Merge branch 'master' into jsinterp
# Conflicts: # youtube_dl/extractor/openload.py
This commit is contained in:
commit
c5c1273ba5
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 *2016.11.18*. 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 Issues with outdated version will be rejected.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 **2016.11.18**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.12.09*. 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 Issues with outdated version will be rejected.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 **2016.12.09**
|
||||
|
||||
### 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 2016.11.18
|
||||
[debug] youtube-dl version 2016.12.09
|
||||
[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: {}
|
||||
|
1
.gitignore
vendored
1
.gitignore
vendored
@ -33,6 +33,7 @@ updates_key.pem
|
||||
*.wav
|
||||
*.ape
|
||||
*.mkv
|
||||
*.swf
|
||||
*.part
|
||||
*.swp
|
||||
test/testdata
|
||||
|
58
ChangeLog
58
ChangeLog
@ -1,8 +1,60 @@
|
||||
version <unreleased>
|
||||
version 2016.12.09
|
||||
|
||||
Core
|
||||
* [socks] Fix error reporting (#11355)
|
||||
|
||||
Extractors
|
||||
- [Crunchyroll] ScaledBorderAndShadow are removed from ASS subtitles
|
||||
(#8207, #9028)
|
||||
* [openload] Fix extraction (#10408)
|
||||
* [pandoratv] Fix extraction (#11023)
|
||||
+ [telebruxelles] Add support for emission URLs
|
||||
* [telebruxelles] Extract all formats
|
||||
+ [bloomberg] Add another video id regular expression (#11371)
|
||||
* [fusion] Update ooyala id regular expression (#11364)
|
||||
+ [1tv] Add support for playlists (#11335)
|
||||
* [1tv] Improve extraction (#11335)
|
||||
+ [aenetworks] Extract more formats (#11321)
|
||||
+ [thisoldhouse] Recognize /tv-episode/ URLs (#11271)
|
||||
|
||||
version 2016.12.01
|
||||
|
||||
Extractors
|
||||
* [soundcloud] Update client id (#11327)
|
||||
* [ruutu] Detect DRM protected videos
|
||||
+ [liveleak] Add support for youtube embeds (#10688)
|
||||
* [spike] Fix full episodes support (#11312)
|
||||
* [comedycentral] Fix full episodes support
|
||||
* [normalboots] Rewrite in terms of JWPlatform (#11184)
|
||||
* [teamfourstar] Rewrite in terms of JWPlatform (#11184)
|
||||
- [screenwavemedia] Remove extractor (#11184)
|
||||
|
||||
|
||||
version 2016.11.27
|
||||
|
||||
Extractors
|
||||
+ [webcaster] Add support for webcaster.pro
|
||||
+ [azubu] Add support for azubu.uol.com.br (#11305)
|
||||
* [viki] Prefer hls formats
|
||||
* [viki] Fix rtmp formats extraction (#11255)
|
||||
* [puls4] Relax URL regular expression (#11267)
|
||||
* [vevo] Improve artist extraction (#10911)
|
||||
* [mitele] Relax URL regular expression and extract more metadata (#11244)
|
||||
+ [cbslocal] Recognize New York site (#11285)
|
||||
+ [youtube:playlist] Pass disable_polymer in URL query (#11193)
|
||||
|
||||
|
||||
version 2016.11.22
|
||||
|
||||
Extractors
|
||||
* [hellporno] Fix video extension extraction (#11247)
|
||||
+ [hellporno] Add support for hellporno.net (#11247)
|
||||
+ [amcnetworks] Recognize more BBC America URLs (#11263)
|
||||
* [funnyordie] Improve extraction (#11208)
|
||||
* [extractor/generic] Improve limelight embeds support
|
||||
- [crunchyroll] Remove ScaledBorderAndShadow from ASS subtitles (#8207, #9028)
|
||||
* [bandcamp] Fix free downloads extraction and extract all formats (#11067)
|
||||
* [twitter:card] Relax URL regular expression (#11225)
|
||||
+ [tvanouvelles] Add support for tvanouvelles.ca (#10616)
|
||||
|
||||
|
||||
version 2016.11.18
|
||||
|
||||
|
2
Makefile
2
Makefile
@ -1,7 +1,7 @@
|
||||
all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
|
||||
|
||||
clean:
|
||||
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
|
||||
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
|
||||
find . -name "*.pyc" -delete
|
||||
find . -name "*.class" -delete
|
||||
|
||||
|
@ -664,7 +664,7 @@ $ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best'
|
||||
# Download best format available but not better that 480p
|
||||
$ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]'
|
||||
|
||||
# Download best video only format but no bigger that 50 MB
|
||||
# Download best video only format but no bigger than 50 MB
|
||||
$ youtube-dl -f 'best[filesize<50M]'
|
||||
|
||||
# Download best format available via direct link over HTTP/HTTPS protocol
|
||||
|
@ -158,6 +158,7 @@
|
||||
- **CollegeRama**
|
||||
- **ComCarCoff**
|
||||
- **ComedyCentral**
|
||||
- **ComedyCentralFullEpisodes**
|
||||
- **ComedyCentralShortname**
|
||||
- **ComedyCentralTV**
|
||||
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
|
||||
@ -643,7 +644,6 @@
|
||||
- **Screencast**
|
||||
- **ScreencastOMatic**
|
||||
- **ScreenJunkies**
|
||||
- **ScreenwaveMedia**
|
||||
- **Seeker**
|
||||
- **SenateISVP**
|
||||
- **SendtoNews**
|
||||
@ -715,7 +715,7 @@
|
||||
- **teachertube:user:collection**: teachertube.com user and collection videos
|
||||
- **TeachingChannel**
|
||||
- **Teamcoco**
|
||||
- **TeamFour**
|
||||
- **TeamFourStar**
|
||||
- **TechTalks**
|
||||
- **techtv.mit.edu**
|
||||
- **ted**
|
||||
@ -771,6 +771,8 @@
|
||||
- **TV2Article**
|
||||
- **TV3**
|
||||
- **TV4**: tv4.se and tv4play.se
|
||||
- **TVANouvelles**
|
||||
- **TVANouvellesArticle**
|
||||
- **TVC**
|
||||
- **TVCArticle**
|
||||
- **tvigle**: Интернет-телевидение Tvigle.ru
|
||||
@ -880,6 +882,8 @@
|
||||
- **WatchIndianPorn**: Watch Indian Porn
|
||||
- **WDR**
|
||||
- **wdr:mobile**
|
||||
- **Webcaster**
|
||||
- **WebcasterFeed**
|
||||
- **WebOfStories**
|
||||
- **WebOfStoriesPlaylist**
|
||||
- **WeiqiTV**: WQTV
|
||||
|
@ -26,7 +26,7 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
|
||||
'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
|
||||
'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
|
||||
'info_dict': {
|
||||
'id': '22253814',
|
||||
'ext': 'mp4',
|
||||
@ -99,7 +99,7 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
|
||||
query = {
|
||||
'mbr': 'true',
|
||||
'assetTypes': 'medium_video_s3'
|
||||
'assetTypes': 'high_video_s3'
|
||||
}
|
||||
video_id = self._html_search_meta('aetn:VideoID', webpage)
|
||||
media_url = self._search_regex(
|
||||
@ -155,7 +155,7 @@ class HistoryTopicIE(AENetworksBaseIE):
|
||||
'id': 'world-war-i-history',
|
||||
'title': 'World War I History',
|
||||
},
|
||||
'playlist_mincount': 24,
|
||||
'playlist_mincount': 23,
|
||||
}, {
|
||||
'url': 'http://www.history.com/topics/world-war-i-history/videos',
|
||||
'only_matching': True,
|
||||
@ -193,7 +193,8 @@ class HistoryTopicIE(AENetworksBaseIE):
|
||||
return self.theplatform_url_result(
|
||||
release_url, video_id, {
|
||||
'mbr': 'true',
|
||||
'switch': 'hls'
|
||||
'switch': 'hls',
|
||||
'assetTypes': 'high_video_ak',
|
||||
})
|
||||
else:
|
||||
webpage = self._download_webpage(url, topic_id)
|
||||
@ -203,6 +204,7 @@ class HistoryTopicIE(AENetworksBaseIE):
|
||||
entries.append(self.theplatform_url_result(
|
||||
video_attributes['data-release-url'], video_attributes['data-id'], {
|
||||
'mbr': 'true',
|
||||
'switch': 'hls'
|
||||
'switch': 'hls',
|
||||
'assetTypes': 'high_video_ak',
|
||||
}))
|
||||
return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))
|
||||
|
@ -10,7 +10,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class AMCNetworksIE(ThePlatformIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?season-\d+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?[^/]+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
|
||||
'md5': '',
|
||||
@ -41,6 +41,9 @@ class AMCNetworksIE(ThePlatformIE):
|
||||
}, {
|
||||
'url': 'http://www.ifc.com/movies/chaos',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -11,7 +11,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class AzubuIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?azubu\.tv/[^/]+#!/play/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/[^/]+#!/play/(?P<id>\d+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1',
|
||||
@ -103,12 +103,15 @@ class AzubuIE(InfoExtractor):
|
||||
|
||||
|
||||
class AzubuLiveIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?azubu\.tv/(?P<id>[^/]+)$'
|
||||
_VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/(?P<id>[^/]+)$'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://www.azubu.tv/MarsTVMDLen',
|
||||
'only_matching': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://azubu.uol.com.br/adolfz',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
user = self._match_id(url)
|
||||
|
@ -45,7 +45,8 @@ class BloombergIE(InfoExtractor):
|
||||
name = self._match_id(url)
|
||||
webpage = self._download_webpage(url, name)
|
||||
video_id = self._search_regex(
|
||||
r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
|
||||
(r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
r'videoId\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
|
||||
webpage, 'id', group='url', default=None)
|
||||
if not video_id:
|
||||
bplayer_data = self._parse_json(self._search_regex(
|
||||
|
@ -4,11 +4,14 @@ from __future__ import unicode_literals
|
||||
from .anvato import AnvatoIE
|
||||
from .sendtonews import SendtoNewsIE
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import unified_timestamp
|
||||
from ..utils import (
|
||||
parse_iso8601,
|
||||
unified_timestamp,
|
||||
)
|
||||
|
||||
|
||||
class CBSLocalIE(AnvatoIE):
|
||||
_VALID_URL = r'https?://[a-z]+\.cbslocal\.com/\d+/\d+/\d+/(?P<id>[0-9a-z-]+)'
|
||||
_VALID_URL = r'https?://[a-z]+\.cbslocal\.com/(?:\d+/\d+/\d+|video)/(?P<id>[0-9a-z-]+)'
|
||||
|
||||
_TESTS = [{
|
||||
# Anvato backend
|
||||
@ -49,6 +52,31 @@ class CBSLocalIE(AnvatoIE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://newyork.cbslocal.com/video/3580809-a-very-blue-anniversary/',
|
||||
'info_dict': {
|
||||
'id': '3580809',
|
||||
'ext': 'mp4',
|
||||
'title': 'A Very Blue Anniversary',
|
||||
'description': 'CBS2’s Cindy Hsu has more.',
|
||||
'thumbnail': 're:^https?://.*',
|
||||
'timestamp': 1479962220,
|
||||
'upload_date': '20161124',
|
||||
'uploader': 'CBS',
|
||||
'subtitles': {
|
||||
'en': 'mincount:5',
|
||||
},
|
||||
'categories': [
|
||||
'Stations\\Spoken Word\\WCBSTV',
|
||||
'Syndication\\AOL',
|
||||
'Syndication\\MSN',
|
||||
'Syndication\\NDN',
|
||||
'Syndication\\Yahoo',
|
||||
'Content\\News',
|
||||
'Content\\News\\Local News',
|
||||
],
|
||||
'tags': ['CBS 2 News Weekends', 'Cindy Hsu', 'Blue Man Group'],
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -64,8 +92,11 @@ class CBSLocalIE(AnvatoIE):
|
||||
info_dict = self._extract_anvato_videos(webpage, display_id)
|
||||
|
||||
time_str = self._html_search_regex(
|
||||
r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False)
|
||||
timestamp = unified_timestamp(time_str)
|
||||
r'class="entry-date">([^<]+)<', webpage, 'released date', default=None)
|
||||
if time_str:
|
||||
timestamp = unified_timestamp(time_str)
|
||||
else:
|
||||
timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage))
|
||||
|
||||
info_dict.update({
|
||||
'display_id': display_id,
|
||||
|
@ -6,7 +6,7 @@ from .common import InfoExtractor
|
||||
|
||||
class ComedyCentralIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
|
||||
(video-clips|episodes|cc-studios|video-collections|full-episodes|shows)
|
||||
(video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
|
||||
/(?P<title>.*)'''
|
||||
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
|
||||
|
||||
@ -27,6 +27,40 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
|
||||
}]
|
||||
|
||||
|
||||
class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
|
||||
(?:full-episodes|shows(?=/[^/]+/full-episodes))
|
||||
/(?P<id>[^?]+)'''
|
||||
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
|
||||
'info_dict': {
|
||||
'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
|
||||
'title': 'November 28, 2016 - Ryan Speedo Green',
|
||||
},
|
||||
'playlist_count': 4,
|
||||
}, {
|
||||
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
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)
|
||||
return videos_info
|
||||
|
||||
|
||||
class ToshIE(MTVServicesInfoExtractor):
|
||||
IE_DESC = 'Tosh.0'
|
||||
_VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
|
||||
|
@ -180,6 +180,7 @@ from .cnn import (
|
||||
from .coub import CoubIE
|
||||
from .collegerama import CollegeRamaIE
|
||||
from .comedycentral import (
|
||||
ComedyCentralFullEpisodesIE,
|
||||
ComedyCentralIE,
|
||||
ComedyCentralShortnameIE,
|
||||
ComedyCentralTVIE,
|
||||
@ -804,7 +805,6 @@ from .scivee import SciVeeIE
|
||||
from .screencast import ScreencastIE
|
||||
from .screencastomatic import ScreencastOMaticIE
|
||||
from .screenjunkies import ScreenJunkiesIE
|
||||
from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
|
||||
from .seeker import SeekerIE
|
||||
from .senateisvp import SenateISVPIE
|
||||
from .sendtonews import SendtoNewsIE
|
||||
@ -897,6 +897,7 @@ from .teachertube import (
|
||||
)
|
||||
from .teachingchannel import TeachingChannelIE
|
||||
from .teamcoco import TeamcocoIE
|
||||
from .teamfourstar import TeamFourStarIE
|
||||
from .techtalks import TechTalksIE
|
||||
from .ted import TEDIE
|
||||
from .tele13 import Tele13IE
|
||||
@ -1121,6 +1122,10 @@ from .wdr import (
|
||||
WDRIE,
|
||||
WDRMobileIE,
|
||||
)
|
||||
from .webcaster import (
|
||||
WebcasterIE,
|
||||
WebcasterFeedIE,
|
||||
)
|
||||
from .webofstories import (
|
||||
WebOfStoriesIE,
|
||||
WebOfStoriesPlaylistIE,
|
||||
|
@ -2,7 +2,10 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
qualities,
|
||||
@ -22,8 +25,7 @@ class FirstTVIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '40049',
|
||||
'ext': 'mp4',
|
||||
'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
|
||||
'description': 'md5:36a39c1d19618fec57d12efe212a8370',
|
||||
'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
|
||||
'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
|
||||
'upload_date': '20150212',
|
||||
'duration': 2694,
|
||||
@ -34,8 +36,7 @@ class FirstTVIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '364746',
|
||||
'ext': 'mp4',
|
||||
'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
|
||||
'description': 'md5:a242eea0031fd180a4497d52640a9572',
|
||||
'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
|
||||
'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
|
||||
'upload_date': '20160407',
|
||||
'duration': 179,
|
||||
@ -44,6 +45,17 @@ class FirstTVIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.1tv.ru/news/issue/2016-12-01/14:00',
|
||||
'info_dict': {
|
||||
'id': '14:00',
|
||||
'title': 'Выпуск новостей в 14:00 1 декабря 2016 года. Новости. Первый канал',
|
||||
'description': 'md5:2e921b948f8c1ff93901da78ebdb1dfd',
|
||||
},
|
||||
'playlist_count': 13,
|
||||
}, {
|
||||
'url': 'http://www.1tv.ru/shows/tochvtoch-supersezon/vystupleniya/evgeniy-dyatlov-vladimir-vysockiy-koni-priveredlivye-toch-v-toch-supersezon-fragment-vypuska-ot-06-11-2016',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -51,43 +63,66 @@ class FirstTVIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
playlist_url = compat_urlparse.urljoin(url, self._search_regex(
|
||||
r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
|
||||
r'data-playlist-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
webpage, 'playlist url', group='url'))
|
||||
|
||||
item = self._download_json(playlist_url, display_id)[0]
|
||||
video_id = item['id']
|
||||
quality = qualities(('ld', 'sd', 'hd', ))
|
||||
formats = []
|
||||
for f in item.get('mbr', []):
|
||||
src = f.get('src')
|
||||
if not src:
|
||||
continue
|
||||
fname = f.get('name')
|
||||
formats.append({
|
||||
'url': src,
|
||||
'format_id': fname,
|
||||
'quality': quality(fname),
|
||||
parsed_url = compat_urlparse.urlparse(playlist_url)
|
||||
qs = compat_urlparse.parse_qs(parsed_url.query)
|
||||
item_ids = qs.get('videos_ids[]') or qs.get('news_ids[]')
|
||||
|
||||
items = self._download_json(playlist_url, display_id)
|
||||
|
||||
if item_ids:
|
||||
items = [
|
||||
item for item in items
|
||||
if item.get('uid') and compat_str(item['uid']) in item_ids]
|
||||
else:
|
||||
items = [items[0]]
|
||||
|
||||
entries = []
|
||||
QUALITIES = ('ld', 'sd', 'hd', )
|
||||
|
||||
for item in items:
|
||||
title = item['title']
|
||||
quality = qualities(QUALITIES)
|
||||
formats = []
|
||||
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))
|
||||
formats.append({
|
||||
'url': src,
|
||||
'format_id': f.get('name'),
|
||||
'tbr': tbr,
|
||||
'quality': quality(f.get('name')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)
|
||||
duration = int_or_none(item.get('duration') or self._html_search_meta(
|
||||
'video:duration', webpage, 'video duration', fatal=False))
|
||||
upload_date = unified_strdate(self._html_search_meta(
|
||||
'ya:ovs:upload_date', webpage, 'upload date', default=None))
|
||||
|
||||
entries.append({
|
||||
'id': compat_str(item.get('id') or item['uid']),
|
||||
'thumbnail': thumbnail,
|
||||
'title': title,
|
||||
'upload_date': upload_date,
|
||||
'duration': int_or_none(duration),
|
||||
'formats': formats
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._html_search_regex(
|
||||
(r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
|
||||
r"'title'\s*:\s*'([^']+)'"),
|
||||
webpage, 'title', default=None) or item['title']
|
||||
webpage, 'title', default=None) or self._og_search_title(
|
||||
webpage, default=None)
|
||||
description = self._html_search_regex(
|
||||
r'<div class="descr">\s*<div> </div>\s*<p>([^<]*)</p></div>',
|
||||
webpage, 'description', default=None) or self._html_search_meta(
|
||||
'description', webpage, 'description')
|
||||
duration = int_or_none(self._html_search_meta(
|
||||
'video:duration', webpage, 'video duration', fatal=False))
|
||||
upload_date = unified_strdate(self._html_search_meta(
|
||||
'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
|
||||
'description', webpage, 'description', default=None)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
|
||||
'title': title,
|
||||
'description': description,
|
||||
'upload_date': upload_date,
|
||||
'duration': int_or_none(duration),
|
||||
'formats': formats
|
||||
}
|
||||
return self.playlist_result(entries, display_id, title, description)
|
||||
|
@ -28,6 +28,9 @@ class FunnyOrDieIE(InfoExtractor):
|
||||
'description': 'Please use this to sell something. www.jonlajoie.com',
|
||||
'thumbnail': 're:^http:.*\.jpg$',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
|
||||
'only_matching': True,
|
||||
@ -51,19 +54,45 @@ class FunnyOrDieIE(InfoExtractor):
|
||||
|
||||
formats = []
|
||||
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False)
|
||||
source_formats = list(filter(
|
||||
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
|
||||
m3u8_formats))
|
||||
|
||||
bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)]
|
||||
bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)]
|
||||
bitrates.sort()
|
||||
|
||||
for bitrate in bitrates:
|
||||
for link in links:
|
||||
formats.append({
|
||||
'url': self._proto_relative_url('%s%d.%s' % (link[0], bitrate, link[1])),
|
||||
'format_id': '%s-%d' % (link[1], bitrate),
|
||||
'vbr': bitrate,
|
||||
})
|
||||
if source_formats:
|
||||
self._sort_formats(source_formats)
|
||||
|
||||
for bitrate, f in zip(bitrates, source_formats or [{}] * len(bitrates)):
|
||||
for path, ext in links:
|
||||
ff = f.copy()
|
||||
if ff:
|
||||
if ext != 'mp4':
|
||||
ff = dict(
|
||||
[(k, v) for k, v in ff.items()
|
||||
if k in ('height', 'width', 'format_id')])
|
||||
ff.update({
|
||||
'format_id': ff['format_id'].replace('hls', ext),
|
||||
'ext': ext,
|
||||
'protocol': 'http',
|
||||
})
|
||||
else:
|
||||
ff.update({
|
||||
'format_id': '%s-%d' % (ext, bitrate),
|
||||
'vbr': bitrate,
|
||||
})
|
||||
ff['url'] = self._proto_relative_url(
|
||||
'%s%d.%s' % (path, bitrate, ext))
|
||||
formats.append(ff)
|
||||
self._check_formats(formats, video_id)
|
||||
|
||||
formats.extend(m3u8_formats)
|
||||
self._sort_formats(
|
||||
formats, field_preference=('height', 'width', 'tbr', 'format_id'))
|
||||
|
||||
subtitles = {}
|
||||
for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage):
|
||||
|
@ -29,7 +29,7 @@ class FusionIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
ooyala_code = self._search_regex(
|
||||
r'data-video-id=(["\'])(?P<code>.+?)\1',
|
||||
r'data-ooyala-id=(["\'])(?P<code>(?:(?!\1).)+)\1',
|
||||
webpage, 'ooyala code', group='code')
|
||||
|
||||
return OoyalaIE._build_url_result(ooyala_code)
|
||||
|
@ -56,10 +56,10 @@ from .dailymotion import (
|
||||
)
|
||||
from .onionstudios import OnionStudiosIE
|
||||
from .viewlift import ViewLiftEmbedIE
|
||||
from .screenwavemedia import ScreenwaveMediaIE
|
||||
from .mtv import MTVServicesEmbeddedIE
|
||||
from .pladform import PladformIE
|
||||
from .videomore import VideomoreIE
|
||||
from .webcaster import WebcasterFeedIE
|
||||
from .googledrive import GoogleDriveIE
|
||||
from .jwplatform import JWPlatformIE
|
||||
from .digiteka import DigitekaIE
|
||||
@ -1189,16 +1189,6 @@ class GenericIE(InfoExtractor):
|
||||
'duration': 248.667,
|
||||
},
|
||||
},
|
||||
# ScreenwaveMedia embed
|
||||
{
|
||||
'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
|
||||
'md5': '24ace5baba0d35d55c6810b51f34e9e0',
|
||||
'info_dict': {
|
||||
'id': 'cinemasnob-55d26273809dd',
|
||||
'ext': 'mp4',
|
||||
'title': 'cinemasnob',
|
||||
},
|
||||
},
|
||||
# BrightcoveInPageEmbed embed
|
||||
{
|
||||
'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
|
||||
@ -2140,6 +2130,11 @@ class GenericIE(InfoExtractor):
|
||||
if videomore_url:
|
||||
return self.url_result(videomore_url)
|
||||
|
||||
# Look for Webcaster embeds
|
||||
webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
|
||||
if webcaster_url:
|
||||
return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
|
||||
|
||||
# Look for Playwire embeds
|
||||
mobj = re.search(
|
||||
r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
|
||||
@ -2206,11 +2201,6 @@ class GenericIE(InfoExtractor):
|
||||
if jwplatform_url:
|
||||
return self.url_result(jwplatform_url, 'JWPlatform')
|
||||
|
||||
# Look for ScreenwaveMedia embeds
|
||||
mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
|
||||
if mobj is not None:
|
||||
return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
|
||||
|
||||
# Look for Digiteka embeds
|
||||
digiteka_url = DigitekaIE._extract_url(webpage)
|
||||
if digiteka_url:
|
||||
|
@ -6,12 +6,13 @@ from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
js_to_json,
|
||||
remove_end,
|
||||
determine_ext,
|
||||
)
|
||||
|
||||
|
||||
class HellPornoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
|
||||
'md5': '1fee339c610d2049699ef2aa699439f1',
|
||||
'info_dict': {
|
||||
@ -22,7 +23,10 @@ class HellPornoIE(InfoExtractor):
|
||||
'thumbnail': 're:https?://.*\.jpg$',
|
||||
'age_limit': 18,
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'http://hellporno.net/v/186271/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
@ -38,7 +42,7 @@ class HellPornoIE(InfoExtractor):
|
||||
|
||||
video_id = flashvars.get('video_id')
|
||||
thumbnail = flashvars.get('preview_url')
|
||||
ext = flashvars.get('postfix', '.mp4')[1:]
|
||||
ext = determine_ext(flashvars.get('postfix'), 'mp4')
|
||||
|
||||
formats = []
|
||||
for video_url_key in ['video_url', 'video_alt_url']:
|
||||
|
@ -54,6 +54,22 @@ class LiveLeakIE(InfoExtractor):
|
||||
'title': 'Crazy Hungarian tourist films close call waterspout in Croatia',
|
||||
'thumbnail': 're:^https?://.*\.jpg$'
|
||||
}
|
||||
}, {
|
||||
# Covers https://github.com/rg3/youtube-dl/pull/10664#issuecomment-247439521
|
||||
'url': 'http://m.liveleak.com/view?i=763_1473349649',
|
||||
'add_ie': ['Youtube'],
|
||||
'info_dict': {
|
||||
'id': '763_1473349649',
|
||||
'ext': 'mp4',
|
||||
'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty',
|
||||
'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.',
|
||||
'uploader': 'Ziz',
|
||||
'upload_date': '20160908',
|
||||
'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw'
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
@ -87,7 +103,7 @@ class LiveLeakIE(InfoExtractor):
|
||||
else:
|
||||
# Maybe an embed?
|
||||
embed_url = self._search_regex(
|
||||
r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
|
||||
r'<iframe[^>]+src="(https?://(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
|
||||
webpage, 'embed URL')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
@ -107,6 +123,7 @@ class LiveLeakIE(InfoExtractor):
|
||||
'format_note': s.get('label'),
|
||||
'url': s['file'],
|
||||
} for i, s in enumerate(sources)]
|
||||
|
||||
for i, s in enumerate(sources):
|
||||
# Removing '.h264_*.mp4' gives the raw video, which is essentially
|
||||
# the same video without the LiveLeak logo at the top (see
|
||||
|
@ -75,7 +75,7 @@ class MiTeleBaseIE(InfoExtractor):
|
||||
|
||||
class MiTeleIE(InfoExtractor):
|
||||
IE_DESC = 'mitele.es'
|
||||
_VALID_URL = r'https?://(?:www\.)?mitele\.es/programas-tv/(?:[^/]+/)(?P<id>[^/]+)/player'
|
||||
_VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
|
||||
@ -86,7 +86,10 @@ class MiTeleIE(InfoExtractor):
|
||||
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
|
||||
'series': 'Diario de',
|
||||
'season': 'La redacción',
|
||||
'season_number': 14,
|
||||
'season_id': 'diario_de_t14_11981',
|
||||
'episode': 'Programa 144',
|
||||
'episode_number': 3,
|
||||
'thumbnail': 're:(?i)^https?://.*\.jpg$',
|
||||
'duration': 2913,
|
||||
},
|
||||
@ -101,7 +104,10 @@ class MiTeleIE(InfoExtractor):
|
||||
'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
|
||||
'series': 'Cuarto Milenio',
|
||||
'season': 'Temporada 6',
|
||||
'season_number': 6,
|
||||
'season_id': 'cuarto_milenio_t06_12715',
|
||||
'episode': 'Programa 226',
|
||||
'episode_number': 24,
|
||||
'thumbnail': 're:(?i)^https?://.*\.jpg$',
|
||||
'duration': 7313,
|
||||
},
|
||||
@ -109,41 +115,77 @@ class MiTeleIE(InfoExtractor):
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': ['Ooyala'],
|
||||
}, {
|
||||
'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
gigya_url = self._search_regex(r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s*src="([^"]*)">[^>]*</script>', webpage, 'gigya', default=None)
|
||||
gigya_sc = self._download_webpage(compat_urlparse.urljoin(r'http://www.mitele.es/', gigya_url), video_id, 'Downloading gigya script')
|
||||
gigya_url = self._search_regex(
|
||||
r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s+src="([^"]*)">[^>]*</script>',
|
||||
webpage, 'gigya', default=None)
|
||||
gigya_sc = self._download_webpage(
|
||||
compat_urlparse.urljoin('http://www.mitele.es/', gigya_url),
|
||||
video_id, 'Downloading gigya script')
|
||||
|
||||
# Get a appKey/uuid for getting the session key
|
||||
appKey_var = self._search_regex(r'value\("appGridApplicationKey",([0-9a-f]+)\)', gigya_sc, 'appKey variable')
|
||||
appKey = self._search_regex(r'var %s="([0-9a-f]+)"' % appKey_var, gigya_sc, 'appKey')
|
||||
uid = compat_str(uuid.uuid4())
|
||||
session_url = 'https://appgrid-api.cloud.accedo.tv/session?appKey=%s&uuid=%s' % (appKey, uid)
|
||||
session_json = self._download_json(session_url, video_id, 'Downloading session keys')
|
||||
sessionKey = compat_str(session_json['sessionKey'])
|
||||
appKey_var = self._search_regex(
|
||||
r'value\s*\(\s*["\']appGridApplicationKey["\']\s*,\s*([0-9a-f]+)',
|
||||
gigya_sc, 'appKey variable')
|
||||
appKey = self._search_regex(
|
||||
r'var\s+%s\s*=\s*["\']([0-9a-f]+)' % appKey_var, gigya_sc, 'appKey')
|
||||
|
||||
session_json = self._download_json(
|
||||
'https://appgrid-api.cloud.accedo.tv/session',
|
||||
video_id, 'Downloading session keys', query={
|
||||
'appKey': appKey,
|
||||
'uuid': compat_str(uuid.uuid4()),
|
||||
})
|
||||
|
||||
paths = self._download_json(
|
||||
'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration',
|
||||
video_id, 'Downloading paths JSON',
|
||||
query={'sessionKey': compat_str(session_json['sessionKey'])})
|
||||
|
||||
paths_url = 'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration?sessionKey=' + sessionKey
|
||||
paths = self._download_json(paths_url, video_id, 'Downloading paths JSON')
|
||||
ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
|
||||
data_p = (
|
||||
'http://' + ooyala_s['base_url'] + ooyala_s['full_path'] + ooyala_s['provider_id'] +
|
||||
'/docs/' + video_id + '?include_titles=Series,Season&product_name=test&format=full')
|
||||
data = self._download_json(data_p, video_id, 'Downloading data JSON')
|
||||
source = data['hits']['hits'][0]['_source']
|
||||
embedCode = source['offers'][0]['embed_codes'][0]
|
||||
source = self._download_json(
|
||||
'http://%s%s%s/docs/%s' % (
|
||||
ooyala_s['base_url'], ooyala_s['full_path'],
|
||||
ooyala_s['provider_id'], video_id),
|
||||
video_id, 'Downloading data JSON', query={
|
||||
'include_titles': 'Series,Season',
|
||||
'product_name': 'test',
|
||||
'format': 'full',
|
||||
})['hits']['hits'][0]['_source']
|
||||
|
||||
embedCode = source['offers'][0]['embed_codes'][0]
|
||||
titles = source['localizable_titles'][0]
|
||||
|
||||
title = titles.get('title_medium') or titles['title_long']
|
||||
episode = titles['title_sort_name']
|
||||
description = titles['summary_long']
|
||||
titles_series = source['localizable_titles_series'][0]
|
||||
series = titles_series['title_long']
|
||||
titles_season = source['localizable_titles_season'][0]
|
||||
season = titles_season['title_medium']
|
||||
duration = parse_duration(source['videos'][0]['duration'])
|
||||
|
||||
description = titles.get('summary_long') or titles.get('summary_medium')
|
||||
|
||||
def get(key1, key2):
|
||||
value1 = source.get(key1)
|
||||
if not value1 or not isinstance(value1, list):
|
||||
return
|
||||
if not isinstance(value1[0], dict):
|
||||
return
|
||||
return value1[0].get(key2)
|
||||
|
||||
series = get('localizable_titles_series', 'title_medium')
|
||||
|
||||
season = get('localizable_titles_season', 'title_medium')
|
||||
season_number = int_or_none(source.get('season_number'))
|
||||
season_id = source.get('season_id')
|
||||
|
||||
episode = titles.get('title_sort_name')
|
||||
episode_number = int_or_none(source.get('episode_number'))
|
||||
|
||||
duration = parse_duration(get('videos', 'duration'))
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
@ -154,7 +196,10 @@ class MiTeleIE(InfoExtractor):
|
||||
'description': description,
|
||||
'series': series,
|
||||
'season': season,
|
||||
'season_number': season_number,
|
||||
'season_id': season_id,
|
||||
'episode': episode,
|
||||
'episode_number': episode_number,
|
||||
'duration': duration,
|
||||
'thumbnail': source['images'][0]['url'],
|
||||
'thumbnail': get('images', 'url'),
|
||||
}
|
||||
|
@ -13,6 +13,7 @@ from ..utils import (
|
||||
fix_xml_ampersands,
|
||||
float_or_none,
|
||||
HEADRequest,
|
||||
NO_DEFAULT,
|
||||
RegexNotFoundError,
|
||||
sanitized_Request,
|
||||
strip_or_none,
|
||||
@ -201,7 +202,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
[self._get_video_info(item) for item in idoc.findall('.//item')],
|
||||
playlist_title=title, playlist_description=description)
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
def _extract_mgid(self, webpage, default=NO_DEFAULT):
|
||||
try:
|
||||
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
|
||||
# or http://media.mtvnservices.com/{mgid}
|
||||
@ -221,7 +222,7 @@ 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')
|
||||
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=default)
|
||||
return mgid
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -2,7 +2,7 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .screenwavemedia import ScreenwaveMediaIE
|
||||
from .jwplatform import JWPlatformIE
|
||||
|
||||
from ..utils import (
|
||||
unified_strdate,
|
||||
@ -25,7 +25,7 @@ class NormalbootsIE(InfoExtractor):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': ['ScreenwaveMedia'],
|
||||
'add_ie': ['JWPlatform'],
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -39,15 +39,13 @@ class NormalbootsIE(InfoExtractor):
|
||||
r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
|
||||
webpage, 'date', fatal=False))
|
||||
|
||||
screenwavemedia_url = self._html_search_regex(
|
||||
ScreenwaveMediaIE.EMBED_PATTERN, webpage, 'screenwave URL',
|
||||
group='url')
|
||||
jwplatform_url = JWPlatformIE._extract_url(webpage)
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'url': screenwavemedia_url,
|
||||
'ie_key': ScreenwaveMediaIE.ie_key(),
|
||||
'url': jwplatform_url,
|
||||
'ie_key': JWPlatformIE.ie_key(),
|
||||
'title': self._og_search_title(webpage),
|
||||
'description': self._og_search_description(webpage),
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
|
@ -1,20 +1,12 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals, division
|
||||
|
||||
import re
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_chr,
|
||||
compat_ord,
|
||||
)
|
||||
from ..compat import compat_chr
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
)
|
||||
from ..jsinterp import JSInterpreter
|
||||
from ..jsinterp.jsgrammar import _NAME_RE
|
||||
|
||||
|
||||
|
||||
class OpenloadIE(InfoExtractor):
|
||||
@ -61,44 +53,6 @@ class OpenloadIE(InfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def openload_decode(self, txt):
|
||||
symbol_dict = {
|
||||
'(゚Д゚) [゚Θ゚]': '_',
|
||||
'(゚Д゚) [゚ω゚ノ]': 'a',
|
||||
'(゚Д゚) [゚Θ゚ノ]': 'b',
|
||||
'(゚Д゚) [\'c\']': 'c',
|
||||
'(゚Д゚) [゚ー゚ノ]': 'd',
|
||||
'(゚Д゚) [゚Д゚ノ]': 'e',
|
||||
'(゚Д゚) [1]': 'f',
|
||||
'(゚Д゚) [\'o\']': 'o',
|
||||
'(o゚ー゚o)': 'u',
|
||||
'(゚Д゚) [\'c\']': 'c',
|
||||
'((゚ー゚) + (o^_^o))': '7',
|
||||
'((o^_^o) +(o^_^o) +(c^_^o))': '6',
|
||||
'((゚ー゚) + (゚Θ゚))': '5',
|
||||
'(-~3)': '4',
|
||||
'(-~-~1)': '3',
|
||||
'(-~1)': '2',
|
||||
'(-~0)': '1',
|
||||
'((c^_^o)-(c^_^o))': '0',
|
||||
}
|
||||
delim = '(゚Д゚)[゚ε゚]+'
|
||||
end_token = '(゚Д゚)[゚o゚]'
|
||||
symbols = '|'.join(map(re.escape, symbol_dict.keys()))
|
||||
txt = re.sub('(%s)\+\s?' % symbols, lambda m: symbol_dict[m.group(1)], txt)
|
||||
ret = ''
|
||||
for aacode in re.findall(r'{0}\+\s?{1}(.*?){0}'.format(re.escape(end_token), re.escape(delim)), txt):
|
||||
for aachar in aacode.split(delim):
|
||||
if aachar.isdigit():
|
||||
ret += compat_chr(int(aachar, 8))
|
||||
else:
|
||||
m = re.match(r'^u([\da-f]{4})$', aachar)
|
||||
if m:
|
||||
ret += compat_chr(int(m.group(1), 16))
|
||||
else:
|
||||
self.report_warning("Cannot decode: %s" % aachar)
|
||||
return ret
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
|
||||
@ -106,36 +60,20 @@ class OpenloadIE(InfoExtractor):
|
||||
if 'File not found' in webpage or 'deleted by the owner' in webpage:
|
||||
raise ExtractorError('File not found', expected=True)
|
||||
|
||||
# The following decryption algorithm is written by @yokrysty and
|
||||
# declared to be freely used in youtube-dl
|
||||
# See https://github.com/rg3/youtube-dl/issues/10408
|
||||
enc_data = self._html_search_regex(
|
||||
r'<span[^>]*>([^<]+)</span>\s*<span[^>]*>[^<]+</span>\s*<span[^>]+id="streamurl"',
|
||||
webpage, 'encrypted data')
|
||||
ol_id = self._search_regex(
|
||||
'<span[^>]+id="[a-zA-Z0-9]+x"[^>]*>([0-9]+)</span>',
|
||||
webpage, 'openload ID')
|
||||
|
||||
enc_code = self._html_search_regex(r'<script[^>]+>(゚ω゚[^<]+)</script>',
|
||||
webpage, 'encrypted code')
|
||||
first_two_chars = int(float(ol_id[0:][:2]))
|
||||
urlcode = ''
|
||||
num = 2
|
||||
|
||||
js_code = self.openload_decode(enc_code)
|
||||
jsi = JSInterpreter(js_code)
|
||||
while num < len(ol_id):
|
||||
urlcode += compat_chr(int(float(ol_id[num:][:3])) -
|
||||
first_two_chars * int(float(ol_id[num + 3:][:2])))
|
||||
num += 5
|
||||
|
||||
m_offset_fun = self._search_regex(r'slice\(0\s*-\s*(%s)\(\)' % _NAME_RE, js_code, 'javascript offset function')
|
||||
m_diff_fun = self._search_regex(r'charCodeAt\(0\)\s*\+\s*(%s)\(\)' % _NAME_RE, js_code, 'javascript diff function')
|
||||
|
||||
offset = jsi.call_function(m_offset_fun)
|
||||
diff = jsi.call_function(m_diff_fun)
|
||||
|
||||
video_url_chars = []
|
||||
|
||||
for idx, c in enumerate(enc_data):
|
||||
j = compat_ord(c)
|
||||
if j >= 33 and j <= 126:
|
||||
j = ((j + 14) % 94) + 33
|
||||
if idx == len(enc_data) - offset:
|
||||
j += diff
|
||||
video_url_chars += compat_chr(j)
|
||||
|
||||
video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)
|
||||
video_url = 'https://openload.co/stream/' + urlcode
|
||||
|
||||
title = self._og_search_title(webpage, default=None) or self._search_regex(
|
||||
r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
|
||||
@ -154,5 +92,4 @@ class OpenloadIE(InfoExtractor):
|
||||
'ext': determine_ext(title),
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
return info_dict
|
||||
|
@ -11,6 +11,7 @@ from ..utils import (
|
||||
float_or_none,
|
||||
parse_duration,
|
||||
str_to_int,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
@ -56,6 +57,22 @@ class PandoraTVIE(InfoExtractor):
|
||||
r'^v(\d+)[Uu]rl$', format_id, 'height', default=None)
|
||||
if not height:
|
||||
continue
|
||||
|
||||
play_url = self._download_json(
|
||||
'http://m.pandora.tv/?c=api&m=play_url', video_id,
|
||||
data=urlencode_postdata({
|
||||
'prgid': video_id,
|
||||
'runtime': info.get('runtime'),
|
||||
'vod_url': format_url,
|
||||
}),
|
||||
headers={
|
||||
'Origin': url,
|
||||
'Content-Type': 'application/x-www-form-urlencoded',
|
||||
})
|
||||
format_url = play_url.get('url')
|
||||
if not format_url:
|
||||
continue
|
||||
|
||||
formats.append({
|
||||
'format_id': '%sp' % height,
|
||||
'url': format_url,
|
||||
|
@ -10,7 +10,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class Puls4IE(ProSiebenSat1BaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>(?:[^/]+/)*?videos/[^?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>[^?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
|
||||
'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
|
||||
@ -22,6 +22,12 @@ class Puls4IE(ProSiebenSat1BaseIE):
|
||||
'upload_date': '20160830',
|
||||
'uploader': 'PULS_4',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident.-Norbert-Hofer',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident-Analyse-des-Interviews-mit-Norbert-Hofer-416598',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_TOKEN = 'puls4'
|
||||
_SALT = '01!kaNgaiNgah1Ie4AeSha'
|
||||
|
@ -5,6 +5,7 @@ from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_urlparse
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
xpath_attr,
|
||||
xpath_text,
|
||||
@ -101,6 +102,11 @@ class RuutuIE(InfoExtractor):
|
||||
})
|
||||
|
||||
extract_formats(video_xml.find('./Clip'))
|
||||
|
||||
drm = xpath_text(video_xml, './Clip/DRM', default=None)
|
||||
if not formats and drm:
|
||||
raise ExtractorError('This video is DRM protected.', expected=True)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
|
@ -1,146 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
js_to_json,
|
||||
)
|
||||
|
||||
|
||||
class ScreenwaveMediaIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=(?P<id>[A-Za-z0-9-]+)'
|
||||
EMBED_PATTERN = r'src=(["\'])(?P<url>(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=.+?)\1'
|
||||
_TESTS = [{
|
||||
'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
playerdata = self._download_webpage(
|
||||
'http://player.screenwavemedia.com/player.php?id=%s' % video_id,
|
||||
video_id, 'Downloading player webpage')
|
||||
|
||||
vidtitle = self._search_regex(
|
||||
r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
|
||||
|
||||
playerconfig = self._download_webpage(
|
||||
'http://player.screenwavemedia.com/player.js',
|
||||
video_id, 'Downloading playerconfig webpage')
|
||||
|
||||
videoserver = self._search_regex(r'SWMServer\s*=\s*"([\d\.]+)"', playerdata, 'videoserver')
|
||||
|
||||
sources = self._parse_json(
|
||||
js_to_json(
|
||||
re.sub(
|
||||
r'(?s)/\*.*?\*/', '',
|
||||
self._search_regex(
|
||||
r'sources\s*:\s*(\[[^\]]+?\])', playerconfig,
|
||||
'sources',
|
||||
).replace(
|
||||
"' + thisObj.options.videoserver + '",
|
||||
videoserver
|
||||
).replace(
|
||||
"' + playerVidId + '",
|
||||
video_id
|
||||
)
|
||||
)
|
||||
),
|
||||
video_id, fatal=False
|
||||
)
|
||||
|
||||
# Fallback to hardcoded sources if JS changes again
|
||||
if not sources:
|
||||
self.report_warning('Falling back to a hardcoded list of streams')
|
||||
sources = [{
|
||||
'file': 'http://%s/vod/%s_%s.mp4' % (videoserver, video_id, format_id),
|
||||
'type': 'mp4',
|
||||
'label': format_label,
|
||||
} for format_id, format_label in (
|
||||
('low', '144p Low'), ('med', '160p Med'), ('high', '360p High'), ('hd1', '720p HD1'))]
|
||||
sources.append({
|
||||
'file': 'http://%s/vod/smil:%s.smil/playlist.m3u8' % (videoserver, video_id),
|
||||
'type': 'hls',
|
||||
})
|
||||
|
||||
formats = []
|
||||
for source in sources:
|
||||
file_ = source.get('file')
|
||||
if not file_:
|
||||
continue
|
||||
if source.get('type') == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(file_, video_id, ext='mp4'))
|
||||
else:
|
||||
format_id = self._search_regex(
|
||||
r'_(.+?)\.[^.]+$', file_, 'format id', default=None)
|
||||
if not self._is_valid_url(file_, video_id, format_id or 'video'):
|
||||
continue
|
||||
format_label = source.get('label')
|
||||
height = int_or_none(self._search_regex(
|
||||
r'^(\d+)[pP]', format_label, 'height', default=None))
|
||||
formats.append({
|
||||
'url': file_,
|
||||
'format_id': format_id,
|
||||
'format': format_label,
|
||||
'ext': source.get('type'),
|
||||
'height': height,
|
||||
})
|
||||
self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': vidtitle,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class TeamFourIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
|
||||
_TEST = {
|
||||
'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
|
||||
'info_dict': {
|
||||
'id': 'TeamFourStar-5292a02f20bfa',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20130401',
|
||||
'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar',
|
||||
'title': 'A Moment With TFS Episode 4',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
playerdata_url = self._search_regex(
|
||||
r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
|
||||
webpage, 'player data URL')
|
||||
|
||||
video_title = self._html_search_regex(
|
||||
r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
|
||||
webpage, 'title')
|
||||
video_date = unified_strdate(self._html_search_regex(
|
||||
r'<div class="heroheadingdate">(?P<date>.+?)</div>',
|
||||
webpage, 'date', fatal=False))
|
||||
video_description = self._html_search_regex(
|
||||
r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
|
||||
webpage, 'description', fatal=False)
|
||||
video_thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'display_id': display_id,
|
||||
'title': video_title,
|
||||
'description': video_description,
|
||||
'upload_date': video_date,
|
||||
'thumbnail': video_thumbnail,
|
||||
'url': playerdata_url,
|
||||
}
|
@ -121,7 +121,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
},
|
||||
]
|
||||
|
||||
_CLIENT_ID = '02gUJC0hH2ct1EGOcYXQIzRFU91c72Ea'
|
||||
_CLIENT_ID = 'fDoItMDbsbZz8dY16ZzARCZmzgHBPotA'
|
||||
_IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
|
||||
|
||||
@staticmethod
|
||||
|
@ -1,5 +1,7 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .mtv import MTVServicesInfoExtractor
|
||||
|
||||
|
||||
@ -16,6 +18,15 @@ class SpikeIE(MTVServicesInfoExtractor):
|
||||
'timestamp': 1388120400,
|
||||
'upload_date': '20131227',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.spike.com/full-episodes/j830qm/lip-sync-battle-joel-mchale-vs-jim-rash-season-2-ep-209',
|
||||
'md5': 'b25c6f16418aefb9ad5a6cae2559321f',
|
||||
'info_dict': {
|
||||
'id': '37ace3a8-1df6-48be-85b8-38df8229e241',
|
||||
'ext': 'mp4',
|
||||
'title': 'Lip Sync Battle|April 28, 2016|2|209|Joel McHale Vs. Jim Rash|Act 1',
|
||||
'description': 'md5:a739ca8f978a7802f67f8016d27ce114',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.spike.com/video-clips/lhtu8m/',
|
||||
'only_matching': True,
|
||||
@ -32,3 +43,12 @@ class SpikeIE(MTVServicesInfoExtractor):
|
||||
|
||||
_FEED_URL = 'http://www.spike.com/feeds/mrss/'
|
||||
_MOBILE_TEMPLATE = 'http://m.spike.com/videos/video.rbml?id=%s'
|
||||
_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)
|
||||
if mgid is None:
|
||||
url_parts = self._search_regex(self._CUSTOM_URL_REGEX, webpage, 'episode_id')
|
||||
video_type, episode_id = url_parts.split('/', 1)
|
||||
mgid = 'mgid:arc:{0}:spike.com:{1}'.format(video_type, episode_id)
|
||||
return mgid
|
||||
|
48
youtube_dl/extractor/teamfourstar.py
Normal file
48
youtube_dl/extractor/teamfourstar.py
Normal file
@ -0,0 +1,48 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .jwplatform import JWPlatformIE
|
||||
from ..utils import unified_strdate
|
||||
|
||||
|
||||
class TeamFourStarIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/(?P<id>[a-z0-9\-]+)'
|
||||
_TEST = {
|
||||
'url': 'http://teamfourstar.com/tfs-abridged-parody-episode-1-2/',
|
||||
'info_dict': {
|
||||
'id': '0WdZO31W',
|
||||
'title': 'TFS Abridged Parody Episode 1',
|
||||
'description': 'md5:d60bc389588ebab2ee7ad432bda953ae',
|
||||
'ext': 'mp4',
|
||||
'timestamp': 1394168400,
|
||||
'upload_date': '20080508',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
jwplatform_url = JWPlatformIE._extract_url(webpage)
|
||||
|
||||
video_title = self._html_search_regex(
|
||||
r'<h1[^>]+class="entry-title"[^>]*>(?P<title>.+?)</h1>',
|
||||
webpage, 'title')
|
||||
video_date = unified_strdate(self._html_search_regex(
|
||||
r'<span[^>]+class="meta-date date updated"[^>]*>(?P<date>.+?)</span>',
|
||||
webpage, 'date', fatal=False))
|
||||
video_description = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class="content-inner"[^>]*>.*?(?P<description><p>.+?)</div>',
|
||||
webpage, 'description', fatal=False)
|
||||
video_thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'display_id': display_id,
|
||||
'title': video_title,
|
||||
'description': video_description,
|
||||
'upload_date': video_date,
|
||||
'thumbnail': video_thumbnail,
|
||||
'url': jwplatform_url,
|
||||
}
|
@ -7,33 +7,30 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class TeleBruxellesIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt|emission)/?(?P<id>[^/#?]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
|
||||
'md5': '59439e568c9ee42fb77588b2096b214f',
|
||||
'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/',
|
||||
'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9',
|
||||
'info_dict': {
|
||||
'id': '11942',
|
||||
'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus',
|
||||
'ext': 'flv',
|
||||
'title': 'Parlement : Francken et Galant répondent aux interpellations de l’opposition',
|
||||
'description': 're:Les auditions des ministres se poursuivent*'
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'requires rtmpdump'
|
||||
'id': '158856',
|
||||
'display_id': 'que-risque-lauteur-dune-fausse-alerte-a-la-bombe',
|
||||
'ext': 'mp4',
|
||||
'title': 'Que risque l’auteur d’une fausse alerte à la bombe ?',
|
||||
'description': 'md5:3cf8df235d44ebc5426373050840e466',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
|
||||
'md5': '181d3fbdcf20b909309e5aef5c6c6047',
|
||||
'url': 'http://bx1.be/sport/futsal-schaerbeek-sincline-5-3-a-thulin/',
|
||||
'md5': 'dfe07ecc9c153ceba8582ac912687675',
|
||||
'info_dict': {
|
||||
'id': '10091',
|
||||
'display_id': 'basket-brussels-bat-mons-80-74',
|
||||
'ext': 'flv',
|
||||
'title': 'Basket : le Brussels bat Mons 80-74',
|
||||
'description': 're:^Ils l\u2019on fait ! En basket, le B*',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'requires rtmpdump'
|
||||
'id': '158433',
|
||||
'display_id': 'futsal-schaerbeek-sincline-5-3-a-thulin',
|
||||
'ext': 'mp4',
|
||||
'title': 'Futsal : Schaerbeek s’incline 5-3 à Thulin',
|
||||
'description': 'md5:fd013f1488d5e2dceb9cebe39e2d569b',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://bx1.be/emission/bxenf1-gastronomie/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -50,13 +47,13 @@ class TeleBruxellesIE(InfoExtractor):
|
||||
r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"',
|
||||
webpage, 'RTMP url')
|
||||
rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
|
||||
formats = self._extract_wowza_formats(rtmp_url, article_id or display_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': article_id or display_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'url': rtmp_url,
|
||||
'ext': 'flv',
|
||||
'rtmp_live': True # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed
|
||||
'formats': formats,
|
||||
}
|
||||
|
@ -5,10 +5,10 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class ThisOldHouseIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to)/(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
|
||||
'md5': '568acf9ca25a639f0c4ff905826b662f',
|
||||
'md5': '946f05bbaa12a33f9ae35580d2dfcfe3',
|
||||
'info_dict': {
|
||||
'id': '2REGtUDQ',
|
||||
'ext': 'mp4',
|
||||
@ -20,6 +20,9 @@ class ThisOldHouseIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -51,7 +51,7 @@ class VevoIE(VevoBaseIE):
|
||||
'artist': 'Hurts',
|
||||
'genre': 'Pop',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file'],
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'v3 SMIL format',
|
||||
'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923',
|
||||
@ -67,7 +67,7 @@ class VevoIE(VevoBaseIE):
|
||||
'artist': 'Cassadee Pope',
|
||||
'genre': 'Country',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file'],
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'Age-limited video',
|
||||
'url': 'https://www.vevo.com/watch/justin-timberlake/tunnel-vision-explicit/USRV81300282',
|
||||
@ -83,7 +83,7 @@ class VevoIE(VevoBaseIE):
|
||||
'artist': 'Justin Timberlake',
|
||||
'genre': 'Pop',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file'],
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'No video_info',
|
||||
'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000',
|
||||
@ -91,15 +91,33 @@ class VevoIE(VevoBaseIE):
|
||||
'info_dict': {
|
||||
'id': 'USUV71503000',
|
||||
'ext': 'mp4',
|
||||
'title': 'K Camp - Till I Die',
|
||||
'title': 'K Camp ft. T.I. - Till I Die',
|
||||
'age_limit': 18,
|
||||
'timestamp': 1449468000,
|
||||
'upload_date': '20151207',
|
||||
'uploader': 'K Camp',
|
||||
'track': 'Till I Die',
|
||||
'artist': 'K Camp',
|
||||
'genre': 'Rap/Hip-Hop',
|
||||
'genre': 'Hip-Hop',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'Featured test',
|
||||
'url': 'https://www.vevo.com/watch/lemaitre/Wait/USUV71402190',
|
||||
'md5': 'd28675e5e8805035d949dc5cf161071d',
|
||||
'info_dict': {
|
||||
'id': 'USUV71402190',
|
||||
'ext': 'mp4',
|
||||
'title': 'Lemaitre ft. LoLo - Wait',
|
||||
'age_limit': 0,
|
||||
'timestamp': 1413432000,
|
||||
'upload_date': '20141016',
|
||||
'uploader': 'Lemaitre',
|
||||
'track': 'Wait',
|
||||
'artist': 'Lemaitre',
|
||||
'genre': 'Electronic',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'Only available via webpage',
|
||||
'url': 'http://www.vevo.com/watch/GBUV71600656',
|
||||
@ -242,8 +260,11 @@ class VevoIE(VevoBaseIE):
|
||||
|
||||
timestamp = parse_iso8601(video_info.get('releaseDate'))
|
||||
artists = video_info.get('artists')
|
||||
if artists:
|
||||
artist = uploader = artists[0]['name']
|
||||
for curr_artist in artists:
|
||||
if curr_artist.get('role') == 'Featured':
|
||||
featured_artist = curr_artist['name']
|
||||
else:
|
||||
artist = uploader = curr_artist['name']
|
||||
view_count = int_or_none(video_info.get('views', {}).get('total'))
|
||||
|
||||
for video_version in video_versions:
|
||||
|
@ -1,11 +1,12 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import time
|
||||
import hmac
|
||||
import hashlib
|
||||
import hmac
|
||||
import itertools
|
||||
import json
|
||||
import re
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
@ -276,10 +277,14 @@ class VikiIE(VikiBaseIE):
|
||||
height = int_or_none(self._search_regex(
|
||||
r'^(\d+)[pP]$', format_id, 'height', default=None))
|
||||
for protocol, format_dict in stream_dict.items():
|
||||
# rtmps URLs does not seem to work
|
||||
if protocol == 'rtmps':
|
||||
continue
|
||||
format_url = format_dict['url']
|
||||
if format_id == 'm3u8':
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
format_dict['url'], video_id, 'mp4',
|
||||
entry_protocol='m3u8_native', preference=-1,
|
||||
format_url, video_id, 'mp4',
|
||||
entry_protocol='m3u8_native',
|
||||
m3u8_id='m3u8-%s' % protocol, fatal=False)
|
||||
# Despite CODECS metadata in m3u8 all video-only formats
|
||||
# are actually video+audio
|
||||
@ -287,9 +292,23 @@ class VikiIE(VikiBaseIE):
|
||||
if f.get('acodec') == 'none' and f.get('vcodec') != 'none':
|
||||
f['acodec'] = None
|
||||
formats.extend(m3u8_formats)
|
||||
elif format_url.startswith('rtmp'):
|
||||
mobj = re.search(
|
||||
r'^(?P<url>rtmp://[^/]+/(?P<app>.+?))/(?P<playpath>mp4:.+)$',
|
||||
format_url)
|
||||
if not mobj:
|
||||
continue
|
||||
formats.append({
|
||||
'format_id': 'rtmp-%s' % format_id,
|
||||
'ext': 'flv',
|
||||
'url': mobj.group('url'),
|
||||
'play_path': mobj.group('playpath'),
|
||||
'app': mobj.group('app'),
|
||||
'page_url': url,
|
||||
})
|
||||
else:
|
||||
formats.append({
|
||||
'url': format_dict['url'],
|
||||
'url': format_url,
|
||||
'format_id': '%s-%s' % (format_id, protocol),
|
||||
'height': height,
|
||||
})
|
||||
|
102
youtube_dl/extractor/webcaster.py
Normal file
102
youtube_dl/extractor/webcaster.py
Normal file
@ -0,0 +1,102 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
xpath_text,
|
||||
)
|
||||
|
||||
|
||||
class WebcasterIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://bl\.webcaster\.pro/(?:quote|media)/start/free_(?P<id>[^/]+)'
|
||||
_TESTS = [{
|
||||
# http://video.khl.ru/quotes/393859
|
||||
'url': 'http://bl.webcaster.pro/quote/start/free_c8cefd240aa593681c8d068cff59f407_hd/q393859/eb173f99dd5f558674dae55f4ba6806d/1480289104?sr%3D105%26fa%3D1%26type_id%3D18',
|
||||
'md5': '0c162f67443f30916ff1c89425dcd4cd',
|
||||
'info_dict': {
|
||||
'id': 'c8cefd240aa593681c8d068cff59f407_hd',
|
||||
'ext': 'mp4',
|
||||
'title': 'Сибирь - Нефтехимик. Лучшие моменты первого периода',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://bl.webcaster.pro/media/start/free_6246c7a4453ac4c42b4398f840d13100_hd/2_2991109016/e8d0d82587ef435480118f9f9c41db41/4635726126',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
video = self._download_xml(url, video_id)
|
||||
|
||||
title = xpath_text(video, './/event_name', 'event name', fatal=True)
|
||||
|
||||
def make_id(parts, separator):
|
||||
return separator.join(filter(None, parts))
|
||||
|
||||
formats = []
|
||||
for format_id in (None, 'noise'):
|
||||
track_tag = make_id(('track', format_id), '_')
|
||||
for track in video.findall('.//iphone/%s' % track_tag):
|
||||
track_url = track.text
|
||||
if not track_url:
|
||||
continue
|
||||
if determine_ext(track_url) == 'm3u8':
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
track_url, video_id, 'mp4',
|
||||
entry_protocol='m3u8_native',
|
||||
m3u8_id=make_id(('hls', format_id), '-'), fatal=False)
|
||||
for f in m3u8_formats:
|
||||
f.update({
|
||||
'source_preference': 0 if format_id == 'noise' else 1,
|
||||
'format_note': track.get('title'),
|
||||
})
|
||||
formats.extend(m3u8_formats)
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = xpath_text(video, './/image', 'thumbnail')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class WebcasterFeedIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://bl\.webcaster\.pro/feed/start/free_(?P<id>[^/]+)'
|
||||
_TEST = {
|
||||
'url': 'http://bl.webcaster.pro/feed/start/free_c8cefd240aa593681c8d068cff59f407_hd/q393859/eb173f99dd5f558674dae55f4ba6806d/1480289104',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _extract_url(ie, webpage):
|
||||
mobj = re.search(
|
||||
r'<(?:object|a[^>]+class=["\']webcaster-player["\'])[^>]+data(?:-config)?=(["\']).*?config=(?P<url>https?://bl\.webcaster\.pro/feed/start/free_.*?)(?:[?&]|\1)',
|
||||
webpage)
|
||||
if mobj:
|
||||
return mobj.group('url')
|
||||
for secure in (True, False):
|
||||
video_url = ie._og_search_video_url(
|
||||
webpage, secure=secure, default=None)
|
||||
if video_url:
|
||||
mobj = re.search(
|
||||
r'config=(?P<url>https?://bl\.webcaster\.pro/feed/start/free_[^?&=]+)',
|
||||
video_url)
|
||||
if mobj:
|
||||
return mobj.group('url')
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
feed = self._download_xml(url, video_id)
|
||||
|
||||
video_url = xpath_text(
|
||||
feed, ('video_hd', 'video'), 'video url', fatal=True)
|
||||
|
||||
return self.url_result(video_url, WebcasterIE.ie_key())
|
@ -1796,7 +1796,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
|
||||
|
|
||||
((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
|
||||
)"""
|
||||
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
|
||||
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
|
||||
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
|
||||
IE_NAME = 'youtube:playlist'
|
||||
_TESTS = [{
|
||||
|
@ -55,12 +55,12 @@ class Socks5AddressType(object):
|
||||
ATYP_IPV6 = 0x04
|
||||
|
||||
|
||||
class ProxyError(IOError):
|
||||
class ProxyError(socket.error):
|
||||
ERR_SUCCESS = 0x00
|
||||
|
||||
def __init__(self, code=None, msg=None):
|
||||
if code is not None and msg is None:
|
||||
msg = self.CODES.get(code) and 'unknown error'
|
||||
msg = self.CODES.get(code) or 'unknown error'
|
||||
super(ProxyError, self).__init__(code, msg)
|
||||
|
||||
|
||||
@ -123,7 +123,7 @@ class sockssocket(socket.socket):
|
||||
while len(data) < cnt:
|
||||
cur = self.recv(cnt - len(data))
|
||||
if not cur:
|
||||
raise IOError('{0} bytes missing'.format(cnt - len(data)))
|
||||
raise EOFError('{0} bytes missing'.format(cnt - len(data)))
|
||||
data += cur
|
||||
return data
|
||||
|
||||
|
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2016.11.18'
|
||||
__version__ = '2016.12.09'
|
||||
|
Loading…
x
Reference in New Issue
Block a user