Merge branch 'master' into PornHub-issue-16078
This commit is contained in:
commit
5debd37c30
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.18**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.10.05*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.10.05**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
|
||||
@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] youtube-dl version 2018.09.18
|
||||
[debug] youtube-dl version 2018.10.05
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
26
ChangeLog
26
ChangeLog
@ -1,3 +1,29 @@
|
||||
version 2018.10.05
|
||||
|
||||
Extractors
|
||||
* [pluralsight] Improve authentication (#17762)
|
||||
* [dailymotion] Fix extraction (#17699)
|
||||
* [crunchyroll] Switch to HTTPS for RpcApi (#17749)
|
||||
+ [philharmoniedeparis] Add support for pad.philharmoniedeparis.fr (#17705)
|
||||
* [philharmoniedeparis] Fix extraction (#17705)
|
||||
+ [jamendo] Add support for licensing.jamendo.com (#17724)
|
||||
+ [openload] Add support for oload.cloud (#17710)
|
||||
* [pluralsight] Fix subtitles extraction (#17726, #17728)
|
||||
+ [vimeo] Add another config regular expression (#17690)
|
||||
* [spike] Fix Paramount Network extraction (#17677)
|
||||
* [hotstar] Fix extraction (#14694, #14931, #17637)
|
||||
|
||||
|
||||
version 2018.09.26
|
||||
|
||||
Extractors
|
||||
* [pluralsight] Fix subtitles extraction (#17671)
|
||||
* [mediaset] Improve embed support (#17668)
|
||||
+ [youtube] Add support for invidio.us (#17613)
|
||||
+ [zattoo] Add support for more zattoo platform sites
|
||||
* [zattoo] Fix extraction (#17175, #17542)
|
||||
|
||||
|
||||
version 2018.09.18
|
||||
|
||||
Core
|
||||
|
@ -511,6 +511,8 @@ The basic usage is not to set any template arguments when downloading a single f
|
||||
- `timestamp` (numeric): UNIX timestamp of the moment the video became available
|
||||
- `upload_date` (string): Video upload date (YYYYMMDD)
|
||||
- `uploader_id` (string): Nickname or id of the video uploader
|
||||
- `channel` (string): Full name of the channel the video is uploaded on
|
||||
- `channel_id` (string): Id of the channel
|
||||
- `location` (string): Physical location where the video was filmed
|
||||
- `duration` (numeric): Length of the video in seconds
|
||||
- `view_count` (numeric): How many users have watched the video on the platform
|
||||
|
@ -98,6 +98,7 @@
|
||||
- **bbc.co.uk:article**: BBC articles
|
||||
- **bbc.co.uk:iplayer:playlist**
|
||||
- **bbc.co.uk:playlist**
|
||||
- **BBVTV**
|
||||
- **Beatport**
|
||||
- **Beeg**
|
||||
- **BehindKink**
|
||||
@ -251,6 +252,7 @@
|
||||
- **egghead:course**: egghead.io course
|
||||
- **egghead:lesson**: egghead.io lesson
|
||||
- **eHow**
|
||||
- **EinsUndEinsTV**
|
||||
- **Einthusan**
|
||||
- **eitb.tv**
|
||||
- **EllenTube**
|
||||
@ -268,6 +270,7 @@
|
||||
- **EsriVideo**
|
||||
- **Europa**
|
||||
- **EveryonesMixtape**
|
||||
- **EWETV**
|
||||
- **ExpoTV**
|
||||
- **Expressen**
|
||||
- **ExtremeTube**
|
||||
@ -327,6 +330,7 @@
|
||||
- **Gfycat**
|
||||
- **GiantBomb**
|
||||
- **Giga**
|
||||
- **GlattvisionTV**
|
||||
- **Glide**: Glide mobile video messages (glide.me)
|
||||
- **Globo**
|
||||
- **GloboArticle**
|
||||
@ -356,7 +360,7 @@
|
||||
- **HitRecord**
|
||||
- **HornBunny**
|
||||
- **HotNewHipHop**
|
||||
- **HotStar**
|
||||
- **hotstar**
|
||||
- **hotstar:playlist**
|
||||
- **Howcast**
|
||||
- **HowStuffWorks**
|
||||
@ -494,6 +498,7 @@
|
||||
- **Mixer:vod**
|
||||
- **MLB**
|
||||
- **Mnet**
|
||||
- **MNetTV**
|
||||
- **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
|
||||
- **Mofosex**
|
||||
- **Mojvideo**
|
||||
@ -525,6 +530,7 @@
|
||||
- **Myvi**
|
||||
- **MyVidster**
|
||||
- **MyviEmbed**
|
||||
- **MyVisionTV**
|
||||
- **n-tv.de**
|
||||
- **natgeo**
|
||||
- **natgeo:episodeguide**
|
||||
@ -550,6 +556,7 @@
|
||||
- **netease:program**: 网易云音乐 - 电台节目
|
||||
- **netease:singer**: 网易云音乐 - 歌手
|
||||
- **netease:song**: 网易云音乐
|
||||
- **NetPlus**
|
||||
- **Netzkino**
|
||||
- **Newgrounds**
|
||||
- **NewgroundsPlaylist**
|
||||
@ -626,6 +633,7 @@
|
||||
- **orf:iptv**: iptv.ORF.at
|
||||
- **orf:oe1**: Radio Österreich 1
|
||||
- **orf:tvthek**: ORF TVthek
|
||||
- **OsnatelTV**
|
||||
- **PacktPub**
|
||||
- **PacktPubCourse**
|
||||
- **PandaTV**: 熊猫TV
|
||||
@ -686,6 +694,7 @@
|
||||
- **qqmusic:playlist**: QQ音乐 - 歌单
|
||||
- **qqmusic:singer**: QQ音乐 - 歌手
|
||||
- **qqmusic:toplist**: QQ音乐 - 排行榜
|
||||
- **QuantumTV**
|
||||
- **Quickline**
|
||||
- **QuicklineLive**
|
||||
- **R7**
|
||||
@ -753,6 +762,7 @@
|
||||
- **safari**: safaribooksonline.com online video
|
||||
- **safari:api**
|
||||
- **safari:course**: safaribooksonline.com online courses
|
||||
- **SAKTV**
|
||||
- **Sapo**: SAPO Vídeos
|
||||
- **savefrom.net**
|
||||
- **SBS**: sbs.com.au
|
||||
@ -1035,12 +1045,14 @@
|
||||
- **vrv**
|
||||
- **vrv:series**
|
||||
- **VShare**
|
||||
- **VTXTV**
|
||||
- **vube**: Vube.com
|
||||
- **VuClip**
|
||||
- **VVVVID**
|
||||
- **VyboryMos**
|
||||
- **Vzaar**
|
||||
- **Walla**
|
||||
- **WalyTV**
|
||||
- **washingtonpost**
|
||||
- **washingtonpost:article**
|
||||
- **wat.tv**
|
||||
|
@ -1,8 +1,10 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import base64
|
||||
import json
|
||||
import re
|
||||
import struct
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .adobepass import AdobePassIE
|
||||
@ -310,6 +312,10 @@ class BrightcoveLegacyIE(InfoExtractor):
|
||||
'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?',
|
||||
expected=True)
|
||||
|
||||
def _brightcove_new_url_result(self, publisher_id, video_id):
|
||||
brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id)
|
||||
return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id)
|
||||
|
||||
def _get_video_info(self, video_id, query, referer=None):
|
||||
headers = {}
|
||||
linkBase = query.get('linkBaseURL')
|
||||
@ -323,6 +329,28 @@ class BrightcoveLegacyIE(InfoExtractor):
|
||||
r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage,
|
||||
'error message', default=None)
|
||||
if error_msg is not None:
|
||||
publisher_id = query.get('publisherId')
|
||||
if publisher_id and publisher_id[0].isdigit():
|
||||
publisher_id = publisher_id[0]
|
||||
if not publisher_id:
|
||||
player_key = query.get('playerKey')
|
||||
if player_key and ',' in player_key[0]:
|
||||
player_key = player_key[0]
|
||||
else:
|
||||
player_id = query.get('playerID')
|
||||
if player_id and player_id[0].isdigit():
|
||||
player_page = self._download_webpage(
|
||||
'http://link.brightcove.com/services/player/bcpid' + player_id[0],
|
||||
video_id, headers=headers, fatal=False)
|
||||
if player_page:
|
||||
player_key = self._search_regex(
|
||||
r'<param\s+name="playerKey"\s+value="([\w~,-]+)"',
|
||||
player_page, 'player key', fatal=False)
|
||||
if player_key:
|
||||
enc_pub_id = player_key.split(',')[1].replace('~', '=')
|
||||
publisher_id = struct.unpack('>Q', base64.urlsafe_b64decode(enc_pub_id))[0]
|
||||
if publisher_id:
|
||||
return self._brightcove_new_url_result(publisher_id, video_id)
|
||||
raise ExtractorError(
|
||||
'brightcove said: %s' % error_msg, expected=True)
|
||||
|
||||
@ -444,8 +472,12 @@ class BrightcoveLegacyIE(InfoExtractor):
|
||||
else:
|
||||
return ad_info
|
||||
|
||||
if 'url' not in info and not info.get('formats'):
|
||||
raise ExtractorError('Unable to extract video url for %s' % video_id)
|
||||
if not info.get('url') and not info.get('formats'):
|
||||
uploader_id = info.get('uploader_id')
|
||||
if uploader_id:
|
||||
info.update(self._brightcove_new_url_result(uploader_id, video_id))
|
||||
else:
|
||||
raise ExtractorError('Unable to extract video url for %s' % video_id)
|
||||
return info
|
||||
|
||||
|
||||
|
@ -45,7 +45,7 @@ class CrunchyrollBaseIE(InfoExtractor):
|
||||
data['req'] = 'RpcApi' + method
|
||||
data = compat_urllib_parse_urlencode(data).encode('utf-8')
|
||||
return self._download_xml(
|
||||
'http://www.crunchyroll.com/xml/',
|
||||
'https://www.crunchyroll.com/xml/',
|
||||
video_id, note, fatal=False, data=data, headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded',
|
||||
})
|
||||
|
@ -3,6 +3,7 @@ from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_age_limit,
|
||||
parse_iso8601,
|
||||
@ -66,9 +67,12 @@ class CWTVIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_data = self._download_json(
|
||||
data = self._download_json(
|
||||
'http://images.cwtv.com/feed/mobileapp/video-meta/apiversion_8/guid_' + video_id,
|
||||
video_id)['video']
|
||||
video_id)
|
||||
if data.get('result') != 'ok':
|
||||
raise ExtractorError(data['msg'], expected=True)
|
||||
video_data = data['video']
|
||||
title = video_data['title']
|
||||
mpx_url = video_data.get('mpx_url') or 'http://link.theplatform.com/s/cwtv/media/guid/2703454149/%s?formats=M3U' % video_id
|
||||
|
||||
|
@ -22,7 +22,10 @@ from ..utils import (
|
||||
parse_iso8601,
|
||||
sanitized_Request,
|
||||
str_to_int,
|
||||
try_get,
|
||||
unescapeHTML,
|
||||
update_url_query,
|
||||
url_or_none,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
@ -171,10 +174,25 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
r'__PLAYER_CONFIG__\s*=\s*({.+?});'],
|
||||
webpage, 'player v5', default=None)
|
||||
if player_v5:
|
||||
player = self._parse_json(player_v5, video_id)
|
||||
metadata = player['metadata']
|
||||
player = self._parse_json(player_v5, video_id, fatal=False) or {}
|
||||
metadata = try_get(player, lambda x: x['metadata'], dict)
|
||||
if not metadata:
|
||||
metadata_url = url_or_none(try_get(
|
||||
player, lambda x: x['context']['metadata_template_url1']))
|
||||
if metadata_url:
|
||||
metadata_url = metadata_url.replace(':videoId', video_id)
|
||||
else:
|
||||
metadata_url = update_url_query(
|
||||
'https://www.dailymotion.com/player/metadata/video/%s'
|
||||
% video_id, {
|
||||
'embedder': url,
|
||||
'integration': 'inline',
|
||||
'GK_PV5_NEON': '1',
|
||||
})
|
||||
metadata = self._download_json(
|
||||
metadata_url, video_id, 'Downloading metadata JSON')
|
||||
|
||||
if metadata.get('error', {}).get('type') == 'password_protected':
|
||||
if try_get(metadata, lambda x: x['error']['type']) == 'password_protected':
|
||||
password = self._downloader.params.get('videopassword')
|
||||
if password:
|
||||
r = int(metadata['id'][1:], 36)
|
||||
|
@ -1153,7 +1153,6 @@ from .tv2 import (
|
||||
TV2ArticleIE,
|
||||
)
|
||||
from .tv2hu import TV2HuIE
|
||||
from .tv3 import TV3IE
|
||||
from .tv4 import TV4IE
|
||||
from .tv5mondeplus import TV5MondePlusIE
|
||||
from .tva import TVAIE
|
||||
@ -1455,8 +1454,20 @@ from .youtube import (
|
||||
from .zapiks import ZapiksIE
|
||||
from .zaq1 import Zaq1IE
|
||||
from .zattoo import (
|
||||
BBVTVIE,
|
||||
EinsUndEinsTVIE,
|
||||
EWETVIE,
|
||||
GlattvisionTVIE,
|
||||
MNetTVIE,
|
||||
MyVisionTVIE,
|
||||
NetPlusIE,
|
||||
OsnatelTVIE,
|
||||
QuantumTVIE,
|
||||
QuicklineIE,
|
||||
QuicklineLiveIE,
|
||||
SAKTVIE,
|
||||
VTXTVIE,
|
||||
WalyTVIE,
|
||||
ZattooIE,
|
||||
ZattooLiveIE,
|
||||
)
|
||||
|
@ -3023,7 +3023,7 @@ class GenericIE(InfoExtractor):
|
||||
wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
|
||||
|
||||
# Look for Mediaset embeds
|
||||
mediaset_urls = MediasetIE._extract_urls(webpage)
|
||||
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())
|
||||
|
@ -1,49 +1,55 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import hashlib
|
||||
import hmac
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class HotStarBaseIE(InfoExtractor):
|
||||
_GEO_COUNTRIES = ['IN']
|
||||
_AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
|
||||
|
||||
def _download_json(self, *args, **kwargs):
|
||||
response = super(HotStarBaseIE, self)._download_json(*args, **kwargs)
|
||||
if response['resultCode'] != 'OK':
|
||||
if kwargs.get('fatal'):
|
||||
raise ExtractorError(
|
||||
response['errorDescription'], expected=True)
|
||||
return None
|
||||
return response['resultObj']
|
||||
|
||||
def _download_content_info(self, content_id):
|
||||
return self._download_json(
|
||||
'https://account.hotstar.com/AVS/besc', content_id, query={
|
||||
'action': 'GetAggregatedContentDetails',
|
||||
'appVersion': '5.0.40',
|
||||
'channel': 'PCTV',
|
||||
'contentId': content_id,
|
||||
})['contentInfo'][0]
|
||||
def _call_api(self, path, video_id, query_name='contentId'):
|
||||
st = int(time.time())
|
||||
exp = st + 6000
|
||||
auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
|
||||
auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
|
||||
response = self._download_json(
|
||||
'https://api.hotstar.com/' + path,
|
||||
video_id, headers={
|
||||
'hotstarauth': auth,
|
||||
'x-country-code': 'IN',
|
||||
'x-platform-code': 'JIO',
|
||||
}, query={
|
||||
query_name: video_id,
|
||||
'tas': 10000,
|
||||
})
|
||||
if response['statusCode'] != 'OK':
|
||||
raise ExtractorError(
|
||||
response['body']['message'], expected=True)
|
||||
return response['body']['results']
|
||||
|
||||
|
||||
class HotStarIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar'
|
||||
_VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
|
||||
'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
|
||||
'info_dict': {
|
||||
'id': '1000076273',
|
||||
'ext': 'mp4',
|
||||
'title': 'On Air With AIB',
|
||||
'title': 'Can You Not Spread Rumours?',
|
||||
'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
|
||||
'timestamp': 1447227000,
|
||||
'timestamp': 1447248600,
|
||||
'upload_date': '20151111',
|
||||
'duration': 381,
|
||||
},
|
||||
@ -58,47 +64,47 @@ class HotStarIE(HotStarBaseIE):
|
||||
'url': 'http://www.hotstar.com/1000000515',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_GEO_BYPASS = False
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
video_data = self._download_content_info(video_id)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
app_state = self._parse_json(self._search_regex(
|
||||
r'<script>window\.APP_STATE\s*=\s*({.+?})</script>',
|
||||
webpage, 'app state'), video_id)
|
||||
video_data = {}
|
||||
for v in app_state.values():
|
||||
content = try_get(v, lambda x: x['initialState']['contentData']['content'], dict)
|
||||
if content and content.get('contentId') == video_id:
|
||||
video_data = content
|
||||
|
||||
title = video_data['episodeTitle']
|
||||
title = video_data['title']
|
||||
|
||||
if video_data.get('encrypted') == 'Y':
|
||||
if video_data.get('drmProtected'):
|
||||
raise ExtractorError('This video is DRM protected.', expected=True)
|
||||
|
||||
formats = []
|
||||
for f in ('JIO',):
|
||||
format_data = self._download_json(
|
||||
'http://getcdn.hotstar.com/AVS/besc',
|
||||
video_id, 'Downloading %s JSON metadata' % f,
|
||||
fatal=False, query={
|
||||
'action': 'GetCDN',
|
||||
'asJson': 'Y',
|
||||
'channel': f,
|
||||
'id': video_id,
|
||||
'type': 'VOD',
|
||||
})
|
||||
if format_data:
|
||||
format_url = format_data.get('src')
|
||||
if not format_url:
|
||||
continue
|
||||
ext = determine_ext(format_url)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, video_id, 'mp4',
|
||||
m3u8_id='hls', fatal=False))
|
||||
elif ext == 'f4m':
|
||||
# produce broken files
|
||||
continue
|
||||
else:
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'width': int_or_none(format_data.get('width')),
|
||||
'height': int_or_none(format_data.get('height')),
|
||||
})
|
||||
format_data = self._call_api('h/v1/play', video_id)['item']
|
||||
format_url = format_data['playbackUrl']
|
||||
ext = determine_ext(format_url)
|
||||
if ext == 'm3u8':
|
||||
try:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, video_id, 'mp4', m3u8_id='hls'))
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
self.raise_geo_restricted(countries=['IN'])
|
||||
raise
|
||||
elif ext == 'f4m':
|
||||
# produce broken files
|
||||
pass
|
||||
else:
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'width': int_or_none(format_data.get('width')),
|
||||
'height': int_or_none(format_data.get('height')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
@ -106,57 +112,43 @@ class HotStarIE(HotStarBaseIE):
|
||||
'title': title,
|
||||
'description': video_data.get('description'),
|
||||
'duration': int_or_none(video_data.get('duration')),
|
||||
'timestamp': int_or_none(video_data.get('broadcastDate')),
|
||||
'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')),
|
||||
'formats': formats,
|
||||
'channel': video_data.get('channelName'),
|
||||
'channel_id': video_data.get('channelId'),
|
||||
'series': video_data.get('showName'),
|
||||
'season': video_data.get('seasonName'),
|
||||
'season_number': int_or_none(video_data.get('seasonNo')),
|
||||
'season_id': video_data.get('seasonId'),
|
||||
'episode': title,
|
||||
'episode_number': int_or_none(video_data.get('episodeNumber')),
|
||||
'series': video_data.get('contentTitle'),
|
||||
'episode_number': int_or_none(video_data.get('episodeNo')),
|
||||
}
|
||||
|
||||
|
||||
class HotStarPlaylistIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar:playlist'
|
||||
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com/tv/[^/]+/(?P<content_id>\d+))/(?P<type>[^/]+)/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.hotstar.com/tv/pratidaan/14982/episodes/14812/9993',
|
||||
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
|
||||
'info_dict': {
|
||||
'id': '14812',
|
||||
'id': '3_2_26',
|
||||
},
|
||||
'playlist_mincount': 75,
|
||||
'playlist_mincount': 20,
|
||||
}, {
|
||||
'url': 'http://www.hotstar.com/tv/pratidaan/14982/popular-clips/9998/9998',
|
||||
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_ITEM_TYPES = {
|
||||
'episodes': 'EPISODE',
|
||||
'popular-clips': 'CLIPS',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
base_url = mobj.group('url')
|
||||
content_id = mobj.group('content_id')
|
||||
playlist_type = mobj.group('type')
|
||||
playlist_id = self._match_id(url)
|
||||
|
||||
content_info = self._download_content_info(content_id)
|
||||
playlist_id = compat_str(content_info['categoryId'])
|
||||
|
||||
collection = self._download_json(
|
||||
'https://search.hotstar.com/AVS/besc', playlist_id, query={
|
||||
'action': 'SearchContents',
|
||||
'appVersion': '5.0.40',
|
||||
'channel': 'PCTV',
|
||||
'moreFilters': 'series:%s;' % playlist_id,
|
||||
'query': '*',
|
||||
'searchOrder': 'last_broadcast_date desc,year desc,title asc',
|
||||
'type': self._ITEM_TYPES.get(playlist_type, 'EPISODE'),
|
||||
})
|
||||
collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')
|
||||
|
||||
entries = [
|
||||
self.url_result(
|
||||
'%s/_/%s' % (base_url, video['contentId']),
|
||||
'https://www.hotstar.com/%s' % video['contentId'],
|
||||
ie=HotStarIE.ie_key(), video_id=video['contentId'])
|
||||
for video in collection['response']['docs']
|
||||
for video in collection['assets']['items']
|
||||
if video.get('contentId')]
|
||||
|
||||
return self.playlist_result(entries, playlist_id)
|
||||
|
@ -26,8 +26,15 @@ class JamendoBaseIE(InfoExtractor):
|
||||
|
||||
|
||||
class JamendoIE(JamendoBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
licensing\.jamendo\.com/[^/]+|
|
||||
(?:www\.)?jamendo\.com
|
||||
)
|
||||
/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
|
||||
'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
|
||||
'info_dict': {
|
||||
@ -40,14 +47,19 @@ class JamendoIE(JamendoBaseIE):
|
||||
'duration': 210,
|
||||
'thumbnail': r're:^https?://.*\.jpg'
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._VALID_URL_RE.match(url)
|
||||
track_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id')
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
webpage = self._download_webpage(
|
||||
'https://www.jamendo.com/track/%s/%s' % (track_id, display_id),
|
||||
display_id)
|
||||
|
||||
title, artist, track = self._extract_meta(webpage)
|
||||
|
||||
|
@ -4,6 +4,11 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .theplatform import ThePlatformBaseIE
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_str,
|
||||
compat_urllib_parse_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
@ -76,12 +81,33 @@ class MediasetIE(ThePlatformBaseIE):
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return [
|
||||
mobj.group('url')
|
||||
for mobj in re.finditer(
|
||||
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1',
|
||||
webpage)]
|
||||
def _extract_urls(ie, webpage):
|
||||
def _qs(url):
|
||||
return compat_parse_qs(compat_urllib_parse_urlparse(url).query)
|
||||
|
||||
def _program_guid(qs):
|
||||
return qs.get('programGuid', [None])[0]
|
||||
|
||||
entries = []
|
||||
for mobj in re.finditer(
|
||||
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1',
|
||||
webpage):
|
||||
embed_url = mobj.group('url')
|
||||
embed_qs = _qs(embed_url)
|
||||
program_guid = _program_guid(embed_qs)
|
||||
if program_guid:
|
||||
entries.append(embed_url)
|
||||
continue
|
||||
video_id = embed_qs.get('id', [None])[0]
|
||||
if not video_id:
|
||||
continue
|
||||
urlh = ie._request_webpage(
|
||||
embed_url, video_id, note='Following embed URL redirect')
|
||||
embed_url = compat_str(urlh.geturl())
|
||||
program_guid = _program_guid(_qs(embed_url))
|
||||
if program_guid:
|
||||
entries.append(embed_url)
|
||||
return entries
|
||||
|
||||
def _real_extract(self, url):
|
||||
guid = self._match_id(url)
|
||||
|
@ -243,7 +243,7 @@ class PhantomJSwrapper(object):
|
||||
|
||||
|
||||
class OpenloadIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://openload.co/f/kUEfGclsU9o',
|
||||
@ -307,10 +307,16 @@ class OpenloadIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://oload.download/f/kUEfGclsU9o',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://oload.cloud/f/4ZDnBXRWiB8',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Its title has not got its extension but url has it
|
||||
'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://oload.cc/embed/5NEAbI2BDSk',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
|
||||
|
@ -2,52 +2,63 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import js_to_json
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
class PatreonIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(?P<id>[^&#]+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.patreon.com/creation?hid=743933',
|
||||
'md5': 'e25505eec1053a6e6813b8ed369875cc',
|
||||
'info_dict': {
|
||||
'id': '743933',
|
||||
'ext': 'mp3',
|
||||
'title': 'Episode 166: David Smalley of Dogma Debate',
|
||||
'uploader': 'Cognitive Dissonance Podcast',
|
||||
'thumbnail': 're:^https?://.*$',
|
||||
},
|
||||
_VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.patreon.com/creation?hid=743933',
|
||||
'md5': 'e25505eec1053a6e6813b8ed369875cc',
|
||||
'info_dict': {
|
||||
'id': '743933',
|
||||
'ext': 'mp3',
|
||||
'title': 'Episode 166: David Smalley of Dogma Debate',
|
||||
'description': 'md5:713b08b772cd6271b9f3906683cfacdf',
|
||||
'uploader': 'Cognitive Dissonance Podcast',
|
||||
'thumbnail': 're:^https?://.*$',
|
||||
'timestamp': 1406473987,
|
||||
'upload_date': '20140727',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.patreon.com/creation?hid=754133',
|
||||
'md5': '3eb09345bf44bf60451b8b0b81759d0a',
|
||||
'info_dict': {
|
||||
'id': '754133',
|
||||
'ext': 'mp3',
|
||||
'title': 'CD 167 Extra',
|
||||
'uploader': 'Cognitive Dissonance Podcast',
|
||||
'thumbnail': 're:^https?://.*$',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.patreon.com/creation?hid=754133',
|
||||
'md5': '3eb09345bf44bf60451b8b0b81759d0a',
|
||||
'info_dict': {
|
||||
'id': '754133',
|
||||
'ext': 'mp3',
|
||||
'title': 'CD 167 Extra',
|
||||
'uploader': 'Cognitive Dissonance Podcast',
|
||||
'thumbnail': 're:^https?://.*$',
|
||||
},
|
||||
{
|
||||
'url': 'https://www.patreon.com/creation?hid=1682498',
|
||||
'info_dict': {
|
||||
'id': 'SU4fj_aEMVw',
|
||||
'ext': 'mp4',
|
||||
'title': 'I\'m on Patreon!',
|
||||
'uploader': 'TraciJHines',
|
||||
'thumbnail': 're:^https?://.*$',
|
||||
'upload_date': '20150211',
|
||||
'description': 'md5:c5a706b1f687817a3de09db1eb93acd4',
|
||||
'uploader_id': 'TraciJHines',
|
||||
},
|
||||
'params': {
|
||||
'noplaylist': True,
|
||||
'skip_download': True,
|
||||
}
|
||||
'skip': 'Patron-only content',
|
||||
}, {
|
||||
'url': 'https://www.patreon.com/creation?hid=1682498',
|
||||
'info_dict': {
|
||||
'id': 'SU4fj_aEMVw',
|
||||
'ext': 'mp4',
|
||||
'title': 'I\'m on Patreon!',
|
||||
'uploader': 'TraciJHines',
|
||||
'thumbnail': 're:^https?://.*$',
|
||||
'upload_date': '20150211',
|
||||
'description': 'md5:c5a706b1f687817a3de09db1eb93acd4',
|
||||
'uploader_id': 'TraciJHines',
|
||||
},
|
||||
'params': {
|
||||
'noplaylist': True,
|
||||
'skip_download': True,
|
||||
}
|
||||
]
|
||||
}, {
|
||||
'url': 'https://www.patreon.com/posts/episode-166-of-743933',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.patreon.com/posts/743933',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
# Currently Patreon exposes download URL via hidden CSS, so login is not
|
||||
# needed. Keeping this commented for when this inevitably changes.
|
||||
@ -78,38 +89,48 @@ class PatreonIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = self._og_search_title(webpage).strip()
|
||||
|
||||
attach_fn = self._html_search_regex(
|
||||
r'<div class="attach"><a target="_blank" href="([^"]+)">',
|
||||
webpage, 'attachment URL', default=None)
|
||||
embed = self._html_search_regex(
|
||||
r'<div[^>]+id="watchCreation"[^>]*>\s*<iframe[^>]+src="([^"]+)"',
|
||||
webpage, 'embedded URL', default=None)
|
||||
|
||||
if attach_fn is not None:
|
||||
video_url = 'http://www.patreon.com' + attach_fn
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
uploader = self._html_search_regex(
|
||||
r'<strong>(.*?)</strong> is creating', webpage, 'uploader')
|
||||
elif embed is not None:
|
||||
return self.url_result(embed)
|
||||
else:
|
||||
playlist = self._parse_json(self._search_regex(
|
||||
r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])',
|
||||
webpage, 'playlist JSON'),
|
||||
video_id, transform_source=js_to_json)
|
||||
data = playlist[0]
|
||||
video_url = self._proto_relative_url(data['mp3'])
|
||||
thumbnail = self._proto_relative_url(data.get('cover'))
|
||||
uploader = data.get('artist')
|
||||
|
||||
return {
|
||||
post = self._download_json(
|
||||
'https://www.patreon.com/api/posts/' + video_id, video_id)
|
||||
attributes = post['data']['attributes']
|
||||
title = attributes['title'].strip()
|
||||
image = attributes.get('image') or {}
|
||||
info = {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': 'mp3',
|
||||
'title': title,
|
||||
'uploader': uploader,
|
||||
'thumbnail': thumbnail,
|
||||
'description': clean_html(attributes.get('content')),
|
||||
'thumbnail': image.get('large_url') or image.get('url'),
|
||||
'timestamp': parse_iso8601(attributes.get('published_at')),
|
||||
'like_count': int_or_none(attributes.get('like_count')),
|
||||
'comment_count': int_or_none(attributes.get('comment_count')),
|
||||
}
|
||||
|
||||
def add_file(file_data):
|
||||
file_url = file_data.get('url')
|
||||
if file_url:
|
||||
info.update({
|
||||
'url': file_url,
|
||||
'ext': determine_ext(file_data.get('name'), 'mp3'),
|
||||
})
|
||||
|
||||
for i in post.get('included', []):
|
||||
i_type = i.get('type')
|
||||
if i_type == 'attachment':
|
||||
add_file(i.get('attributes') or {})
|
||||
elif i_type == 'user':
|
||||
user_attributes = i.get('attributes')
|
||||
if user_attributes:
|
||||
info.update({
|
||||
'uploader': user_attributes.get('full_name'),
|
||||
'uploader_url': user_attributes.get('url'),
|
||||
})
|
||||
|
||||
if not info.get('url'):
|
||||
add_file(attributes.get('post_file') or {})
|
||||
|
||||
if not info.get('url'):
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'url': attributes['embed']['url'],
|
||||
})
|
||||
|
||||
return info
|
||||
|
@ -2,31 +2,38 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
xpath_text,
|
||||
try_get,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class PhilharmonieDeParisIE(InfoExtractor):
|
||||
IE_DESC = 'Philharmonie de Paris'
|
||||
_VALID_URL = r'https?://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)|
|
||||
pad\.philharmoniedeparis\.fr/doc/CIMU/
|
||||
)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://pad.philharmoniedeparis.fr/doc/CIMU/1086697/jazz-a-la-villette-knower',
|
||||
'md5': 'a0a4b195f544645073631cbec166a2c2',
|
||||
'info_dict': {
|
||||
'id': '1086697',
|
||||
'ext': 'mp4',
|
||||
'title': 'Jazz à la Villette : Knower',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
|
||||
'info_dict': {
|
||||
'id': '1032066',
|
||||
'ext': 'flv',
|
||||
'title': 'md5:d1f5585d87d041d07ce9434804bc8425',
|
||||
'timestamp': 1428179400,
|
||||
'upload_date': '20150404',
|
||||
'duration': 6592.278,
|
||||
'title': 'md5:0a031b81807b3593cffa3c9a87a167a0',
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
}
|
||||
'playlist_mincount': 2,
|
||||
}, {
|
||||
'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
|
||||
'only_matching': True,
|
||||
@ -34,45 +41,60 @@ class PhilharmonieDeParisIE(InfoExtractor):
|
||||
'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_LIVE_URL = 'https://live.philharmoniedeparis.fr'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
concert = self._download_xml(
|
||||
'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id,
|
||||
video_id).find('./concert')
|
||||
config = self._download_json(
|
||||
'%s/otoPlayer/config.ashx' % self._LIVE_URL, video_id, query={
|
||||
'id': video_id,
|
||||
'lang': 'fr-FR',
|
||||
})
|
||||
|
||||
formats = []
|
||||
info_dict = {
|
||||
'id': video_id,
|
||||
'title': xpath_text(concert, './titre', 'title', fatal=True),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
fichiers = concert.find('./fichiers')
|
||||
stream = fichiers.attrib['serveurstream']
|
||||
for fichier in fichiers.findall('./fichier'):
|
||||
info_dict['duration'] = float_or_none(fichier.get('timecodefin'))
|
||||
for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]):
|
||||
format_url = fichier.get('url%s' % suffix)
|
||||
if not format_url:
|
||||
def extract_entry(source):
|
||||
if not isinstance(source, dict):
|
||||
return
|
||||
title = source.get('title')
|
||||
if not title:
|
||||
return
|
||||
files = source.get('files')
|
||||
if not isinstance(files, dict):
|
||||
return
|
||||
format_urls = set()
|
||||
formats = []
|
||||
for format_id in ('mobile', 'desktop'):
|
||||
format_url = try_get(
|
||||
files, lambda x: x[format_id]['file'], compat_str)
|
||||
if not format_url or format_url in format_urls:
|
||||
continue
|
||||
formats.append({
|
||||
'url': stream,
|
||||
'play_path': format_url,
|
||||
'ext': 'flv',
|
||||
'format_id': format_id,
|
||||
'width': int_or_none(concert.get('largeur%s' % suffix)),
|
||||
'height': int_or_none(concert.get('hauteur%s' % suffix)),
|
||||
'quality': quality,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
format_urls.add(format_url)
|
||||
m3u8_url = urljoin(self._LIVE_URL, format_url)
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
if not formats:
|
||||
return
|
||||
self._sort_formats(formats)
|
||||
return {
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
date, hour = concert.get('date'), concert.get('heure')
|
||||
if date and hour:
|
||||
info_dict['timestamp'] = parse_iso8601(
|
||||
'%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour))
|
||||
elif date:
|
||||
info_dict['upload_date'] = date
|
||||
thumbnail = urljoin(self._LIVE_URL, config.get('image'))
|
||||
|
||||
return info_dict
|
||||
info = extract_entry(config)
|
||||
if info:
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'thumbnail': thumbnail,
|
||||
})
|
||||
return info
|
||||
|
||||
entries = []
|
||||
for num, chapter in enumerate(config['chapters'], start=1):
|
||||
entry = extract_entry(chapter)
|
||||
entry['id'] = '%s-%d' % (video_id, num)
|
||||
entries.append(entry)
|
||||
|
||||
return self.playlist_result(entries, video_id, config.get('title'))
|
||||
|
@ -4,6 +4,7 @@ import collections
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
@ -196,7 +197,10 @@ query viewClip {
|
||||
if error:
|
||||
raise ExtractorError('Unable to login: %s' % error, expected=True)
|
||||
|
||||
if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
|
||||
if all(not re.search(p, response) for p in (
|
||||
r'__INITIAL_STATE__', r'["\']currentUser["\']',
|
||||
# new layout?
|
||||
r'>\s*Sign out\s*<')):
|
||||
BLOCKED = 'Your account has been blocked due to suspicious activity'
|
||||
if BLOCKED in response:
|
||||
raise ExtractorError(
|
||||
@ -210,18 +214,26 @@ query viewClip {
|
||||
|
||||
raise ExtractorError('Unable to log in')
|
||||
|
||||
def _get_subtitles(self, author, clip_idx, lang, name, duration, video_id):
|
||||
captions_post = {
|
||||
'a': author,
|
||||
'cn': clip_idx,
|
||||
'lc': lang,
|
||||
'm': name,
|
||||
}
|
||||
captions = self._download_json(
|
||||
'%s/player/retrieve-captions' % self._API_BASE, video_id,
|
||||
'Downloading captions JSON', 'Unable to download captions JSON',
|
||||
fatal=False, data=json.dumps(captions_post).encode('utf-8'),
|
||||
headers={'Content-Type': 'application/json;charset=utf-8'})
|
||||
def _get_subtitles(self, author, clip_idx, clip_id, lang, name, duration, video_id):
|
||||
captions = None
|
||||
if clip_id:
|
||||
captions = self._download_json(
|
||||
'%s/transcript/api/v1/caption/json/%s/%s'
|
||||
% (self._API_BASE, clip_id, lang), video_id,
|
||||
'Downloading captions JSON', 'Unable to download captions JSON',
|
||||
fatal=False)
|
||||
if not captions:
|
||||
captions_post = {
|
||||
'a': author,
|
||||
'cn': int(clip_idx),
|
||||
'lc': lang,
|
||||
'm': name,
|
||||
}
|
||||
captions = self._download_json(
|
||||
'%s/player/retrieve-captions' % self._API_BASE, video_id,
|
||||
'Downloading captions JSON', 'Unable to download captions JSON',
|
||||
fatal=False, data=json.dumps(captions_post).encode('utf-8'),
|
||||
headers={'Content-Type': 'application/json;charset=utf-8'})
|
||||
if captions:
|
||||
return {
|
||||
lang: [{
|
||||
@ -413,7 +425,7 @@ query viewClip {
|
||||
|
||||
# TODO: other languages?
|
||||
subtitles = self.extract_subtitles(
|
||||
author, clip_idx, 'en', name, duration, display_id)
|
||||
author, clip_idx, clip.get('clipId'), 'en', name, duration, display_id)
|
||||
|
||||
return {
|
||||
'id': clip_id,
|
||||
|
@ -103,7 +103,8 @@ class RutubeIE(RutubeBaseIE):
|
||||
|
||||
options = self._download_json(
|
||||
'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
|
||||
video_id, 'Downloading options JSON')
|
||||
video_id, 'Downloading options JSON',
|
||||
headers=self.geo_verification_headers())
|
||||
|
||||
formats = []
|
||||
for format_id, format_url in options['video_balancer'].items():
|
||||
|
@ -44,3 +44,10 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
|
||||
|
||||
_FEED_URL = 'http://www.paramountnetwork.com/feeds/mrss/'
|
||||
_GEO_COUNTRIES = ['US']
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
cs = self._parse_json(self._search_regex(
|
||||
r'window\.__DATA__\s*=\s*({.+})',
|
||||
webpage, 'data'), None)['children']
|
||||
c = next(c for c in cs if c.get('type') == 'VideoPlayer')
|
||||
return c['props']['media']['video']['config']['uri']
|
||||
|
@ -212,8 +212,6 @@ class TEDIE(InfoExtractor):
|
||||
|
||||
http_url = None
|
||||
for format_id, resources in resources_.items():
|
||||
if not isinstance(resources, dict):
|
||||
continue
|
||||
if format_id == 'h264':
|
||||
for resource in resources:
|
||||
h264_url = resource.get('file')
|
||||
@ -242,6 +240,8 @@ class TEDIE(InfoExtractor):
|
||||
'tbr': int_or_none(resource.get('bitrate')),
|
||||
})
|
||||
elif format_id == 'hls':
|
||||
if not isinstance(resources, dict):
|
||||
continue
|
||||
stream_url = url_or_none(resources.get('stream'))
|
||||
if not stream_url:
|
||||
continue
|
||||
|
@ -1,34 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class TV3IE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tv3\.co\.nz/(?P<id>[^/]+)/tabid/\d+/articleID/\d+/MCat/\d+/Default\.aspx'
|
||||
_TEST = {
|
||||
'url': 'http://www.tv3.co.nz/MOTORSPORT-SRS-SsangYong-Hampton-Downs-Round-3/tabid/3692/articleID/121615/MCat/2915/Default.aspx',
|
||||
'info_dict': {
|
||||
'id': '4659127992001',
|
||||
'ext': 'mp4',
|
||||
'title': 'CRC Motorsport: SRS SsangYong Hampton Downs Round 3 - S2015 Ep3',
|
||||
'description': 'SsangYong Racing Series returns for Round 3 with drivers from New Zealand and Australia taking to the grid at Hampton Downs raceway.',
|
||||
'uploader_id': '3812193411001',
|
||||
'upload_date': '20151213',
|
||||
'timestamp': 1449975272,
|
||||
},
|
||||
'expected_warnings': [
|
||||
'Failed to download MPD manifest'
|
||||
],
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/3812193411001/default_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
brightcove_id = self._search_regex(r'<param\s*name="@videoPlayer"\s*value="(\d+)"', webpage, 'brightcove id')
|
||||
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
|
@ -551,6 +551,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
else:
|
||||
config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
|
||||
config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
|
||||
config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
|
||||
config = self._search_regex(config_re, webpage, 'info section',
|
||||
flags=re.DOTALL)
|
||||
config = json.loads(config)
|
||||
|
@ -349,6 +349,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
(?:www\.)?hooktube\.com/|
|
||||
(?:www\.)?yourepeat\.com/|
|
||||
tube\.majestyc\.net/|
|
||||
(?:www\.)?invidio\.us/|
|
||||
youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
|
||||
(?:.*?\#/)? # handle anchor (#/) redirect urls
|
||||
(?: # the various things that can precede the ID:
|
||||
@ -1068,6 +1069,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'https://invidio.us/watch?v=BaW_jenozKc',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
@ -2419,7 +2424,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
|
||||
|
||||
class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
|
||||
IE_DESC = 'YouTube.com channels'
|
||||
_VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
|
||||
_VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
|
||||
_TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
|
||||
_VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
|
||||
IE_NAME = 'youtube:channel'
|
||||
@ -2440,6 +2445,9 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
|
||||
'id': 'UUs0ifCMCm1icqRbqhUINa0w',
|
||||
'title': 'Uploads from Deus Ex',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
|
@ -18,12 +18,12 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class ZattooBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'zattoo'
|
||||
_HOST_URL = 'https://zattoo.com'
|
||||
|
||||
class ZattooPlatformBaseIE(InfoExtractor):
|
||||
_power_guide_hash = None
|
||||
|
||||
def _host_url(self):
|
||||
return 'https://%s' % self._HOST
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
if not username or not password:
|
||||
@ -33,13 +33,13 @@ class ZattooBaseIE(InfoExtractor):
|
||||
|
||||
try:
|
||||
data = self._download_json(
|
||||
'%s/zapi/v2/account/login' % self._HOST_URL, None, 'Logging in',
|
||||
'%s/zapi/v2/account/login' % self._host_url(), None, 'Logging in',
|
||||
data=urlencode_postdata({
|
||||
'login': username,
|
||||
'password': password,
|
||||
'remember': 'true',
|
||||
}), headers={
|
||||
'Referer': '%s/login' % self._HOST_URL,
|
||||
'Referer': '%s/login' % self._host_url(),
|
||||
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
|
||||
})
|
||||
except ExtractorError as e:
|
||||
@ -53,7 +53,7 @@ class ZattooBaseIE(InfoExtractor):
|
||||
|
||||
def _real_initialize(self):
|
||||
webpage = self._download_webpage(
|
||||
self._HOST_URL, None, 'Downloading app token')
|
||||
self._host_url(), None, 'Downloading app token')
|
||||
app_token = self._html_search_regex(
|
||||
r'appToken\s*=\s*(["\'])(?P<token>(?:(?!\1).)+?)\1',
|
||||
webpage, 'app token', group='token')
|
||||
@ -62,7 +62,7 @@ class ZattooBaseIE(InfoExtractor):
|
||||
|
||||
# Will setup appropriate cookies
|
||||
self._request_webpage(
|
||||
'%s/zapi/v2/session/hello' % self._HOST_URL, None,
|
||||
'%s/zapi/v2/session/hello' % self._host_url(), None,
|
||||
'Opening session', data=urlencode_postdata({
|
||||
'client_app_token': app_token,
|
||||
'uuid': compat_str(uuid4()),
|
||||
@ -75,7 +75,7 @@ class ZattooBaseIE(InfoExtractor):
|
||||
|
||||
def _extract_cid(self, video_id, channel_name):
|
||||
channel_groups = self._download_json(
|
||||
'%s/zapi/v2/cached/channels/%s' % (self._HOST_URL,
|
||||
'%s/zapi/v2/cached/channels/%s' % (self._host_url(),
|
||||
self._power_guide_hash),
|
||||
video_id, 'Downloading channel list',
|
||||
query={'details': False})['channel_groups']
|
||||
@ -93,28 +93,30 @@ class ZattooBaseIE(InfoExtractor):
|
||||
|
||||
def _extract_cid_and_video_info(self, video_id):
|
||||
data = self._download_json(
|
||||
'%s/zapi/program/details' % self._HOST_URL,
|
||||
'%s/zapi/v2/cached/program/power_details/%s' % (
|
||||
self._host_url(), self._power_guide_hash),
|
||||
video_id,
|
||||
'Downloading video information',
|
||||
query={
|
||||
'program_id': video_id,
|
||||
'complete': True
|
||||
'program_ids': video_id,
|
||||
'complete': True,
|
||||
})
|
||||
|
||||
p = data['program']
|
||||
p = data['programs'][0]
|
||||
cid = p['cid']
|
||||
|
||||
info_dict = {
|
||||
'id': video_id,
|
||||
'title': p.get('title') or p['episode_title'],
|
||||
'description': p.get('description'),
|
||||
'thumbnail': p.get('image_url'),
|
||||
'title': p.get('t') or p['et'],
|
||||
'description': p.get('d'),
|
||||
'thumbnail': p.get('i_url'),
|
||||
'creator': p.get('channel_name'),
|
||||
'episode': p.get('episode_title'),
|
||||
'episode_number': int_or_none(p.get('episode_number')),
|
||||
'season_number': int_or_none(p.get('season_number')),
|
||||
'episode': p.get('et'),
|
||||
'episode_number': int_or_none(p.get('e_no')),
|
||||
'season_number': int_or_none(p.get('s_no')),
|
||||
'release_year': int_or_none(p.get('year')),
|
||||
'categories': try_get(p, lambda x: x['categories'], list),
|
||||
'categories': try_get(p, lambda x: x['c'], list),
|
||||
'tags': try_get(p, lambda x: x['g'], list)
|
||||
}
|
||||
|
||||
return cid, info_dict
|
||||
@ -126,11 +128,11 @@ class ZattooBaseIE(InfoExtractor):
|
||||
|
||||
if is_live:
|
||||
postdata_common.update({'timeshift': 10800})
|
||||
url = '%s/zapi/watch/live/%s' % (self._HOST_URL, cid)
|
||||
url = '%s/zapi/watch/live/%s' % (self._host_url(), cid)
|
||||
elif record_id:
|
||||
url = '%s/zapi/watch/recording/%s' % (self._HOST_URL, record_id)
|
||||
url = '%s/zapi/watch/recording/%s' % (self._host_url(), record_id)
|
||||
else:
|
||||
url = '%s/zapi/watch/recall/%s/%s' % (self._HOST_URL, cid, video_id)
|
||||
url = '%s/zapi/watch/recall/%s/%s' % (self._host_url(), cid, video_id)
|
||||
|
||||
formats = []
|
||||
for stream_type in ('dash', 'hls', 'hls5', 'hds'):
|
||||
@ -201,13 +203,13 @@ class ZattooBaseIE(InfoExtractor):
|
||||
return info_dict
|
||||
|
||||
|
||||
class QuicklineBaseIE(ZattooBaseIE):
|
||||
class QuicklineBaseIE(ZattooPlatformBaseIE):
|
||||
_NETRC_MACHINE = 'quickline'
|
||||
_HOST_URL = 'https://mobiltv.quickline.com'
|
||||
_HOST = 'mobiltv.quickline.com'
|
||||
|
||||
|
||||
class QuicklineIE(QuicklineBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?mobiltv\.quickline\.com/watch/(?P<channel>[^/]+)/(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?%s/watch/(?P<channel>[^/]+)/(?P<id>[0-9]+)' % re.escape(QuicklineBaseIE._HOST)
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://mobiltv.quickline.com/watch/prosieben/130671867-maze-runner-die-auserwaehlten-in-der-brandwueste',
|
||||
@ -220,7 +222,7 @@ class QuicklineIE(QuicklineBaseIE):
|
||||
|
||||
|
||||
class QuicklineLiveIE(QuicklineBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?mobiltv\.quickline\.com/watch/(?P<id>[^/]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?%s/watch/(?P<id>[^/]+)' % re.escape(QuicklineBaseIE._HOST)
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://mobiltv.quickline.com/watch/srf1',
|
||||
@ -236,8 +238,18 @@ class QuicklineLiveIE(QuicklineBaseIE):
|
||||
return self._extract_video(channel_name, video_id, is_live=True)
|
||||
|
||||
|
||||
class ZattooBaseIE(ZattooPlatformBaseIE):
|
||||
_NETRC_MACHINE = 'zattoo'
|
||||
_HOST = 'zattoo.com'
|
||||
|
||||
|
||||
def _make_valid_url(tmpl, host):
|
||||
return tmpl % re.escape(host)
|
||||
|
||||
|
||||
class ZattooIE(ZattooBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?zattoo\.com/watch/(?P<channel>[^/]+?)/(?P<id>[0-9]+)[^/]+(?:/(?P<recid>[0-9]+))?'
|
||||
_VALID_URL_TEMPLATE = r'https?://(?:www\.)?%s/watch/(?P<channel>[^/]+?)/(?P<id>[0-9]+)[^/]+(?:/(?P<recid>[0-9]+))?'
|
||||
_VALID_URL = _make_valid_url(_VALID_URL_TEMPLATE, ZattooBaseIE._HOST)
|
||||
|
||||
# Since regular videos are only available for 7 days and recorded videos
|
||||
# are only available for a specific user, we cannot have detailed tests.
|
||||
@ -269,3 +281,135 @@ class ZattooLiveIE(ZattooBaseIE):
|
||||
def _real_extract(self, url):
|
||||
channel_name = video_id = self._match_id(url)
|
||||
return self._extract_video(channel_name, video_id, is_live=True)
|
||||
|
||||
|
||||
class NetPlusIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'netplus'
|
||||
_HOST = 'netplus.tv'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.netplus.tv/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class MNetTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'mnettv'
|
||||
_HOST = 'tvplus.m-net.de'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.tvplus.m-net.de/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class WalyTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'walytv'
|
||||
_HOST = 'player.waly.tv'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.player.waly.tv/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class BBVTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'bbvtv'
|
||||
_HOST = 'bbv-tv.net'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bbv-tv.net/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class VTXTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'vtxtv'
|
||||
_HOST = 'vtxtv.ch'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.vtxtv.ch/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class MyVisionTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'myvisiontv'
|
||||
_HOST = 'myvisiontv.ch'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.myvisiontv.ch/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class GlattvisionTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'glattvisiontv'
|
||||
_HOST = 'iptv.glattvision.ch'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.iptv.glattvision.ch/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class SAKTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'saktv'
|
||||
_HOST = 'saktv.ch'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.saktv.ch/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class EWETVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'ewetv'
|
||||
_HOST = 'tvonline.ewe.de'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.tvonline.ewe.de/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class QuantumTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'quantumtv'
|
||||
_HOST = 'quantum-tv.com'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.quantum-tv.com/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class OsnatelTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = 'osnateltv'
|
||||
_HOST = 'onlinetv.osnatel.de'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.onlinetv.osnatel.de/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class EinsUndEinsTVIE(ZattooIE):
|
||||
_NETRC_MACHINE = '1und1tv'
|
||||
_HOST = '1und1.tv'
|
||||
_VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.1und1.tv/watch/abc/123-abc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2018.09.18'
|
||||
__version__ = '2018.10.05'
|
||||
|
Loading…
x
Reference in New Issue
Block a user