Compare commits
30 Commits
2017.03.15
...
2017.03.22
Author | SHA1 | Date | |
---|---|---|---|
![]() |
093dad9e25 | ||
![]() |
e8686e51d7 | ||
![]() |
8e5a7c5e67 | ||
![]() |
e1e35d1ac6 | ||
![]() |
21fbf0f955 | ||
![]() |
97952bdb78 | ||
![]() |
8a8cc339b6 | ||
![]() |
957f453429 | ||
![]() |
0e9a73e612 | ||
![]() |
0ecdd3adbd | ||
![]() |
9487ce03e9 | ||
![]() |
45e6ad21b4 | ||
![]() |
68220649fa | ||
![]() |
46b18f2349 | ||
![]() |
772b5ff57f | ||
![]() |
f68ef1e2ab | ||
![]() |
febfe1e262 | ||
![]() |
5f0daab1ca | ||
![]() |
2a721cdff2 | ||
![]() |
e7a51a4c02 | ||
![]() |
3e5856d860 | ||
![]() |
ea883a687c | ||
![]() |
7f3590c43b | ||
![]() |
7d539ee10a | ||
![]() |
6ad476079d | ||
![]() |
0efbc6b56d | ||
![]() |
21bfcd3d6e | ||
![]() |
b51dc9db0e | ||
![]() |
a309684285 | ||
![]() |
ba448445b8 |
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 *2017.03.15*. 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 Issues with outdated version will be rejected.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 **2017.03.15**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.03.22*. 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 Issues with outdated version will be rejected.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 **2017.03.22**
|
||||
|
||||
### 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 2017.03.15
|
||||
[debug] youtube-dl version 2017.03.22
|
||||
[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: {}
|
||||
|
1
AUTHORS
1
AUTHORS
@@ -209,3 +209,4 @@ Olivier Bilodeau
|
||||
Lars Vierbergen
|
||||
Juanjo Benages
|
||||
Xiao Di Guan
|
||||
Thomas Winant
|
||||
|
34
ChangeLog
34
ChangeLog
@@ -1,3 +1,37 @@
|
||||
version 2017.03.22
|
||||
|
||||
Extractors
|
||||
- [pluralsight] Omit module title from video title (#12506)
|
||||
* [pornhub] Decode obfuscated video URL (#12470, #12515)
|
||||
* [senateisvp] Allow https URL scheme for embeds (#12512)
|
||||
|
||||
|
||||
version 2017.03.20
|
||||
|
||||
Core
|
||||
+ [YoutubeDL] Allow multiple input URLs to be used with stdout (-) as
|
||||
output template
|
||||
+ [adobepass] Detect and output error on authz token extraction (#12472)
|
||||
|
||||
Extractors
|
||||
+ [bostonglobe] Add extractor for bostonglobe.com (#12099)
|
||||
+ [toongoggles] Add support for toongoggles.com (#12171)
|
||||
+ [medialaan] Add support for Medialaan sites (#9974, #11912)
|
||||
+ [discoverynetworks] Add support for more domains and bypass geo restiction
|
||||
* [openload] Fix extraction (#10408)
|
||||
|
||||
|
||||
version 2017.03.16
|
||||
|
||||
Core
|
||||
+ [postprocessor/ffmpeg] Add support for flac
|
||||
+ [extractor/common] Extract SMIL formats from jwplayer
|
||||
|
||||
Extractors
|
||||
+ [generic] Add forgotten return for jwplayer formats
|
||||
* [redbulltv] Improve extraction
|
||||
|
||||
|
||||
version 2017.03.15
|
||||
|
||||
Core
|
||||
|
@@ -375,8 +375,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
|
||||
(requires ffmpeg or avconv and ffprobe or
|
||||
avprobe)
|
||||
--audio-format FORMAT Specify audio format: "best", "aac",
|
||||
"vorbis", "mp3", "m4a", "opus", or "wav";
|
||||
"best" by default; No effect without -x
|
||||
"flac", "mp3", "m4a", "opus", "vorbis", or
|
||||
"wav"; "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
|
||||
|
@@ -108,6 +108,7 @@
|
||||
- **blinkx**
|
||||
- **Bloomberg**
|
||||
- **BokeCC**
|
||||
- **BostonGlobe**
|
||||
- **Bpb**: Bundeszentrale für politische Bildung
|
||||
- **BR**: Bayerischer Rundfunk Mediathek
|
||||
- **BravoTV**
|
||||
@@ -209,6 +210,7 @@
|
||||
- **Discovery**
|
||||
- **DiscoveryGo**
|
||||
- **DiscoveryGoPlaylist**
|
||||
- **DiscoveryNetworksDe**
|
||||
- **Disney**
|
||||
- **Dotsub**
|
||||
- **DouyuTV**: 斗鱼
|
||||
@@ -425,6 +427,7 @@
|
||||
- **MatchTV**
|
||||
- **MDR**: MDR.DE and KiKA
|
||||
- **media.ccc.de**
|
||||
- **Medialaan**
|
||||
- **Meipai**: 美拍
|
||||
- **MelonVOD**
|
||||
- **META**
|
||||
@@ -777,12 +780,12 @@
|
||||
- **ThisAV**
|
||||
- **ThisOldHouse**
|
||||
- **tinypic**: tinypic.com videos
|
||||
- **tlc.de**
|
||||
- **TMZ**
|
||||
- **TMZArticle**
|
||||
- **TNAFlix**
|
||||
- **TNAFlixNetworkEmbed**
|
||||
- **toggle**
|
||||
- **ToonGoggles**
|
||||
- **Tosh**: Tosh.0
|
||||
- **tou.tv**
|
||||
- **Toypics**: Toypics user profile
|
||||
|
@@ -8,7 +8,7 @@ import sys
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from test.helper import FakeYDL
|
||||
from test.helper import FakeYDL, expect_dict
|
||||
from youtube_dl.extractor.common import InfoExtractor
|
||||
from youtube_dl.extractor import YoutubeIE, get_info_extractor
|
||||
from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError
|
||||
@@ -84,6 +84,97 @@ class TestInfoExtractor(unittest.TestCase):
|
||||
self.assertRaises(ExtractorError, self.ie._download_json, uri, None)
|
||||
self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
|
||||
|
||||
def test_extract_jwplayer_data_realworld(self):
|
||||
# from http://www.suffolk.edu/sjc/
|
||||
expect_dict(
|
||||
self,
|
||||
self.ie._extract_jwplayer_data(r'''
|
||||
<script type='text/javascript'>
|
||||
jwplayer('my-video').setup({
|
||||
file: 'rtmp://192.138.214.154/live/sjclive',
|
||||
fallback: 'true',
|
||||
width: '95%',
|
||||
aspectratio: '16:9',
|
||||
primary: 'flash',
|
||||
mediaid:'XEgvuql4'
|
||||
});
|
||||
</script>
|
||||
''', None, require_title=False),
|
||||
{
|
||||
'id': 'XEgvuql4',
|
||||
'formats': [{
|
||||
'url': 'rtmp://192.138.214.154/live/sjclive',
|
||||
'ext': 'flv'
|
||||
}]
|
||||
})
|
||||
|
||||
# from https://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary/
|
||||
expect_dict(
|
||||
self,
|
||||
self.ie._extract_jwplayer_data(r'''
|
||||
<script type="text/javascript">
|
||||
jwplayer("mediaplayer").setup({
|
||||
'videoid': "7564",
|
||||
'width': "100%",
|
||||
'aspectratio': "16:9",
|
||||
'stretching': "exactfit",
|
||||
'autostart': 'false',
|
||||
'flashplayer': "https://t04.vipstreamservice.com/jwplayer/v5.10/player.swf",
|
||||
'file': "https://cdn.pornoxo.com/key=MF+oEbaxqTKb50P-w9G3nA,end=1489689259,ip=104.199.146.27/ip=104.199.146.27/speed=6573765/buffer=3.0/2009-12/4b2157147afe5efa93ce1978e0265289c193874e02597.flv",
|
||||
'image': "https://t03.vipstreamservice.com/thumbs/pxo-full/2009-12/14/a4b2157147afe5efa93ce1978e0265289c193874e02597.flv-full-13.jpg",
|
||||
'filefallback': "https://cdn.pornoxo.com/key=9ZPsTR5EvPLQrBaak2MUGA,end=1489689259,ip=104.199.146.27/ip=104.199.146.27/speed=6573765/buffer=3.0/2009-12/m_4b2157147afe5efa93ce1978e0265289c193874e02597.mp4",
|
||||
'logo.hide': true,
|
||||
'skin': "https://t04.vipstreamservice.com/jwplayer/skin/modieus-blk.zip",
|
||||
'plugins': "https://t04.vipstreamservice.com/jwplayer/dock/dockableskinnableplugin.swf",
|
||||
'dockableskinnableplugin.piclink': "/index.php?key=ajax-videothumbsn&vid=7564&data=2009-12--14--4b2157147afe5efa93ce1978e0265289c193874e02597.flv--17370",
|
||||
'controlbar': 'bottom',
|
||||
'modes': [
|
||||
{type: 'flash', src: 'https://t04.vipstreamservice.com/jwplayer/v5.10/player.swf'}
|
||||
],
|
||||
'provider': 'http'
|
||||
});
|
||||
//noinspection JSAnnotator
|
||||
invideo.setup({
|
||||
adsUrl: "/banner-iframe/?zoneId=32",
|
||||
adsUrl2: "",
|
||||
autostart: false
|
||||
});
|
||||
</script>
|
||||
''', 'dummy', require_title=False),
|
||||
{
|
||||
'thumbnail': 'https://t03.vipstreamservice.com/thumbs/pxo-full/2009-12/14/a4b2157147afe5efa93ce1978e0265289c193874e02597.flv-full-13.jpg',
|
||||
'formats': [{
|
||||
'url': 'https://cdn.pornoxo.com/key=MF+oEbaxqTKb50P-w9G3nA,end=1489689259,ip=104.199.146.27/ip=104.199.146.27/speed=6573765/buffer=3.0/2009-12/4b2157147afe5efa93ce1978e0265289c193874e02597.flv',
|
||||
'ext': 'flv'
|
||||
}]
|
||||
})
|
||||
|
||||
# from http://www.indiedb.com/games/king-machine/videos
|
||||
expect_dict(
|
||||
self,
|
||||
self.ie._extract_jwplayer_data(r'''
|
||||
<script>
|
||||
jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/\/www.indiedb.com\/","displaytitle":false,"autostart":false,"repeat":false,"title":"king machine trailer 1","sharing":{"link":"http:\/\/www.indiedb.com\/games\/king-machine\/videos\/king-machine-trailer-1","code":"<iframe width=\"560\" height=\"315\" src=\"http:\/\/www.indiedb.com\/media\/iframe\/1522983\" frameborder=\"0\" allowfullscreen><\/iframe><br><a href=\"http:\/\/www.indiedb.com\/games\/king-machine\/videos\/king-machine-trailer-1\">king machine trailer 1 - Indie DB<\/a>"},"related":{"file":"http:\/\/rss.indiedb.com\/media\/recommended\/1522983\/feed\/rss.xml","dimensions":"160x120","onclick":"link"},"sources":[{"file":"http:\/\/cdn.dbolical.com\/cache\/videos\/games\/1\/50\/49678\/encode_mp4\/king-machine-trailer.mp4","label":"360p SD","default":"true"},{"file":"http:\/\/cdn.dbolical.com\/cache\/videos\/games\/1\/50\/49678\/encode720p_mp4\/king-machine-trailer.mp4","label":"720p HD"}],"image":"http:\/\/media.indiedb.com\/cache\/images\/games\/1\/50\/49678\/thumb_620x2000\/king-machine-trailer.mp4.jpg","advertising":{"client":"vast","tag":"http:\/\/ads.intergi.com\/adrawdata\/3.0\/5205\/4251742\/0\/1013\/ADTECH;cors=yes;width=560;height=315;referring_url=http:\/\/www.indiedb.com\/games\/king-machine\/videos\/king-machine-trailer-1;content_url=http:\/\/www.indiedb.com\/games\/king-machine\/videos\/king-machine-trailer-1;media_id=1522983;title=king+machine+trailer+1;device=__DEVICE__;model=__MODEL__;os=Windows+OS;osversion=__OSVERSION__;ua=__UA__;ip=109.171.17.81;uniqueid=1522983;tags=__TAGS__;number=58cac25928151;time=1489683033"},"width":620,"height":349}).once("play", function(event) {
|
||||
videoAnalytics("play");
|
||||
}).once("complete", function(event) {
|
||||
videoAnalytics("completed");
|
||||
});
|
||||
</script>
|
||||
''', 'dummy'),
|
||||
{
|
||||
'title': 'king machine trailer 1',
|
||||
'thumbnail': 'http://media.indiedb.com/cache/images/games/1/50/49678/thumb_620x2000/king-machine-trailer.mp4.jpg',
|
||||
'formats': [{
|
||||
'url': 'http://cdn.dbolical.com/cache/videos/games/1/50/49678/encode_mp4/king-machine-trailer.mp4',
|
||||
'height': 360,
|
||||
'ext': 'mp4'
|
||||
}, {
|
||||
'url': 'http://cdn.dbolical.com/cache/videos/games/1/50/49678/encode720p_mp4/king-machine-trailer.mp4',
|
||||
'height': 720,
|
||||
'ext': 'mp4'
|
||||
}]
|
||||
})
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
@@ -1872,6 +1872,7 @@ class YoutubeDL(object):
|
||||
"""Download a given list of URLs."""
|
||||
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
|
||||
if (len(url_list) > 1 and
|
||||
outtmpl != '-' and
|
||||
'%' not in outtmpl and
|
||||
self.params.get('max_downloads') != 1):
|
||||
raise SameFileError(outtmpl)
|
||||
|
@@ -196,7 +196,7 @@ def _real_main(argv=None):
|
||||
if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
|
||||
raise ValueError('Playlist end must be greater than playlist start')
|
||||
if opts.extractaudio:
|
||||
if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
|
||||
if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
|
||||
parser.error('invalid audio format specified')
|
||||
if opts.audioquality:
|
||||
opts.audioquality = opts.audioquality.strip('k').strip('K')
|
||||
|
@@ -1458,6 +1458,8 @@ class AdobePassIE(InfoExtractor):
|
||||
self._downloader.cache.store(self._MVPD_CACHE, requestor_id, {})
|
||||
count += 1
|
||||
continue
|
||||
if '<error' in authorize:
|
||||
raise ExtractorError(xml_text(authorize, 'details'), expected=True)
|
||||
authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
|
||||
requestor_info[guid] = authz_token
|
||||
self._downloader.cache.store(self._MVPD_CACHE, requestor_id, requestor_info)
|
||||
|
72
youtube_dl/extractor/bostonglobe.py
Normal file
72
youtube_dl/extractor/bostonglobe.py
Normal file
@@ -0,0 +1,72 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
)
|
||||
|
||||
|
||||
class BostonGlobeIE(InfoExtractor):
|
||||
_VALID_URL = r'(?i)https?://(?:www\.)?bostonglobe\.com/.*/(?P<id>[^/]+)/\w+(?:\.html)?'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.bostonglobe.com/metro/2017/02/11/tree-finally-succumbs-disease-leaving-hole-neighborhood/h1b4lviqzMTIn9sVy8F3gP/story.html',
|
||||
'md5': '0a62181079c85c2d2b618c9a738aedaf',
|
||||
'info_dict': {
|
||||
'title': 'A tree finally succumbs to disease, leaving a hole in a neighborhood',
|
||||
'id': '5320421710001',
|
||||
'ext': 'mp4',
|
||||
'description': 'It arrived as a sapling when the Back Bay was in its infancy, a spindly American elm tamped down into a square of dirt cut into the brick sidewalk of 1880s Marlborough Street, no higher than the first bay window of the new brownstone behind it.',
|
||||
'timestamp': 1486877593,
|
||||
'upload_date': '20170212',
|
||||
'uploader_id': '245991542',
|
||||
},
|
||||
},
|
||||
{
|
||||
# Embedded youtube video; we hand it off to the Generic extractor.
|
||||
'url': 'https://www.bostonglobe.com/lifestyle/names/2017/02/17/does-ben-affleck-play-matt-damon-favorite-version-batman/ruqkc9VxKBYmh5txn1XhSI/story.html',
|
||||
'md5': '582b40327089d5c0c949b3c54b13c24b',
|
||||
'info_dict': {
|
||||
'title': "Who Is Matt Damon's Favorite Batman?",
|
||||
'id': 'ZW1QCnlA6Qc',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20170217',
|
||||
'description': 'md5:3b3dccb9375867e0b4d527ed87d307cb',
|
||||
'uploader': 'The Late Late Show with James Corden',
|
||||
'uploader_id': 'TheLateLateShow',
|
||||
},
|
||||
'expected_warnings': ['404'],
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
page_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, page_id)
|
||||
|
||||
page_title = self._og_search_title(webpage, default=None)
|
||||
|
||||
# <video data-brightcove-video-id="5320421710001" data-account="245991542" data-player="SJWAiyYWg" data-embed="default" class="video-js" controls itemscope itemtype="http://schema.org/VideoObject">
|
||||
entries = []
|
||||
for video in re.findall(r'(?i)(<video[^>]+>)', webpage):
|
||||
attrs = extract_attributes(video)
|
||||
|
||||
video_id = attrs.get('data-brightcove-video-id')
|
||||
account_id = attrs.get('data-account')
|
||||
player_id = attrs.get('data-player')
|
||||
embed = attrs.get('data-embed')
|
||||
|
||||
if video_id and account_id and player_id and embed:
|
||||
entries.append(
|
||||
'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
|
||||
% (account_id, player_id, embed, video_id))
|
||||
|
||||
if len(entries) == 0:
|
||||
return self.url_result(url, 'Generic')
|
||||
elif len(entries) == 1:
|
||||
return self.url_result(entries[0], 'BrightcoveNew')
|
||||
else:
|
||||
return self.playlist_from_matches(entries, page_id, page_title, ie='BrightcoveNew')
|
@@ -36,34 +36,35 @@ from ..utils import (
|
||||
clean_html,
|
||||
compiled_regex_type,
|
||||
determine_ext,
|
||||
determine_protocol,
|
||||
error_to_compat_str,
|
||||
ExtractorError,
|
||||
extract_attributes,
|
||||
fix_xml_ampersands,
|
||||
float_or_none,
|
||||
GeoRestrictedError,
|
||||
GeoUtils,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
mimetype2ext,
|
||||
orderedSet,
|
||||
parse_codecs,
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
parse_m3u8_attributes,
|
||||
RegexNotFoundError,
|
||||
sanitize_filename,
|
||||
sanitized_Request,
|
||||
sanitize_filename,
|
||||
unescapeHTML,
|
||||
unified_strdate,
|
||||
unified_timestamp,
|
||||
update_Request,
|
||||
update_url_query,
|
||||
urljoin,
|
||||
url_basename,
|
||||
xpath_element,
|
||||
xpath_text,
|
||||
xpath_with_ns,
|
||||
determine_protocol,
|
||||
parse_duration,
|
||||
mimetype2ext,
|
||||
update_Request,
|
||||
update_url_query,
|
||||
parse_m3u8_attributes,
|
||||
extract_attributes,
|
||||
parse_codecs,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
@@ -714,6 +715,13 @@ class InfoExtractor(object):
|
||||
video_info['title'] = video_title
|
||||
return video_info
|
||||
|
||||
def playlist_from_matches(self, matches, video_id, video_title, getter=None, ie=None):
|
||||
urlrs = orderedSet(
|
||||
self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
|
||||
for m in matches)
|
||||
return self.playlist_result(
|
||||
urlrs, playlist_id=video_id, playlist_title=video_title)
|
||||
|
||||
@staticmethod
|
||||
def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None):
|
||||
"""Returns a playlist"""
|
||||
@@ -2247,6 +2255,9 @@ class InfoExtractor(object):
|
||||
elif ext == 'mpd':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
source_url, video_id, mpd_id=mpd_id, fatal=False))
|
||||
elif ext == 'smil':
|
||||
formats.extend(self._extract_smil_formats(
|
||||
source_url, video_id, fatal=False))
|
||||
# https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
|
||||
elif source_type.startswith('audio') or ext in (
|
||||
'oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
|
||||
|
@@ -9,13 +9,13 @@ from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import smuggle_url
|
||||
|
||||
|
||||
class TlcDeIE(InfoExtractor):
|
||||
IE_NAME = 'tlc.de'
|
||||
_VALID_URL = r'https?://(?:www\.)?tlc\.de/(?:[^/]+/)*videos/(?P<title>[^/?#]+)?(?:.*#(?P<id>\d+))?'
|
||||
class DiscoveryNetworksDeIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:discovery|tlc|animalplanet|dmax)\.de/(?:.*#(?P<id>\d+)|(?:[^/]+/)*videos/(?P<title>[^/?#]+))'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
|
||||
'info_dict': {
|
||||
'id': '3235167922001',
|
||||
@@ -29,7 +29,13 @@ class TlcDeIE(InfoExtractor):
|
||||
'upload_date': '20140404',
|
||||
'uploader_id': '1659832546',
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.dmax.de/programme/storage-hunters-uk/videos/storage-hunters-uk-episode-6/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.discovery.de/#5332316765001',
|
||||
'only_matching': True,
|
||||
}]
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -39,5 +45,8 @@ class TlcDeIE(InfoExtractor):
|
||||
title = mobj.group('title')
|
||||
webpage = self._download_webpage(url, title)
|
||||
brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
|
||||
brightcove_id = compat_parse_qs(compat_urlparse.urlparse(brightcove_legacy_url).query)['@videoPlayer'][0]
|
||||
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
|
||||
brightcove_id = compat_parse_qs(compat_urlparse.urlparse(
|
||||
brightcove_legacy_url).query)['@videoPlayer'][0]
|
||||
return self.url_result(smuggle_url(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['DE']}),
|
||||
'BrightcoveNew', brightcove_id)
|
@@ -117,6 +117,7 @@ from .bleacherreport import (
|
||||
from .blinkx import BlinkxIE
|
||||
from .bloomberg import BloombergIE
|
||||
from .bokecc import BokeCCIE
|
||||
from .bostonglobe import BostonGlobeIE
|
||||
from .bpb import BpbIE
|
||||
from .br import BRIE
|
||||
from .bravotv import BravoTVIE
|
||||
@@ -269,6 +270,7 @@ from .discoverygo import (
|
||||
DiscoveryGoIE,
|
||||
DiscoveryGoPlaylistIE,
|
||||
)
|
||||
from .discoverynetworks import DiscoveryNetworksDeIE
|
||||
from .disney import DisneyIE
|
||||
from .dispeak import DigitallySpeakingIE
|
||||
from .dropbox import DropboxIE
|
||||
@@ -973,7 +975,6 @@ from .thisav import ThisAVIE
|
||||
from .thisoldhouse import ThisOldHouseIE
|
||||
from .threeqsdn import ThreeQSDNIE
|
||||
from .tinypic import TinyPicIE
|
||||
from .tlc import TlcDeIE
|
||||
from .tmz import (
|
||||
TMZIE,
|
||||
TMZArticleIE,
|
||||
@@ -986,6 +987,7 @@ from .tnaflix import (
|
||||
)
|
||||
from .toggle import ToggleIE
|
||||
from .tonline import TOnlineIE
|
||||
from .toongoggles import ToonGogglesIE
|
||||
from .toutv import TouTvIE
|
||||
from .toypics import ToypicsUserIE, ToypicsIE
|
||||
from .traileraddict import TrailerAddictIE
|
||||
@@ -1174,6 +1176,7 @@ from .voxmedia import VoxMediaIE
|
||||
from .vporn import VpornIE
|
||||
from .vrt import VRTIE
|
||||
from .vrak import VrakIE
|
||||
from .medialaan import MedialaanIE
|
||||
from .vube import VubeIE
|
||||
from .vuclip import VuClipIE
|
||||
from .vvvvid import VVVVIDIE
|
||||
|
@@ -1542,6 +1542,17 @@ class GenericIE(InfoExtractor):
|
||||
'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# Senate ISVP iframe https
|
||||
'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
|
||||
'md5': 'fb8c70b0b515e5037981a2492099aab8',
|
||||
'info_dict': {
|
||||
'id': 'govtaff020316',
|
||||
'ext': 'mp4',
|
||||
'title': 'Integrated Senate Video Player',
|
||||
},
|
||||
'add_ie': [SenateISVPIE.ie_key()],
|
||||
},
|
||||
# {
|
||||
# # TODO: find another test
|
||||
# # http://schema.org/VideoObject
|
||||
@@ -1841,14 +1852,6 @@ class GenericIE(InfoExtractor):
|
||||
video_description = self._og_search_description(webpage, default=None)
|
||||
video_thumbnail = self._og_search_thumbnail(webpage, default=None)
|
||||
|
||||
# Helper method
|
||||
def _playlist_from_matches(matches, getter=None, ie=None):
|
||||
urlrs = orderedSet(
|
||||
self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
|
||||
for m in matches)
|
||||
return self.playlist_result(
|
||||
urlrs, playlist_id=video_id, playlist_title=video_title)
|
||||
|
||||
# Look for Brightcove Legacy Studio embeds
|
||||
bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
|
||||
if bc_urls:
|
||||
@@ -1869,28 +1872,28 @@ class GenericIE(InfoExtractor):
|
||||
# Look for Brightcove New Studio embeds
|
||||
bc_urls = BrightcoveNewIE._extract_urls(webpage)
|
||||
if bc_urls:
|
||||
return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
|
||||
return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
|
||||
|
||||
# Look for ThePlatform embeds
|
||||
tp_urls = ThePlatformIE._extract_urls(webpage)
|
||||
if tp_urls:
|
||||
return _playlist_from_matches(tp_urls, ie='ThePlatform')
|
||||
return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
|
||||
|
||||
# Look for Vessel embeds
|
||||
vessel_urls = VesselIE._extract_urls(webpage)
|
||||
if vessel_urls:
|
||||
return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
|
||||
return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
|
||||
|
||||
# Look for embedded rtl.nl player
|
||||
matches = re.findall(
|
||||
r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
|
||||
webpage)
|
||||
if matches:
|
||||
return _playlist_from_matches(matches, ie='RtlNl')
|
||||
return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
|
||||
|
||||
vimeo_urls = VimeoIE._extract_urls(url, webpage)
|
||||
if vimeo_urls:
|
||||
return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
|
||||
return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
|
||||
|
||||
vid_me_embed_url = self._search_regex(
|
||||
r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
|
||||
@@ -1912,25 +1915,25 @@ class GenericIE(InfoExtractor):
|
||||
(?:embed|v|p)/.+?)
|
||||
\1''', webpage)
|
||||
if matches:
|
||||
return _playlist_from_matches(
|
||||
matches, lambda m: unescapeHTML(m[1]))
|
||||
return self.playlist_from_matches(
|
||||
matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
|
||||
|
||||
# Look for lazyYT YouTube embed
|
||||
matches = re.findall(
|
||||
r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
|
||||
if matches:
|
||||
return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
|
||||
return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
|
||||
|
||||
# Look for Wordpress "YouTube Video Importer" plugin
|
||||
matches = re.findall(r'''(?x)<div[^>]+
|
||||
class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
|
||||
data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
|
||||
if matches:
|
||||
return _playlist_from_matches(matches, lambda m: m[-1])
|
||||
return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
|
||||
|
||||
matches = DailymotionIE._extract_urls(webpage)
|
||||
if matches:
|
||||
return _playlist_from_matches(matches)
|
||||
return self.playlist_from_matches(matches, video_id, video_title)
|
||||
|
||||
# Look for embedded Dailymotion playlist player (#3822)
|
||||
m = re.search(
|
||||
@@ -1939,8 +1942,8 @@ class GenericIE(InfoExtractor):
|
||||
playlists = re.findall(
|
||||
r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
|
||||
if playlists:
|
||||
return _playlist_from_matches(
|
||||
playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
|
||||
return self.playlist_from_matches(
|
||||
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
|
||||
|
||||
# Look for embedded Wistia player
|
||||
match = re.search(
|
||||
@@ -2047,8 +2050,9 @@ class GenericIE(InfoExtractor):
|
||||
if mobj is not None:
|
||||
embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
|
||||
if embeds:
|
||||
return _playlist_from_matches(
|
||||
embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
|
||||
return self.playlist_from_matches(
|
||||
embeds, video_id, video_title,
|
||||
getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
|
||||
|
||||
# Look for Aparat videos
|
||||
mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
|
||||
@@ -2110,13 +2114,13 @@ class GenericIE(InfoExtractor):
|
||||
# Look for funnyordie embed
|
||||
matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
|
||||
if matches:
|
||||
return _playlist_from_matches(
|
||||
matches, getter=unescapeHTML, ie='FunnyOrDie')
|
||||
return self.playlist_from_matches(
|
||||
matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
|
||||
|
||||
# Look for BBC iPlayer embed
|
||||
matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
|
||||
if matches:
|
||||
return _playlist_from_matches(matches, ie='BBCCoUk')
|
||||
return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
|
||||
|
||||
# Look for embedded RUTV player
|
||||
rutv_url = RUTVIE._extract_url(webpage)
|
||||
@@ -2131,32 +2135,32 @@ class GenericIE(InfoExtractor):
|
||||
# Look for embedded SportBox player
|
||||
sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
|
||||
if sportbox_urls:
|
||||
return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
|
||||
return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
|
||||
|
||||
# Look for embedded XHamster player
|
||||
xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
|
||||
if xhamster_urls:
|
||||
return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
|
||||
return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
|
||||
|
||||
# Look for embedded TNAFlixNetwork player
|
||||
tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
|
||||
if tnaflix_urls:
|
||||
return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
|
||||
return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
|
||||
|
||||
# Look for embedded PornHub player
|
||||
pornhub_urls = PornHubIE._extract_urls(webpage)
|
||||
if pornhub_urls:
|
||||
return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
|
||||
return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
|
||||
|
||||
# Look for embedded DrTuber player
|
||||
drtuber_urls = DrTuberIE._extract_urls(webpage)
|
||||
if drtuber_urls:
|
||||
return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
|
||||
return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
|
||||
|
||||
# Look for embedded RedTube player
|
||||
redtube_urls = RedTubeIE._extract_urls(webpage)
|
||||
if redtube_urls:
|
||||
return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
|
||||
return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
|
||||
|
||||
# Look for embedded Tvigle player
|
||||
mobj = re.search(
|
||||
@@ -2202,12 +2206,12 @@ class GenericIE(InfoExtractor):
|
||||
# Look for embedded soundcloud player
|
||||
soundcloud_urls = SoundcloudIE._extract_urls(webpage)
|
||||
if soundcloud_urls:
|
||||
return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
|
||||
return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
|
||||
|
||||
# Look for tunein player
|
||||
tunein_urls = TuneInBaseIE._extract_urls(webpage)
|
||||
if tunein_urls:
|
||||
return _playlist_from_matches(tunein_urls)
|
||||
return self.playlist_from_matches(tunein_urls, video_id, video_title)
|
||||
|
||||
# Look for embedded mtvservices player
|
||||
mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
|
||||
@@ -2490,35 +2494,35 @@ class GenericIE(InfoExtractor):
|
||||
# Look for DBTV embeds
|
||||
dbtv_urls = DBTVIE._extract_urls(webpage)
|
||||
if dbtv_urls:
|
||||
return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
|
||||
return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
|
||||
|
||||
# Look for Videa embeds
|
||||
videa_urls = VideaIE._extract_urls(webpage)
|
||||
if videa_urls:
|
||||
return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
|
||||
return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
|
||||
|
||||
# Look for 20 minuten embeds
|
||||
twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
|
||||
if twentymin_urls:
|
||||
return _playlist_from_matches(
|
||||
twentymin_urls, ie=TwentyMinutenIE.ie_key())
|
||||
return self.playlist_from_matches(
|
||||
twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
|
||||
|
||||
# Look for Openload embeds
|
||||
openload_urls = OpenloadIE._extract_urls(webpage)
|
||||
if openload_urls:
|
||||
return _playlist_from_matches(
|
||||
openload_urls, ie=OpenloadIE.ie_key())
|
||||
return self.playlist_from_matches(
|
||||
openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
|
||||
|
||||
# Look for VideoPress embeds
|
||||
videopress_urls = VideoPressIE._extract_urls(webpage)
|
||||
if videopress_urls:
|
||||
return _playlist_from_matches(
|
||||
videopress_urls, ie=VideoPressIE.ie_key())
|
||||
return self.playlist_from_matches(
|
||||
videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
|
||||
|
||||
# Look for Rutube embeds
|
||||
rutube_urls = RutubeIE._extract_urls(webpage)
|
||||
if rutube_urls:
|
||||
return _playlist_from_matches(
|
||||
return self.playlist_from_matches(
|
||||
rutube_urls, ie=RutubeIE.ie_key())
|
||||
|
||||
# Looking for http://schema.org/VideoObject
|
||||
@@ -2554,6 +2558,7 @@ class GenericIE(InfoExtractor):
|
||||
jwplayer_data, video_id, require_title=False)
|
||||
if not info.get('title'):
|
||||
info['title'] = video_title
|
||||
return info
|
||||
except ExtractorError:
|
||||
pass
|
||||
|
||||
|
259
youtube_dl/extractor/medialaan.py
Normal file
259
youtube_dl/extractor/medialaan.py
Normal file
@@ -0,0 +1,259 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class MedialaanIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:www\.)?
|
||||
(?:
|
||||
(?P<site_id>vtm|q2|vtmkzoom)\.be/
|
||||
(?:
|
||||
video(?:/[^/]+/id/|/?\?.*?\baid=)|
|
||||
(?:[^/]+/)*
|
||||
)
|
||||
)
|
||||
(?P<id>[^/?#&]+)
|
||||
'''
|
||||
_NETRC_MACHINE = 'medialaan'
|
||||
_APIKEY = '3_HZ0FtkMW_gOyKlqQzW5_0FHRC7Nd5XpXJZcDdXY4pk5eES2ZWmejRW5egwVm4ug-'
|
||||
_SITE_TO_APP_ID = {
|
||||
'vtm': 'vtm_watch',
|
||||
'q2': 'q2',
|
||||
'vtmkzoom': 'vtmkzoom',
|
||||
}
|
||||
_TESTS = [{
|
||||
# vod
|
||||
'url': 'http://vtm.be/video/volledige-afleveringen/id/vtm_20170219_VM0678361_vtmwatch',
|
||||
'info_dict': {
|
||||
'id': 'vtm_20170219_VM0678361_vtmwatch',
|
||||
'ext': 'mp4',
|
||||
'title': 'Allemaal Chris afl. 6',
|
||||
'description': 'md5:4be86427521e7b07e0adb0c9c554ddb2',
|
||||
'timestamp': 1487533280,
|
||||
'upload_date': '20170219',
|
||||
'duration': 2562,
|
||||
'series': 'Allemaal Chris',
|
||||
'season': 'Allemaal Chris',
|
||||
'season_number': 1,
|
||||
'season_id': '256936078124527',
|
||||
'episode': 'Allemaal Chris afl. 6',
|
||||
'episode_number': 6,
|
||||
'episode_id': '256936078591527',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Requires account credentials',
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://vtm.be/video?aid=168332',
|
||||
'info_dict': {
|
||||
'id': '168332',
|
||||
'ext': 'mp4',
|
||||
'title': '"Veronique liegt!"',
|
||||
'description': 'md5:1385e2b743923afe54ba4adc38476155',
|
||||
'timestamp': 1489002029,
|
||||
'upload_date': '20170308',
|
||||
'duration': 96,
|
||||
},
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://vtm.be/video/volledige-afleveringen/id/257107153551000',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://vtm.be/video?aid=163157',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://www.q2.be/video/volledige-afleveringen/id/2be_20170301_VM0684442_q2',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
self._logged_in = False
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
if username is None:
|
||||
self.raise_login_required()
|
||||
|
||||
auth_data = {
|
||||
'APIKey': self._APIKEY,
|
||||
'sdk': 'js_6.1',
|
||||
'format': 'json',
|
||||
'loginID': username,
|
||||
'password': password,
|
||||
}
|
||||
|
||||
auth_info = self._download_json(
|
||||
'https://accounts.eu1.gigya.com/accounts.login', None,
|
||||
note='Logging in', errnote='Unable to log in',
|
||||
data=urlencode_postdata(auth_data))
|
||||
|
||||
error_message = auth_info.get('errorDetails') or auth_info.get('errorMessage')
|
||||
if error_message:
|
||||
raise ExtractorError(
|
||||
'Unable to login: %s' % error_message, expected=True)
|
||||
|
||||
self._uid = auth_info['UID']
|
||||
self._uid_signature = auth_info['UIDSignature']
|
||||
self._signature_timestamp = auth_info['signatureTimestamp']
|
||||
|
||||
self._logged_in = True
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id, site_id = mobj.group('id', 'site_id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
config = self._parse_json(
|
||||
self._search_regex(
|
||||
r'videoJSConfig\s*=\s*JSON\.parse\(\'({.+?})\'\);',
|
||||
webpage, 'config', default='{}'), video_id,
|
||||
transform_source=lambda s: s.replace(
|
||||
'\\\\', '\\').replace(r'\"', '"').replace(r"\'", "'"))
|
||||
|
||||
vod_id = config.get('vodId') or self._search_regex(
|
||||
(r'\\"vodId\\"\s*:\s*\\"(.+?)\\"',
|
||||
r'<[^>]+id=["\']vod-(\d+)'),
|
||||
webpage, 'video_id', default=None)
|
||||
|
||||
# clip, no authentication required
|
||||
if not vod_id:
|
||||
player = self._parse_json(
|
||||
self._search_regex(
|
||||
r'vmmaplayer\(({.+?})\);', webpage, 'vmma player',
|
||||
default=''),
|
||||
video_id, transform_source=lambda s: '[%s]' % s, fatal=False)
|
||||
if player:
|
||||
video = player[-1]
|
||||
info = {
|
||||
'id': video_id,
|
||||
'url': video['videoUrl'],
|
||||
'title': video['title'],
|
||||
'thumbnail': video.get('imageUrl'),
|
||||
'timestamp': int_or_none(video.get('createdDate')),
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
}
|
||||
else:
|
||||
info = self._parse_html5_media_entries(
|
||||
url, webpage, video_id, m3u8_id='hls')[0]
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'title': self._html_search_meta('description', webpage),
|
||||
'duration': parse_duration(self._html_search_meta('duration', webpage)),
|
||||
})
|
||||
# vod, authentication required
|
||||
else:
|
||||
if not self._logged_in:
|
||||
self._login()
|
||||
|
||||
settings = self._parse_json(
|
||||
self._search_regex(
|
||||
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
|
||||
webpage, 'drupal settings', default='{}'),
|
||||
video_id)
|
||||
|
||||
def get(container, item):
|
||||
return try_get(
|
||||
settings, lambda x: x[container][item],
|
||||
compat_str) or self._search_regex(
|
||||
r'"%s"\s*:\s*"([^"]+)' % item, webpage, item,
|
||||
default=None)
|
||||
|
||||
app_id = get('vod', 'app_id') or self._SITE_TO_APP_ID.get(site_id, 'vtm_watch')
|
||||
sso = get('vod', 'gigyaDatabase') or 'vtm-sso'
|
||||
|
||||
data = self._download_json(
|
||||
'http://vod.medialaan.io/api/1.0/item/%s/video' % vod_id,
|
||||
video_id, query={
|
||||
'app_id': app_id,
|
||||
'user_network': sso,
|
||||
'UID': self._uid,
|
||||
'UIDSignature': self._uid_signature,
|
||||
'signatureTimestamp': self._signature_timestamp,
|
||||
})
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
data['response']['uri'], video_id, entry_protocol='m3u8_native',
|
||||
ext='mp4', m3u8_id='hls')
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
info = {
|
||||
'id': vod_id,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
api_key = get('vod', 'apiKey')
|
||||
channel = get('medialaanGigya', 'channel')
|
||||
|
||||
if api_key:
|
||||
videos = self._download_json(
|
||||
'http://vod.medialaan.io/vod/v2/videos', video_id, fatal=False,
|
||||
query={
|
||||
'channels': channel,
|
||||
'ids': vod_id,
|
||||
'limit': 1,
|
||||
'apikey': api_key,
|
||||
})
|
||||
if videos:
|
||||
video = try_get(
|
||||
videos, lambda x: x['response']['videos'][0], dict)
|
||||
if video:
|
||||
def get(container, item, expected_type=None):
|
||||
return try_get(
|
||||
video, lambda x: x[container][item], expected_type)
|
||||
|
||||
def get_string(container, item):
|
||||
return get(container, item, compat_str)
|
||||
|
||||
info.update({
|
||||
'series': get_string('program', 'title'),
|
||||
'season': get_string('season', 'title'),
|
||||
'season_number': int_or_none(get('season', 'number')),
|
||||
'season_id': get_string('season', 'id'),
|
||||
'episode': get_string('episode', 'title'),
|
||||
'episode_number': int_or_none(get('episode', 'number')),
|
||||
'episode_id': get_string('episode', 'id'),
|
||||
'duration': int_or_none(
|
||||
video.get('duration')) or int_or_none(
|
||||
video.get('durationMillis'), scale=1000),
|
||||
'title': get_string('episode', 'title'),
|
||||
'description': get_string('episode', 'text'),
|
||||
'timestamp': unified_timestamp(get_string(
|
||||
'publication', 'begin')),
|
||||
})
|
||||
|
||||
if not info.get('title'):
|
||||
info['title'] = try_get(
|
||||
config, lambda x: x['videoConfig']['title'],
|
||||
compat_str) or self._html_search_regex(
|
||||
r'\\"title\\"\s*:\s*\\"(.+?)\\"', webpage, 'title',
|
||||
default=None) or self._og_search_title(webpage)
|
||||
|
||||
if not info.get('description'):
|
||||
info['description'] = self._html_search_regex(
|
||||
r'<div[^>]+class="field-item\s+even">\s*<p>(.+?)</p>',
|
||||
webpage, 'description', default=None)
|
||||
|
||||
return info
|
@@ -78,34 +78,45 @@ class OpenloadIE(InfoExtractor):
|
||||
video_url_chars = []
|
||||
|
||||
first_char = ord(ol_id[0])
|
||||
key = first_char - 50
|
||||
key = first_char - 55
|
||||
maxKey = max(2, key)
|
||||
key = min(maxKey, len(ol_id) - 22)
|
||||
t = ol_id[key:key + 20]
|
||||
key = min(maxKey, len(ol_id) - 38)
|
||||
t = ol_id[key:key + 36]
|
||||
|
||||
hashMap = {}
|
||||
v = ol_id.replace(t, "")
|
||||
v = ol_id.replace(t, '')
|
||||
h = 0
|
||||
|
||||
while h < len(t):
|
||||
f = t[h:h + 2]
|
||||
i = int(f, 16)
|
||||
hashMap[h / 2] = i
|
||||
h += 2
|
||||
f = t[h:h + 3]
|
||||
i = int(f, 8)
|
||||
hashMap[h / 3] = i
|
||||
h += 3
|
||||
|
||||
h = 0
|
||||
|
||||
H = 0
|
||||
while h < len(v):
|
||||
B = v[h:h + 3]
|
||||
B = ''
|
||||
C = ''
|
||||
if len(v) >= h + 2:
|
||||
B = v[h:h + 2]
|
||||
if len(v) >= h + 3:
|
||||
C = v[h:h + 3]
|
||||
i = int(B, 16)
|
||||
if (h / 3) % 3 == 0:
|
||||
i = int(B, 8)
|
||||
index = (h / 3) % 10
|
||||
h += 2
|
||||
if H % 3 == 0:
|
||||
i = int(C, 8)
|
||||
h += 1
|
||||
elif H % 2 == 0 and H != 0 and ord(v[H - 1]) < 60:
|
||||
i = int(C, 10)
|
||||
h += 1
|
||||
index = H % 7
|
||||
|
||||
A = hashMap[index]
|
||||
i = i ^ 47
|
||||
i = i ^ A
|
||||
i ^= 213
|
||||
i ^= A
|
||||
video_url_chars.append(compat_chr(i))
|
||||
h += 3
|
||||
H += 1
|
||||
|
||||
video_url = 'https://openload.co/stream/%s?mime=true'
|
||||
video_url = video_url % (''.join(video_url_chars))
|
||||
|
@@ -40,7 +40,7 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
'info_dict': {
|
||||
'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
|
||||
'ext': 'mp4',
|
||||
'title': 'Management of SQL Server - Demo Monitoring',
|
||||
'title': 'Demo Monitoring',
|
||||
'duration': 338,
|
||||
},
|
||||
'skip': 'Requires pluralsight account credentials',
|
||||
@@ -187,7 +187,7 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
if not clip:
|
||||
raise ExtractorError('Unable to resolve clip')
|
||||
|
||||
title = '%s - %s' % (module['title'], clip['title'])
|
||||
title = clip['title']
|
||||
|
||||
QUALITIES = {
|
||||
'low': {'width': 640, 'height': 480},
|
||||
|
@@ -1,7 +1,9 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import functools
|
||||
import itertools
|
||||
import operator
|
||||
# import os
|
||||
import re
|
||||
|
||||
@@ -18,6 +20,7 @@ from ..utils import (
|
||||
js_to_json,
|
||||
orderedSet,
|
||||
# sanitized_Request,
|
||||
remove_quotes,
|
||||
str_to_int,
|
||||
)
|
||||
# from ..aes import (
|
||||
@@ -129,9 +132,32 @@ class PornHubIE(InfoExtractor):
|
||||
|
||||
tv_webpage = dl_webpage('tv')
|
||||
|
||||
video_url = self._search_regex(
|
||||
r'<video[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//.+?)\1', tv_webpage,
|
||||
'video url', group='url')
|
||||
assignments = self._search_regex(
|
||||
r'(var.+?mediastring.+?)</script>', tv_webpage,
|
||||
'encoded url').split(';')
|
||||
|
||||
js_vars = {}
|
||||
|
||||
def parse_js_value(inp):
|
||||
inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
|
||||
if '+' in inp:
|
||||
inps = inp.split('+')
|
||||
return functools.reduce(
|
||||
operator.concat, map(parse_js_value, inps))
|
||||
inp = inp.strip()
|
||||
if inp in js_vars:
|
||||
return js_vars[inp]
|
||||
return remove_quotes(inp)
|
||||
|
||||
for assn in assignments:
|
||||
assn = assn.strip()
|
||||
if not assn:
|
||||
continue
|
||||
assn = re.sub(r'var\s+', '', assn)
|
||||
vname, value = assn.split('=', 1)
|
||||
js_vars[vname] = parse_js_value(value)
|
||||
|
||||
video_url = js_vars['mediastring']
|
||||
|
||||
title = self._search_regex(
|
||||
r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)
|
||||
|
@@ -2,11 +2,13 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
# unified_timestamp,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
@@ -15,15 +17,15 @@ class RedBullTVIE(InfoExtractor):
|
||||
_TESTS = [{
|
||||
# film
|
||||
'url': 'https://www.redbull.tv/video/AP-1Q756YYX51W11/abc-of-wrc',
|
||||
'md5': '78e860f631d7a846e712fab8c5fe2c38',
|
||||
'md5': 'fb0445b98aa4394e504b413d98031d1f',
|
||||
'info_dict': {
|
||||
'id': 'AP-1Q756YYX51W11',
|
||||
'ext': 'mp4',
|
||||
'title': 'ABC of...WRC',
|
||||
'description': 'md5:5c7ed8f4015c8492ecf64b6ab31e7d31',
|
||||
'duration': 1582.04,
|
||||
'timestamp': 1488405786,
|
||||
'upload_date': '20170301',
|
||||
# 'timestamp': 1488405786,
|
||||
# 'upload_date': '20170301',
|
||||
},
|
||||
}, {
|
||||
# episode
|
||||
@@ -34,8 +36,8 @@ class RedBullTVIE(InfoExtractor):
|
||||
'title': 'Grime - Hashtags S2 E4',
|
||||
'description': 'md5:334b741c8c1ce65be057eab6773c1cf5',
|
||||
'duration': 904.6,
|
||||
'timestamp': 1487290093,
|
||||
'upload_date': '20170217',
|
||||
# 'timestamp': 1487290093,
|
||||
# 'upload_date': '20170217',
|
||||
'series': 'Hashtags',
|
||||
'season_number': 2,
|
||||
'episode_number': 4,
|
||||
@@ -48,29 +50,40 @@ class RedBullTVIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
access_token = self._download_json(
|
||||
'https://api-v2.redbull.tv/start', video_id,
|
||||
session = self._download_json(
|
||||
'https://api-v2.redbull.tv/session', video_id,
|
||||
note='Downloading access token', query={
|
||||
'build': '4.0.9',
|
||||
'category': 'smartphone',
|
||||
'os_version': 23,
|
||||
'os_family': 'android',
|
||||
})['auth']['access_token']
|
||||
'build': '4.370.0',
|
||||
'category': 'personal_computer',
|
||||
'os_version': '1.0',
|
||||
'os_family': 'http',
|
||||
})
|
||||
if session.get('code') == 'error':
|
||||
raise ExtractorError('%s said: %s' % (
|
||||
self.IE_NAME, session['message']))
|
||||
auth = '%s %s' % (session.get('token_type', 'Bearer'), session['access_token'])
|
||||
|
||||
info = self._download_json(
|
||||
'https://api-v2.redbull.tv/views/%s' % video_id,
|
||||
video_id, note='Downloading video information',
|
||||
headers={'Authorization': 'Bearer ' + access_token}
|
||||
)['blocks'][0]['top'][0]
|
||||
try:
|
||||
info = self._download_json(
|
||||
'https://api-v2.redbull.tv/content/%s' % video_id,
|
||||
video_id, note='Downloading video information',
|
||||
headers={'Authorization': auth}
|
||||
)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
|
||||
error_message = self._parse_json(
|
||||
e.cause.read().decode(), video_id)['message']
|
||||
raise ExtractorError('%s said: %s' % (
|
||||
self.IE_NAME, error_message), expected=True)
|
||||
raise
|
||||
|
||||
video = info['video_product']
|
||||
|
||||
title = info['title'].strip()
|
||||
m3u8_url = video['url']
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls')
|
||||
video['url'], video_id, 'mp4', 'm3u8_native')
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
for _, captions in (try_get(
|
||||
@@ -82,9 +95,12 @@ class RedBullTVIE(InfoExtractor):
|
||||
caption_url = caption.get('url')
|
||||
if not caption_url:
|
||||
continue
|
||||
ext = caption.get('format')
|
||||
if ext == 'xml':
|
||||
ext = 'ttml'
|
||||
subtitles.setdefault(caption.get('lang') or 'en', []).append({
|
||||
'url': caption_url,
|
||||
'ext': caption.get('format'),
|
||||
'ext': ext,
|
||||
})
|
||||
|
||||
subheading = info.get('subheading')
|
||||
@@ -97,7 +113,7 @@ class RedBullTVIE(InfoExtractor):
|
||||
'description': info.get('long_description') or info.get(
|
||||
'short_description'),
|
||||
'duration': float_or_none(video.get('duration'), scale=1000),
|
||||
'timestamp': unified_timestamp(info.get('published')),
|
||||
# 'timestamp': unified_timestamp(info.get('published')),
|
||||
'series': info.get('show_title'),
|
||||
'season_number': int_or_none(info.get('season_number')),
|
||||
'episode_number': int_or_none(info.get('episode_number')),
|
||||
|
@@ -89,7 +89,7 @@ class SenateISVPIE(InfoExtractor):
|
||||
@staticmethod
|
||||
def _search_iframe_url(webpage):
|
||||
mobj = re.search(
|
||||
r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
|
||||
r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
|
||||
webpage)
|
||||
if mobj:
|
||||
return mobj.group('url')
|
||||
|
81
youtube_dl/extractor/toongoggles.py
Normal file
81
youtube_dl/extractor/toongoggles.py
Normal file
@@ -0,0 +1,81 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
)
|
||||
|
||||
|
||||
class ToonGogglesIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?toongoggles\.com/shows/(?P<show_id>\d+)(?:/[^/]+/episodes/(?P<episode_id>\d+))?'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.toongoggles.com/shows/217143/bernard-season-2/episodes/217147/football',
|
||||
'md5': '18289fc2b951eff6b953a9d8f01e6831',
|
||||
'info_dict': {
|
||||
'id': '217147',
|
||||
'ext': 'mp4',
|
||||
'title': 'Football',
|
||||
'uploader_id': '1',
|
||||
'description': 'Bernard decides to play football in order to be better than Lloyd and tries to beat him no matter how, he even cheats.',
|
||||
'upload_date': '20160718',
|
||||
'timestamp': 1468879330,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.toongoggles.com/shows/227759/om-nom-stories-around-the-world',
|
||||
'info_dict': {
|
||||
'id': '227759',
|
||||
'title': 'Om Nom Stories Around The World',
|
||||
},
|
||||
'playlist_mincount': 11,
|
||||
}]
|
||||
|
||||
def _call_api(self, action, page_id, query):
|
||||
query.update({
|
||||
'for_ng': 1,
|
||||
'for_web': 1,
|
||||
'show_meta': 1,
|
||||
'version': 7.0,
|
||||
})
|
||||
return self._download_json('http://api.toongoggles.com/' + action, page_id, query=query)
|
||||
|
||||
def _parse_episode_data(self, episode_data):
|
||||
title = episode_data['episode_name']
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': episode_data['episode_id'],
|
||||
'title': title,
|
||||
'url': 'kaltura:513551:' + episode_data['entry_id'],
|
||||
'thumbnail': episode_data.get('thumbnail_url'),
|
||||
'description': episode_data.get('description'),
|
||||
'duration': parse_duration(episode_data.get('hms')),
|
||||
'series': episode_data.get('show_name'),
|
||||
'season_number': int_or_none(episode_data.get('season_num')),
|
||||
'episode_id': episode_data.get('episode_id'),
|
||||
'episode': title,
|
||||
'episode_number': int_or_none(episode_data.get('episode_num')),
|
||||
'categories': episode_data.get('categories'),
|
||||
'ie_key': 'Kaltura',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
show_id, episode_id = re.match(self._VALID_URL, url).groups()
|
||||
if episode_id:
|
||||
episode_data = self._call_api('search', episode_id, {
|
||||
'filter': 'episode',
|
||||
'id': episode_id,
|
||||
})['objects'][0]
|
||||
return self._parse_episode_data(episode_data)
|
||||
else:
|
||||
show_data = self._call_api('getepisodesbyshow', show_id, {
|
||||
'max': 1000000000,
|
||||
'showid': show_id,
|
||||
})
|
||||
entries = []
|
||||
for episode_data in show_data.get('objects', []):
|
||||
entries.append(self._parse_episode_data(episode_data))
|
||||
return self.playlist_result(entries, show_id, show_data.get('show_name'))
|
@@ -773,7 +773,7 @@ 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; No effect without -x')
|
||||
help='Specify audio format: "best", "aac", "flac", "mp3", "m4a", "opus", "vorbis", or "wav"; "%default" by default; No effect without -x')
|
||||
postproc.add_option(
|
||||
'--audio-quality', metavar='QUALITY',
|
||||
dest='audioquality', default='5',
|
||||
|
@@ -26,15 +26,25 @@ from ..utils import (
|
||||
|
||||
|
||||
EXT_TO_OUT_FORMATS = {
|
||||
"aac": "adts",
|
||||
"m4a": "ipod",
|
||||
"mka": "matroska",
|
||||
"mkv": "matroska",
|
||||
"mpg": "mpeg",
|
||||
"ogv": "ogg",
|
||||
"ts": "mpegts",
|
||||
"wma": "asf",
|
||||
"wmv": "asf",
|
||||
'aac': 'adts',
|
||||
'flac': 'flac',
|
||||
'm4a': 'ipod',
|
||||
'mka': 'matroska',
|
||||
'mkv': 'matroska',
|
||||
'mpg': 'mpeg',
|
||||
'ogv': 'ogg',
|
||||
'ts': 'mpegts',
|
||||
'wma': 'asf',
|
||||
'wmv': 'asf',
|
||||
}
|
||||
ACODECS = {
|
||||
'mp3': 'libmp3lame',
|
||||
'aac': 'aac',
|
||||
'flac': 'flac',
|
||||
'm4a': 'aac',
|
||||
'opus': 'opus',
|
||||
'vorbis': 'libvorbis',
|
||||
'wav': None,
|
||||
}
|
||||
|
||||
|
||||
@@ -237,7 +247,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
|
||||
acodec = 'copy'
|
||||
extension = 'm4a'
|
||||
more_opts = ['-bsf:a', 'aac_adtstoasc']
|
||||
elif filecodec in ['aac', 'mp3', 'vorbis', 'opus']:
|
||||
elif filecodec in ['aac', 'flac', 'mp3', 'vorbis', 'opus']:
|
||||
# Lossless if possible
|
||||
acodec = 'copy'
|
||||
extension = filecodec
|
||||
@@ -256,8 +266,8 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
|
||||
else:
|
||||
more_opts += ['-b:a', self._preferredquality + 'k']
|
||||
else:
|
||||
# We convert the audio (lossy)
|
||||
acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'opus': 'opus', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
|
||||
# We convert the audio (lossy if codec is lossy)
|
||||
acodec = ACODECS[self._preferredcodec]
|
||||
extension = self._preferredcodec
|
||||
more_opts = []
|
||||
if self._preferredquality is not None:
|
||||
|
@@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2017.03.15'
|
||||
__version__ = '2017.03.22'
|
||||
|
Reference in New Issue
Block a user