Merge pull request #6 from rg3/master

up
This commit is contained in:
世外桃源 2017-01-23 14:40:58 +08:00 committed by GitHub
commit cb3322eb89
55 changed files with 1201 additions and 357 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.05*. 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 Issues with outdated version will be rejected.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 **2017.01.05**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.22*. 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 Issues with outdated version will be rejected.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 **2017.01.22**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[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 2017.01.05
[debug] youtube-dl version 2017.01.22
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@ -124,7 +124,7 @@ After you have ensured this site is distributing its content legally, you can fo
'id': '42',
'ext': 'mp4',
'title': 'Video title goes here',
'thumbnail': 're:^https?://.*\.jpg$',
'thumbnail': r're:^https?://.*\.jpg$',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:

View File

@ -1,9 +1,92 @@
version <unreleased>
version 2017.01.22
Extractors
+ [pornflip] Add support for pornflip.com (#11556, #11795)
* [chaturbate] Fix extraction (#11797, #11802)
+ [azmedien] Add support for AZ Medien sites (#11784, #11785)
+ [nextmedia] Support redirected URLs
+ [vimeo:channel] Extract videos' titles for playlist entries (#11796)
+ [youtube] Extract episode metadata (#9695, #11774)
+ [cspan] Support Ustream embedded videos (#11547)
+ [1tv] Add support for HLS videos (#11786)
* [uol] Fix extraction (#11770)
* [mtv] Relax triforce feed regular expression (#11766)
version 2017.01.18
Extractors
* [bilibili] Fix extraction (#11077)
+ [canalplus] Add fallback for video id (#11764)
* [20min] Fix extraction (#11683, #11751)
* [imdb] Extend URL regular expression (#11744)
+ [naver] Add support for tv.naver.com links (#11743)
version 2017.01.16
Core
* [options] Apply custom config to final composite configuration (#11741)
* [YoutubeDL] Improve protocol auto determining (#11720)
Extractors
* [xiami] Relax URL regular expressions
* [xiami] Improve track metadata extraction (#11699)
+ [limelight] Check hand-make direct HTTP links
+ [limelight] Add support for direct HTTP links at video.llnw.net (#11737)
+ [brightcove] Recognize another player ID pattern (#11688)
+ [niconico] Support login via cookies (#7968)
* [yourupload] Fix extraction (#11601)
+ [beam:live] Add support for beam.pro live streams (#10702, #11596)
* [vevo] Improve geo restriction detection
+ [dramafever] Add support for URLs with language code (#11714)
* [cbc] Improve playlist support (#11704)
version 2017.01.14
Core
+ [common] Add ability to customize akamai manifest host
+ [utils] Add more date formats
Extractors
- [mtv] Eliminate _transform_rtmp_url
* [mtv] Generalize triforce mgid extraction
+ [cmt] Add support for full episodes and video clips (#11623)
+ [mitele] Extract DASH formats
+ [ooyala] Add support for videos with embedToken (#11684)
* [mixcloud] Fix extraction (#11674)
* [openload] Fix extraction (#10408)
* [tv4] Improve extraction (#11698)
* [freesound] Fix and improve extraction (#11602)
+ [nick] Add support for beta.nick.com (#11655)
* [mtv,cc] Use HLS by default with native HLS downloader (#11641)
* [mtv] Fix non-HLS extraction
version 2017.01.10
Extractors
* [youtube] Fix extraction (#11663, #11664)
+ [inc] Add support for inc.com (#11277, #11647)
+ [youtube] Add itag 212 (#11575)
+ [egghead:course] Add support for egghead.io courses
version 2017.01.08
Core
* Fix "invalid escape sequence" errors under Python 3.6 (#11581)
Extractors
+ [hitrecord] Add support for hitrecord.org (#10867, #11626)
- [videott] Remove extractor
* [swrmediathek] Improve extraction
- [sharesix] Remove extractor
- [aol:features] Remove extractor
* [sendtonews] Improve info extraction
* [3sat,phoenix] Fix extraction (#11619)
* [comedycentral/mtv] Add support for HLS videos (#11600)
* [discoverygo] Fix JSON data parsing (#11219, #11522)

View File

@ -374,7 +374,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
avprobe)
--audio-format FORMAT Specify audio format: "best", "aac",
"vorbis", "mp3", "m4a", "opus", or "wav";
"best" by default
"best" by default; No effect without -x
--audio-quality QUALITY Specify ffmpeg/avconv audio quality, insert
a value between 0 (better) and 9 (worse)
for VBR or a specific bitrate like 128K
@ -841,7 +841,7 @@ Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox).
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, Mac OS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).

View File

@ -74,6 +74,8 @@
- **awaan:live**
- **awaan:season**
- **awaan:video**
- **AZMedien**: AZ Medien videos
- **AZMedienShow**: AZ Medien shows
- **Azubu**
- **AzubuLive**
- **BaiduVideo**: 百度视频
@ -86,6 +88,7 @@
- **bbc.co.uk:article**: BBC articles
- **bbc.co.uk:iplayer:playlist**
- **bbc.co.uk:playlist**
- **Beam:live**
- **Beatport**
- **Beeg**
- **BehindKink**
@ -214,6 +217,7 @@
- **EaglePlatform**
- **EbaumsWorld**
- **EchoMsk**
- **egghead:course**: egghead.io course
- **eHow**
- **Einthusan**
- **eitb.tv**
@ -240,7 +244,6 @@
- **fc2**
- **fc2:embed**
- **Fczenit**
- **features.aol.com**
- **fernsehkritik.tv**
- **Firstpost**
- **FiveTV**
@ -304,6 +307,7 @@
- **history:topic**: History.com Topic
- **hitbox**
- **hitbox:live**
- **HitRecord**
- **HornBunny**
- **HotNewHipHop**
- **HotStar**
@ -321,6 +325,7 @@
- **Imgur**
- **ImgurAlbum**
- **Ina**
- **Inc**
- **Indavideo**
- **IndavideoEmbed**
- **InfoQ**
@ -569,6 +574,7 @@
- **PolskieRadio**
- **PolskieRadioCategory**
- **PornCom**
- **PornFlip**
- **PornHd**
- **PornHub**: PornHub and Thumbzilla
- **PornHubPlaylist**
@ -650,7 +656,6 @@
- **screen.yahoo:search**: Yahoo screen search
- **Screencast**
- **ScreencastOMatic**
- **ScreenJunkies**
- **Seeker**
- **SenateISVP**
- **SendtoNews**
@ -658,7 +663,6 @@
- **Sexu**
- **Shahid**
- **Shared**: shared.sx
- **ShareSix**
- **ShowRoomLive**
- **Sina**
- **SixPlay**
@ -845,7 +849,6 @@
- **videomore:season**
- **videomore:video**
- **VideoPremium**
- **VideoTt**: video.tt - Your True Tube (Currently broken)
- **videoweed**: VideoWeed
- **Vidio**
- **vidme**

View File

@ -295,6 +295,9 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
def test_unified_timestamps(self):
self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)

View File

@ -1363,7 +1363,7 @@ class YoutubeDL(object):
format['ext'] = determine_ext(format['url']).lower()
# Automatically determine protocol if missing (useful for format
# selection purposes)
if 'protocol' not in format:
if format.get('protocol') is None:
format['protocol'] = determine_protocol(format)
# Add HTTP headers, so that external programs can use them from the
# json output

View File

@ -0,0 +1,145 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
get_element_by_class,
strip_or_none,
)
class AZMedienBaseIE(InfoExtractor):
def _kaltura_video(self, partner_id, entry_id):
return self.url_result(
'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
video_id=entry_id)
class AZMedienIE(AZMedienBaseIE):
IE_DESC = 'AZ Medien videos'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?:
telezueri\.ch|
telebaern\.tv|
telem1\.ch
)/
[0-9]+-show-[^/\#]+
(?:
/[0-9]+-episode-[^/\#]+
(?:
/[0-9]+-segment-(?:[^/\#]+\#)?|
\#
)|
\#
)
(?P<id>[^\#]+)
'''
_TESTS = [{
# URL with 'segment'
'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
'info_dict': {
'id': '1_2444peh4',
'ext': 'mov',
'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
'uploader_id': 'TeleZ?ri',
'upload_date': '20161218',
'timestamp': 1482084490,
},
'params': {
'skip_download': True,
},
}, {
# URL with 'segment' and fragment:
'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
'only_matching': True
}, {
# URL with 'episode' and fragment:
'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
'only_matching': True
}, {
# URL with 'show' and fragment:
'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
'only_matching': True
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
partner_id = self._search_regex(
r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
webpage, 'kaltura partner id')
entry_id = self._html_search_regex(
r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
% re.escape(video_id), webpage, 'kaltura entry id', group='id')
return self._kaltura_video(partner_id, entry_id)
class AZMedienShowIE(AZMedienBaseIE):
IE_DESC = 'AZ Medien shows'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?:
telezueri\.ch|
telebaern\.tv|
telem1\.ch
)/
(?P<id>[0-9]+-show-[^/\#]+
(?:
/[0-9]+-episode-[^/\#]+
)?
)$
'''
_TESTS = [{
# URL with 'episode'
'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
'info_dict': {
'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
'title': 'News - Donnerstag, 15. Dezember 2016',
},
'playlist_count': 9,
}, {
# URL with 'show' only
'url': 'http://www.telezueri.ch/86-show-talktaeglich',
'only_matching': True
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
entries = []
partner_id = self._search_regex(
r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
webpage, 'kaltura partner id', default=None)
if partner_id:
entries = [
self._kaltura_video(partner_id, m.group('id'))
for m in re.finditer(
r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
if not entries:
entries = [
self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
for m in re.finditer(
r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
title = self._search_regex(
r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
webpage, 'title',
default=strip_or_none(get_element_by_class(
'title-block-cell', webpage)), group='title')
return self.playlist_result(entries, show_id, title)

View File

@ -0,0 +1,73 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
compat_str,
int_or_none,
parse_iso8601,
try_get,
)
class BeamProLiveIE(InfoExtractor):
IE_NAME = 'Beam:live'
_VALID_URL = r'https?://(?:\w+\.)?beam\.pro/(?P<id>[^/?#&]+)'
_RATINGS = {'family': 0, 'teen': 13, '18+': 18}
_TEST = {
'url': 'http://www.beam.pro/niterhayven',
'info_dict': {
'id': '261562',
'ext': 'mp4',
'title': 'Introducing The Witcher 3 // The Grind Starts Now!',
'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
'thumbnail': r're:https://.*\.jpg$',
'timestamp': 1483477281,
'upload_date': '20170103',
'uploader': 'niterhayven',
'uploader_id': '373396',
'age_limit': 18,
'is_live': True,
'view_count': int,
},
'skip': 'niterhayven is offline',
'params': {
'skip_download': True,
},
}
def _real_extract(self, url):
channel_name = self._match_id(url)
chan = self._download_json(
'https://beam.pro/api/v1/channels/%s' % channel_name, channel_name)
if chan.get('online') is False:
raise ExtractorError(
'{0} is offline'.format(channel_name), expected=True)
channel_id = chan['id']
formats = self._extract_m3u8_formats(
'https://beam.pro/api/v1/channels/%s/manifest.m3u8' % channel_id,
channel_name, ext='mp4', m3u8_id='hls', fatal=False)
self._sort_formats(formats)
user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
return {
'id': compat_str(chan.get('id') or channel_name),
'title': self._live_title(chan.get('name') or channel_name),
'description': clean_html(chan.get('description')),
'thumbnail': try_get(chan, lambda x: x['thumbnail']['url'], compat_str),
'timestamp': parse_iso8601(chan.get('updatedAt')),
'uploader': chan.get('token') or try_get(
chan, lambda x: x['user']['username'], compat_str),
'uploader_id': compat_str(user_id) if user_id else None,
'age_limit': self._RATINGS.get(chan.get('audience')),
'is_live': True,
'view_count': int_or_none(chan.get('viewersTotal')),
'formats': formats,
}

View File

@ -34,8 +34,8 @@ class BiliBiliIE(InfoExtractor):
},
}
_APP_KEY = '6f90a59ac58a4123'
_BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
_APP_KEY = '84956560bc028eb7'
_BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e'
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@ -179,7 +179,7 @@ class BrightcoveLegacyIE(InfoExtractor):
params = {}
playerID = find_param('playerID')
playerID = find_param('playerID') or find_param('playerId')
if playerID is None:
raise ExtractorError('Cannot find player ID')
params['playerID'] = playerID
@ -204,7 +204,7 @@ class BrightcoveLegacyIE(InfoExtractor):
# // build Brightcove <object /> XML
# }
m = re.search(
r'''(?x)customBC.\createVideo\(
r'''(?x)customBC\.createVideo\(
.*? # skipping width and height
["\'](?P<playerID>\d+)["\']\s*,\s* # playerID
["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s* # playerKey begins with AQ and is 50 characters

View File

@ -107,7 +107,7 @@ class CanalplusIE(InfoExtractor):
[r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
r'id=["\']canal_video_player(?P<id>\d+)',
r'data-video=["\'](?P<id>\d+)'],
webpage, 'video id', group='id')
webpage, 'video id', default=mobj.group('vid'), group='id')
info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
video_data = self._download_json(info_url, video_id, 'Downloading video JSON')

View File

@ -90,36 +90,49 @@ class CBCIE(InfoExtractor):
},
}],
'skip': 'Geo-restricted to Canada',
}, {
# multiple CBC.APP.Caffeine.initInstance(...)
'url': 'http://www.cbc.ca/news/canada/calgary/dog-indoor-exercise-winter-1.3928238',
'info_dict': {
'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
'id': 'dog-indoor-exercise-winter-1.3928238',
},
'playlist_mincount': 6,
}]
@classmethod
def suitable(cls, url):
return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url)
def _extract_player_init(self, player_init, display_id):
player_info = self._parse_json(player_init, display_id, js_to_json)
media_id = player_info.get('mediaId')
if not media_id:
clip_id = player_info['clipId']
feed = self._download_json(
'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
clip_id, fatal=False)
if feed:
media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
if not media_id:
media_id = self._download_json(
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
clip_id)['entries'][0]['id'].split('/')[-1]
return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_init = self._search_regex(
r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init',
default=None)
if player_init:
player_info = self._parse_json(player_init, display_id, js_to_json)
media_id = player_info.get('mediaId')
if not media_id:
clip_id = player_info['clipId']
feed = self._download_json(
'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
clip_id, fatal=False)
if feed:
media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
if not media_id:
media_id = self._download_json(
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
clip_id)['entries'][0]['id'].split('/')[-1]
return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
else:
entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
return self.playlist_result(entries)
entries = [
self._extract_player_init(player_init, display_id)
for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
entries.extend([
self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)])
return self.playlist_result(
entries, display_id,
self._og_search_title(webpage, fatal=False),
self._og_search_description(webpage))
class CBCPlayerIE(InfoExtractor):

View File

@ -1,5 +1,7 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
@ -31,30 +33,35 @@ class ChaturbateIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
m3u8_url = self._search_regex(
r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
'playlist', default=None, group='url')
m3u8_formats = [(m.group('id').lower(), m.group('url')) for m in re.finditer(
r'hlsSource(?P<id>.+?)\s*=\s*(?P<q>["\'])(?P<url>http.+?)(?P=q)', webpage)]
if not m3u8_url:
if not m3u8_formats:
error = self._search_regex(
[r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
webpage, 'error', group='error', default=None)
if not error:
if any(p not in webpage for p in (
if any(p in webpage for p in (
self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
error = self._ROOM_OFFLINE
if error:
raise ExtractorError(error, expected=True)
raise ExtractorError('Unable to find stream URL')
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
formats = []
for m3u8_id, m3u8_url in m3u8_formats:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4',
# ffmpeg skips segments for fast m3u8
preference=-10 if m3u8_id == 'fast' else None,
m3u8_id=m3u8_id, fatal=False, live=True))
self._sort_formats(formats)
return {
'id': video_id,
'title': self._live_title(video_id),
'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
'age_limit': self._rta_search(webpage),
'is_live': True,
'formats': formats,

View File

@ -19,6 +19,7 @@ class ChirbitIE(InfoExtractor):
'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
'duration': 306,
'uploader': 'Gerryaudio',
},
'params': {
'skip_download': True,
@ -54,6 +55,9 @@ class ChirbitIE(InfoExtractor):
duration = parse_duration(self._search_regex(
r'class=["\']c-length["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
uploader = self._search_regex(
r'id=["\']chirbit-username["\'][^>]*>([^<]+)',
webpage, 'uploader', fatal=False)
return {
'id': audio_id,
@ -61,6 +65,7 @@ class ChirbitIE(InfoExtractor):
'title': title,
'description': description,
'duration': duration,
'uploader': uploader,
}

View File

@ -1,13 +1,11 @@
from __future__ import unicode_literals
from .mtv import MTVIE
from ..utils import ExtractorError
class CMTIE(MTVIE):
IE_NAME = 'cmt.com'
_VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
_FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
_VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows|full-episodes|video-clips)/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
@ -33,17 +31,24 @@ class CMTIE(MTVIE):
}, {
'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
'only_matching': True,
}, {
'url': 'http://www.cmt.com/full-episodes/537qb3/nashville-the-wayfaring-stranger-season-5-ep-501',
'only_matching': True,
}, {
'url': 'http://www.cmt.com/video-clips/t9e4ci/nashville-juliette-in-2-minutes',
'only_matching': True,
}]
@classmethod
def _transform_rtmp_url(cls, rtmp_video_url):
if 'error_not_available.swf' in rtmp_video_url:
raise ExtractorError(
'%s said: video is not available' % cls.IE_NAME, expected=True)
return super(CMTIE, cls)._transform_rtmp_url(rtmp_video_url)
def _extract_mgid(self, webpage):
return self._search_regex(
mgid = self._search_regex(
r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P<mgid>.+?)\1',
webpage, 'mgid', group='mgid')
webpage, 'mgid', group='mgid', default=None)
if not mgid:
mgid = self._extract_triforce_mgid(webpage)
return mgid
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mgid = self._extract_mgid(webpage)
return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)

View File

@ -48,17 +48,8 @@ class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
feed = self._parse_json(feed_json, playlist_id)
zones = feed['manifest']['zones']
video_zone = zones['t2_lc_promo1']
feed = self._download_json(video_zone['feed'], playlist_id)
mgid = feed['result']['data']['id']
videos_info = self._get_videos_info(mgid, use_hls=True)
mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1')
videos_info = self._get_videos_info(mgid)
return videos_info
@ -94,12 +85,6 @@ class ToshIE(MTVServicesInfoExtractor):
'only_matching': True,
}]
@classmethod
def _transform_rtmp_url(cls, rtmp_video_url):
new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
return new_urls
class ComedyCentralTVIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'

View File

@ -1967,10 +1967,13 @@ class InfoExtractor(object):
entries.append(media_info)
return entries
def _extract_akamai_formats(self, manifest_url, video_id):
def _extract_akamai_formats(self, manifest_url, video_id, hosts={}):
formats = []
hdcore_sign = 'hdcore=3.7.0'
f4m_url = re.sub(r'(https?://.+?)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
f4m_url = re.sub(r'(https?://[^/+])/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
hds_host = hosts.get('hds')
if hds_host:
f4m_url = re.sub(r'(https?://)[^/]+', r'\1' + hds_host, f4m_url)
if 'hdcore=' not in f4m_url:
f4m_url += ('&' if '?' in f4m_url else '?') + hdcore_sign
f4m_formats = self._extract_f4m_formats(
@ -1978,7 +1981,10 @@ class InfoExtractor(object):
for entry in f4m_formats:
entry.update({'extra_param_to_segment_url': hdcore_sign})
formats.extend(f4m_formats)
m3u8_url = re.sub(r'(https?://.+?)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
m3u8_url = re.sub(r'(https?://[^/]+)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
hls_host = hosts.get('hls')
if hls_host:
m3u8_url = re.sub(r'(https?://)[^/]+', r'\1' + hls_host, m3u8_url)
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))

View File

@ -12,6 +12,7 @@ from ..utils import (
ExtractorError,
)
from .senateisvp import SenateISVPIE
from .ustream import UstreamIE
class CSpanIE(InfoExtractor):
@ -22,14 +23,13 @@ class CSpanIE(InfoExtractor):
'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
'info_dict': {
'id': '315139',
'ext': 'mp4',
'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
},
'playlist_mincount': 2,
'skip': 'Regularly fails on travis, for unknown reasons',
}, {
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
# md5 is unstable
'info_dict': {
'id': 'c4486943',
'ext': 'mp4',
@ -38,14 +38,11 @@ class CSpanIE(InfoExtractor):
}
}, {
'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
'md5': '2ae5051559169baadba13fc35345ae74',
'info_dict': {
'id': '342759',
'ext': 'mp4',
'title': 'General Motors Ignition Switch Recall',
'duration': 14848,
'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
},
'playlist_mincount': 6,
}, {
# Video from senate.gov
'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
@ -57,12 +54,30 @@ class CSpanIE(InfoExtractor):
'params': {
'skip_download': True, # m3u8 downloads
}
}, {
# Ustream embedded video
'url': 'https://www.c-span.org/video/?114917-1/armed-services',
'info_dict': {
'id': '58428542',
'ext': 'flv',
'title': 'USHR07 Armed Services Committee',
'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee',
'timestamp': 1423060374,
'upload_date': '20150204',
'uploader': 'HouseCommittee',
'uploader_id': '12987475',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_type = None
webpage = self._download_webpage(url, video_id)
ustream_url = UstreamIE._extract_url(webpage)
if ustream_url:
return self.url_result(ustream_url, UstreamIE.ie_key())
# We first look for clipid, because clipprog always appears before
patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
results = list(filter(None, (re.search(p, webpage) for p in patterns)))

View File

@ -66,7 +66,7 @@ class DramaFeverBaseIE(AMPIE):
class DramaFeverIE(DramaFeverBaseIE):
IE_NAME = 'dramafever'
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
_TESTS = [{
'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
'info_dict': {
@ -103,6 +103,9 @@ class DramaFeverIE(DramaFeverBaseIE):
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
'only_matching': True,
}]
def _real_extract(self, url):
@ -148,7 +151,7 @@ class DramaFeverIE(DramaFeverBaseIE):
class DramaFeverSeriesIE(DramaFeverBaseIE):
IE_NAME = 'dramafever:series'
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
_TESTS = [{
'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
'info_dict': {

View File

@ -0,0 +1,39 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class EggheadCourseIE(InfoExtractor):
IE_DESC = 'egghead.io course'
IE_NAME = 'egghead:course'
_VALID_URL = r'https://egghead\.io/courses/(?P<id>[a-zA-Z_0-9-]+)'
_TEST = {
'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
'playlist_count': 29,
'info_dict': {
'id': 'professor-frisby-introduces-composable-functional-javascript',
'title': 'Professor Frisby Introduces Composable Functional JavaScript',
'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
},
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'title')
ul = self._search_regex(r'(?s)<ul class="series-lessons-list">(.*?)</ul>', webpage, 'session list')
found = re.findall(r'(?s)<a class="[^"]*"\s*href="([^"]+)">\s*<li class="item', ul)
entries = [self.url_result(m) for m in found]
return {
'_type': 'playlist',
'id': playlist_id,
'title': title,
'description': self._og_search_description(webpage),
'entries': entries,
}

View File

@ -77,6 +77,10 @@ from .awaan import (
AWAANLiveIE,
AWAANSeasonIE,
)
from .azmedien import (
AZMedienIE,
AZMedienShowIE,
)
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE
@ -88,6 +92,7 @@ from .bbc import (
BBCCoUkPlaylistIE,
BBCIE,
)
from .beampro import BeamProLiveIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .bellmedia import BellMediaIE
@ -252,6 +257,7 @@ from .dw import (
from .eagleplatform import EaglePlatformIE
from .ebaumsworld import EbaumsWorldIE
from .echomsk import EchoMskIE
from .egghead import EggheadCourseIE
from .ehow import EHowIE
from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE
@ -366,6 +372,7 @@ from .hgtv import (
)
from .historicfilms import HistoricFilmsIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hitrecord import HitRecordIE
from .hornbunny import HornBunnyIE
from .hotnewhiphop import HotNewHipHopIE
from .hotstar import HotStarIE
@ -393,6 +400,7 @@ from .imgur import (
ImgurAlbumIE,
)
from .ina import InaIE
from .inc import IncIE
from .indavideo import (
IndavideoIE,
IndavideoEmbedIE,
@ -716,6 +724,7 @@ from .polskieradio import (
)
from .porn91 import Porn91IE
from .porncom import PornComIE
from .pornflip import PornFlipIE
from .pornhd import PornHdIE
from .pornhub import (
PornHubIE,

View File

@ -86,18 +86,43 @@ class FirstTVIE(InfoExtractor):
title = item['title']
quality = qualities(QUALITIES)
formats = []
path = None
for f in item.get('mbr', []):
src = f.get('src')
if not src or not isinstance(src, compat_str):
continue
tbr = int_or_none(self._search_regex(
r'_(\d{3,})\.mp4', src, 'tbr', default=None))
if not path:
path = self._search_regex(
r'//[^/]+/(.+?)_\d+\.mp4', src,
'm3u8 path', default=None)
formats.append({
'url': src,
'format_id': f.get('name'),
'tbr': tbr,
'quality': quality(f.get('name')),
'source_preference': quality(f.get('name')),
})
# m3u8 URL format is reverse engineered from [1] (search for
# master.m3u8). dashEdges (that is currently balancer-vod.1tv.ru)
# is taken from [2].
# 1. http://static.1tv.ru/player/eump1tv-current/eump-1tv.all.min.js?rnd=9097422834:formatted
# 2. http://static.1tv.ru/player/eump1tv-config/config-main.js?rnd=9097422834
if not path and len(formats) == 1:
path = self._search_regex(
r'//[^/]+/(.+?$)', formats[0]['url'],
'm3u8 path', default=None)
if path:
if len(formats) == 1:
m3u8_path = ','
else:
tbrs = [compat_str(t) for t in sorted(f['tbr'] for f in formats)]
m3u8_path = '_,%s,%s' % (','.join(tbrs), '.mp4')
formats.extend(self._extract_m3u8_formats(
'http://balancer-vod.1tv.ru/%s%s.urlset/master.m3u8'
% (path, m3u8_path),
display_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
self._sort_formats(formats)
thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)

View File

@ -81,7 +81,7 @@ class FlipagramIE(InfoExtractor):
'filesize': int_or_none(cover.get('size')),
} for cover in flipagram.get('covers', []) if cover.get('url')]
# Note that this only retrieves comments that are initally loaded.
# Note that this only retrieves comments that are initially loaded.
# For videos with large amounts of comments, most won't be retrieved.
comments = []
for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []):

View File

@ -3,10 +3,16 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
get_element_by_class,
get_element_by_id,
unified_strdate,
)
class FreesoundIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?freesound\.org/people/[^/]+/sounds/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
'md5': '12280ceb42c81f19a515c745eae07650',
@ -14,26 +20,60 @@ class FreesoundIE(InfoExtractor):
'id': '194503',
'ext': 'mp3',
'title': 'gulls in the city.wav',
'uploader': 'miklovan',
'description': 'the sounds of seagulls in the city',
'duration': 130.233,
'uploader': 'miklovan',
'upload_date': '20130715',
'tags': list,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
music_id = mobj.group('id')
webpage = self._download_webpage(url, music_id)
title = self._html_search_regex(
r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
webpage, 'music title', flags=re.DOTALL)
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
audio_url = self._og_search_property('audio', webpage, 'song url')
title = self._og_search_property('audio:title', webpage, 'song title')
description = self._html_search_regex(
r'<div id="sound_description">(.*?)</div>', webpage, 'description',
fatal=False, flags=re.DOTALL)
r'(?s)id=["\']sound_description["\'][^>]*>(.+?)</div>',
webpage, 'description', fatal=False)
duration = float_or_none(
get_element_by_class('duration', webpage), scale=1000)
upload_date = unified_strdate(get_element_by_id('sound_date', webpage))
uploader = self._og_search_property(
'audio:artist', webpage, 'uploader', fatal=False)
channels = self._html_search_regex(
r'Channels</dt><dd>(.+?)</dd>', webpage,
'channels info', fatal=False)
tags_str = get_element_by_class('tags', webpage)
tags = re.findall(r'<a[^>]+>([^<]+)', tags_str) if tags_str else None
audio_urls = [audio_url]
LQ_FORMAT = '-lq.mp3'
if LQ_FORMAT in audio_url:
audio_urls.append(audio_url.replace(LQ_FORMAT, '-hq.mp3'))
formats = [{
'url': format_url,
'format_note': channels,
'quality': quality,
} for quality, format_url in enumerate(audio_urls)]
self._sort_formats(formats)
return {
'id': music_id,
'id': audio_id,
'title': title,
'url': self._og_search_property('audio', webpage, 'music url'),
'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
'description': description,
'duration': duration,
'uploader': uploader,
'upload_date': upload_date,
'tags': tags,
'formats': formats,
}

View File

@ -78,6 +78,8 @@ from .vbox7 import Vbox7IE
from .dbtv import DBTVIE
from .piksel import PikselIE
from .videa import VideaIE
from .twentymin import TwentyMinutenIE
from .ustream import UstreamIE
class GenericIE(InfoExtractor):
@ -422,6 +424,26 @@ class GenericIE(InfoExtractor):
'skip_download': True, # m3u8 download
},
},
{
# Brightcove with alternative playerID key
'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
'info_dict': {
'id': 'nmeth.2062_SV1',
'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
},
'playlist': [{
'info_dict': {
'id': '2228375078001',
'ext': 'mp4',
'title': 'nmeth.2062-sv1',
'description': 'nmeth.2062-sv1',
'timestamp': 1363357591,
'upload_date': '20130315',
'uploader': 'Nature Publishing Group',
'uploader_id': '1964492299001',
},
}],
},
# ooyala video
{
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
@ -567,17 +589,6 @@ class GenericIE(InfoExtractor):
'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
}
},
# Embedded Ustream video
{
'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
'md5': '27b99cdb639c9b12a79bca876a073417',
'info_dict': {
'id': '45734260',
'ext': 'flv',
'uploader': 'AU SPA: The NSA and Privacy',
'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
}
},
# nowvideo embed hidden behind percent encoding
{
'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
@ -1448,6 +1459,20 @@ class GenericIE(InfoExtractor):
},
'playlist_mincount': 2,
},
{
# 20 minuten embed
'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
'info_dict': {
'id': '523629',
'ext': 'mp4',
'title': 'So kommen Sie bei Eis und Schnee sicher an',
'description': 'md5:117c212f64b25e3d95747e5276863f7d',
},
'params': {
'skip_download': True,
},
'add_ie': [TwentyMinutenIE.ie_key()],
}
# {
# # TODO: find another test
# # http://schema.org/VideoObject
@ -1939,7 +1964,14 @@ class GenericIE(InfoExtractor):
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:
return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
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)
@ -2070,10 +2102,9 @@ class GenericIE(InfoExtractor):
return self.url_result(mobj.group('url'), 'TED')
# Look for embedded Ustream videos
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Ustream')
ustream_url = UstreamIE._extract_url(webpage)
if ustream_url:
return self.url_result(ustream_url, UstreamIE.ie_key())
# Look for embedded arte.tv player
mobj = re.search(
@ -2394,6 +2425,12 @@ class GenericIE(InfoExtractor):
if videa_urls:
return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
# Look for 20 minuten embeds
twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
if twentymin_urls:
return _playlist_from_matches(
twentymin_urls, ie=TwentyMinutenIE.ie_key())
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')

View File

@ -0,0 +1,68 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
float_or_none,
int_or_none,
try_get,
)
class HitRecordIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hitrecord\.org/records/(?P<id>\d+)'
_TEST = {
'url': 'https://hitrecord.org/records/2954362',
'md5': 'fe1cdc2023bce0bbb95c39c57426aa71',
'info_dict': {
'id': '2954362',
'ext': 'mp4',
'title': 'A Very Different World (HITRECORD x ACLU)',
'description': 'md5:e62defaffab5075a5277736bead95a3d',
'duration': 139.327,
'timestamp': 1471557582,
'upload_date': '20160818',
'uploader': 'Zuzi.C12',
'uploader_id': '362811',
'view_count': int,
'like_count': int,
'comment_count': int,
'tags': list,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'https://hitrecord.org/api/web/records/%s' % video_id, video_id)
title = video['title']
video_url = video['source_url']['mp4_url']
tags = None
tags_list = try_get(video, lambda x: x['tags'], list)
if tags_list:
tags = [
t['text']
for t in tags_list
if isinstance(t, dict) and t.get('text') and
isinstance(t['text'], compat_str)]
return {
'id': video_id,
'url': video_url,
'title': title,
'description': clean_html(video.get('body')),
'duration': float_or_none(video.get('duration'), 1000),
'timestamp': int_or_none(video.get('created_at_i')),
'uploader': try_get(
video, lambda x: x['user']['username'], compat_str),
'uploader_id': try_get(
video, lambda x: compat_str(x['user']['id'])),
'view_count': int_or_none(video.get('total_views_count')),
'like_count': int_or_none(video.get('hearts_count')),
'comment_count': int_or_none(video.get('comments_count')),
'tags': tags,
}

View File

@ -13,7 +13,7 @@ from ..utils import (
class ImdbIE(InfoExtractor):
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-)vi(?P<id>\d+)'
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-|videoplayer/)vi(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
@ -32,6 +32,9 @@ class ImdbIE(InfoExtractor):
}, {
'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/videoplayer/vi1562949145',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -0,0 +1,41 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .kaltura import KalturaIE
class IncIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?inc\.com/(?:[^/]+/)+(?P<id>[^.]+).html'
_TESTS = [{
'url': 'http://www.inc.com/tip-sheet/bill-gates-says-these-5-books-will-make-you-smarter.html',
'md5': '7416739c9c16438c09fa35619d6ba5cb',
'info_dict': {
'id': '1_wqig47aq',
'ext': 'mov',
'title': 'Bill Gates Says These 5 Books Will Make You Smarter',
'description': 'md5:bea7ff6cce100886fc1995acb743237e',
'timestamp': 1474414430,
'upload_date': '20160920',
'uploader_id': 'video@inc.com',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.inc.com/video/david-whitford/founders-forum-tripadvisor-steve-kaufer-most-enjoyable-moment-for-entrepreneur.html',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
partner_id = self._search_regex(
r'var\s+_?bizo_data_partner_id\s*=\s*["\'](\d+)', webpage, 'partner id')
kaltura_id = self._parse_json(self._search_regex(
r'pageInfo\.videos\s*=\s*\[(.+)\];', webpage, 'kaltura id'),
display_id)['vid_kaltura_id']
return self.url_result(
'kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())

View File

@ -59,14 +59,26 @@ class LimelightBaseIE(InfoExtractor):
format_id = 'rtmp'
if stream.get('videoBitRate'):
format_id += '-%d' % int_or_none(stream['videoBitRate'])
http_url = 'http://cpl.delvenetworks.com/' + rtmp.group('playpath')[4:]
urls.append(http_url)
http_fmt = fmt.copy()
http_fmt.update({
'url': http_url,
'format_id': format_id.replace('rtmp', 'http'),
})
formats.append(http_fmt)
http_format_id = format_id.replace('rtmp', 'http')
CDN_HOSTS = (
('delvenetworks.com', 'cpl.delvenetworks.com'),
('video.llnw.net', 's2.content.video.llnw.net'),
)
for cdn_host, http_host in CDN_HOSTS:
if cdn_host not in rtmp.group('host').lower():
continue
http_url = 'http://%s/%s' % (http_host, rtmp.group('playpath')[4:])
urls.append(http_url)
if self._is_valid_url(http_url, video_id, http_format_id):
http_fmt = fmt.copy()
http_fmt.update({
'url': http_url,
'format_id': http_format_id,
})
formats.append(http_fmt)
break
fmt.update({
'url': rtmp.group('url'),
'play_path': rtmp.group('playpath'),

View File

@ -190,7 +190,7 @@ class MiTeleIE(InfoExtractor):
return {
'_type': 'url_transparent',
# for some reason only HLS is supported
'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8'}),
'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}),
'id': video_id,
'title': title,
'description': description,

View File

@ -16,7 +16,6 @@ from ..utils import (
clean_html,
ExtractorError,
OnDemandPagedList,
parse_count,
str_to_int,
)
@ -36,7 +35,6 @@ class MixcloudIE(InfoExtractor):
'uploader_id': 'dholbach',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
'like_count': int,
},
}, {
'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
@ -49,7 +47,6 @@ class MixcloudIE(InfoExtractor):
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*',
'view_count': int,
'like_count': int,
},
}, {
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
@ -89,26 +86,18 @@ class MixcloudIE(InfoExtractor):
song_url = play_info['stream_url']
PREFIX = (
r'm-play-on-spacebar[^>]+'
r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
title = self._html_search_regex(
PREFIX + r'm-title="([^"]+)"', webpage, 'title')
title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title')
thumbnail = self._proto_relative_url(self._html_search_regex(
PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
fatal=False))
r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False))
uploader = self._html_search_regex(
PREFIX + r'm-owner-name="([^"]+)"',
webpage, 'uploader', fatal=False)
r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False)
uploader_id = self._search_regex(
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
description = self._og_search_description(webpage)
like_count = parse_count(self._search_regex(
r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
webpage, 'like count', default=None))
view_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
r'/listeners/?">([0-9,.]+)</a>'],
r'/listeners/?">([0-9,.]+)</a>',
r'm-tooltip=["\']([\d,.]+) plays'],
webpage, 'play count', default=None))
return {
@ -120,7 +109,6 @@ class MixcloudIE(InfoExtractor):
'uploader': uploader,
'uploader_id': uploader_id,
'view_count': view_count,
'like_count': like_count,
}

View File

@ -13,11 +13,11 @@ from ..utils import (
fix_xml_ampersands,
float_or_none,
HEADRequest,
NO_DEFAULT,
RegexNotFoundError,
sanitized_Request,
strip_or_none,
timeconvert,
try_get,
unescapeHTML,
update_url_query,
url_basename,
@ -42,15 +42,6 @@ class MTVServicesInfoExtractor(InfoExtractor):
# Remove the templates, like &device={device}
return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
# This was originally implemented for ComedyCentral, but it also works here
@classmethod
def _transform_rtmp_url(cls, rtmp_video_url):
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
if not m:
return {'rtmp': rtmp_video_url}
base = 'http://viacommtvstrmfs.fplive.net/'
return {'http': base + m.group('finalid')}
def _get_feed_url(self, uri):
return self._FEED_URL
@ -88,24 +79,31 @@ class MTVServicesInfoExtractor(InfoExtractor):
formats = []
for rendition in mdoc.findall('.//rendition'):
if rendition.attrib['method'] == 'hls':
if rendition.get('method') == 'hls':
hls_url = rendition.find('./src').text
formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4'))
formats.extend(self._extract_m3u8_formats(
hls_url, video_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls'))
else:
# fms
try:
_, _, ext = rendition.attrib['type'].partition('/')
rtmp_video_url = rendition.find('./src').text
if 'error_not_available.swf' in rtmp_video_url:
raise ExtractorError(
'%s said: video is not available' % self.IE_NAME,
expected=True)
if rtmp_video_url.endswith('siteunavail.png'):
continue
new_urls = self._transform_rtmp_url(rtmp_video_url)
formats.extend([{
'ext': 'flv' if new_url.startswith('rtmp') else ext,
'url': new_url,
'format_id': '-'.join(filter(None, [kind, rendition.get('bitrate')])),
'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext,
'url': rtmp_video_url,
'format_id': '-'.join(filter(None, [
'rtmp' if rtmp_video_url.startswith('rtmp') else None,
rendition.get('bitrate')])),
'width': int(rendition.get('width')),
'height': int(rendition.get('height')),
} for kind, new_url in new_urls.items()])
}])
except (KeyError, TypeError):
raise ExtractorError('Invalid rendition field.')
self._sort_formats(formats)
@ -123,7 +121,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
} for typographic in transcript.findall('./typographic')]
return subtitles
def _get_video_info(self, itemdoc, use_hls):
def _get_video_info(self, itemdoc, use_hls=True):
uri = itemdoc.find('guid').text
video_id = self._id_from_uri(uri)
self.report_extraction(video_id)
@ -193,13 +191,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
data['lang'] = self._LANG
return data
def _get_videos_info(self, uri, use_hls=False):
def _get_videos_info(self, uri, use_hls=True):
video_id = self._id_from_uri(uri)
feed_url = self._get_feed_url(uri)
info_url = update_url_query(feed_url, self._get_feed_query(uri))
return self._get_videos_info_from_url(info_url, video_id, use_hls)
def _get_videos_info_from_url(self, url, video_id, use_hls):
def _get_videos_info_from_url(self, url, video_id, use_hls=True):
idoc = self._download_xml(
url, video_id,
'Downloading info', transform_source=fix_xml_ampersands)
@ -211,7 +209,28 @@ class MTVServicesInfoExtractor(InfoExtractor):
[self._get_video_info(item, use_hls) for item in idoc.findall('.//item')],
playlist_title=title, playlist_description=description)
def _extract_mgid(self, webpage, default=NO_DEFAULT):
def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
triforce_feed = self._parse_json(self._search_regex(
r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage,
'triforce feed', default='{}'), video_id, fatal=False)
data_zone = self._search_regex(
r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage,
'data zone', default=data_zone, group='zone')
feed_url = try_get(
triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
compat_str)
if not feed_url:
return
feed = self._download_json(feed_url, video_id, fatal=False)
if not feed:
return
return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
def _extract_mgid(self, webpage):
try:
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
# or http://media.mtvnservices.com/{mgid}
@ -231,7 +250,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
sm4_embed = self._html_search_meta(
'sm4:video:embed', webpage, 'sm4 embed', default='')
mgid = self._search_regex(
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=default)
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
if not mgid:
mgid = self._extract_triforce_mgid(webpage)
return mgid
def _real_extract(self, url):

View File

@ -12,10 +12,10 @@ from ..utils import (
class NaverIE(InfoExtractor):
_VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
_VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/v/(?P<id>\d+)'
_TESTS = [{
'url': 'http://tvcast.naver.com/v/81652',
'url': 'http://tv.naver.com/v/81652',
'info_dict': {
'id': '81652',
'ext': 'mp4',
@ -24,7 +24,7 @@ class NaverIE(InfoExtractor):
'upload_date': '20130903',
},
}, {
'url': 'http://tvcast.naver.com/v/395837',
'url': 'http://tv.naver.com/v/395837',
'md5': '638ed4c12012c458fefcddfd01f173cd',
'info_dict': {
'id': '395837',
@ -34,6 +34,9 @@ class NaverIE(InfoExtractor):
'upload_date': '20150519',
},
'skip': 'Georestricted',
}, {
'url': 'http://tvcast.naver.com/v/81652',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import parse_iso8601
@ -30,6 +31,12 @@ class NextMediaIE(InfoExtractor):
return self._extract_from_nextmedia_page(news_id, url, page)
def _extract_from_nextmedia_page(self, news_id, url, page):
redirection_url = self._search_regex(
r'window\.location\.href\s*=\s*([\'"])(?P<url>(?!\1).+)\1',
page, 'redirection URL', default=None, group='url')
if redirection_url:
return self.url_result(compat_urlparse.urljoin(url, redirection_url))
title = self._fetch_title(page)
video_url = self._search_regex(self._URL_PATTERN, page, 'video url')
@ -93,7 +100,7 @@ class NextMediaActionNewsIE(NextMediaIE):
class AppleDailyIE(NextMediaIE):
IE_DESC = '臺灣蘋果日報'
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews|actionnews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/[^/]+/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
_TESTS = [{
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@ -157,6 +164,10 @@ class AppleDailyIE(NextMediaIE):
}, {
'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
'only_matching': True,
}, {
# Redirected from http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694
'url': 'http://ent.appledaily.com.tw/section/article/headline/20150128/36354694',
'only_matching': True,
}]
_URL_PATTERN = r'\{url: \'(.+)\'\}'

View File

@ -10,7 +10,7 @@ from ..utils import update_url_query
class NickIE(MTVServicesInfoExtractor):
# None of videos on the website are still alive?
IE_NAME = 'nick.com'
_VALID_URL = r'https?://(?:www\.)?nick(?:jr)?\.com/(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
_VALID_URL = r'https?://(?:(?:www|beta)\.)?nick(?:jr)?\.com/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
_FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm'
_TESTS = [{
'url': 'http://www.nick.com/videos/clip/alvinnn-and-the-chipmunks-112-full-episode.html',
@ -57,6 +57,9 @@ class NickIE(MTVServicesInfoExtractor):
}, {
'url': 'http://www.nickjr.com/paw-patrol/videos/pups-save-a-goldrush-s3-ep302-full-episode/',
'only_matching': True,
}, {
'url': 'http://beta.nick.com/nicky-ricky-dicky-and-dawn/videos/nicky-ricky-dicky-dawn-301-full-episode/',
'only_matching': True,
}]
def _get_feed_query(self, uri):

View File

@ -7,7 +7,6 @@ import datetime
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_urlparse,
)
from ..utils import (
@ -40,6 +39,7 @@ class NiconicoIE(InfoExtractor):
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
'duration': 33,
},
'skip': 'Requires an account',
}, {
# File downloaded with and without credentials are different, so omit
# the md5 field
@ -55,6 +55,7 @@ class NiconicoIE(InfoExtractor):
'timestamp': 1304065916,
'duration': 209,
},
'skip': 'Requires an account',
}, {
# 'video exists but is marked as "deleted"
# md5 is unstable
@ -65,9 +66,10 @@ class NiconicoIE(InfoExtractor):
'description': 'deleted',
'title': 'ドラえもんエターナル第3話「決戦第3新東京市」前編',
'upload_date': '20071224',
'timestamp': 1198527840, # timestamp field has different value if logged in
'timestamp': int, # timestamp field has different value if logged in
'duration': 304,
},
'skip': 'Requires an account',
}, {
'url': 'http://www.nicovideo.jp/watch/so22543406',
'info_dict': {
@ -79,13 +81,12 @@ class NiconicoIE(InfoExtractor):
'upload_date': '20140104',
'uploader': 'アニメロチャンネル',
'uploader_id': '312',
}
},
'skip': 'The viewing period of the video you were searching for has expired.',
}]
_VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
_NETRC_MACHINE = 'niconico'
# Determine whether the downloader used authentication to download video
_AUTHENTICATED = False
def _real_initialize(self):
self._login()
@ -109,8 +110,6 @@ class NiconicoIE(InfoExtractor):
if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
self._downloader.report_warning('unable to log in: bad username or password')
return False
# Successful login
self._AUTHENTICATED = True
return True
def _real_extract(self, url):
@ -128,35 +127,19 @@ class NiconicoIE(InfoExtractor):
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
note='Downloading video info page')
if self._AUTHENTICATED:
# Get flv info
flv_info_webpage = self._download_webpage(
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
video_id, 'Downloading flv info')
else:
# Get external player info
ext_player_info = self._download_webpage(
'http://ext.nicovideo.jp/thumb_watch/' + video_id, video_id)
thumb_play_key = self._search_regex(
r'\'thumbPlayKey\'\s*:\s*\'(.*?)\'', ext_player_info, 'thumbPlayKey')
# Get flv info
flv_info_data = compat_urllib_parse_urlencode({
'k': thumb_play_key,
'v': video_id
})
flv_info_request = sanitized_Request(
'http://ext.nicovideo.jp/thumb_watch', flv_info_data,
{'Content-Type': 'application/x-www-form-urlencoded'})
flv_info_webpage = self._download_webpage(
flv_info_request, video_id,
note='Downloading flv info', errnote='Unable to download flv info')
# Get flv info
flv_info_webpage = self._download_webpage(
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
video_id, 'Downloading flv info')
flv_info = compat_urlparse.parse_qs(flv_info_webpage)
if 'url' not in flv_info:
if 'deleted' in flv_info:
raise ExtractorError('The video has been deleted.',
expected=True)
elif 'closed' in flv_info:
raise ExtractorError('Niconico videos now require logging in',
expected=True)
else:
raise ExtractorError('Unable to find video URL')

View File

@ -18,7 +18,7 @@ class OoyalaBaseIE(InfoExtractor):
_CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
_AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?'
def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None):
def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None, embed_token=None):
content_tree = self._download_json(content_tree_url, video_id)['content_tree']
metadata = content_tree[list(content_tree)[0]]
embed_code = metadata['embed_code']
@ -29,7 +29,8 @@ class OoyalaBaseIE(InfoExtractor):
self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
compat_urllib_parse_urlencode({
'domain': domain,
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds',
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
'embedToken': embed_token,
}), video_id)
cur_auth_data = auth_data['authorization_data'][embed_code]
@ -52,6 +53,12 @@ class OoyalaBaseIE(InfoExtractor):
elif delivery_type == 'hds' or ext == 'f4m':
formats.extend(self._extract_f4m_formats(
s_url + '?hdcore=3.7.0', embed_code, f4m_id='hds', fatal=False))
elif delivery_type == 'dash' or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
s_url, embed_code, mpd_id='dash', fatal=False))
elif delivery_type == 'smooth':
self._extract_ism_formats(
s_url, embed_code, ism_id='mss', fatal=False)
elif ext == 'smil':
formats.extend(self._extract_smil_formats(
s_url, embed_code, fatal=False))
@ -146,8 +153,9 @@ class OoyalaIE(OoyalaBaseIE):
embed_code = self._match_id(url)
domain = smuggled_data.get('domain')
supportedformats = smuggled_data.get('supportedformats')
embed_token = smuggled_data.get('embed_token')
content_tree_url = self._CONTENT_TREE_BASE + 'embed_code/%s/%s' % (embed_code, embed_code)
return self._extract(content_tree_url, embed_code, domain, supportedformats)
return self._extract(content_tree_url, embed_code, domain, supportedformats, embed_token)
class OoyalaExternalIE(OoyalaBaseIE):

View File

@ -64,16 +64,17 @@ class OpenloadIE(InfoExtractor):
raise ExtractorError('File not found', expected=True)
ol_id = self._search_regex(
'<span[^>]+id="[a-zA-Z0-9]+x"[^>]*>([0-9]+)</span>',
'<span[^>]+id="[^"]+"[^>]*>([0-9]+)</span>',
webpage, 'openload ID')
first_two_chars = int(float(ol_id[0:][:2]))
first_three_chars = int(float(ol_id[0:][:3]))
fifth_char = int(float(ol_id[3:5]))
urlcode = ''
num = 2
num = 5
while num < len(ol_id):
urlcode += compat_chr(int(float(ol_id[num:][:3])) -
first_two_chars * int(float(ol_id[num + 3:][:2])))
urlcode += compat_chr(int(float(ol_id[num:][:3])) +
first_three_chars - fifth_char * int(float(ol_id[num + 3:][:2])))
num += 5
video_url = 'https://openload.co/stream/' + urlcode

View File

@ -0,0 +1,92 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
)
from ..utils import (
int_or_none,
try_get,
unified_timestamp,
)
class PornFlipIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:v|embed)/(?P<id>[0-9A-Za-z]{11})'
_TESTS = [{
'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
'md5': '98c46639849145ae1fd77af532a9278c',
'info_dict': {
'id': 'wz7DfNhMmep',
'ext': 'mp4',
'title': '2 Amateurs swallow make his dream cumshots true',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 112,
'timestamp': 1481655502,
'upload_date': '20161213',
'uploader_id': '106786',
'uploader': 'figifoto',
'view_count': int,
'age_limit': 18,
}
}, {
'url': 'https://www.pornflip.com/embed/wz7DfNhMmep',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://www.pornflip.com/v/%s' % video_id, video_id)
flashvars = compat_parse_qs(self._search_regex(
r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
webpage, 'flashvars', group='flashvars'))
title = flashvars['video_vars[title]'][0]
def flashvar(kind):
return try_get(
flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
formats = []
for key, value in flashvars.items():
if not (value and isinstance(value, list)):
continue
format_url = value[0]
if key == 'video_vars[hds_manifest]':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False))
continue
height = self._search_regex(
r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
if not height:
continue
formats.append({
'url': format_url,
'format_id': 'http-%s' % height,
'height': int_or_none(height),
})
self._sort_formats(formats)
uploader = self._html_search_regex(
(r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
webpage, 'uploader', fatal=False, group='uploader')
return {
'id': video_id,
'formats': formats,
'title': title,
'thumbnail': flashvar('big_thumb'),
'duration': int_or_none(flashvar('duration')),
'timestamp': unified_timestamp(self._html_search_meta(
'uploadDate', webpage, 'timestamp')),
'uploader_id': flashvar('author_id'),
'uploader': uploader,
'view_count': int_or_none(flashvar('views')),
'age_limit': 18,
}

View File

@ -46,7 +46,7 @@ class SpikeIE(MTVServicesInfoExtractor):
_CUSTOM_URL_REGEX = re.compile(r'spikenetworkapp://([^/]+/[-a-fA-F0-9]+)')
def _extract_mgid(self, webpage):
mgid = super(SpikeIE, self)._extract_mgid(webpage, default=None)
mgid = super(SpikeIE, self)._extract_mgid(webpage)
if mgid is None:
url_parts = self._search_regex(self._CUSTOM_URL_REGEX, webpage, 'episode_id')
video_type, episode_id = url_parts.split('/', 1)

View File

@ -4,11 +4,10 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
try_get,
update_url_query,
determine_ext,
)
@ -28,7 +27,7 @@ class TV4IE(InfoExtractor):
_TESTS = [
{
'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650',
'md5': '909d6454b87b10a25aa04c4bdd416a9b',
'md5': 'cb837212f342d77cec06e6dad190e96d',
'info_dict': {
'id': '2491650',
'ext': 'mp4',
@ -40,7 +39,7 @@ class TV4IE(InfoExtractor):
},
{
'url': 'http://www.tv4play.se/iframe/video/3054113',
'md5': '77f851c55139ffe0ebd41b6a5552489b',
'md5': 'cb837212f342d77cec06e6dad190e96d',
'info_dict': {
'id': '3054113',
'ext': 'mp4',
@ -75,11 +74,10 @@ class TV4IE(InfoExtractor):
# If is_geo_restricted is true, it doesn't necessarily mean we can't download it
if info.get('is_geo_restricted'):
self.report_warning('This content might not be available in your country due to licensing restrictions.')
if info.get('requires_subscription'):
raise ExtractorError('This content requires subscription.', expected=True)
title = info['title']
subtitles = {}
formats = []
# http formats are linked with unresolvable host
for kind in ('hls', ''):
@ -87,26 +85,41 @@ class TV4IE(InfoExtractor):
'https://prima.tv4play.se/api/web/asset/%s/play.json' % video_id,
video_id, 'Downloading sources JSON', query={
'protocol': kind,
'videoFormat': 'MP4+WEBVTTS+WEBVTT',
'videoFormat': 'MP4+WEBVTT',
})
item = try_get(data, lambda x: x['playback']['items']['item'], dict)
manifest_url = item.get('url')
if not isinstance(manifest_url, compat_str):
items = try_get(data, lambda x: x['playback']['items']['item'])
if not items:
continue
if kind == 'hls':
formats.extend(self._extract_m3u8_formats(
manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=kind, fatal=False))
else:
formats.extend(self._extract_f4m_formats(
update_url_query(manifest_url, {'hdcore': '3.8.0'}),
video_id, f4m_id='hds', fatal=False))
if isinstance(items, dict):
items = [items]
for item in items:
manifest_url = item.get('url')
if not isinstance(manifest_url, compat_str):
continue
ext = determine_ext(manifest_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=kind, fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_akamai_formats(
manifest_url, video_id, {
'hls': 'tv4play-i.akamaihd.net',
}))
elif ext == 'webvtt':
subtitles = self._merge_subtitles(
subtitles, {
'sv': [{
'url': manifest_url,
'ext': 'vtt',
}]})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'subtitles': subtitles,
'description': info.get('description'),
'timestamp': parse_iso8601(info.get('broadcast_date_time')),
'duration': int_or_none(info.get('duration')),

View File

@ -12,7 +12,7 @@ from ..utils import (
class TwentyFourVideoIE(InfoExtractor):
IE_NAME = '24video'
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.24video.net/video/view/1044982',
@ -43,7 +43,7 @@ class TwentyFourVideoIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://www.24video.net/video/view/%s' % video_id, video_id)
'http://www.24video.sex/video/view/%s' % video_id, video_id)
title = self._og_search_title(webpage)
description = self._html_search_regex(
@ -69,11 +69,11 @@ class TwentyFourVideoIE(InfoExtractor):
# Sets some cookies
self._download_xml(
r'http://www.24video.net/video/xml/%s?mode=init' % video_id,
r'http://www.24video.sex/video/xml/%s?mode=init' % video_id,
video_id, 'Downloading init XML')
video_xml = self._download_xml(
'http://www.24video.net/video/xml/%s?mode=play' % video_id,
'http://www.24video.sex/video/xml/%s?mode=play' % video_id,
video_id, 'Downloading video XML')
video = xpath_element(video_xml, './/video', 'video', fatal=True)

View File

@ -4,91 +4,88 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import remove_end
from ..utils import (
int_or_none,
try_get,
)
class TwentyMinutenIE(InfoExtractor):
IE_NAME = '20min'
_VALID_URL = r'https?://(?:www\.)?20min\.ch/(?:videotv/*\?.*\bvid=(?P<id>\d+)|(?:[^/]+/)*(?P<display_id>[^/#?]+))'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?20min\.ch/
(?:
videotv/*\?.*?\bvid=|
videoplayer/videoplayer\.html\?.*?\bvideoId@
)
(?P<id>\d+)
'''
_TESTS = [{
# regular video
'url': 'http://www.20min.ch/videotv/?vid=469148&cid=2',
'md5': 'b52d6bc6ea6398e6a38f12cfd418149c',
'md5': 'e7264320db31eed8c38364150c12496e',
'info_dict': {
'id': '469148',
'ext': 'flv',
'title': '85 000 Franken für 15 perfekte Minuten',
'description': 'Was die Besucher vom Silvesterzauber erwarten können. (Video: Alice Grosjean/Murat Temel)',
'thumbnail': 'http://thumbnails.20min-tv.ch/server063/469148/frame-72-469148.jpg'
}
}, {
# news article with video
'url': 'http://www.20min.ch/schweiz/news/story/-Wir-muessen-mutig-nach-vorne-schauen--22050469',
'md5': 'cd4cbb99b94130cff423e967cd275e5e',
'info_dict': {
'id': '469408',
'display_id': '-Wir-muessen-mutig-nach-vorne-schauen--22050469',
'ext': 'flv',
'title': '«Wir müssen mutig nach vorne schauen»',
'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.',
'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg'
},
'skip': '"This video is no longer available" is shown both on the web page and in the downloaded file.',
}, {
# YouTube embed
'url': 'http://www.20min.ch/ro/sports/football/story/Il-marque-une-bicyclette-de-plus-de-30-metres--21115184',
'md5': 'cec64d59aa01c0ed9dbba9cf639dd82f',
'info_dict': {
'id': 'ivM7A7SpDOs',
'ext': 'mp4',
'title': 'GOLAZO DE CHILENA DE JAVI GÓMEZ, FINALISTA AL BALÓN DE CLM 2016',
'description': 'md5:903c92fbf2b2f66c09de514bc25e9f5a',
'upload_date': '20160424',
'uploader': 'RTVCM Castilla-La Mancha',
'uploader_id': 'RTVCM',
'title': '85 000 Franken für 15 perfekte Minuten',
'thumbnail': r're:https?://.*\.jpg$',
},
}, {
'url': 'http://www.20min.ch/videoplayer/videoplayer.html?params=client@twentyDE|videoId@523629',
'info_dict': {
'id': '523629',
'ext': 'mp4',
'title': 'So kommen Sie bei Eis und Schnee sicher an',
'description': 'md5:117c212f64b25e3d95747e5276863f7d',
'thumbnail': r're:https?://.*\.jpg$',
},
'params': {
'skip_download': True,
},
'add_ie': ['Youtube'],
}, {
'url': 'http://www.20min.ch/videotv/?cid=44&vid=468738',
'only_matching': True,
}, {
'url': 'http://www.20min.ch/ro/sortir/cinema/story/Grandir-au-bahut--c-est-dur-18927411',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [m.group('url') for m in re.finditer(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:www\.)?20min\.ch/videoplayer/videoplayer.html\?.*?\bvideoId@\d+.*?)\1',
webpage)]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
video_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video = self._download_json(
'http://api.20min.ch/video/%s/show' % video_id,
video_id)['content']
youtube_url = self._html_search_regex(
r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
webpage, 'YouTube embed URL', default=None)
if youtube_url is not None:
return self.url_result(youtube_url, 'Youtube')
title = video['title']
title = self._html_search_regex(
r'<h1>.*?<span>(.+?)</span></h1>',
webpage, 'title', default=None)
if not title:
title = remove_end(re.sub(
r'^20 [Mm]inuten.*? -', '', self._og_search_title(webpage)), ' - News')
formats = [{
'format_id': format_id,
'url': 'http://podcast.20min-tv.ch/podcast/20min/%s%s.mp4' % (video_id, p),
'quality': quality,
} for quality, (format_id, p) in enumerate([('sd', ''), ('hd', 'h')])]
self._sort_formats(formats)
if not video_id:
video_id = self._search_regex(
r'"file\d?"\s*,\s*\"(\d+)', webpage, 'video id')
description = video.get('lead')
thumbnail = video.get('thumbnail')
description = self._html_search_meta(
'description', webpage, 'description')
thumbnail = self._og_search_thumbnail(webpage)
def extract_count(kind):
return try_get(
video,
lambda x: int_or_none(x['communityobject']['thumbs_%s' % kind]))
like_count = extract_count('up')
dislike_count = extract_count('down')
return {
'id': video_id,
'display_id': display_id,
'url': 'http://speed.20min-tv.ch/%sm.flv' % video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'like_count': like_count,
'dislike_count': dislike_count,
'formats': formats,
}

View File

@ -84,12 +84,27 @@ class UOLIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
if not video_id.isdigit():
embed_page = self._download_webpage('https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id, video_id)
video_id = self._search_regex(r'mediaId=(\d+)', embed_page, 'media id')
media_id = None
if video_id.isdigit():
media_id = video_id
if not media_id:
embed_page = self._download_webpage(
'https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id,
video_id, 'Downloading embed page', fatal=False)
if embed_page:
media_id = self._search_regex(
(r'uol\.com\.br/(\d+)', r'mediaId=(\d+)'),
embed_page, 'media id', default=None)
if not media_id:
webpage = self._download_webpage(url, video_id)
media_id = self._search_regex(r'mediaId=(\d+)', webpage, 'media id')
video_data = self._download_json(
'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % video_id,
video_id)['item']
'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % media_id,
media_id)['item']
title = video_data['title']
query = {
@ -118,7 +133,7 @@ class UOLIE(InfoExtractor):
tags.append(tag_description)
return {
'id': video_id,
'id': media_id,
'title': title,
'description': clean_html(video_data.get('desMedia')),
'thumbnail': video_data.get('thumbnail'),

View File

@ -69,6 +69,13 @@ class UstreamIE(InfoExtractor):
},
}]
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
if mobj is not None:
return mobj.group('url')
def _get_stream_info(self, url, video_id, app_id_ver, extra_note=None):
def num_to_hex(n):
return hex(n)[2:]

View File

@ -206,7 +206,7 @@ class VevoIE(VevoBaseIE):
note='Retrieving oauth token',
errnote='Unable to retrieve oauth token')
if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage:
if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage):
self.raise_geo_restricted(
'%s said: This page is currently unavailable in your region' % self.IE_NAME)

View File

@ -254,7 +254,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_id': 'user18948128',
'uploader': 'Jaime Marquínez Ferrándiz',
'duration': 10,
'description': 'This is "youtube-dl password protected test video" by on Vimeo, the home for high quality videos and the people who love them.',
'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
},
'params': {
'videopassword': 'youtube-dl',
@ -306,7 +306,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
{
# contains original format
'url': 'https://vimeo.com/33951933',
'md5': '2d9f5475e0537f013d0073e812ab89e6',
'md5': '53c688fa95a55bf4b7293d37a89c5c53',
'info_dict': {
'id': '33951933',
'ext': 'mp4',
@ -324,7 +324,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'url': 'https://vimeo.com/channels/tributes/6213729',
'info_dict': {
'id': '6213729',
'ext': 'mp4',
'ext': 'mov',
'title': 'Vimeo Tribute: The Shining',
'uploader': 'Casey Donahue',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
@ -338,7 +338,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'expected_warnings': ['Unable to download JSON metadata'],
},
{
# redirects to ondemand extractor and should be passed throught it
# redirects to ondemand extractor and should be passed through it
# for successful extraction
'url': 'https://vimeo.com/73445910',
'info_dict': {
@ -629,6 +629,9 @@ class VimeoOndemandIE(VimeoBaseInfoExtractor):
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
'uploader_id': 'gumfilms',
},
'params': {
'format': 'best[protocol=https]',
},
}, {
# requires Referer to be passed along with og:video:url
'url': 'https://vimeo.com/ondemand/36938/126682985',
@ -727,12 +730,12 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
# Try extracting href first since not all videos are available via
# short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
clips = re.findall(
r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)', webpage)
r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
if clips:
for video_id, video_url in clips:
for video_id, video_url, video_title in clips:
yield self.url_result(
compat_urlparse.urljoin(base_url, video_url),
VimeoIE.ie_key(), video_id=video_id)
VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
# More relaxed fallback
else:
for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):

View File

@ -16,7 +16,9 @@ class XiamiBaseIE(InfoExtractor):
return webpage
def _extract_track(self, track, track_id=None):
title = track['title']
track_name = track.get('songName') or track.get('name') or track['subName']
artist = track.get('artist') or track.get('artist_name') or track.get('singers')
title = '%s - %s' % (artist, track_name) if artist else track_name
track_url = self._decrypt(track['location'])
subtitles = {}
@ -31,9 +33,10 @@ class XiamiBaseIE(InfoExtractor):
'thumbnail': track.get('pic') or track.get('album_pic'),
'duration': int_or_none(track.get('length')),
'creator': track.get('artist', '').split(';')[0],
'track': title,
'album': track.get('album_name'),
'artist': track.get('artist'),
'track': track_name,
'track_number': int_or_none(track.get('track')),
'album': track.get('album_name') or track.get('title'),
'artist': artist,
'subtitles': subtitles,
}
@ -68,14 +71,14 @@ class XiamiBaseIE(InfoExtractor):
class XiamiSongIE(XiamiBaseIE):
IE_NAME = 'xiami:song'
IE_DESC = '虾米音乐'
_VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.xiami.com/song/1775610518',
'md5': '521dd6bea40fd5c9c69f913c232cb57e',
'info_dict': {
'id': '1775610518',
'ext': 'mp3',
'title': 'Woman',
'title': 'HONNE - Woman',
'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
'duration': 265,
'creator': 'HONNE',
@ -95,7 +98,7 @@ class XiamiSongIE(XiamiBaseIE):
'info_dict': {
'id': '1775256504',
'ext': 'mp3',
'title': '悟空',
'title': '戴荃 - 悟空',
'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
'duration': 200,
'creator': '戴荃',
@ -109,6 +112,26 @@ class XiamiSongIE(XiamiBaseIE):
},
},
'skip': 'Georestricted',
}, {
'url': 'http://www.xiami.com/song/1775953850',
'info_dict': {
'id': '1775953850',
'ext': 'mp3',
'title': 'До Скону - Чума Пожирает Землю',
'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
'duration': 683,
'creator': 'До Скону',
'track': 'Чума Пожирает Землю',
'track_number': 7,
'album': 'Ад',
'artist': 'До Скону',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.xiami.com/song/xLHGwgd07a1',
'only_matching': True,
}]
def _real_extract(self, url):
@ -124,7 +147,7 @@ class XiamiPlaylistBaseIE(XiamiBaseIE):
class XiamiAlbumIE(XiamiPlaylistBaseIE):
IE_NAME = 'xiami:album'
IE_DESC = '虾米音乐 - 专辑'
_VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[^/?#&]+)'
_TYPE = '1'
_TESTS = [{
'url': 'http://www.xiami.com/album/2100300444',
@ -136,28 +159,34 @@ class XiamiAlbumIE(XiamiPlaylistBaseIE):
}, {
'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
'only_matching': True,
}, {
'url': 'http://www.xiami.com/album/URVDji2a506',
'only_matching': True,
}]
class XiamiArtistIE(XiamiPlaylistBaseIE):
IE_NAME = 'xiami:artist'
IE_DESC = '虾米音乐 - 歌手'
_VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[^/?#&]+)'
_TYPE = '2'
_TEST = {
_TESTS = [{
'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
'info_dict': {
'id': '2132',
},
'playlist_count': 20,
'skip': 'Georestricted',
}
}, {
'url': 'http://www.xiami.com/artist/bC5Tk2K6eb99',
'only_matching': True,
}]
class XiamiCollectionIE(XiamiPlaylistBaseIE):
IE_NAME = 'xiami:collection'
IE_DESC = '虾米音乐 - 精选集'
_VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[^/?#&]+)'
_TYPE = '3'
_TEST = {
'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',

View File

@ -2,44 +2,37 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import urljoin
class YourUploadIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?
(?:yourupload\.com/watch|
embed\.yourupload\.com|
embed\.yucache\.net
)/(?P<id>[A-Za-z0-9]+)
'''
_TESTS = [
{
'url': 'http://yourupload.com/watch/14i14h',
'md5': '5e2c63385454c557f97c4c4131a393cd',
'info_dict': {
'id': '14i14h',
'ext': 'mp4',
'title': 'BigBuckBunny_320x180.mp4',
'thumbnail': r're:^https?://.*\.jpe?g',
}
},
{
'url': 'http://embed.yourupload.com/14i14h',
'only_matching': True,
},
{
'url': 'http://embed.yucache.net/14i14h?client_file_id=803349',
'only_matching': True,
},
]
_VALID_URL = r'https?://(?:www\.)?(?:yourupload\.com/(?:watch|embed)|embed\.yourupload\.com)/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'http://yourupload.com/watch/14i14h',
'md5': '5e2c63385454c557f97c4c4131a393cd',
'info_dict': {
'id': '14i14h',
'ext': 'mp4',
'title': 'BigBuckBunny_320x180.mp4',
'thumbnail': r're:^https?://.*\.jpe?g',
}
}, {
'url': 'http://www.yourupload.com/embed/14i14h',
'only_matching': True,
}, {
'url': 'http://embed.yourupload.com/14i14h',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
embed_url = 'http://embed.yucache.net/{0:}'.format(video_id)
embed_url = 'http://www.yourupload.com/embed/%s' % video_id
webpage = self._download_webpage(embed_url, video_id)
title = self._og_search_title(webpage)
video_url = self._og_search_video_url(webpage)
video_url = urljoin(embed_url, self._og_search_video_url(webpage))
thumbnail = self._og_search_thumbnail(webpage, default=None)
return {

View File

@ -316,6 +316,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
'138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
'160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
'212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
'264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
'298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
'299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
@ -862,6 +863,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'params': {
'skip_download': True,
},
},
{
# YouTube Red video with episode data
'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
'info_dict': {
'id': 'iqKdEhx-dD4',
'ext': 'mp4',
'title': 'Isolation - Mind Field (Ep 1)',
'description': 'md5:3a72f23c086a1496c9e2c54a25fa0822',
'upload_date': '20170118',
'uploader': 'Vsauce',
'uploader_id': 'Vsauce',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
'license': 'Standard YouTube License',
'series': 'Mind Field',
'season_number': 1,
'episode_number': 1,
},
'params': {
'skip_download': True,
},
'expected_warnings': [
'Skipping DASH manifest',
],
},
{
# itag 212
'url': '1t24XAntNCY',
'only_matching': True,
}
]
@ -1448,6 +1478,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
else:
video_alt_title = video_creator = None
m_episode = re.search(
r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
video_webpage)
if m_episode:
series = m_episode.group('series')
season_number = int(m_episode.group('season'))
episode_number = int(m_episode.group('episode'))
else:
series = season_number = episode_number = None
m_cat_container = self._search_regex(
r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
video_webpage, 'categories', default=None)
@ -1737,6 +1777,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'is_live': is_live,
'start_time': start_time,
'end_time': end_time,
'series': series,
'season_number': season_number,
'episode_number': episode_number,
}
@ -1813,6 +1856,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
'title': 'YDL_Empty_List',
},
'playlist_count': 0,
'skip': 'This playlist is private',
}, {
'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
@ -1844,6 +1888,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
},
'playlist_count': 2,
'skip': 'This playlist is private',
}, {
'note': 'embedded',
'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
@ -1955,14 +2000,18 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
url = self._TEMPLATE_URL % playlist_id
page = self._download_webpage(url, playlist_id)
for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
# the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
match = match.strip()
# Check if the playlist exists or is private
if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match):
raise ExtractorError(
'The playlist doesn\'t exist or is private, use --username or '
'--netrc to access it.',
expected=True)
mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
if mobj:
reason = mobj.group('reason')
message = 'This playlist %s' % reason
if 'private' in reason:
message += ', use --username or --netrc to access it'
message += '.'
raise ExtractorError(message, expected=True)
elif re.match(r'[^<]*Invalid parameters[^<]*', match):
raise ExtractorError(
'Invalid parameters. Maybe URL is incorrect.',

View File

@ -213,7 +213,7 @@ class JSInterpreter(object):
def extract_object(self, objname):
obj = {}
obj_m = re.search(
(r'(?:var\s+)?%s\s*=\s*\{' % re.escape(objname)) +
(r'(?<!this\.)%s\s*=\s*\{' % re.escape(objname)) +
r'\s*(?P<fields>([a-zA-Z$0-9]+\s*:\s*function\(.*?\)\s*\{.*?\}(?:,\s*)?)*)' +
r'\}\s*;',
self.code)

View File

@ -751,7 +751,7 @@ def parseOpts(overrideArguments=None):
help='Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
postproc.add_option(
'--audio-format', metavar='FORMAT', dest='audioformat', default='best',
help='Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default')
help='Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default; No effect without -x')
postproc.add_option(
'--audio-quality', metavar='QUALITY',
dest='audioquality', default='5',
@ -867,7 +867,7 @@ def parseOpts(overrideArguments=None):
if '--ignore-config' not in system_conf:
user_conf = _readUserConf()
argv = system_conf + user_conf + command_line_conf
argv = system_conf + user_conf + custom_conf + command_line_conf
opts, args = parser.parse_args(argv)
if opts.verbose:
for conf_label, conf in (

View File

@ -128,7 +128,13 @@ DATE_FORMATS = (
'%d %B %Y',
'%d %b %Y',
'%B %d %Y',
'%B %dst %Y',
'%B %dnd %Y',
'%B %dth %Y',
'%b %d %Y',
'%b %dst %Y',
'%b %dnd %Y',
'%b %dth %Y',
'%b %dst %Y %I:%M',
'%b %dnd %Y %I:%M',
'%b %dth %Y %I:%M',

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2017.01.05'
__version__ = '2017.01.22'