[cleanup] Remove questionable extractors (#9911)

Closes #6279, Closes #6799
Authored by: seproDev
This commit is contained in:
sepro 2024-05-12 22:12:11 +02:00 committed by GitHub
parent cf212d0a33
commit 01395a3434
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
9 changed files with 14 additions and 651 deletions

View File

@ -288,7 +288,6 @@
from .buzzfeed import BuzzFeedIE
from .byutv import BYUtvIE
from .c56 import C56IE
from .cableav import CableAVIE
from .callin import CallinIE
from .caltrans import CaltransIE
from .cam4 import CAM4IE
@ -548,7 +547,6 @@
EggheadLessonIE,
)
from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE
from .eitb import EitbIE
from .elementorembed import ElementorEmbedIE
from .elonet import ElonetIE
@ -861,10 +859,6 @@
)
from .ixigua import IxiguaIE
from .izlesene import IzleseneIE
from .jable import (
JableIE,
JablePlaylistIE,
)
from .jamendo import (
JamendoIE,
JamendoAlbumIE,
@ -1499,7 +1493,6 @@
)
from .popcorntimes import PopcorntimesIE
from .popcorntv import PopcornTVIE
from .porn91 import Porn91IE
from .pornbox import PornboxIE
from .pornflip import PornFlipIE
from .pornhub import (
@ -2377,7 +2370,6 @@
)
from .xanimu import XanimuIE
from .xboxclips import XboxClipsIE
from .xfileshare import XFileShareIE
from .xhamster import (
XHamsterIE,
XHamsterEmbedIE,
@ -2432,8 +2424,6 @@
YouNowMomentIE,
)
from .youporn import YouPornIE
from .yourporn import YourPornIE
from .yourupload import YourUploadIE
from .zaiko import (
ZaikoIE,
ZaikoETicketIE,

View File

@ -1,32 +0,0 @@
from .common import InfoExtractor
class CableAVIE(InfoExtractor):
_VALID_URL = r'https?://cableav\.tv/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://cableav.tv/lS4iR9lWjN8/',
'md5': '7e3fe5e49d61c4233b7f5b0f69b15e18',
'info_dict': {
'id': 'lS4iR9lWjN8',
'ext': 'mp4',
'title': '國產麻豆AV 叮叮映畫 DDF001 情欲小說家 - CableAV',
'description': '國產AV 480p, 720p 国产麻豆AV 叮叮映画 DDF001 情欲小说家',
'thumbnail': r're:^https?://.*\.jpg$',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._og_search_video_url(webpage, secure=False)
formats = self._extract_m3u8_formats(video_url, video_id, 'mp4')
return {
'id': video_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
}

View File

@ -1,105 +0,0 @@
import json
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_str,
compat_urlparse,
)
from ..utils import (
extract_attributes,
ExtractorError,
get_elements_by_class,
urlencode_postdata,
)
class EinthusanIE(InfoExtractor):
_VALID_URL = r'https?://(?P<host>einthusan\.(?:tv|com|ca))/movie/watch/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://einthusan.tv/movie/watch/9097/',
'md5': 'ff0f7f2065031b8a2cf13a933731c035',
'info_dict': {
'id': '9097',
'ext': 'mp4',
'title': 'Ae Dil Hai Mushkil',
'description': 'md5:33ef934c82a671a94652a9b4e54d931b',
'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi',
'only_matching': True,
}, {
'url': 'https://einthusan.com/movie/watch/9097/',
'only_matching': True,
}, {
'url': 'https://einthusan.ca/movie/watch/4E9n/?lang=hindi',
'only_matching': True,
}]
# reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
def _decrypt(self, encrypted_data, video_id):
return self._parse_json(compat_b64decode((
encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1]
)).decode('utf-8'), video_id)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
host = mobj.group('host')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title')
player_params = extract_attributes(self._search_regex(
r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters'))
page_id = self._html_search_regex(
'<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
video_data = self._download_json(
'https://%s/ajax/movie/watch/%s/' % (host, video_id), video_id,
data=urlencode_postdata({
'xEvent': 'UIVideoPlayer.PingOutcome',
'xJson': json.dumps({
'EJOutcomes': player_params['data-ejpingables'],
'NativeHLS': False
}),
'arcVersion': 3,
'appVersion': 59,
'gorilla.csrf.Token': page_id,
}))['Data']
if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'):
raise ExtractorError(
'Download rate reached. Please try again later.', expected=True)
ej_links = self._decrypt(video_data['EJLinks'], video_id)
formats = []
m3u8_url = ej_links.get('HLSLink')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
mp4_url = ej_links.get('MP4Link')
if mp4_url:
formats.append({
'url': mp4_url,
})
description = get_elements_by_class('synopsis', webpage)[0]
thumbnail = self._html_search_regex(
r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''',
webpage, 'thumbnail url', fatal=False, group='url')
if thumbnail is not None:
thumbnail = compat_urlparse.urljoin(url, thumbnail)
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
}

View File

@ -1,103 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
int_or_none,
orderedSet,
unified_strdate,
)
class JableIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?jable\.tv/videos/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://jable.tv/videos/pppd-812/',
'md5': 'f1537283a9bc073c31ff86ca35d9b2a6',
'info_dict': {
'id': 'pppd-812',
'ext': 'mp4',
'title': 'PPPD-812 只要表現好巨乳女教師吉根柚莉愛就獎勵學生們在白虎穴內射出精液',
'description': 'md5:5b6d4199a854f62c5e56e26ccad19967',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
'like_count': int,
'view_count': int,
},
}, {
'url': 'https://jable.tv/videos/apak-220/',
'md5': '71f9239d69ced58ab74a816908847cc1',
'info_dict': {
'id': 'apak-220',
'ext': 'mp4',
'title': 'md5:5c3861b7cf80112a6e2b70bccf170824',
'description': '',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
'like_count': int,
'view_count': int,
'upload_date': '20220319',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = self._extract_m3u8_formats(
self._search_regex(r'var\s+hlsUrl\s*=\s*\'([^\']+)', webpage, 'hls_url'), video_id, 'mp4', m3u8_id='hls')
return {
'id': video_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage, default=''),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'formats': formats,
'age_limit': 18,
'upload_date': unified_strdate(self._search_regex(
r'class="inactive-color">\D+\s+(\d{4}-\d+-\d+)', webpage, 'upload_date', default=None)),
'view_count': int_or_none(self._search_regex(
r'#icon-eye"></use></svg>\n*<span class="mr-3">([\d ]+)',
webpage, 'view_count', default='').replace(' ', '')),
'like_count': int_or_none(self._search_regex(
r'#icon-heart"></use></svg><span class="count">(\d+)', webpage, 'link_count', default=None)),
}
class JablePlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?jable\.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://jable.tv/models/kaede-karen/',
'info_dict': {
'id': 'kaede-karen',
'title': '楓カレン',
},
'playlist_count': 34,
}, {
'url': 'https://jable.tv/categories/roleplay/',
'only_matching': True,
}, {
'url': 'https://jable.tv/tags/girl/',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
def page_func(page_num):
return [
self.url_result(player_url, JableIE)
for player_url in orderedSet(re.findall(
r'href="(https://jable.tv/videos/[\w-]+/?)"',
self._download_webpage(url, playlist_id, query={
'mode': 'async',
'from': page_num + 1,
'function': 'get_block',
'block_id': 'list_videos_common_videos_list',
}, note=f'Downloading page {page_num + 1}')))]
return self.playlist_result(
InAdvancePagedList(page_func, int_or_none(self._search_regex(
r'from:(\d+)">[^<]+\s*&raquo;', webpage, 'last page number', default=1)), 24),
playlist_id, self._search_regex(
r'<h2 class="h3-md mb-1">([^<]+)', webpage, 'playlist title', default=None))

View File

@ -1,95 +0,0 @@
import urllib.parse
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
parse_duration,
remove_end,
unified_strdate,
ExtractorError,
)
class Porn91IE(InfoExtractor):
IE_NAME = '91porn'
_VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/view_video.php\?([^#]+&)?viewkey=(?P<id>\w+)'
_TESTS = [{
'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
'md5': 'd869db281402e0ef4ddef3c38b866f86',
'info_dict': {
'id': '7e42283b4f5ab36da134',
'title': '18岁大一漂亮学妹水嫩性感再爽一次',
'description': 'md5:1ff241f579b07ae936a54e810ad2e891',
'ext': 'mp4',
'duration': 431,
'upload_date': '20150520',
'comment_count': int,
'view_count': int,
'age_limit': 18,
}
}, {
'url': 'https://91porn.com/view_video.php?viewkey=7ef0cf3d362c699ab91c',
'md5': 'f8fd50540468a6d795378cd778b40226',
'info_dict': {
'id': '7ef0cf3d362c699ab91c',
'title': '真实空乘,冲上云霄第二部',
'description': 'md5:618bf9652cafcc66cd277bd96789baea',
'ext': 'mp4',
'duration': 248,
'upload_date': '20221119',
'comment_count': int,
'view_count': int,
'age_limit': 18,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
self._set_cookie('91porn.com', 'language', 'cn_CN')
webpage = self._download_webpage(
'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
if '视频不存在,可能已经被删除或者被举报为不良内容!' in webpage:
raise ExtractorError('91 Porn says: Video does not exist', expected=True)
daily_limit = self._search_regex(
r'作为游客,你每天只可观看([\d]+)个视频', webpage, 'exceeded daily limit', default=None, fatal=False)
if daily_limit:
raise ExtractorError(f'91 Porn says: Daily limit {daily_limit} videos exceeded', expected=True)
video_link_url = self._search_regex(
r'document\.write\(\s*strencode2\s*\(\s*((?:"[^"]+")|(?:\'[^\']+\'))', webpage, 'video link')
video_link_url = self._search_regex(
r'src=["\']([^"\']+)["\']', urllib.parse.unquote(video_link_url), 'unquoted video link')
formats, subtitles = self._get_formats_and_subtitle(video_link_url, video_id)
return {
'id': video_id,
'title': remove_end(self._html_extract_title(webpage).replace('\n', ''), 'Chinese homemade video').strip(),
'formats': formats,
'subtitles': subtitles,
'upload_date': unified_strdate(self._search_regex(
r'<span\s+class=["\']title-yakov["\']>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload_date', fatal=False)),
'description': self._html_search_regex(
r'<span\s+class=["\']more title["\']>\s*([^<]+)', webpage, 'description', fatal=False),
'duration': parse_duration(self._search_regex(
r'时长:\s*<span[^>]*>\s*(\d+(?::\d+){1,2})', webpage, 'duration', fatal=False)),
'comment_count': int_or_none(self._search_regex(
r'留言:\s*<span[^>]*>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)),
'view_count': int_or_none(self._search_regex(
r'热度:\s*<span[^>]*>\s*(\d+)\s*</span>', webpage, 'view count', fatal=False)),
'age_limit': 18,
}
def _get_formats_and_subtitle(self, video_link_url, video_id):
ext = determine_ext(video_link_url)
if ext == 'm3u8':
formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_link_url, video_id, ext='mp4')
else:
formats = [{'url': video_link_url, 'ext': ext}]
subtitles = {}
return formats, subtitles

View File

@ -173,6 +173,20 @@ class KnownPiracyIE(UnsupportedInfoExtractor):
r'filemoon\.sx',
r'hentai\.animestigma\.com',
r'thisav\.com',
r'gounlimited\.to',
r'highstream\.tv',
r'uqload\.com',
r'vedbam\.xyz',
r'vadbam\.net'
r'vidlo\.us',
r'wolfstream\.tv',
r'xvideosharing\.com',
r'(?:\w+\.)?viidshar\.com',
r'sxyprn\.com',
r'jable\.tv',
r'91porn\.com',
r'einthusan\.(?:tv|com|ca)',
r'yourupload\.com',
)
_TESTS = [{

View File

@ -1,198 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
decode_packed_codes,
determine_ext,
int_or_none,
js_to_json,
urlencode_postdata,
)
# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58
def aa_decode(aa_code):
symbol_table = [
('7', '((゚ー゚) + (o^_^o))'),
('6', '((o^_^o) +(o^_^o))'),
('5', '((゚ー゚) + (゚Θ゚))'),
('2', '((o^_^o) - (゚Θ゚))'),
('4', '(゚ー゚)'),
('3', '(o^_^o)'),
('1', '(゚Θ゚)'),
('0', '(c^_^o)'),
]
delim = '(゚Д゚)[゚ε゚]+'
ret = ''
for aa_char in aa_code.split(delim):
for val, pat in symbol_table:
aa_char = aa_char.replace(pat, val)
aa_char = aa_char.replace('+ ', '')
m = re.match(r'^\d+', aa_char)
if m:
ret += chr(int(m.group(0), 8))
else:
m = re.match(r'^u([\da-f]+)', aa_char)
if m:
ret += chr(int(m.group(1), 16))
return ret
class XFileShareIE(InfoExtractor):
_SITES = (
(r'aparat\.cam', 'Aparat'),
(r'clipwatching\.com', 'ClipWatching'),
(r'gounlimited\.to', 'GoUnlimited'),
(r'govid\.me', 'GoVid'),
(r'holavid\.com', 'HolaVid'),
(r'streamty\.com', 'Streamty'),
(r'thevideobee\.to', 'TheVideoBee'),
(r'uqload\.com', 'Uqload'),
(r'vidbom\.com', 'VidBom'),
(r'vidlo\.us', 'vidlo'),
(r'vidlocker\.xyz', 'VidLocker'),
(r'vidshare\.tv', 'VidShare'),
(r'vup\.to', 'VUp'),
(r'wolfstream\.tv', 'WolfStream'),
(r'xvideosharing\.com', 'XVideoSharing'),
)
IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
_VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
% '|'.join(site for site in list(zip(*_SITES))[0]))
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]
_FILE_NOT_FOUND_REGEXES = (
r'>(?:404 - )?File Not Found<',
r'>The file was removed by administrator<',
)
_TESTS = [{
'url': 'https://uqload.com/dltx1wztngdz',
'md5': '3cfbb65e4c90e93d7b37bcb65a595557',
'info_dict': {
'id': 'dltx1wztngdz',
'ext': 'mp4',
'title': 'Rick Astley Never Gonna Give You mp4',
'thumbnail': r're:https://.*\.jpg'
}
}, {
'url': 'http://xvideosharing.com/fq65f94nd2ve',
'md5': '4181f63957e8fe90ac836fa58dc3c8a6',
'info_dict': {
'id': 'fq65f94nd2ve',
'ext': 'mp4',
'title': 'sample',
'thumbnail': r're:http://.*\.jpg',
},
}, {
'url': 'https://aparat.cam/n4d6dh0wvlpr',
'only_matching': True,
}, {
'url': 'https://wolfstream.tv/nthme29v9u2x',
'only_matching': True,
}]
def _real_extract(self, url):
host, video_id = self._match_valid_url(url).groups()
url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
webpage = self._download_webpage(url, video_id)
if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = self._hidden_inputs(webpage)
if fields.get('op') == 'download1':
countdown = int_or_none(self._search_regex(
r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
webpage, 'countdown', default=None))
if countdown:
self._sleep(countdown, video_id)
webpage = self._download_webpage(
url, video_id, 'Downloading video page',
data=urlencode_postdata(fields), headers={
'Referer': url,
'Content-type': 'application/x-www-form-urlencoded',
})
title = (self._search_regex(
(r'style="z-index: [0-9]+;">([^<]+)</span>',
r'<td nowrap>([^<]+)</td>',
r'h4-fine[^>]*>([^<]+)<',
r'>Watch (.+)[ <]',
r'<h2 class="video-page-head">([^<]+)</h2>',
r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<', # streamin.to
r'title\s*:\s*"([^"]+)"'), # govid.me
webpage, 'title', default=None) or self._og_search_title(
webpage, default=None) or video_id).strip()
for regex, func in (
(r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes),
(r'(゚.+)', aa_decode)):
obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
if obf_code:
webpage = webpage.replace(obf_code, func(obf_code))
formats = []
jwplayer_data = self._search_regex(
[
r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);',
r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);',
], webpage,
'jwplayer data', default=None)
if jwplayer_data:
jwplayer_data = self._parse_json(
jwplayer_data.replace(r"\'", "'"), video_id, js_to_json)
if jwplayer_data:
formats = self._parse_jwplayer_data(
jwplayer_data, video_id, False,
m3u8_id='hls', mpd_id='dash')['formats']
if not formats:
urls = []
for regex in (
r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
for mobj in re.finditer(regex, webpage):
video_url = mobj.group('url')
if video_url not in urls:
urls.append(video_url)
sources = self._search_regex(
r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
if sources:
urls.extend(self._parse_json(sources, video_id))
formats = []
for video_url in urls:
if determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False))
else:
formats.append({
'url': video_url,
'format_id': 'sd',
})
thumbnail = self._search_regex(
[
r'<video[^>]+poster="([^"]+)"',
r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
], webpage, 'thumbnail', default=None)
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
'http_headers': {'Referer': url}
}

View File

@ -1,65 +0,0 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
parse_duration,
urljoin,
)
class YourPornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)'
_TESTS = [{
'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
'md5': '6f8682b6464033d87acaa7a8ff0c092e',
'info_dict': {
'id': '57ffcb2e1179b',
'ext': 'mp4',
'title': 'md5:c9f43630bd968267672651ba905a7d35',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 165,
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
parts = self._parse_json(
self._search_regex(
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
group='data'),
video_id)[video_id].split('/')
num = 0
for c in parts[6] + parts[7]:
if c.isnumeric():
num += int(c)
parts[5] = compat_str(int(parts[5]) - num)
parts[1] += '8'
video_url = urljoin(url, '/'.join(parts))
title = (self._search_regex(
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
default=None) or self._og_search_description(webpage)).strip()
thumbnail = self._og_search_thumbnail(webpage)
duration = parse_duration(self._search_regex(
r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration',
default=None))
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'age_limit': 18,
'ext': 'mp4',
}

View File

@ -1,43 +0,0 @@
from .common import InfoExtractor
from ..utils import urljoin
class YourUploadIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:yourupload\.com/(?:watch|embed)|embed\.yourupload\.com)/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'http://yourupload.com/watch/14i14h',
'md5': '5e2c63385454c557f97c4c4131a393cd',
'info_dict': {
'id': '14i14h',
'ext': 'mp4',
'title': 'BigBuckBunny_320x180.mp4',
'thumbnail': r're:^https?://.*\.jpe?g',
}
}, {
'url': 'http://www.yourupload.com/embed/14i14h',
'only_matching': True,
}, {
'url': 'http://embed.yourupload.com/14i14h',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
embed_url = 'http://www.yourupload.com/embed/%s' % video_id
webpage = self._download_webpage(embed_url, video_id)
title = self._og_search_title(webpage)
video_url = urljoin(embed_url, self._og_search_video_url(webpage))
thumbnail = self._og_search_thumbnail(webpage, default=None)
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumbnail,
'http_headers': {
'Referer': embed_url,
},
}