1
0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-03 17:02:51 +08:00

Merge pull request #7 from rg3/master

updating again
This commit is contained in:
Kade 2018-01-22 19:16:29 -05:00 committed by GitHub
commit 1b5ac7d616
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
24 changed files with 306 additions and 250 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.01.14*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.01.14**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.01.21*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.01.21**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2018.01.14
[debug] youtube-dl version 2018.01.21
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@ -1,3 +1,31 @@
version 2018.01.21
Core
* [extractor/common] Improve jwplayer DASH formats extraction (#9242, #15187)
* [utils] Improve scientific notation handling in js_to_json (#14789)
Extractors
+ [southparkdk] Add support for southparkstudios.nu
+ [southpark] Add support for collections (#14803)
* [franceinter] Fix upload date extraction (#14996)
+ [rtvs] Add support for rtvs.sk (#9242, #15187)
* [restudy] Fix extraction and extend URL regular expression (#15347)
* [youtube:live] Improve live detection (#15365)
+ [springboardplatform] Add support for springboardplatform.com
* [prosiebensat1] Add another clip id regular expression (#15290)
- [ringtv] Remove extractor (#15345)
version 2018.01.18
Extractors
* [soundcloud] Update client id (#15306)
- [kamcord] Remove extractor (#15322)
+ [spiegel] Add support for nexx videos (#15285)
* [twitch] Fix authentication and error capture (#14090, #15264)
* [vk] Detect more errors due to copyright complaints (#15259)
version 2018.01.14
Extractors

View File

@ -383,7 +383,6 @@
- **JWPlatform**
- **Kakao**
- **Kaltura**
- **Kamcord**
- **KanalPlay**: Kanal 5/9/11 Play
- **Kankan**
- **Karaoketv**
@ -683,7 +682,6 @@
- **revision**
- **revision3:embed**
- **RICE**
- **RingTV**
- **RMCDecouverte**
- **RockstarGames**
- **RoosterTeeth**
@ -704,6 +702,7 @@
- **rtve.es:live**: RTVE.es live streams
- **rtve.es:television**
- **RTVNH**
- **RTVS**
- **Rudo**
- **RUHD**
- **RulePorn**
@ -774,6 +773,7 @@
- **Sport5**
- **SportBoxEmbed**
- **SportDeutschland**
- **SpringboardPlatform**
- **Sprout**
- **sr:mediathek**: Saarländischer Rundfunk
- **SRGSSR**

View File

@ -92,8 +92,8 @@ class TestDownload(unittest.TestCase):
def generator(test_case, tname):
def test_template(self):
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])()
other_ies = [get_info_extractor(ie_key)() for ie_key in test_case.get('add_ie', [])]
is_playlist = any(k.startswith('playlist') for k in test_case)
test_cases = test_case.get(
'playlist', [] if is_playlist else [test_case])

View File

@ -814,6 +814,9 @@ class TestUtil(unittest.TestCase):
inp = '''{"duration": "00:01:07"}'''
self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
inp = '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}'''
self.assertEqual(js_to_json(inp), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''')
def test_js_to_json_edgecases(self):
on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@ -885,6 +888,13 @@ class TestUtil(unittest.TestCase):
on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
self.assertEqual(json.loads(on), {'42': 42})
on = js_to_json('{42:4.2e1}')
self.assertEqual(json.loads(on), {'42': 42.0})
def test_js_to_json_malformed(self):
self.assertEqual(js_to_json('42a1'), '42"a1"')
self.assertEqual(js_to_json('42a-1'), '42"a"-1')
def test_extract_attributes(self):
self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})

View File

@ -2420,7 +2420,7 @@ class InfoExtractor(object):
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=m3u8_id, fatal=False))
elif ext == 'mpd':
elif source_type == 'dash' or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
source_url, video_id, mpd_id=mpd_id, fatal=False))
elif ext == 'smil':

View File

@ -490,7 +490,6 @@ from .jwplatform import JWPlatformIE
from .jpopsukitv import JpopsukiIE
from .kakao import KakaoIE
from .kaltura import KalturaIE
from .kamcord import KamcordIE
from .kanalplay import KanalPlayIE
from .kankan import KankanIE
from .karaoketv import KaraoketvIE
@ -882,7 +881,6 @@ from .revision3 import (
Revision3IE,
)
from .rice import RICEIE
from .ringtv import RingTVIE
from .rmcdecouverte import RMCDecouverteIE
from .ro220 import Ro220IE
from .rockstargames import RockstarGamesIE
@ -902,6 +900,7 @@ from .rtp import RTPIE
from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
from .rtvnh import RTVNHIE
from .rtvs import RTVSIE
from .rudo import RudoIE
from .ruhd import RUHDIE
from .ruleporn import RulePornIE
@ -991,6 +990,7 @@ from .stitcher import StitcherIE
from .sport5 import Sport5IE
from .sportbox import SportBoxEmbedIE
from .sportdeutschland import SportDeutschlandIE
from .springboardplatform import SpringboardPlatformIE
from .sprout import SproutIE
from .srgssr import (
SRGSSRIE,
@ -1046,7 +1046,6 @@ from .theplatform import (
ThePlatformFeedIE,
)
from .thescene import TheSceneIE
from .thesixtyone import TheSixtyOneIE
from .thestar import TheStarIE
from .thesun import TheSunIE
from .theweatherchannel import TheWeatherChannelIE

View File

@ -33,7 +33,7 @@ class FranceInterIE(InfoExtractor):
description = self._og_search_description(webpage)
upload_date_str = self._search_regex(
r'class=["\']cover-emission-period["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
webpage, 'upload date', fatal=False)
if upload_date_str:
upload_date_list = upload_date_str.split()

View File

@ -101,6 +101,7 @@ from .vzaar import VzaarIE
from .channel9 import Channel9IE
from .vshare import VShareIE
from .mediasite import MediasiteIE
from .springboardplatform import SpringboardPlatformIE
class GenericIE(InfoExtractor):
@ -1938,6 +1939,21 @@ class GenericIE(InfoExtractor):
'timestamp': 1474354800,
'upload_date': '20160920',
}
},
{
'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
'info_dict': {
'id': '1731611',
'ext': 'mp4',
'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
'description': 'md5:eb5f23826a027ba95277d105f248b825',
'timestamp': 1516100691,
'upload_date': '20180116',
},
'params': {
'skip_download': True,
},
'add_ie': [SpringboardPlatformIE.ie_key()],
}
# {
# # TODO: find another test
@ -2906,6 +2922,12 @@ class GenericIE(InfoExtractor):
for mediasite_url in mediasite_urls]
return self.playlist_result(entries, video_id, video_title)
springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
if springboardplatform_urls:
return self.playlist_from_matches(
springboardplatform_urls, video_id, video_title,
ie=SpringboardPlatformIE.ie_key())
def merge_dicts(dict1, dict2):
merged = {}
for k, v in dict1.items():

View File

@ -1,71 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
qualities,
)
class KamcordIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kamcord\.com/v/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://www.kamcord.com/v/hNYRduDgWb4',
'md5': 'c3180e8a9cfac2e86e1b88cb8751b54c',
'info_dict': {
'id': 'hNYRduDgWb4',
'ext': 'mp4',
'title': 'Drinking Madness',
'uploader': 'jacksfilms',
'uploader_id': '3044562',
'view_count': int,
'like_count': int,
'comment_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video = self._parse_json(
self._search_regex(
r'window\.__props\s*=\s*({.+?});?(?:\n|\s*</script)',
webpage, 'video'),
video_id)['video']
title = video['title']
formats = self._extract_m3u8_formats(
video['play']['hls'], video_id, 'mp4', entry_protocol='m3u8_native')
self._sort_formats(formats)
uploader = video.get('user', {}).get('username')
uploader_id = video.get('user', {}).get('id')
view_count = int_or_none(video.get('viewCount'))
like_count = int_or_none(video.get('heartCount'))
comment_count = int_or_none(video.get('messageCount'))
preference_key = qualities(('small', 'medium', 'large'))
thumbnails = [{
'url': thumbnail_url,
'id': thumbnail_id,
'preference': preference_key(thumbnail_id),
} for thumbnail_id, thumbnail_url in (video.get('thumbnail') or {}).items()
if isinstance(thumbnail_id, compat_str) and isinstance(thumbnail_url, compat_str)]
return {
'id': video_id,
'title': title,
'uploader': uploader,
'uploader_id': uploader_id,
'view_count': view_count,
'like_count': like_count,
'comment_count': comment_count,
'thumbnails': thumbnails,
'formats': formats,
}

View File

@ -344,6 +344,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
r'clip[iI]d=(\d+)',
r'clip[iI]d\s*=\s*["\'](\d+)',
r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)",
r'proMamsId&quot;\s*:\s*&quot;(\d+)',
]
_TITLE_REGEXES = [
r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',

View File

@ -5,8 +5,8 @@ from .common import InfoExtractor
class RestudyIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?restudy\.dk/video/play/id/(?P<id>[0-9]+)'
_TEST = {
_VALID_URL = r'https?://(?:(?:www|portal)\.)?restudy\.dk/video/[^/]+/id/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.restudy.dk/video/play/id/1637',
'info_dict': {
'id': '1637',
@ -18,7 +18,10 @@ class RestudyIE(InfoExtractor):
# rtmp download
'skip_download': True,
}
}
}, {
'url': 'https://portal.restudy.dk/video/leiden-frosteffekt/id/1637',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -29,7 +32,7 @@ class RestudyIE(InfoExtractor):
description = self._og_search_description(webpage).strip()
formats = self._extract_smil_formats(
'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml' % video_id,
'https://cdn.portal.restudy.dk/dynamic/themes/front/awsmedia/SmilDirectory/video_%s.xml' % video_id,
video_id)
self._sort_formats(formats)

View File

@ -1,44 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class RingTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ringtv\.craveonline\.com/(?P<type>news|videos/video)/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://ringtv.craveonline.com/news/310833-luis-collazo-says-victor-ortiz-better-not-quit-on-jan-30',
'md5': 'd25945f5df41cdca2d2587165ac28720',
'info_dict': {
'id': '857645',
'ext': 'mp4',
'title': 'Video: Luis Collazo says Victor Ortiz "better not quit on Jan. 30" - Ring TV',
'description': 'Luis Collazo is excited about his Jan. 30 showdown with fellow former welterweight titleholder Victor Ortiz at Barclays Center in his hometown of Brooklyn. The SuperBowl week fight headlines a Golden Boy Live! card on Fox Sports 1.',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id').split('-')[0]
webpage = self._download_webpage(url, video_id)
if mobj.group('type') == 'news':
video_id = self._search_regex(
r'''(?x)<iframe[^>]+src="http://cms\.springboardplatform\.com/
embed_iframe/[0-9]+/video/([0-9]+)/''',
webpage, 'real video ID')
title = self._og_search_title(webpage)
description = self._html_search_regex(
r'addthis:description="([^"]+)"',
webpage, 'description', fatal=False)
final_url = 'http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4' % video_id
thumbnail_url = 'http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg' % video_id
return {
'id': video_id,
'url': final_url,
'title': title,
'thumbnail': thumbnail_url,
'description': description,
}

View File

@ -0,0 +1,47 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class RTVSIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv/\d+/(?P<id>\d+)'
_TESTS = [{
# radio archive
'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
'md5': '134d5d6debdeddf8a5d761cbc9edacb8',
'info_dict': {
'id': '414872',
'ext': 'mp3',
'title': 'Ostrov pokladov 1 časť.mp3'
},
'params': {
'skip_download': True,
}
}, {
# tv archive
'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118',
'md5': '85e2c55cf988403b70cac24f5c086dc6',
'info_dict': {
'id': '63118',
'ext': 'mp4',
'title': 'Amaro Džives - Náš deň',
'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.'
},
'params': {
'skip_download': True,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
playlist_url = self._search_regex(
r'playlist["\']?\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'playlist url', group='url')
data = self._download_json(
playlist_url, video_id, 'Downloading playlist')[0]
return self._parse_jwplayer_data(data, video_id=video_id)

View File

@ -157,7 +157,7 @@ class SoundcloudIE(InfoExtractor):
},
]
_CLIENT_ID = 'c6CU49JDMapyrQo06UxU9xouB9ZVzqCn'
_CLIENT_ID = 'DQskPX1pntALRzMp4HSxya3Mc0AO66Ro'
_IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
@staticmethod

View File

@ -6,7 +6,7 @@ from .mtv import MTVServicesInfoExtractor
class SouthParkIE(MTVServicesInfoExtractor):
IE_NAME = 'southpark.cc.com'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
@ -20,6 +20,9 @@ class SouthParkIE(MTVServicesInfoExtractor):
'timestamp': 1112760000,
'upload_date': '20050406',
},
}, {
'url': 'http://southpark.cc.com/collections/7758/fan-favorites/1',
'only_matching': True,
}]
@ -41,7 +44,7 @@ class SouthParkEsIE(SouthParkIE):
class SouthParkDeIE(SouthParkIE):
IE_NAME = 'southpark.de'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden|collections)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
_TESTS = [{
@ -70,12 +73,15 @@ class SouthParkDeIE(SouthParkIE):
'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
},
'playlist_count': 3,
}, {
'url': 'http://www.southpark.de/collections/2476/superhero-showdown/1',
'only_matching': True,
}]
class SouthParkNlIE(SouthParkIE):
IE_NAME = 'southpark.nl'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southpark.nl/feeds/video-player/mrss/'
_TESTS = [{
@ -90,7 +96,7 @@ class SouthParkNlIE(SouthParkIE):
class SouthParkDkIE(SouthParkIE):
IE_NAME = 'southparkstudios.dk'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southparkstudios\.dk/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southparkstudios\.(?:dk|nu)/(?:clips|full-episodes|collections)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southparkstudios.dk/feeds/video-player/mrss/'
_TESTS = [{
@ -100,4 +106,10 @@ class SouthParkDkIE(SouthParkIE):
'description': 'Butters is convinced he\'s living in a virtual reality.',
},
'playlist_mincount': 3,
}, {
'url': 'http://www.southparkstudios.dk/collections/2476/superhero-showdown/1',
'only_matching': True,
}, {
'url': 'http://www.southparkstudios.nu/collections/2476/superhero-showdown/1',
'only_matching': True,
}]

View File

@ -4,7 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .nexx import NexxEmbedIE
from .nexx import (
NexxIE,
NexxEmbedIE,
)
from .spiegeltv import SpiegeltvIE
from ..compat import compat_urlparse
from ..utils import (
@ -51,6 +54,10 @@ class SpiegelIE(InfoExtractor):
}, {
'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
'only_matching': True,
}, {
# nexx video
'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
'only_matching': True,
}]
def _real_extract(self, url):
@ -61,6 +68,14 @@ class SpiegelIE(InfoExtractor):
if SpiegeltvIE.suitable(handle.geturl()):
return self.url_result(handle.geturl(), 'Spiegeltv')
nexx_id = self._search_regex(
r'nexxOmniaId\s*:\s*(\d+)', webpage, 'nexx id', default=None)
if nexx_id:
domain_id = NexxIE._extract_domain_id(webpage) or '748'
return self.url_result(
'nexx:%s:%s' % (domain_id, nexx_id), ie=NexxIE.ie_key(),
video_id=nexx_id)
video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default=''))
title = video_data.get('data-video-title') or get_element_by_attribute('class', 'module-title', webpage)

View File

@ -0,0 +1,125 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
xpath_attr,
xpath_text,
xpath_element,
unescapeHTML,
unified_timestamp,
)
class SpringboardPlatformIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
cms\.springboardplatform\.com/
(?:
(?:previews|embed_iframe)/(?P<index>\d+)/video/(?P<id>\d+)|
xml_feeds_advanced/index/(?P<index_2>\d+)/rss3/(?P<id_2>\d+)
)
'''
_TESTS = [{
'url': 'http://cms.springboardplatform.com/previews/159/video/981017/0/0/1',
'md5': '5c3cb7b5c55740d482561099e920f192',
'info_dict': {
'id': '981017',
'ext': 'mp4',
'title': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX',
'description': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1409132328,
'upload_date': '20140827',
'duration': 193,
},
}, {
'url': 'http://cms.springboardplatform.com/embed_iframe/159/video/981017/rab007/rapbasement.com/1/1',
'only_matching': True,
}, {
'url': 'http://cms.springboardplatform.com/embed_iframe/20/video/1731611/ki055/kidzworld.com/10',
'only_matching': True,
}, {
'url': 'http://cms.springboardplatform.com/xml_feeds_advanced/index/159/rss3/981017/0/0/1/',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cms\.springboardplatform\.com/embed_iframe/\d+/video/\d+.*?)\1',
webpage)]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') or mobj.group('id_2')
index = mobj.group('index') or mobj.group('index_2')
video = self._download_xml(
'http://cms.springboardplatform.com/xml_feeds_advanced/index/%s/rss3/%s'
% (index, video_id), video_id)
item = xpath_element(video, './/item', 'item', fatal=True)
content = xpath_element(
item, './{http://search.yahoo.com/mrss/}content', 'content',
fatal=True)
title = unescapeHTML(xpath_text(item, './title', 'title', fatal=True))
video_url = content.attrib['url']
if 'error_video.mp4' in video_url:
raise ExtractorError(
'Video %s no longer exists' % video_id, expected=True)
duration = int_or_none(content.get('duration'))
tbr = int_or_none(content.get('bitrate'))
filesize = int_or_none(content.get('fileSize'))
width = int_or_none(content.get('width'))
height = int_or_none(content.get('height'))
description = unescapeHTML(xpath_text(
item, './description', 'description'))
thumbnail = xpath_attr(
item, './{http://search.yahoo.com/mrss/}thumbnail', 'url',
'thumbnail')
timestamp = unified_timestamp(xpath_text(
item, './{http://cms.springboardplatform.com/namespaces.html}created',
'timestamp'))
formats = [{
'url': video_url,
'format_id': 'http',
'tbr': tbr,
'filesize': filesize,
'width': width,
'height': height,
}]
m3u8_format = formats[0].copy()
m3u8_format.update({
'url': re.sub(r'(https?://)cdn\.', r'\1hls.', video_url) + '.m3u8',
'ext': 'mp4',
'format_id': 'hls',
'protocol': 'm3u8_native',
})
formats.append(m3u8_format)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'formats': formats,
}

View File

@ -1,106 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unified_strdate
class TheSixtyOneIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?thesixtyone\.com/
(?:.*?/)*
(?:
s|
song/comments/list|
song
)/(?:[^/]+/)?(?P<id>[A-Za-z0-9]+)/?$'''
_SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}'
_SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}/thesixtyone_production/audio/{0:}_stream'
_THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop'
_TESTS = [
{
'url': 'http://www.thesixtyone.com/s/SrE3zD7s1jt/',
'md5': '821cc43b0530d3222e3e2b70bb4622ea',
'info_dict': {
'id': 'SrE3zD7s1jt',
'ext': 'mp3',
'title': 'CASIO - Unicorn War Mixtape',
'thumbnail': 're:^https?://.*_desktop$',
'upload_date': '20071217',
'duration': 3208,
}
},
{
'url': 'http://www.thesixtyone.com/song/comments/list/SrE3zD7s1jt',
'only_matching': True,
},
{
'url': 'http://www.thesixtyone.com/s/ULoiyjuJWli#/s/SrE3zD7s1jt/',
'only_matching': True,
},
{
'url': 'http://www.thesixtyone.com/#/s/SrE3zD7s1jt/',
'only_matching': True,
},
{
'url': 'http://www.thesixtyone.com/song/SrE3zD7s1jt/',
'only_matching': True,
},
{
'url': 'http://www.thesixtyone.com/maryatmidnight/song/StrawberriesandCream/yvWtLp0c4GQ/',
'only_matching': True,
},
]
_DECODE_MAP = {
'x': 'a',
'm': 'b',
'w': 'c',
'q': 'd',
'n': 'e',
'p': 'f',
'a': '0',
'h': '1',
'e': '2',
'u': '3',
's': '4',
'i': '5',
'o': '6',
'y': '7',
'r': '8',
'c': '9'
}
def _real_extract(self, url):
song_id = self._match_id(url)
webpage = self._download_webpage(
self._SONG_URL_TEMPLATE.format(song_id), song_id)
song_data = self._parse_json(self._search_regex(
r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'), song_id)
if self._search_regex(r'(t61\.s3_audio_load\s*=\s*1\.0;)', webpage, 's3_audio_load marker', default=None):
song_data['audio_server'] = 's3.amazonaws.com'
else:
song_data['audio_server'] = song_data['audio_server'] + '.thesixtyone.com'
keys = [self._DECODE_MAP.get(s, s) for s in song_data['key']]
url = self._SONG_FILE_URL_TEMPLATE.format(
"".join(reversed(keys)), **song_data)
formats = [{
'format_id': 'sd',
'url': url,
'ext': 'mp3',
}]
return {
'id': song_id,
'title': '{artist:} - {name:}'.format(**song_data),
'formats': formats,
'comment_count': song_data.get('comments_count'),
'duration': song_data.get('play_time'),
'like_count': song_data.get('score'),
'thumbnail': self._THUMBNAIL_URL_TEMPLATE.format(**song_data),
'upload_date': unified_strdate(song_data.get('publish_date')),
}

View File

@ -85,10 +85,15 @@ class TwitchBaseIE(InfoExtractor):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
response = self._parse_json(
e.cause.read().decode('utf-8'), None)
fail(response['message'])
fail(response.get('message') or response['errors'][0])
raise
redirect_url = urljoin(post_url, response['redirect'])
if 'Authenticated successfully' in response.get('message', ''):
return None, None
redirect_url = urljoin(
post_url,
response.get('redirect') or response['redirect_path'])
return self._download_webpage_handle(
redirect_url, None, 'Downloading login redirect page',
headers=headers)
@ -106,6 +111,10 @@ class TwitchBaseIE(InfoExtractor):
'password': password,
})
# Successful login
if not redirect_page:
return
if re.search(r'(?i)<form[^>]+id="two-factor-submit"', redirect_page) is not None:
# TODO: Add mechanism to request an SMS or phone call
tfa_token = self._get_tfa_info('two-factor authentication token')

View File

@ -318,9 +318,14 @@ class VKIE(VKBaseIE):
'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
expected=True)
ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
ERRORS = {
r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
'Video %s has been removed from public access due to rightholder complaint.',
ERROR_COPYRIGHT,
r'>The video .*? was removed from public access by request of the copyright holder.<':
ERROR_COPYRIGHT,
r'<!>Please log in or <':
'Video %s is only available for registered users, '

View File

@ -2530,10 +2530,11 @@ class YoutubeLiveIE(YoutubeBaseInfoExtractor):
webpage = self._download_webpage(url, channel_id, fatal=False)
if webpage:
page_type = self._og_search_property(
'type', webpage, 'page type', default=None)
'type', webpage, 'page type', default='')
video_id = self._html_search_meta(
'videoId', webpage, 'video id', default=None)
if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
if page_type.startswith('video') and video_id and re.match(
r'^[0-9A-Za-z_-]{11}$', video_id):
return self.url_result(video_id, YoutubeIE.ie_key())
return self.url_result(base_url)

View File

@ -2267,7 +2267,7 @@ def js_to_json(code):
"(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
'(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
{comment}|,(?={skip}[\]}}])|
[a-zA-Z_][.a-zA-Z_0-9]*|
(?:(?<![0-9])[eE]|[a-df-zA-DF-Z_])[.a-zA-Z_0-9]*|
\b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?|
[0-9]+(?={skip}:)
'''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code)

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2018.01.14'
__version__ = '2018.01.21'