
@ -2707,27 +2741,34 @@ 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
# 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('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
title = try_get(
shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
yield self.url_result(shelf_url, video_title=title)
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 +2873,11 @@ 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 +2920,9 @@ 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 +2971,7 @@ 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 +3016,7 @@ 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')
@ -3013,7 +3061,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
webpage = self._download_webpage(url, item_id)
identity_token = self._search_regex(
r'\bID_TOKEN["\']\s*:\s/l*["\'](.+?)["\']', webpage,
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
data = self._extract_yt_initial_data(item_id, webpage)
tabs = try_get(
@ -3149,6 +3197,25 @@ class YoutubeYtUserIE(InfoExtractor):
ie=YoutubeTabIE.ie_key(), video_id=user_id)
class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
IE_NAME = 'youtube:favorites'
IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
_VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
_LOGIN_REQUIRED = True
_TESTS = [{
'url': ':ytfav',
'only_matching': True,
}, {
'url': ':ytfavorites',
'only_matching': True,
}]
def _real_extract(self, url):
return self.url_result(
'https://www.youtube.com/playlist?list=LL',
ie=YoutubeTabIE.ie_key())
class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com searches'
# there doesn't appear to be a real limit, for example if you search for
@ -3270,10 +3337,10 @@ 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
@ -3284,55 +3351,17 @@ 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,
}]
@ -3344,23 +3373,38 @@ 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):

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2020.11.21.1'
__version__ = '2020.11.24'