-# coding: utf-8
-
-from __future__ import unicode_literals
-
import os
import re
-import sys
+import urllib.parse
+import xml.etree.ElementTree
-from .common import InfoExtractor
+from .common import InfoExtractor # isort: split
+from .brightcove import BrightcoveLegacyIE, BrightcoveNewIE
+from .commonprotocols import RtmpIE
from .youtube import YoutubeIE
-from ..compat import (
- compat_etree_fromstring,
- compat_str,
- compat_urllib_parse_unquote,
- compat_urlparse,
- compat_xml_parse_error,
-)
+from ..compat import compat_etree_fromstring
from ..utils import (
+ KNOWN_EXTENSIONS,
+ ExtractorError,
+ UnsupportedError,
determine_ext,
dict_get,
- ExtractorError,
- float_or_none,
- HEADRequest,
+ format_field,
int_or_none,
is_html,
js_to_json,
- KNOWN_EXTENSIONS,
merge_dicts,
mimetype2ext,
orderedSet,
parse_duration,
parse_resolution,
- sanitized_Request,
smuggle_url,
str_or_none,
+ try_call,
unescapeHTML,
unified_timestamp,
unsmuggle_url,
- UnsupportedError,
url_or_none,
xpath_attr,
xpath_text,
xpath_with_ns,
)
-from .commonprotocols import RtmpIE
-from .brightcove import (
- BrightcoveLegacyIE,
- BrightcoveNewIE,
-)
-from .nexx import (
- NexxIE,
- NexxEmbedIE,
-)
-from .nbc import NBCSportsVPlayerIE
-from .ooyala import OoyalaIE
-from .rutv import RUTVIE
-from .tvc import TVCIE
-from .sportbox import SportBoxIE
-from .myvi import MyviIE
-from .condenast import CondeNastIE
-from .udn import UDNEmbedIE
-from .senategov import SenateISVPIE
-from .svt import SVTIE
-from .pornhub import PornHubIE
-from .xhamster import XHamsterEmbedIE
-from .tnaflix import TNAFlixNetworkEmbedIE
-from .drtuber import DrTuberIE
-from .redtube import RedTubeIE
-from .tube8 import Tube8IE
-from .mofosex import MofosexEmbedIE
-from .spankwire import SpankwireIE
-from .youporn import YouPornIE
-from .vimeo import (
- VimeoIE,
- VHXEmbedIE,
-)
-from .dailymotion import DailymotionIE
-from .dailymail import DailyMailIE
-from .onionstudios import OnionStudiosIE
-from .viewlift import ViewLiftEmbedIE
-from .mtv import MTVServicesEmbeddedIE
-from .pladform import PladformIE
-from .videomore import VideomoreIE
-from .webcaster import WebcasterFeedIE
-from .googledrive import GoogleDriveIE
-from .jwplatform import JWPlatformIE
-from .digiteka import DigitekaIE
-from .arkena import ArkenaIE
-from .instagram import InstagramIE
-from .threeqsdn import ThreeQSDNIE
-from .theplatform import ThePlatformIE
-from .kaltura import KalturaIE
-from .eagleplatform import EaglePlatformIE
-from .facebook import FacebookIE
-from .soundcloud import SoundcloudEmbedIE
-from .tunein import TuneInBaseIE
-from .vbox7 import Vbox7IE
-from .dbtv import DBTVIE
-from .piksel import PikselIE
-from .videa import VideaIE
-from .twentymin import TwentyMinutenIE
-from .ustream import UstreamIE
-from .arte import ArteTVEmbedIE
-from .videopress import VideoPressIE
-from .rutube import RutubeIE
-from .glomex import GlomexEmbedIE
-from .megatvcom import MegaTVComEmbedIE
-from .ant1newsgr import Ant1NewsGrEmbedIE
-from .limelight import LimelightBaseIE
-from .anvato import AnvatoIE
-from .washingtonpost import WashingtonPostIE
-from .wistia import WistiaIE
-from .mediaset import MediasetIE
-from .joj import JojIE
-from .megaphone import MegaphoneIE
-from .vzaar import VzaarIE
-from .channel9 import Channel9IE
-from .vshare import VShareIE
-from .mediasite import MediasiteIE
-from .springboardplatform import SpringboardPlatformIE
-from .ted import TedEmbedIE
-from .yapfiles import YapFilesIE
-from .vice import ViceIE
-from .xfileshare import XFileShareIE
-from .cloudflarestream import CloudflareStreamIE
-from .peertube import PeerTubeIE
-from .teachable import TeachableIE
-from .indavideo import IndavideoEmbedIE
-from .apa import APAIE
-from .foxnews import FoxNewsIE
-from .viqeo import ViqeoIE
-from .expressen import ExpressenIE
-from .zype import ZypeIE
-from .odnoklassniki import OdnoklassnikiIE
-from .vk import VKIE
-from .kinja import KinjaEmbedIE
-from .gedidigital import GediDigitalIE
-from .rcs import RCSEmbedsIE
-from .bitchute import BitChuteIE
-from .rumble import RumbleEmbedIE
-from .arcpublishing import ArcPublishingIE
-from .medialaan import MedialaanIE
-from .simplecast import SimplecastIE
-from .wimtv import WimTVIE
-from .tvopengr import TVOpenGrEmbedIE
-from .ertgr import ERTWebtvEmbedIE
-from .tvp import TVPEmbedIE
-from .blogger import BloggerIE
-from .mainstreaming import MainStreamingIE
-from .gfycat import GfycatIE
-from .panopto import PanoptoBaseIE
class GenericIE(InfoExtractor):
IE_DESC = 'Generic downloader that works on some sites'
_VALID_URL = r'.*'
IE_NAME = 'generic'
- _NETRC_MACHINE = False # Supress username warning
+ _NETRC_MACHINE = False # Suppress username warning
_TESTS = [
# Direct link to a video
{
'skip_download': True,
}
},
- # YouTube <object> embed
- {
- 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
- 'md5': '516718101ec834f74318df76259fb3cc',
- 'info_dict': {
- 'id': 'msN87y-iEx0',
- 'ext': 'webm',
- 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
- 'upload_date': '20080526',
- 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
- 'uploader': 'Christopher Sykes',
- 'uploader_id': 'ChristopherJSykes',
- },
- 'add_ie': ['Youtube'],
- },
- # Camtasia studio
- {
- 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
- 'playlist': [{
- 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
- 'info_dict': {
- 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
- 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
- 'ext': 'flv',
- 'duration': 2235.90,
- }
- }, {
- 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
- 'info_dict': {
- 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
- 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
- 'ext': 'flv',
- 'duration': 2235.93,
- }
- }],
- 'info_dict': {
- 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
- }
- },
# Flowplayer
{
'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
'filesize': 24687186,
},
},
- {
- 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
- 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
- 'info_dict': {
- 'id': 'uxjb0lwrcz',
- 'ext': 'mp4',
- 'title': 'Conversation about Hexagonal Rails Part 1',
- 'description': 'a Martin Fowler video from ThoughtWorks',
- 'duration': 1715.0,
- 'uploader': 'thoughtworks.wistia.com',
- 'timestamp': 1401832161,
- 'upload_date': '20140603',
- },
- },
# Wistia standard embed (async)
{
'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
'timestamp': 468923808,
'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
},
- 'add_ie': [JWPlatformIE.ie_key()],
+ 'add_ie': ['JWPlatform'],
},
{
# Video.js embed, multiple formats
'params': {
'skip_download': True,
},
- 'add_ie': [ArkenaIE.ie_key()],
+ 'add_ie': ['Arkena'],
},
{
'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
'params': {
'skip_download': True,
},
- 'add_ie': [Vbox7IE.ie_key()],
+ 'add_ie': ['Vbox7'],
},
{
# DBTV embeds
'params': {
'skip_download': True,
},
- 'add_ie': [TwentyMinutenIE.ie_key()],
+ 'add_ie': ['TwentyMinuten'],
},
{
# VideoPress embed
'params': {
'skip_download': True,
},
- 'add_ie': [VideoPressIE.ie_key()],
+ 'add_ie': ['VideoPress'],
},
{
# Rutube embed
'params': {
'skip_download': True,
},
- 'add_ie': [RutubeIE.ie_key()],
+ 'add_ie': ['Rutube'],
},
{
# glomex:embed
'ext': 'mp4',
'title': 'Integrated Senate Video Player',
},
- 'add_ie': [SenateISVPIE.ie_key()],
+ 'add_ie': ['SenateISVP'],
},
{
# Limelight embeds (1 channel embed + 4 media embeds)
'uploader': 'The Washington Post',
'upload_date': '20160211',
},
- 'add_ie': [WashingtonPostIE.ie_key()],
+ 'add_ie': ['WashingtonPost'],
},
{
# Mediaset embed
'params': {
'skip_download': True,
},
- 'add_ie': [MediasetIE.ie_key()],
+ 'add_ie': ['Mediaset'],
},
{
# JOJ.sk embeds
'title': 'Slovenskom sa prehnala vlna silných búrok',
},
'playlist_mincount': 5,
- 'add_ie': [JojIE.ie_key()],
+ 'add_ie': ['Joj'],
},
{
# AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
'params': {
'skip_download': True,
},
- 'add_ie': [SpringboardPlatformIE.ie_key()],
+ 'add_ie': ['SpringboardPlatform'],
},
{
'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
'ext': 'mp4',
'title': 'Котята',
},
- 'add_ie': [YapFilesIE.ie_key()],
+ 'add_ie': ['YapFiles'],
'params': {
'skip_download': True,
},
'ext': 'mp4',
'title': '31c9291ab41fac05471db4e73aa11717',
},
- 'add_ie': [CloudflareStreamIE.ie_key()],
+ 'add_ie': ['CloudflareStream'],
'params': {
'skip_download': True,
},
'uploader': 'StreetKitchen',
'uploader_id': '546363',
},
- 'add_ie': [IndavideoEmbedIE.ie_key()],
+ 'add_ie': ['IndavideoEmbed'],
'params': {
'skip_download': True,
},
# Panopto embeds
'url': 'https://www.monash.edu/learning-teaching/teachhq/learning-technologies/panopto/how-to/insert-a-quiz-into-a-panopto-video',
'info_dict': {
- 'title': 'Insert a quiz into a Panopto video',
- 'id': 'insert-a-quiz-into-a-panopto-video'
+ 'ext': 'mp4',
+ 'id': '0bd3f16c-824a-436a-8486-ac5900693aef',
+ 'title': 'Quizzes in Panopto',
},
- 'playlist_count': 1
- }
+ },
+ {
+ # Ruutu embed
+ 'url': 'https://www.nelonen.fi/ohjelmat/madventures-suomi/2160731-riku-ja-tunna-lahtevat-peurajahtiin-tv-sta-tutun-biologin-kanssa---metsastysreissu-huipentuu-kasvissyojan-painajaiseen',
+ 'md5': 'a2513a98d3496099e6eced40f7e6a14b',
+ 'info_dict': {
+ 'id': '4044426',
+ 'ext': 'mp4',
+ 'title': 'Riku ja Tunna lähtevät peurajahtiin tv:stä tutun biologin kanssa – metsästysreissu huipentuu kasvissyöjän painajaiseen!',
+ 'thumbnail': r're:^https?://.+\.jpg$',
+ 'duration': 108,
+ 'series': 'Madventures Suomi',
+ 'description': 'md5:aa55b44bd06a1e337a6f1d0b46507381',
+ 'categories': ['Matkailu', 'Elämäntyyli'],
+ 'age_limit': 0,
+ 'upload_date': '20220308',
+ },
+ },
+ {
+ # Multiple Ruutu embeds
+ 'url': 'https://www.hs.fi/kotimaa/art-2000008762560.html',
+ 'info_dict': {
+ 'title': 'Koronavirus | Epidemiahuippu voi olla Suomessa ohi, mutta koronaviruksen poistamista yleisvaarallisten tautien joukosta harkitaan vasta syksyllä',
+ 'id': 'art-2000008762560'
+ },
+ 'playlist_count': 3
+ },
+ {
+ # Ruutu embed in hs.fi with a single video
+ 'url': 'https://www.hs.fi/kotimaa/art-2000008793421.html',
+ 'md5': 'f8964e65d8fada6e8a562389bf366bb4',
+ 'info_dict': {
+ 'id': '4081841',
+ 'ext': 'mp4',
+ 'title': 'Puolustusvoimat siirsi panssariajoneuvoja harjoituksiin Niinisaloon 2.5.2022',
+ 'thumbnail': r're:^https?://.+\.jpg$',
+ 'duration': 138,
+ 'age_limit': 0,
+ 'upload_date': '20220504',
+ },
+ },
+ {
+ # Webpage contains double BOM
+ 'url': 'https://www.filmarkivet.se/movies/paris-d-moll/',
+ 'md5': 'df02cadc719dcc63d43288366f037754',
+ 'info_dict': {
+ 'id': 'paris-d-moll',
+ 'ext': 'mp4',
+ 'upload_date': '20220518',
+ 'title': 'Paris d-moll',
+ 'description': 'md5:319e37ea5542293db37e1e13072fe330',
+ 'thumbnail': 'https://www.filmarkivet.se/wp-content/uploads/parisdmoll2.jpg',
+ 'timestamp': 1652833414,
+ 'age_limit': 0,
+ }
+ },
+ {
+ 'url': 'https://www.mollymovieclub.com/p/interstellar?s=r#details',
+ 'md5': '198bde8bed23d0b23c70725c83c9b6d9',
+ 'info_dict': {
+ 'id': '53602801',
+ 'ext': 'mpga',
+ 'title': 'Interstellar',
+ 'description': 'Listen now | Episode One',
+ 'thumbnail': 'md5:c30d9c83f738e16d8551d7219d321538',
+ 'uploader': 'Molly Movie Club',
+ 'uploader_id': '839621',
+ },
+ },
+ {
+ 'url': 'https://www.blockedandreported.org/p/episode-117-lets-talk-about-depp?s=r',
+ 'md5': 'c0cc44ee7415daeed13c26e5b56d6aa0',
+ 'info_dict': {
+ 'id': '57962052',
+ 'ext': 'mpga',
+ 'title': 'md5:855b2756f0ee10f6723fa00b16266f8d',
+ 'description': 'md5:fe512a5e94136ad260c80bde00ea4eef',
+ 'thumbnail': 'md5:2218f27dfe517bb5ac16c47d0aebac59',
+ 'uploader': 'Blocked and Reported',
+ 'uploader_id': '500230',
+ },
+ },
+ {
+ 'url': 'https://www.skimag.com/video/ski-people-1980/',
+ 'md5': '022a7e31c70620ebec18deeab376ee03',
+ 'info_dict': {
+ 'id': 'YTmgRiNU',
+ 'ext': 'mp4',
+ 'title': '1980 Ski People',
+ 'timestamp': 1610407738,
+ 'description': 'md5:cf9c3d101452c91e141f292b19fe4843',
+ 'thumbnail': 'https://cdn.jwplayer.com/v2/media/YTmgRiNU/poster.jpg?width=720',
+ 'duration': 5688.0,
+ 'upload_date': '20210111',
+ }
+ },
+ {
+ 'note': 'Rumble embed',
+ 'url': 'https://rumble.com/vdmum1-moose-the-dog-helps-girls-dig-a-snow-fort.html',
+ 'md5': '53af34098a7f92c4e51cf0bd1c33f009',
+ 'info_dict': {
+ 'id': 'vb0ofn',
+ 'ext': 'mp4',
+ 'timestamp': 1612662578,
+ 'uploader': 'LovingMontana',
+ 'channel': 'LovingMontana',
+ 'upload_date': '20210207',
+ 'title': 'Winter-loving dog helps girls dig a snow fort ',
+ 'channel_url': 'https://rumble.com/c/c-546523',
+ 'thumbnail': 'https://sp.rmbl.ws/s8/1/5/f/x/x/5fxxb.OvCc.1-small-Moose-The-Dog-Helps-Girls-D.jpg',
+ 'duration': 103,
+ }
+ },
+ {
+ 'note': 'Rumble JS embed',
+ 'url': 'https://therightscoop.com/what-does-9-plus-1-plus-1-equal-listen-to-this-audio-of-attempted-kavanaugh-assassins-call-and-youll-get-it',
+ 'md5': '4701209ac99095592e73dbba21889690',
+ 'info_dict': {
+ 'id': 'v15eqxl',
+ 'ext': 'mp4',
+ 'channel': 'Mr Producer Media',
+ 'duration': 92,
+ 'title': '911 Audio From The Man Who Wanted To Kill Supreme Court Justice Kavanaugh',
+ 'channel_url': 'https://rumble.com/c/RichSementa',
+ 'thumbnail': 'https://sp.rmbl.ws/s8/1/P/j/f/A/PjfAe.OvCc-small-911-Audio-From-The-Man-Who-.jpg',
+ 'timestamp': 1654892716,
+ 'uploader': 'Mr Producer Media',
+ 'upload_date': '20220610',
+ }
+ },
+ {
+ 'note': 'JSON LD with multiple @type',
+ 'url': 'https://www.nu.nl/280161/video/hoe-een-bladvlo-dit-verwoestende-japanse-onkruid-moet-vernietigen.html',
+ 'md5': 'c7949f34f57273013fb7ccb1156393db',
+ 'info_dict': {
+ 'id': 'ipy2AcGL',
+ 'ext': 'mp4',
+ 'description': 'md5:6a9d644bab0dc2dc06849c2505d8383d',
+ 'thumbnail': r're:https://media\.nu\.nl/m/.+\.jpg',
+ 'title': 'Hoe een bladvlo dit verwoestende Japanse onkruid moet vernietigen',
+ 'timestamp': 1586577474,
+ 'upload_date': '20200411',
+ 'age_limit': 0,
+ 'duration': 111.0,
+ }
+ },
]
def report_following_redirect(self, new_url):
"""Report information extraction."""
self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
- def report_detected(self, name):
- self._downloader.write_debug(f'Identified a {name}')
+ def report_detected(self, name, num=1, note=None):
+ if num > 1:
+ name += 's'
+ elif not num:
+ return
+ else:
+ num = 'a'
- def _extract_rss(self, url, video_id, doc):
- playlist_title = doc.find('./channel/title').text
- playlist_desc_el = doc.find('./channel/description')
- playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
+ self._downloader.write_debug(f'Identified {num} {name}{format_field(note, None, "; %s")}')
+ def _extract_rss(self, url, video_id, doc):
NS_MAP = {
'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
}
entries = []
for it in doc.findall('./channel/item'):
- next_url = None
- enclosure_nodes = it.findall('./enclosure')
- for e in enclosure_nodes:
- next_url = e.attrib.get('url')
- if next_url:
- break
-
- if not next_url:
- next_url = xpath_text(it, 'link', fatal=False)
-
+ next_url = next(
+ (e.attrib.get('url') for e in it.findall('./enclosure')),
+ xpath_text(it, 'link', fatal=False))
if not next_url:
continue
- if it.find('guid').text is not None:
- next_url = smuggle_url(next_url, {'force_videoid': it.find('guid').text})
+ guid = try_call(lambda: it.find('guid').text)
+ if guid:
+ next_url = smuggle_url(next_url, {'force_videoid': guid})
def itunes(key):
- return xpath_text(
- it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
- default=None)
-
- duration = itunes('duration')
- explicit = (itunes('explicit') or '').lower()
- if explicit in ('true', 'yes'):
- age_limit = 18
- elif explicit in ('false', 'no'):
- age_limit = 0
- else:
- age_limit = None
+ return xpath_text(it, xpath_with_ns(f'./itunes:{key}', NS_MAP), default=None)
entries.append({
'_type': 'url_transparent',
'url': next_url,
- 'title': it.find('title').text,
+ 'title': try_call(lambda: it.find('title').text),
'description': xpath_text(it, 'description', default=None),
- 'timestamp': unified_timestamp(
- xpath_text(it, 'pubDate', default=None)),
- 'duration': int_or_none(duration) or parse_duration(duration),
+ 'timestamp': unified_timestamp(xpath_text(it, 'pubDate', default=None)),
+ 'duration': parse_duration(itunes('duration')),
'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
'episode': itunes('title'),
'episode_number': int_or_none(itunes('episode')),
'season_number': int_or_none(itunes('season')),
- 'age_limit': age_limit,
+ 'age_limit': {'true': 18, 'yes': 18, 'false': 0, 'no': 0}.get((itunes('explicit') or '').lower()),
})
return {
'_type': 'playlist',
'id': url,
- 'title': playlist_title,
- 'description': playlist_desc,
+ 'title': try_call(lambda: doc.find('./channel/title').text),
+ 'description': try_call(lambda: doc.find('./channel/description').text),
'entries': entries,
}
- def _extract_camtasia(self, url, video_id, webpage):
- """ Returns None if no camtasia video can be found. """
-
- camtasia_cfg = self._search_regex(
- r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
- webpage, 'camtasia configuration file', default=None)
- if camtasia_cfg is None:
- return None
-
- title = self._html_search_meta('DC.title', webpage, fatal=True)
-
- camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
- camtasia_cfg = self._download_xml(
- camtasia_url, video_id,
- note='Downloading camtasia configuration',
- errnote='Failed to download camtasia configuration')
- fileset_node = camtasia_cfg.find('./playlist/array/fileset')
-
- entries = []
- for n in fileset_node.getchildren():
- url_n = n.find('./uri')
- if url_n is None:
- continue
-
- entries.append({
- 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
- 'title': '%s - %s' % (title, n.tag),
- 'url': compat_urlparse.urljoin(url, url_n.text),
- 'duration': float_or_none(n.find('./duration').text),
- })
-
- return {
- '_type': 'playlist',
- 'entries': entries,
- 'title': title,
- }
-
def _kvs_getrealurl(self, video_url, license_code):
if not video_url.startswith('function/0/'):
return video_url # not obfuscated
for o in range(len(newmagic) - 1, -1, -1):
new = ''
- l = (o + sum([int(n) for n in license[o:]])) % 32
+ l = (o + sum(int(n) for n in license[o:])) % 32
for i in range(0, len(newmagic)):
if i == o:
if url.startswith('//'):
return self.url_result(self.http_scheme() + url)
- parsed_url = compat_urlparse.urlparse(url)
+ parsed_url = urllib.parse.urlparse(url)
if not parsed_url.scheme:
default_search = self.get_param('default_search')
if default_search is None:
else:
video_id = self._generic_id(url)
- self.to_screen('%s: Requesting header' % video_id)
-
- head_req = HEADRequest(url)
- head_response = self._request_webpage(
- head_req, video_id,
- note=False, errnote='Could not send HEAD request to %s' % url,
- fatal=False)
-
- if head_response is not False:
- # Check for redirect
- new_url = head_response.geturl()
- if url != new_url:
- self.report_following_redirect(new_url)
- if force_videoid:
- new_url = smuggle_url(
- new_url, {'force_videoid': force_videoid})
- return self.url_result(new_url)
-
- full_response = None
- if head_response is False:
- request = sanitized_Request(url)
- request.add_header('Accept-Encoding', '*')
- full_response = self._request_webpage(request, video_id)
- head_response = full_response
+ # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
+ # making it impossible to download only chunk of the file (yet we need only 512kB to
+ # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
+ # that will always result in downloading the whole file that is not desirable.
+ # Therefore for extraction pass we have to override Accept-Encoding to any in order
+ # to accept raw bytes and being able to download only a chunk.
+ # It may probably better to solve this by checking Content-Type for application/octet-stream
+ # after a HEAD request, but not sure if we can rely on this.
+ full_response = self._request_webpage(url, video_id, headers={'Accept-Encoding': '*'})
+ new_url = full_response.geturl()
+ if url != new_url:
+ self.report_following_redirect(new_url)
+ if force_videoid:
+ new_url = smuggle_url(new_url, {'force_videoid': force_videoid})
+ return self.url_result(new_url)
info_dict = {
'id': video_id,
'title': self._generic_title(url),
- 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
+ 'timestamp': unified_timestamp(full_response.headers.get('Last-Modified'))
}
# Check for direct link to a video
- content_type = head_response.headers.get('Content-Type', '').lower()
+ content_type = full_response.headers.get('Content-Type', '').lower()
m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
if m:
self.report_detected('direct video link')
- format_id = compat_str(m.group('format_id'))
+ format_id = str(m.group('format_id'))
subtitles = {}
if format_id.endswith('mpegurl'):
formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
if not self.get_param('test', False) and not is_intentional:
force = self.get_param('force_generic_extractor', False)
- self.report_warning(
- '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
-
- if not full_response:
- request = sanitized_Request(url)
- # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
- # making it impossible to download only chunk of the file (yet we need only 512kB to
- # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
- # that will always result in downloading the whole file that is not desirable.
- # Therefore for extraction pass we have to override Accept-Encoding to any in order
- # to accept raw bytes and being able to download only a chunk.
- # It may probably better to solve this by checking Content-Type for application/octet-stream
- # after HEAD request finishes, but not sure if we can rely on this.
- request.add_header('Accept-Encoding', '*')
- full_response = self._request_webpage(request, video_id)
+ self.report_warning('%s generic information extractor' % ('Forcing' if force else 'Falling back on'))
first_bytes = full_response.read(512)
try:
try:
doc = compat_etree_fromstring(webpage)
- except compat_xml_parse_error:
+ except xml.etree.ElementTree.ParseError:
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
self.report_detected('RSS feed')
self.report_detected('F4M manifest')
self._sort_formats(info_dict['formats'])
return info_dict
- except compat_xml_parse_error:
+ except xml.etree.ElementTree.ParseError:
pass
- # Is it a Camtasia project?
- camtasia_res = self._extract_camtasia(url, video_id, webpage)
- if camtasia_res is not None:
- self.report_detected('Camtasia video')
- return camtasia_res
+ info_dict.update({
+ # it's tempting to parse this further, but you would
+ # have to take into account all the variations like
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ 'title': (self._og_search_title(webpage, default=None)
+ or self._html_extract_title(webpage, 'video title', default='video')),
+ 'description': self._og_search_description(webpage, default=None),
+ 'thumbnail': self._og_search_thumbnail(webpage, default=None),
+ 'age_limit': self._rta_search(webpage),
+ })
+
+ domain_name = self._search_regex(r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
# Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
# Unescaping the whole page allows to handle those cases in a generic way
# FIXME: unescaping the whole page may break URLs, commenting out for now.
# There probably should be a second run of generic extractor on unescaped webpage.
- # webpage = compat_urllib_parse_unquote(webpage)
+ # webpage = urllib.parse.unquote(webpage)
# Unescape squarespace embeds to be detected by generic extractor,
# see https://github.com/ytdl-org/youtube-dl/issues/21294
r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
lambda x: unescapeHTML(x.group(0)), webpage)
- # it's tempting to parse this further, but you would
- # have to take into account all the variations like
- # Video Title - Site Name
- # Site Name | Video Title
- # Video Title - Tagline | Site Name
- # and so on and so forth; it's just not practical
- video_title = (self._og_search_title(webpage, default=None)
- or self._html_extract_title(webpage, 'video title', default='video'))
-
- # Try to detect age limit automatically
- age_limit = self._rta_search(webpage)
- # And then there are the jokers who advertise that they use RTA,
- # but actually don't.
- AGE_LIMIT_MARKERS = [
- r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
- ]
- if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
- age_limit = 18
-
- # video uploader is domain name
- video_uploader = self._search_regex(
- r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
-
- video_description = self._og_search_description(webpage, default=None)
- video_thumbnail = self._og_search_thumbnail(webpage, default=None)
-
- info_dict.update({
- 'title': video_title,
- 'description': video_description,
- 'thumbnail': video_thumbnail,
- 'age_limit': age_limit,
- })
-
- self._downloader.write_debug('Looking for video embeds')
-
- # Look for Brightcove Legacy Studio embeds
+ # TODO: Move to respective extractors
+ self._downloader.write_debug('Looking for Brightcove embeds')
bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
if bc_urls:
entries = [{
return {
'_type': 'playlist',
- 'title': video_title,
+ 'title': info_dict['title'],
'id': video_id,
'entries': entries,
}
-
- # Look for Brightcove New Studio embeds
- bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
+ bc_urls = BrightcoveNewIE._extract_brightcove_urls(self, webpage)
if bc_urls:
return self.playlist_from_matches(
- bc_urls, video_id, video_title,
+ bc_urls, video_id, info_dict['title'],
getter=lambda x: smuggle_url(x, {'referrer': url}),
ie='BrightcoveNew')
- # Look for Nexx embeds
- nexx_urls = NexxIE._extract_urls(webpage)
- if nexx_urls:
- return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
-
- # Look for Nexx iFrame embeds
- nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
- if nexx_embed_urls:
- return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
-
- # Look for ThePlatform embeds
- tp_urls = ThePlatformIE._extract_urls(webpage)
- if tp_urls:
- return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
-
- arc_urls = ArcPublishingIE._extract_urls(webpage)
- if arc_urls:
- return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
-
- mychannels_urls = MedialaanIE._extract_urls(webpage)
- if mychannels_urls:
- return self.playlist_from_matches(
- mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
-
- # Look for embedded rtl.nl player
- matches = re.findall(
- r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
- webpage)
- if matches:
- return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
-
- vimeo_urls = VimeoIE._extract_urls(url, webpage)
- if vimeo_urls:
- return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
-
- vhx_url = VHXEmbedIE._extract_url(webpage)
- if vhx_url:
- return self.url_result(vhx_url, VHXEmbedIE.ie_key())
-
- # Invidious Instances
- # https://github.com/yt-dlp/yt-dlp/issues/195
- # https://github.com/iv-org/invidious/pull/1730
- youtube_url = self._search_regex(
- r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
- webpage, 'youtube link', default=None)
- if youtube_url:
- return self.url_result(youtube_url, YoutubeIE.ie_key())
-
- # Look for YouTube embeds
- youtube_urls = YoutubeIE._extract_urls(webpage)
- if youtube_urls:
- return self.playlist_from_matches(
- youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
-
- matches = DailymotionIE._extract_urls(webpage)
- if matches:
- return self.playlist_from_matches(matches, video_id, video_title)
-
- # Look for embedded Dailymotion playlist player (#3822)
- m = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
- if m:
- playlists = re.findall(
- r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
- if playlists:
- return self.playlist_from_matches(
- playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
-
- # Look for DailyMail embeds
- dailymail_urls = DailyMailIE._extract_urls(webpage)
- if dailymail_urls:
- return self.playlist_from_matches(
- dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
-
- # Look for Teachable embeds, must be before Wistia
- teachable_url = TeachableIE._extract_url(webpage, url)
- if teachable_url:
- return self.url_result(teachable_url)
-
- # Look for embedded Wistia player
- wistia_urls = WistiaIE._extract_urls(webpage)
- if wistia_urls:
- playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
- for entry in playlist['entries']:
- entry.update({
- '_type': 'url_transparent',
- 'uploader': video_uploader,
- })
- return playlist
-
- # Look for SVT player
- svt_url = SVTIE._extract_url(webpage)
- if svt_url:
- return self.url_result(svt_url, 'SVT')
-
- # Look for Bandcamp pages with custom domain
- mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
- if mobj is not None:
- burl = unescapeHTML(mobj.group(1))
- # Don't set the extractor because it can be a track url or an album
- return self.url_result(burl)
-
- # Look for embedded Vevo player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'))
-
- # Look for embedded Viddler player
- mobj = re.search(
- r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
- webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'))
-
- # Look for NYTimes player
- mobj = re.search(
- r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
- webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'))
-
- # Look for Libsyn player
- mobj = re.search(
- r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'))
-
- # Look for Ooyala videos
- mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
- or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
- or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
- or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
- or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
- if mobj is not None:
- embed_token = self._search_regex(
- r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
- webpage, 'ooyala embed token', default=None)
- return OoyalaIE._build_url_result(smuggle_url(
- mobj.group('ec'), {
- 'domain': url,
- 'embed_token': embed_token,
- }))
-
- # Look for multiple Ooyala embeds on SBN network websites
- mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
- if mobj is not None:
- embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
- if embeds:
- return self.playlist_from_matches(
- embeds, video_id, video_title,
- getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
-
- # Look for Aparat videos
- mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
- if mobj is not None:
- return self.url_result(mobj.group(1), 'Aparat')
-
- # Look for MPORA videos
- mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
- if mobj is not None:
- return self.url_result(mobj.group(1), 'Mpora')
-
- # Look for embedded Facebook player
- facebook_urls = FacebookIE._extract_urls(webpage)
- if facebook_urls:
- return self.playlist_from_matches(facebook_urls, video_id, video_title)
-
- # Look for embedded VK player
- mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'VK')
-
- # Look for embedded Odnoklassniki player
- odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
- if odnoklassniki_url:
- return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
-
- # Look for sibnet embedded player
- sibnet_urls = VKIE._extract_sibnet_urls(webpage)
- if sibnet_urls:
- return self.playlist_from_matches(sibnet_urls, video_id, video_title)
-
- # Look for embedded ivi player
- mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'Ivi')
-
- # Look for embedded Huffington Post player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'HuffPost')
-
- # Look for embed.ly
- mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'))
- mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
- if mobj is not None:
- return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
-
- # Look for funnyordie embed
- matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
- if matches:
- return self.playlist_from_matches(
- matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
-
- # Look for Simplecast embeds
- simplecast_urls = SimplecastIE._extract_urls(webpage)
- if simplecast_urls:
- return self.playlist_from_matches(
- simplecast_urls, video_id, video_title)
-
- # Look for BBC iPlayer embed
- matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
- if matches:
- return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
-
- # Look for embedded RUTV player
- rutv_url = RUTVIE._extract_url(webpage)
- if rutv_url:
- return self.url_result(rutv_url, 'RUTV')
-
- # Look for embedded TVC player
- tvc_url = TVCIE._extract_url(webpage)
- if tvc_url:
- return self.url_result(tvc_url, 'TVC')
-
- # Look for embedded SportBox player
- sportbox_urls = SportBoxIE._extract_urls(webpage)
- if sportbox_urls:
- return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
-
- # Look for embedded XHamster player
- xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
- if xhamster_urls:
- return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
-
- # Look for embedded TNAFlixNetwork player
- tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
- if tnaflix_urls:
- return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
-
- # Look for embedded PornHub player
- pornhub_urls = PornHubIE._extract_urls(webpage)
- if pornhub_urls:
- return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
-
- # Look for embedded DrTuber player
- drtuber_urls = DrTuberIE._extract_urls(webpage)
- if drtuber_urls:
- return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
-
- # Look for embedded RedTube player
- redtube_urls = RedTubeIE._extract_urls(webpage)
- if redtube_urls:
- return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
-
- # Look for embedded Tube8 player
- tube8_urls = Tube8IE._extract_urls(webpage)
- if tube8_urls:
- return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
-
- # Look for embedded Mofosex player
- mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
- if mofosex_urls:
- return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
-
- # Look for embedded Spankwire player
- spankwire_urls = SpankwireIE._extract_urls(webpage)
- if spankwire_urls:
- return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
-
- # Look for embedded YouPorn player
- youporn_urls = YouPornIE._extract_urls(webpage)
- if youporn_urls:
- return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
-
- # Look for embedded Tvigle player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'Tvigle')
-
- # Look for embedded TED player
- ted_urls = TedEmbedIE._extract_urls(webpage)
- if ted_urls:
- return self.playlist_from_matches(ted_urls, video_id, video_title, ie=TedEmbedIE.ie_key())
-
- # Look for embedded Ustream videos
- ustream_url = UstreamIE._extract_url(webpage)
- if ustream_url:
- return self.url_result(ustream_url, UstreamIE.ie_key())
-
- # Look for embedded arte.tv player
- arte_urls = ArteTVEmbedIE._extract_urls(webpage)
- if arte_urls:
- return self.playlist_from_matches(arte_urls, video_id, video_title)
-
- # Look for embedded francetv player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
- webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'))
-
- # Look for embedded Myvi.ru player
- myvi_url = MyviIE._extract_url(webpage)
- if myvi_url:
- return self.url_result(myvi_url)
-
- # Look for embedded soundcloud player
- soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
- if soundcloud_urls:
- return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
-
- # Look for tunein player
- tunein_urls = TuneInBaseIE._extract_urls(webpage)
- if tunein_urls:
- return self.playlist_from_matches(tunein_urls, video_id, video_title)
-
- # Look for embedded mtvservices player
- mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
- if mtvservices_url:
- return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
-
- # Look for embedded yahoo player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
- webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'Yahoo')
-
- # Look for embedded sbs.com.au player
- mobj = re.search(
- r'''(?x)
- (?:
- <meta\s+property="og:video"\s+content=|
- <iframe[^>]+?src=
- )
- (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
- webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'SBS')
-
- # Look for embedded Cinchcast player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
- webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'Cinchcast')
-
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
- webpage)
- if not mobj:
- mobj = re.search(
- r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
- webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'MLB')
-
- mobj = re.search(
- r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
- webpage)
- if mobj is not None:
- return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
-
- mobj = re.search(
- r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
- webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'Livestream')
-
- # Look for Zapiks embed
- mobj = re.search(
- r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'), 'Zapiks')
-
- # Look for Kaltura embeds
- kaltura_urls = KalturaIE._extract_urls(webpage)
- if kaltura_urls:
- return self.playlist_from_matches(
- kaltura_urls, video_id, video_title,
- getter=lambda x: smuggle_url(x, {'source_url': url}),
- ie=KalturaIE.ie_key())
-
- # Look for EaglePlatform embeds
- eagleplatform_url = EaglePlatformIE._extract_url(webpage)
- if eagleplatform_url:
- return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
-
- # Look for ClipYou (uses EaglePlatform) embeds
- mobj = re.search(
- r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
- if mobj is not None:
- return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
-
- # Look for Pladform embeds
- pladform_url = PladformIE._extract_url(webpage)
- if pladform_url:
- return self.url_result(pladform_url)
-
- # Look for Videomore embeds
- videomore_url = VideomoreIE._extract_url(webpage)
- if videomore_url:
- return self.url_result(videomore_url)
-
- # Look for Webcaster embeds
- webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
- if webcaster_url:
- return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
-
- # Look for Playwire embeds
- mobj = re.search(
- r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'))
-
- # Look for Crooks and Liars embeds
- mobj = re.search(
- r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
- if mobj is not None:
- return self.url_result(mobj.group('url'))
-
- # Look for NBC Sports VPlayer embeds
- nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
- if nbc_sports_url:
- return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
-
- # Look for NBC News embeds
- nbc_news_embed_url = re.search(
- r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
- if nbc_news_embed_url:
- return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
-
- # Look for Google Drive embeds
- google_drive_url = GoogleDriveIE._extract_url(webpage)
- if google_drive_url:
- return self.url_result(google_drive_url, 'GoogleDrive')
-
- # Look for UDN embeds
- mobj = re.search(
- r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
- if mobj is not None:
- return self.url_result(
- compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
-
- # Look for Senate ISVP iframe
- senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
- if senate_isvp_url:
- return self.url_result(senate_isvp_url, 'SenateISVP')
-
- # Look for Kinja embeds
- kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
- if kinja_embed_urls:
- return self.playlist_from_matches(
- kinja_embed_urls, video_id, video_title)
-
- # Look for OnionStudios embeds
- onionstudios_url = OnionStudiosIE._extract_url(webpage)
- if onionstudios_url:
- return self.url_result(onionstudios_url)
-
- # Look for Blogger embeds
- blogger_urls = BloggerIE._extract_urls(webpage)
- if blogger_urls:
- return self.playlist_from_matches(blogger_urls, video_id, video_title, ie=BloggerIE.ie_key())
-
- # Look for ViewLift embeds
- viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
- if viewlift_url:
- return self.url_result(viewlift_url)
-
- # Look for JWPlatform embeds
- jwplatform_urls = JWPlatformIE._extract_urls(webpage)
- if jwplatform_urls:
- return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
-
- # Look for Digiteka embeds
- digiteka_url = DigitekaIE._extract_url(webpage)
- if digiteka_url:
- return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
-
- # Look for Arkena embeds
- arkena_url = ArkenaIE._extract_url(webpage)
- if arkena_url:
- return self.url_result(arkena_url, ArkenaIE.ie_key())
-
- # Look for Piksel embeds
- piksel_url = PikselIE._extract_url(webpage)
- if piksel_url:
- return self.url_result(piksel_url, PikselIE.ie_key())
-
- # Look for Limelight embeds
- limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
- if limelight_urls:
- return self.playlist_result(
- limelight_urls, video_id, video_title, video_description)
-
- # Look for Anvato embeds
- anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
- if anvato_urls:
- return self.playlist_result(
- anvato_urls, video_id, video_title, video_description)
-
- # Look for AdobeTVVideo embeds
- mobj = re.search(
- r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
- webpage)
- if mobj is not None:
- return self.url_result(
- self._proto_relative_url(unescapeHTML(mobj.group(1))),
- 'AdobeTVVideo')
-
- # Look for Vine embeds
- mobj = re.search(
- r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
- webpage)
- if mobj is not None:
- return self.url_result(
- self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
-
- # Look for VODPlatform embeds
- mobj = re.search(
- r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
- webpage)
- if mobj is not None:
- return self.url_result(
- self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
-
- # Look for Mangomolo embeds
- mobj = re.search(
- r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
- (?:
- admin\.mangomolo\.com/analytics/index\.php/customers/embed|
- player\.mangomolo\.com/v1
- )/
- (?:
- video\?.*?\bid=(?P<video_id>\d+)|
- (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
- ).+?)\1''', webpage)
- if mobj is not None:
- info = {
- '_type': 'url_transparent',
- 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
- 'title': video_title,
- 'description': video_description,
- 'thumbnail': video_thumbnail,
- 'uploader': video_uploader,
- }
- video_id = mobj.group('video_id')
- if video_id:
- info.update({
- 'ie_key': 'MangomoloVideo',
- 'id': video_id,
- })
- else:
- info.update({
- 'ie_key': 'MangomoloLive',
- 'id': mobj.group('channel_id'),
- })
- return info
-
- # Look for Instagram embeds
- instagram_embed_url = InstagramIE._extract_embed_url(webpage)
- if instagram_embed_url is not None:
- return self.url_result(
- self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
-
- # Look for 3Q SDN embeds
- threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
- if threeqsdn_url:
- return {
- '_type': 'url_transparent',
- 'ie_key': ThreeQSDNIE.ie_key(),
- 'url': self._proto_relative_url(threeqsdn_url),
- 'title': video_title,
- 'description': video_description,
- 'thumbnail': video_thumbnail,
- 'uploader': video_uploader,
- }
-
- # Look for VBOX7 embeds
- vbox7_url = Vbox7IE._extract_url(webpage)
- if vbox7_url:
- return self.url_result(vbox7_url, Vbox7IE.ie_key())
-
- # Look for DBTV embeds
- dbtv_urls = DBTVIE._extract_urls(webpage)
- if dbtv_urls:
- return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
-
- # Look for Videa embeds
- videa_urls = VideaIE._extract_urls(webpage)
- if videa_urls:
- return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
-
- # Look for 20 minuten embeds
- twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
- if twentymin_urls:
- return self.playlist_from_matches(
- twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
-
- # Look for VideoPress embeds
- videopress_urls = VideoPressIE._extract_urls(webpage)
- if videopress_urls:
- return self.playlist_from_matches(
- videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
-
- # Look for Rutube embeds
- rutube_urls = RutubeIE._extract_urls(webpage)
- if rutube_urls:
- return self.playlist_from_matches(
- rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
-
- # Look for Glomex embeds
- glomex_urls = list(GlomexEmbedIE._extract_urls(webpage, url))
- if glomex_urls:
- return self.playlist_from_matches(
- glomex_urls, video_id, video_title, ie=GlomexEmbedIE.ie_key())
-
- # Look for megatv.com embeds
- megatvcom_urls = list(MegaTVComEmbedIE._extract_urls(webpage))
- if megatvcom_urls:
- return self.playlist_from_matches(
- megatvcom_urls, video_id, video_title, ie=MegaTVComEmbedIE.ie_key())
-
- # Look for ant1news.gr embeds
- ant1newsgr_urls = list(Ant1NewsGrEmbedIE._extract_urls(webpage))
- if ant1newsgr_urls:
- return self.playlist_from_matches(
- ant1newsgr_urls, video_id, video_title, ie=Ant1NewsGrEmbedIE.ie_key())
-
- # Look for WashingtonPost embeds
- wapo_urls = WashingtonPostIE._extract_urls(webpage)
- if wapo_urls:
- return self.playlist_from_matches(
- wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
-
- # Look for Mediaset embeds
- mediaset_urls = MediasetIE._extract_urls(self, webpage)
- if mediaset_urls:
- return self.playlist_from_matches(
- mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
-
- # Look for JOJ.sk embeds
- joj_urls = JojIE._extract_urls(webpage)
- if joj_urls:
- return self.playlist_from_matches(
- joj_urls, video_id, video_title, ie=JojIE.ie_key())
-
- # Look for megaphone.fm embeds
- mpfn_urls = MegaphoneIE._extract_urls(webpage)
- if mpfn_urls:
- return self.playlist_from_matches(
- mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
-
- # Look for vzaar embeds
- vzaar_urls = VzaarIE._extract_urls(webpage)
- if vzaar_urls:
- return self.playlist_from_matches(
- vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
-
- channel9_urls = Channel9IE._extract_urls(webpage)
- if channel9_urls:
- return self.playlist_from_matches(
- channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
-
- vshare_urls = VShareIE._extract_urls(webpage)
- if vshare_urls:
- return self.playlist_from_matches(
- vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
-
- # Look for Mediasite embeds
- mediasite_urls = MediasiteIE._extract_urls(webpage)
- if mediasite_urls:
- entries = [
- self.url_result(smuggle_url(
- compat_urlparse.urljoin(url, mediasite_url),
- {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
- for mediasite_url in mediasite_urls]
- return self.playlist_result(entries, video_id, video_title)
-
- springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
- if springboardplatform_urls:
- return self.playlist_from_matches(
- springboardplatform_urls, video_id, video_title,
- ie=SpringboardPlatformIE.ie_key())
-
- yapfiles_urls = YapFilesIE._extract_urls(webpage)
- if yapfiles_urls:
- return self.playlist_from_matches(
- yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
-
- vice_urls = ViceIE._extract_urls(webpage)
- if vice_urls:
- return self.playlist_from_matches(
- vice_urls, video_id, video_title, ie=ViceIE.ie_key())
-
- xfileshare_urls = XFileShareIE._extract_urls(webpage)
- if xfileshare_urls:
- return self.playlist_from_matches(
- xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
-
- cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
- if cloudflarestream_urls:
- return self.playlist_from_matches(
- cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
-
- peertube_urls = PeerTubeIE._extract_urls(webpage, url)
- if peertube_urls:
- return self.playlist_from_matches(
- peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
-
- indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
- if indavideo_urls:
- return self.playlist_from_matches(
- indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
-
- apa_urls = APAIE._extract_urls(webpage)
- if apa_urls:
- return self.playlist_from_matches(
- apa_urls, video_id, video_title, ie=APAIE.ie_key())
-
- foxnews_urls = FoxNewsIE._extract_urls(webpage)
- if foxnews_urls:
- return self.playlist_from_matches(
- foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
-
- sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
- r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
- webpage)]
- if sharevideos_urls:
- return self.playlist_from_matches(
- sharevideos_urls, video_id, video_title)
-
- viqeo_urls = ViqeoIE._extract_urls(webpage)
- if viqeo_urls:
- return self.playlist_from_matches(
- viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
-
- expressen_urls = ExpressenIE._extract_urls(webpage)
- if expressen_urls:
- return self.playlist_from_matches(
- expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
-
- zype_urls = ZypeIE._extract_urls(webpage)
- if zype_urls:
- return self.playlist_from_matches(
- zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
-
- gedi_urls = GediDigitalIE._extract_urls(webpage)
- if gedi_urls:
- return self.playlist_from_matches(
- gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
-
- # Look for RCS media group embeds
- rcs_urls = RCSEmbedsIE._extract_urls(webpage)
- if rcs_urls:
- return self.playlist_from_matches(
- rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
-
- wimtv_urls = WimTVIE._extract_urls(webpage)
- if wimtv_urls:
- return self.playlist_from_matches(
- wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
-
- bitchute_urls = BitChuteIE._extract_urls(webpage)
- if bitchute_urls:
- return self.playlist_from_matches(
- bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
-
- rumble_urls = RumbleEmbedIE._extract_urls(webpage)
- if len(rumble_urls) == 1:
- return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
- if rumble_urls:
- return self.playlist_from_matches(
- rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
-
- # Look for (tvopen|ethnos).gr embeds
- tvopengr_urls = list(TVOpenGrEmbedIE._extract_urls(webpage))
- if tvopengr_urls:
- return self.playlist_from_matches(tvopengr_urls, video_id, video_title, ie=TVOpenGrEmbedIE.ie_key())
-
- # Look for ert.gr webtv embeds
- ertwebtv_urls = list(ERTWebtvEmbedIE._extract_urls(webpage))
- if len(ertwebtv_urls) == 1:
- return self.url_result(self._proto_relative_url(ertwebtv_urls[0]), video_title=video_title, url_transparent=True)
- elif ertwebtv_urls:
- return self.playlist_from_matches(ertwebtv_urls, video_id, video_title, ie=ERTWebtvEmbedIE.ie_key())
-
- tvp_urls = TVPEmbedIE._extract_urls(webpage)
- if tvp_urls:
- return self.playlist_from_matches(tvp_urls, video_id, video_title, ie=TVPEmbedIE.ie_key())
-
- # Look for MainStreaming embeds
- mainstreaming_urls = MainStreamingIE._extract_urls(webpage)
- if mainstreaming_urls:
- return self.playlist_from_matches(mainstreaming_urls, video_id, video_title, ie=MainStreamingIE.ie_key())
-
- # Look for Gfycat Embeds
- gfycat_urls = GfycatIE._extract_urls(webpage)
- if gfycat_urls:
- return self.playlist_from_matches(gfycat_urls, video_id, video_title, ie=GfycatIE.ie_key())
-
- panopto_urls = PanoptoBaseIE._extract_urls(webpage)
- if panopto_urls:
- return self.playlist_from_matches(panopto_urls, video_id, video_title)
- # Look for HTML5 media
- entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
- if entries:
- self.report_detected('HTML5 media')
- if len(entries) == 1:
- entries[0].update({
- 'id': video_id,
- 'title': video_title,
- })
- else:
- for num, entry in enumerate(entries, start=1):
- entry.update({
- 'id': '%s-%s' % (video_id, num),
- 'title': '%s (%d)' % (video_title, num),
- })
- for entry in entries:
- self._sort_formats(entry['formats'])
- return self.playlist_result(entries, video_id, video_title)
+ self._downloader.write_debug('Looking for embeds')
+ embeds = []
+ for ie in self._downloader._ies.values():
+ gen = ie.extract_from_webpage(self._downloader, url, webpage)
+ current_embeds = []
+ try:
+ while True:
+ current_embeds.append(next(gen))
+ except self.StopExtraction:
+ self.report_detected(f'{ie.IE_NAME} exclusive embed', len(current_embeds),
+ embeds and 'discarding other embeds')
+ embeds = current_embeds
+ break
+ except StopIteration:
+ self.report_detected(f'{ie.IE_NAME} embed', len(current_embeds))
+ embeds.extend(current_embeds)
+
+ del current_embeds
+ if len(embeds) == 1:
+ return {**info_dict, **embeds[0]}
+ elif embeds:
+ return self.playlist_result(embeds, **info_dict)
jwplayer_data = self._find_jwplayer_data(
webpage, video_id, transform_source=js_to_json)
return {
**info_dict,
'_type': 'url',
- 'ie_key': JWPlatformIE.ie_key(),
+ 'ie_key': 'JWPlatform',
'url': jwplayer_data['playlist'],
}
try:
subtitles = {}
for source in sources:
src = source.get('src')
- if not src or not isinstance(src, compat_str):
+ if not src or not isinstance(src, str):
continue
- src = compat_urlparse.urljoin(url, src)
+ src = urllib.parse.urljoin(url, src)
src_type = source.get('type')
- if isinstance(src_type, compat_str):
+ if isinstance(src_type, str):
src_type = src_type.lower()
ext = determine_ext(src).lower()
if src_type == 'video/youtube':
if not src:
continue
subtitles.setdefault(dict_get(sub, ('language', 'srclang')) or 'und', []).append({
- 'url': compat_urlparse.urljoin(url, src),
+ 'url': urllib.parse.urljoin(url, src),
'name': sub.get('label'),
'http_headers': {
'Referer': full_response.geturl(),
json_ld = self._search_json_ld(webpage, video_id, default={})
if json_ld.get('url') not in (url, None):
self.report_detected('JSON LD')
- if determine_ext(json_ld['url']) == 'm3u8':
- json_ld['formats'], json_ld['subtitles'] = self._extract_m3u8_formats_and_subtitles(
- json_ld['url'], video_id, 'mp4')
- json_ld.pop('url')
- self._sort_formats(json_ld['formats'])
- else:
- json_ld['_type'] = 'url_transparent'
- json_ld['url'] = smuggle_url(json_ld['url'], {'force_videoid': video_id, 'to_generic': True})
- return merge_dicts(json_ld, info_dict)
+ return merge_dicts({
+ '_type': 'url_transparent',
+ 'url': smuggle_url(json_ld['url'], {'force_videoid': video_id, 'to_generic': True}),
+ }, json_ld, info_dict)
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
if RtmpIE.suitable(vurl):
return True
- vpath = compat_urlparse.urlparse(vurl).path
- vext = determine_ext(vpath)
- return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
+ vpath = urllib.parse.urlparse(vurl).path
+ vext = determine_ext(vpath, None)
+ return vext not in (None, 'swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
def filter_video(urls):
return list(filter(check_video, urls))
self.report_detected('Twitter card')
if not found:
# We look for Open Graph info:
- # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
+ # We have to match any number spaces between elements, some sites try to align them, e.g.: statigr.am
m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
# We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
if m_video_type is not None:
webpage)
if not found:
# Look also in Refresh HTTP header
- refresh_header = head_response.headers.get('Refresh')
+ refresh_header = full_response.headers.get('Refresh')
if refresh_header:
- # In python 2 response HTTP headers are bytestrings
- if sys.version_info < (3, 0) and isinstance(refresh_header, str):
- refresh_header = refresh_header.decode('iso-8859-1')
found = re.search(REDIRECT_REGEX, refresh_header)
if found:
- new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
+ new_url = urllib.parse.urljoin(url, unescapeHTML(found.group(1)))
if new_url != url:
self.report_following_redirect(new_url)
return {
for video_url in orderedSet(found):
video_url = unescapeHTML(video_url)
video_url = video_url.replace('\\/', '/')
- video_url = compat_urlparse.urljoin(url, video_url)
- video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
+ video_url = urllib.parse.urljoin(url, video_url)
+ video_id = urllib.parse.unquote(os.path.basename(video_url))
# Sometimes, jwplayer extraction will result in a YouTube URL
if YoutubeIE.suitable(video_url):
entries.append(self.url_result(video_url, 'Youtube'))
continue
- # here's a fun little line of code for you:
video_id = os.path.splitext(video_id)[0]
headers = {
'referer': full_response.geturl()
entry_info_dict = {
'id': video_id,
- 'uploader': video_uploader,
- 'title': video_title,
- 'age_limit': age_limit,
+ 'uploader': domain_name,
+ 'title': info_dict['title'],
+ 'age_limit': info_dict['age_limit'],
'http_headers': headers,
}
entries.append(entry_info_dict)
if len(entries) == 1:
- return entries[0]
+ return merge_dicts(entries[0], info_dict)
else:
for num, e in enumerate(entries, start=1):
# 'url' results don't have a title