Compare commits

...

10 Commits

Author SHA1 Message Date
McSwindler
1cbb4d9c4e
Merge 506966d1e8 into eb15fd5a32 2024-11-17 21:17:34 +05:30
krichbanana
eb15fd5a32
[ie/kenh14] Add extractor (#3996)
Closes #3937
Authored by: krichbanana, pzhlkj6612

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
2024-11-17 14:12:26 +00:00
sepro
7cecd299e4
[ie/chaturbate] Don't break embed detection (#11565)
Bugfix for 720b3dc453

Authored by: seproDev
2024-11-17 13:32:12 +01:00
bashonly
506966d1e8
Apply suggestions from code review 2024-06-12 06:51:34 +00:00
bashonly
2ef8a19f6b
Apply suggestions from code review 2024-06-12 06:47:04 +00:00
bashonly
8ab50693a1
Merge branch 'master' into watchertv 2024-06-12 01:44:00 -05:00
McSwindler
31b11c339b
[watchertv] add comments for required fields
Co-authored-by: pukkandan <pukkandan.ytdlp@gmail.com>
2024-04-24 22:12:55 -05:00
McSwindler
123ac3301c [watchertv] create DropoutBase IEs for Dropout and WatcherTV to extend 2024-04-23 22:48:18 -05:00
McSwindler
dd41cc4ade [watchertv] update extractor to extend dropout instead of duplicating 2024-04-21 08:51:10 -05:00
McSwindler
1b71001149 [watchertv] Add extractor 2024-04-20 12:07:02 -05:00
5 changed files with 383 additions and 96 deletions

View File

@ -946,6 +946,10 @@ from .kaltura import KalturaIE
from .kankanews import KankaNewsIE
from .karaoketv import KaraoketvIE
from .kelbyone import KelbyOneIE
from .kenh14 import (
Kenh14PlaylistIE,
Kenh14VideoIE,
)
from .khanacademy import (
KhanAcademyIE,
KhanAcademyUnitIE,
@ -2414,6 +2418,10 @@ from .washingtonpost import (
WashingtonPostIE,
)
from .wat import WatIE
from .watchertv import (
WatcherTVIE,
WatcherTVSeasonIE,
)
from .wdr import (
WDRIE,
WDRElefantIE,

View File

@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor):
'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
}
def _extract_from_webpage(self, video_id, tld):
def _extract_from_html(self, video_id, tld):
webpage = self._download_webpage(
f'https://chaturbate.{tld}/{video_id}/', video_id,
headers=self.geo_verification_headers(), impersonate=True)
@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor):
def _real_extract(self, url):
video_id, tld = self._match_valid_url(url).group('id', 'tld')
return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)
return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)

View File

@ -17,83 +17,12 @@ from ..utils import (
)
class DropoutIE(InfoExtractor):
_LOGIN_URL = 'https://www.dropout.tv/login'
_NETRC_MACHINE = 'dropout'
_VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
_TESTS = [
{
'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
'note': 'Episode in a series',
'md5': '5e000fdfd8d8fa46ff40456f1c2af04a',
'info_dict': {
'id': '738153',
'display_id': 'yes-or-no',
'ext': 'mp4',
'title': 'Yes or No',
'description': 'Ally, Brennan, and Zac are asked a simple question, but is there a correct answer?',
'release_date': '20200508',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/351e3f24-c4a3-459a-8b79-dc80f1e5b7fd.jpg',
'series': 'Game Changer',
'season_number': 2,
'season': 'Season 2',
'episode_number': 6,
'episode': 'Yes or No',
'duration': 1180,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
{
'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1/videos/episode-1',
'note': 'Episode in a series (missing release_date)',
'md5': '712caf7c191f1c47c8f1879520c2fa5c',
'info_dict': {
'id': '320562',
'display_id': 'episode-1',
'ext': 'mp4',
'title': 'The Beginning Begins',
'description': 'The cast introduces their PCs, including a neurotic elf, a goblin PI, and a corn-worshipping cleric.',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/4421ed0d-f630-4c88-9004-5251b2b8adfa.jpg',
'series': 'Dimension 20: Fantasy High',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'The Beginning Begins',
'duration': 6838,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
{
'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
'note': 'Episode not in a series',
'md5': 'c30fa18999c5880d156339f13c953a26',
'info_dict': {
'id': '1915774',
'display_id': 'misfits-magic-holiday-special',
'ext': 'mp4',
'title': 'Misfits & Magic Holiday Special',
'description': 'The magical misfits spend Christmas break at Gowpenny, with an unwelcome visitor.',
'release_date': '20211215',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/d91ea8a6-b250-42ed-907e-b30fb1c65176-8e24b8e5.jpg',
'duration': 11698,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
]
class DropoutBaseIE(InfoExtractor):
"""Subclasses must define _HOST"""
def _get_authenticity_token(self, display_id):
signin_page = self._download_webpage(
self._LOGIN_URL, display_id, note='Getting authenticity token')
f'{self._HOST}/login', display_id, note='Getting authenticity token')
return self._html_search_regex(
r'name=["\']authenticity_token["\'] value=["\'](.+?)["\']',
signin_page, 'authenticity_token')
@ -104,7 +33,7 @@ class DropoutIE(InfoExtractor):
return True
response = self._download_webpage(
self._LOGIN_URL, display_id, note='Logging in', fatal=False,
f'{self._HOST}/login', display_id, note='Logging in', fatal=False,
data=urlencode_postdata({
'email': username,
'password': password,
@ -125,7 +54,7 @@ class DropoutIE(InfoExtractor):
display_id = self._match_id(url)
webpage = None
if self._get_cookies('https://www.dropout.tv').get('_session'):
if self._get_cookies(self._HOST).get('_session'):
webpage = self._download_webpage(url, display_id)
if not webpage or '<div id="watch-unauthorized"' in webpage:
login_err = self._login(display_id)
@ -148,7 +77,7 @@ class DropoutIE(InfoExtractor):
return {
'_type': 'url_transparent',
'ie_key': VHXEmbedIE.ie_key(),
'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.dropout.tv'),
'url': VHXEmbedIE._smuggle_referrer(embed_url, self._HOST),
'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'),
'display_id': display_id,
'title': title,
@ -165,9 +94,105 @@ class DropoutIE(InfoExtractor):
}
class DropoutSeasonIE(InfoExtractor):
class DropoutIE(DropoutBaseIE):
_HOST = 'https://www.dropout.tv'
_NETRC_MACHINE = 'dropout'
_VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
_TESTS = [
{
'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
'note': 'Episode in a series',
'md5': 'fc55805bac60b1ce2ffdc35fb9c51195',
'info_dict': {
'id': '738153',
'display_id': 'yes-or-no',
'ext': 'mp4',
'title': 'Yes or No',
'description': 'Ally, Brennan, and Zac are asked a simple question, but is there a correct answer?',
'release_date': '20200508',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/351e3f24-c4a3-459a-8b79-dc80f1e5b7fd.jpg',
'series': 'Game Changer',
'season_number': 2,
'season': 'Season 2',
'episode_number': 6,
'episode': 'Yes or No',
'duration': 1180,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
{
'url': 'https://www.dropout.tv/ch-shorts/season:1/videos/post-apocalyptic-dane-cook',
'note': 'Episode in a series (missing release_date)',
'md5': 'f260b8d7d0fdbaceae713c9196dac07f',
'info_dict': {
'id': '449042',
'display_id': 'post-apocalyptic-dane-cook',
'ext': 'mp4',
'title': 'Post-Apocalyptic Dane Cook',
'description': 'Dane Cook is back with his all new special. Don\'t worry, it\'s not the end of the world.',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/5b0678df-d9c3-4864-b811-24db03072f4a.jpg',
'series': 'CH Shorts',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Post-Apocalyptic Dane Cook',
'duration': 135,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
{
'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
'note': 'Episode not in a series',
'md5': '147e0607bd877a791665c0b7219b512c',
'info_dict': {
'id': '1915774',
'display_id': 'misfits-magic-holiday-special',
'ext': 'mp4',
'title': 'Misfits & Magic Holiday Special',
'description': 'The magical misfits spend Christmas break at Gowpenny, with an unwelcome visitor.',
'release_date': '20211215',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/d91ea8a6-b250-42ed-907e-b30fb1c65176-8e24b8e5.jpg',
'duration': 11698,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
]
class DropoutSeasonBaseIE(InfoExtractor):
"""Subclasses must define _VIDEO_IE"""
_PAGE_SIZE = 24
def _fetch_page(self, url, season_id, page):
page += 1
webpage = self._download_webpage(
f'{url}?page={page}', season_id, note=f'Downloading page {page}', expected_status={400})
yield from [self.url_result(item_url, self._VIDEO_IE) for item_url in traverse_obj(
get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
def _real_extract(self, url):
season_id = self._match_id(url)
season_num = self._match_valid_url(url).group('season') or 1
season_title = season_id.replace('-', ' ').title()
return self.playlist_result(
OnDemandPagedList(functools.partial(self._fetch_page, url, season_id), self._PAGE_SIZE),
f'{season_id}-season-{season_num}', f'{season_title} - Season {season_num}')
class DropoutSeasonIE(DropoutSeasonBaseIE):
_VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_VIDEO_IE = DropoutIE
_TESTS = [
{
'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1',
@ -206,19 +231,3 @@ class DropoutSeasonIE(InfoExtractor):
},
},
]
def _fetch_page(self, url, season_id, page):
page += 1
webpage = self._download_webpage(
f'{url}?page={page}', season_id, note=f'Downloading page {page}', expected_status={400})
yield from [self.url_result(item_url, DropoutIE) for item_url in traverse_obj(
get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
def _real_extract(self, url):
season_id = self._match_id(url)
season_num = self._match_valid_url(url).group('season') or 1
season_title = season_id.replace('-', ' ').title()
return self.playlist_result(
OnDemandPagedList(functools.partial(self._fetch_page, url, season_id), self._PAGE_SIZE),
f'{season_id}-season-{season_num}', f'{season_title} - Season {season_num}')

160
yt_dlp/extractor/kenh14.py Normal file
View File

@ -0,0 +1,160 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_attribute,
get_elements_html_by_class,
int_or_none,
parse_duration,
parse_iso8601,
remove_start,
strip_or_none,
unescapeHTML,
update_url,
url_or_none,
)
from ..utils.traversal import traverse_obj
class Kenh14VideoIE(InfoExtractor):
_VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
_TESTS = [{
'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
'md5': '1ed67f9c3a1e74acf15db69590cf6210',
'info_dict': {
'id': '316173',
'ext': 'mp4',
'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
'tags': [],
'uploader': 'Unbox Therapy',
'upload_date': '20220517',
'view_count': int,
'duration': 722.86,
'timestamp': 1652764468,
},
}, {
'url': 'https://video.kenh14.vn/video-316174.chn',
'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
'info_dict': {
'id': '316174',
'ext': 'mp4',
'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
'tags': [],
'upload_date': '20220517',
'view_count': int,
'duration': 70.04,
'timestamp': 1652766021,
},
}, {
'url': 'https://video.kenh14.vn/0-344740.chn',
'md5': 'b843495d5e728142c8870c09b46df2a9',
'info_dict': {
'id': '344740',
'ext': 'mov',
'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
'uploader': 'Quang Vũ',
'upload_date': '20241024',
'view_count': int,
'duration': 198.88,
'timestamp': 1729741590,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
direct_url = attrs['data-vid']
metadata = self._download_json(
'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}]
subtitles = {}
video_data = self._download_json(
f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False)
if hls_url := traverse_obj(video_data, ('hls', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})):
fmts, subs = self._extract_mpd_formats_and_subtitles(
dash_url, video_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
**traverse_obj(metadata, {
'duration': ('duration', {parse_duration}),
'uploader': ('author', {strip_or_none}),
'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}),
'view_count': ('views', {int_or_none}),
}),
'id': video_id,
'title': (
traverse_obj(metadata, ('title', {strip_or_none}))
or clean_html(self._og_search_title(webpage))
or clean_html(get_element_by_class('vdbw-title', webpage))),
'formats': formats,
'subtitles': subtitles,
'description': (
clean_html(self._og_search_description(webpage))
or clean_html(get_element_by_class('vdbw-sapo', webpage))),
'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
{lambda x: x.split(';')}, ..., filter)),
}
class Kenh14PlaylistIE(InfoExtractor):
_VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
_TESTS = [{
'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
'info_dict': {
'id': '71',
'title': 'Trần Tình (Naked love) mùa 2',
'description': 'md5:e9522339304956dea931722dd72eddb2',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
},
'playlist_count': 9,
}, {
'url': 'https://video.kenh14.vn/playlist/0-72.chn',
'info_dict': {
'id': '72',
'title': 'Lau Lại Đầu Từ',
'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
},
'playlist_count': 6,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
category_detail = get_element_by_class('category-detail', webpage) or ''
embed_info = traverse_obj(
self._yield_json_ld(webpage, playlist_id),
(lambda _, v: v['name'] and v['alternateName'], any)) or {}
return self.playlist_from_matches(
get_elements_html_by_class('video-item', webpage), playlist_id,
(clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
ie=Kenh14VideoIE, playlist_description=(
clean_html(get_element_by_class('description', category_detail))
or unescapeHTML(embed_info.get('alternateName'))),
thumbnail=traverse_obj(
self._og_search_thumbnail(webpage),
({url_or_none}, {update_url(query=None)})))

View File

@ -0,0 +1,110 @@
from .dropout import DropoutBaseIE, DropoutSeasonBaseIE
class WatcherTVIE(DropoutBaseIE):
_HOST = 'https://www.watchertv.com'
_NETRC_MACHINE = 'watchertv'
_VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
_TESTS = [
{
'url': 'https://www.watchertv.com/ghost-files/season:2/videos/gf-201',
'note': 'Episode in a series',
'md5': '99c9aab2cb62157467b7ef5e37266e4e',
'info_dict': {
'id': '3129338',
'display_id': 'gf-201',
'ext': 'mp4',
'title': 'The Death Row Poltergeists of Missouri State Penitentiary',
'description': 'Where Curiosity Meets Comedy',
'release_date': '20230825',
'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/92c02f39-2ed6-4b51-9e63-1a907b82e2bc.png',
'series': 'Ghost Files',
'season_number': 2,
'season': 'Season 2',
'episode_number': 1,
'episode': 'The Death Row Poltergeists of Missouri State Penitentiary',
'duration': 3853,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
{
'url': 'https://www.watchertv.com/road-files/season:1/videos/rf101',
'note': 'Episode in a series (missing release_date)',
'md5': '02f9aaafc8ad9bd1be366cf6a61a68d8',
'info_dict': {
'id': '3187312',
'display_id': 'rf101',
'ext': 'mp4',
'title': 'Road Files: Haunted Hill House',
'description': 'Where Curiosity Meets Comedy',
'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/7445f23c-a3e7-47fb-835a-d288273e2698.png',
'series': 'Road Files',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Road Files: Haunted Hill House',
'duration': 516,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
{
'url': 'https://www.watchertv.com/videos/welcome-beta-users',
'note': 'Episode not in a series',
'md5': 'fd1db805f9adc442c38d706bba21ad03',
'info_dict': {
'id': '3187107',
'display_id': 'welcome-beta-users',
'ext': 'mp4',
'title': 'Welcome to Watcher!',
'description': 'Where Curiosity Meets Comedy',
'release_date': '20240419',
'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/fbb90dc8-ebb0-4597-9a83-95729e234030.jpg',
'duration': 92,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
]
class WatcherTVSeasonIE(DropoutSeasonBaseIE):
_VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_VIDEO_IE = WatcherTVIE
_TESTS = [
{
'url': 'https://www.watchertv.com/ghost-files/season:1',
'note': 'Multi-season series with the season in the url',
'playlist_count': 8,
'info_dict': {
'id': 'ghost-files-season-1',
'title': 'Ghost Files - Season 1',
},
},
{
'url': 'https://www.watchertv.com/are-you-scared',
'note': 'Multi-season series with the season not in the url',
'playlist_count': 3,
'info_dict': {
'id': 'are-you-scared-season-1',
'title': 'Are You Scared - Season 1',
},
},
{
'url': 'https://www.watchertv.com/watcher-one-offs',
'note': 'Single-season series',
'playlist_count': 16,
'info_dict': {
'id': 'watcher-one-offs-season-1',
'title': 'Watcher One Offs - Season 1',
},
},
]