Merge branch 'master' into fix.25.12.2018
# Conflicts: # youtube_dl/version.py
This commit is contained in:
Avi Peretz
commit
471056460f
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 *2019.03.18*. If it's not, read [this FAQ entry](https://github.com/ytdl-org/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 Issues with outdated version will be rejected.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 **2019.03.18**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.04.24*. If it's not, read [this FAQ entry](https://github.com/ytdl-org/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 Issues with outdated version will be rejected.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 **2019.04.24**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through the [README](https://github.com/ytdl-org/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/ytdl-org/youtube-dl#faq) and [BUGS](https://github.com/ytdl-org/youtube-dl#bugs) sections
|
||||
@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] youtube-dl version 2019.03.18
|
||||
[debug] youtube-dl version 2019.04.24
|
||||
[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: {}
|
||||
|
||||
93
ChangeLog
93
ChangeLog
@ -1,3 +1,96 @@
|
||||
version 2019.04.24
|
||||
|
||||
Extractors
|
||||
* [youtube] Fix extraction (#20758, #20759, #20761, #20762, #20764, #20766,
|
||||
#20767, #20769, #20771, #20768, #20770)
|
||||
* [toutv] Fix extraction and extract series info (#20757)
|
||||
+ [vrv] Add support for movie listings (#19229)
|
||||
+ [youtube] Print error when no data is available (#20737)
|
||||
+ [soundcloud] Add support for new rendition and improve extraction (#20699)
|
||||
+ [ooyala] Add support for geo verification proxy
|
||||
+ [nrl] Add support for nrl.com (#15991)
|
||||
+ [vimeo] Extract live archive source format (#19144)
|
||||
+ [vimeo] Add support for live streams and improve info extraction (#19144)
|
||||
+ [ntvcojp] Add support for cu.ntv.co.jp
|
||||
+ [nhk] Extract RTMPT format
|
||||
+ [nhk] Add support for audio URLs
|
||||
+ [udemy] Add another course id extraction pattern (#20491)
|
||||
+ [openload] Add support for oload.services (#20691)
|
||||
+ [openload] Add support for openloed.co (#20691, #20693)
|
||||
* [bravotv] Fix extraction (#19213)
|
||||
|
||||
|
||||
version 2019.04.17
|
||||
|
||||
Extractors
|
||||
* [openload] Randomize User-Agent (closes #20688)
|
||||
+ [openload] Add support for oladblock domains (#20471)
|
||||
* [adn] Fix subtitle extraction (#12724)
|
||||
+ [aol] Add support for localized websites
|
||||
+ [yahoo] Add support GYAO episode URLs
|
||||
+ [yahoo] Add support for streaming.yahoo.co.jp (#5811, #7098)
|
||||
+ [yahoo] Add support for gyao.yahoo.co.jp
|
||||
* [aenetworks] Fix history topic extraction and extract more formats
|
||||
+ [cbs] Extract smpte and vtt subtitles
|
||||
+ [streamango] Add support for streamcherry.com (#20592)
|
||||
+ [yourporn] Add support for sxyprn.com (#20646)
|
||||
* [mgtv] Fix extraction (#20650)
|
||||
* [linkedin:learning] Use urljoin for form action URL (#20431)
|
||||
+ [gdc] Add support for kaltura embeds (#20575)
|
||||
* [dispeak] Improve mp4 bitrate extraction
|
||||
* [kaltura] Sanitize embed URLs
|
||||
* [jwplatfom] Do not match manifest URLs (#20596)
|
||||
* [aol] Restrict URL regular expression and improve format extraction
|
||||
+ [tiktok] Add support for new URL schema (#20573)
|
||||
+ [stv:player] Add support for player.stv.tv (#20586)
|
||||
|
||||
|
||||
version 2019.04.07
|
||||
|
||||
Core
|
||||
+ [downloader/external] Pass rtmp_conn to ffmpeg
|
||||
|
||||
Extractors
|
||||
+ [ruutu] Add support for audio podcasts (#20473, #20545)
|
||||
+ [xvideos] Extract all thumbnails (#20432)
|
||||
+ [platzi] Add support for platzi.com (#20562)
|
||||
* [dvtv] Fix extraction (#18514, #19174)
|
||||
+ [vrv] Add basic support for individual movie links (#19229)
|
||||
+ [bfi:player] Add support for player.bfi.org.uk (#19235)
|
||||
* [hbo] Fix extraction and extract subtitles (#14629, #13709)
|
||||
* [youtube] Extract srv[1-3] subtitle formats (#20566)
|
||||
* [adultswim] Fix extraction (#18025)
|
||||
* [teamcoco] Fix extraction and add suport for subdomains (#17099, #20339)
|
||||
* [adn] Fix subtitle compatibility with ffmpeg
|
||||
* [adn] Fix extraction and add support for positioning styles (#20549)
|
||||
* [vk] Use unique video id (#17848)
|
||||
* [newstube] Fix extraction
|
||||
* [rtl2] Actualize extraction
|
||||
+ [adobeconnect] Add support for adobeconnect.com (#20283)
|
||||
+ [gaia] Add support for authentication (#14605)
|
||||
+ [mediasite] Add support for dashed ids and named catalogs (#20531)
|
||||
|
||||
|
||||
version 2019.04.01
|
||||
|
||||
Core
|
||||
* [utils] Improve int_or_none and float_or_none (#20403)
|
||||
* Check for valid --min-sleep-interval when --max-sleep-interval is specified
|
||||
(#20435)
|
||||
|
||||
Extractors
|
||||
+ [weibo] Extend URL regular expression (#20496)
|
||||
+ [xhamster] Add support for xhamster.one (#20508)
|
||||
+ [mediasite] Add support for catalogs (#20507)
|
||||
+ [teamtreehouse] Add support for teamtreehouse.com (#9836)
|
||||
+ [ina] Add support for audio URLs
|
||||
* [ina] Improve extraction
|
||||
* [cwtv] Fix episode number extraction (#20461)
|
||||
* [npo] Improve DRM detection
|
||||
+ [pornhub] Add support for DASH formats (#20403)
|
||||
* [svtplay] Update API endpoint (#20430)
|
||||
|
||||
|
||||
version 2019.03.18
|
||||
|
||||
Core
|
||||
|
||||
@ -642,6 +642,7 @@ The simplest case is requesting a specific format, for example with `-f 22` you
|
||||
You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download the best quality format of a particular file extension served as a single file, e.g. `-f webm` will download the best quality format with the `webm` extension served as a single file.
|
||||
|
||||
You can also use special names to select particular edge case formats:
|
||||
|
||||
- `best`: Select the best quality format represented by a single file with video and audio.
|
||||
- `worst`: Select the worst quality format represented by a single file with video and audio.
|
||||
- `bestvideo`: Select the best quality video-only format (e.g. DASH video). May not be available.
|
||||
@ -658,6 +659,7 @@ If you want to download several formats of the same video use a comma as a separ
|
||||
You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).
|
||||
|
||||
The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals):
|
||||
|
||||
- `filesize`: The number of bytes, if known in advance
|
||||
- `width`: Width of the video, if known
|
||||
- `height`: Height of the video, if known
|
||||
@ -668,6 +670,7 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `
|
||||
- `fps`: Frame rate
|
||||
|
||||
Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields:
|
||||
|
||||
- `ext`: File extension
|
||||
- `acodec`: Name of the audio codec in use
|
||||
- `vcodec`: Name of the video codec in use
|
||||
@ -697,7 +700,7 @@ Note that on Windows you may need to use double quotes instead of single.
|
||||
# Download best mp4 format available or any other best if no mp4 available
|
||||
$ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best'
|
||||
|
||||
# Download best format available but not better that 480p
|
||||
# Download best format available but no better than 480p
|
||||
$ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]'
|
||||
|
||||
# Download best video only format but no bigger than 50 MB
|
||||
|
||||
@ -28,6 +28,7 @@
|
||||
- **acast:channel**
|
||||
- **AddAnime**
|
||||
- **ADN**: Anime Digital Network
|
||||
- **AdobeConnect**
|
||||
- **AdobeTV**
|
||||
- **AdobeTVChannel**
|
||||
- **AdobeTVShow**
|
||||
@ -45,6 +46,7 @@
|
||||
- **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
|
||||
- **AnimeOnDemand**
|
||||
- **Anvato**
|
||||
- **aol.com**
|
||||
- **APA**
|
||||
- **Aparat**
|
||||
- **AppleConnect**
|
||||
@ -101,6 +103,7 @@
|
||||
- **Bellator**
|
||||
- **BellMedia**
|
||||
- **Bet**
|
||||
- **bfi:player**
|
||||
- **Bigflix**
|
||||
- **Bild**: Bild.de
|
||||
- **BiliBili**
|
||||
@ -198,6 +201,7 @@
|
||||
- **CSpan**: C-SPAN
|
||||
- **CtsNews**: 華視新聞
|
||||
- **CTVNews**
|
||||
- **cu.ntv.co.jp**: Nippon Television Network
|
||||
- **Culturebox**
|
||||
- **CultureUnplugged**
|
||||
- **curiositystream**
|
||||
@ -345,7 +349,6 @@
|
||||
- **Groupon**
|
||||
- **Hark**
|
||||
- **hbo**
|
||||
- **hbo:episode**
|
||||
- **HearThisAt**
|
||||
- **Heise**
|
||||
- **HellPorno**
|
||||
@ -488,6 +491,8 @@
|
||||
- **Medialaan**
|
||||
- **Mediaset**
|
||||
- **Mediasite**
|
||||
- **MediasiteCatalog**
|
||||
- **MediasiteNamedCatalog**
|
||||
- **Medici**
|
||||
- **megaphone.fm**: megaphone.fm embedded players
|
||||
- **Meipai**: 美拍
|
||||
@ -620,6 +625,7 @@
|
||||
- **NRKTVEpisodes**
|
||||
- **NRKTVSeason**
|
||||
- **NRKTVSeries**
|
||||
- **NRLTV**
|
||||
- **ntv.ru**
|
||||
- **Nuvid**
|
||||
- **NYTimes**
|
||||
@ -629,7 +635,6 @@
|
||||
- **OdaTV**
|
||||
- **Odnoklassniki**
|
||||
- **OktoberfestTV**
|
||||
- **on.aol.com**
|
||||
- **OnDemandKorea**
|
||||
- **onet.pl**
|
||||
- **onet.tv**
|
||||
@ -670,6 +675,8 @@
|
||||
- **Piksel**
|
||||
- **Pinkbike**
|
||||
- **Pladform**
|
||||
- **Platzi**
|
||||
- **PlatziCourse**
|
||||
- **play.fm**
|
||||
- **PlayPlusTV**
|
||||
- **PlaysTV**
|
||||
@ -848,6 +855,7 @@
|
||||
- **StreamCZ**
|
||||
- **StreetVoice**
|
||||
- **StretchInternet**
|
||||
- **stv:player**
|
||||
- **SunPorno**
|
||||
- **SVT**
|
||||
- **SVTPage**
|
||||
@ -869,6 +877,7 @@
|
||||
- **teachertube:user:collection**: teachertube.com user and collection videos
|
||||
- **TeachingChannel**
|
||||
- **Teamcoco**
|
||||
- **TeamTreeHouse**
|
||||
- **TechTalks**
|
||||
- **techtv.mit.edu**
|
||||
- **ted**
|
||||
@ -1118,6 +1127,8 @@
|
||||
- **XVideos**
|
||||
- **XXXYMovies**
|
||||
- **Yahoo**: Yahoo screen and movies
|
||||
- **yahoo:gyao**
|
||||
- **yahoo:gyao:player**
|
||||
- **YandexDisk**
|
||||
- **yandexmusic:album**: Яндекс.Музыка - Альбом
|
||||
- **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
|
||||
|
||||
@ -309,6 +309,8 @@ class YoutubeDL(object):
|
||||
The following options are used by the post processors:
|
||||
prefer_ffmpeg: If False, use avconv instead of ffmpeg if both are available,
|
||||
otherwise prefer ffmpeg.
|
||||
ffmpeg_location: Location of the ffmpeg/avconv binary; either the path
|
||||
to the binary or its containing directory.
|
||||
postprocessor_args: A list of additional command-line arguments for the
|
||||
postprocessor.
|
||||
|
||||
|
||||
@ -289,6 +289,7 @@ class FFmpegFD(ExternalFD):
|
||||
tc_url = info_dict.get('tc_url')
|
||||
flash_version = info_dict.get('flash_version')
|
||||
live = info_dict.get('rtmp_live', False)
|
||||
conn = info_dict.get('rtmp_conn')
|
||||
if player_url is not None:
|
||||
args += ['-rtmp_swfverify', player_url]
|
||||
if page_url is not None:
|
||||
@ -303,6 +304,11 @@ class FFmpegFD(ExternalFD):
|
||||
args += ['-rtmp_flashver', flash_version]
|
||||
if live:
|
||||
args += ['-rtmp_live', 'live']
|
||||
if isinstance(conn, list):
|
||||
for entry in conn:
|
||||
args += ['-rtmp_conn', entry]
|
||||
elif isinstance(conn, compat_str):
|
||||
args += ['-rtmp_conn', conn]
|
||||
|
||||
args += ['-i', url, '-c', 'copy']
|
||||
|
||||
|
||||
@ -21,7 +21,6 @@ from ..utils import (
|
||||
intlist_to_bytes,
|
||||
long_to_bytes,
|
||||
pkcs1pad,
|
||||
srt_subtitles_timecode,
|
||||
strip_or_none,
|
||||
urljoin,
|
||||
)
|
||||
@ -42,6 +41,18 @@ class ADNIE(InfoExtractor):
|
||||
}
|
||||
_BASE_URL = 'http://animedigitalnetwork.fr'
|
||||
_RSA_KEY = (0xc35ae1e4356b65a73b551493da94b8cb443491c0aa092a357a5aee57ffc14dda85326f42d716e539a34542a0d3f363adf16c5ec222d713d5997194030ee2e4f0d1fb328c01a81cf6868c090d50de8e169c6b13d1675b9eeed1cbc51e1fffca9b38af07f37abd790924cd3bee59d0257cfda4fe5f3f0534877e21ce5821447d1b, 65537)
|
||||
_POS_ALIGN_MAP = {
|
||||
'start': 1,
|
||||
'end': 3,
|
||||
}
|
||||
_LINE_ALIGN_MAP = {
|
||||
'middle': 8,
|
||||
'end': 4,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _ass_subtitles_timecode(seconds):
|
||||
return '%01d:%02d:%02d.%02d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 100)
|
||||
|
||||
def _get_subtitles(self, sub_path, video_id):
|
||||
if not sub_path:
|
||||
@ -49,14 +60,19 @@ class ADNIE(InfoExtractor):
|
||||
|
||||
enc_subtitles = self._download_webpage(
|
||||
urljoin(self._BASE_URL, sub_path),
|
||||
video_id, fatal=False)
|
||||
video_id, 'Downloading subtitles location', fatal=False) or '{}'
|
||||
subtitle_location = (self._parse_json(enc_subtitles, video_id, fatal=False) or {}).get('location')
|
||||
if subtitle_location:
|
||||
enc_subtitles = self._download_webpage(
|
||||
urljoin(self._BASE_URL, subtitle_location),
|
||||
video_id, 'Downloading subtitles data', fatal=False)
|
||||
if not enc_subtitles:
|
||||
return None
|
||||
|
||||
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
|
||||
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
|
||||
bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
|
||||
bytes_to_intlist(binascii.unhexlify(self._K + '9032ad7083106400')),
|
||||
bytes_to_intlist(binascii.unhexlify(self._K + '4421de0a5f0814ba')),
|
||||
bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
|
||||
))
|
||||
subtitles_json = self._parse_json(
|
||||
@ -67,23 +83,27 @@ class ADNIE(InfoExtractor):
|
||||
|
||||
subtitles = {}
|
||||
for sub_lang, sub in subtitles_json.items():
|
||||
srt = ''
|
||||
for num, current in enumerate(sub):
|
||||
start, end, text = (
|
||||
ssa = '''[Script Info]
|
||||
ScriptType:V4.00
|
||||
[V4 Styles]
|
||||
Format: Name,Fontname,Fontsize,PrimaryColour,SecondaryColour,TertiaryColour,BackColour,Bold,Italic,BorderStyle,Outline,Shadow,Alignment,MarginL,MarginR,MarginV,AlphaLevel,Encoding
|
||||
Style: Default,Arial,18,16777215,16777215,16777215,0,-1,0,1,1,0,2,20,20,20,0,0
|
||||
[Events]
|
||||
Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
|
||||
for current in sub:
|
||||
start, end, text, line_align, position_align = (
|
||||
float_or_none(current.get('startTime')),
|
||||
float_or_none(current.get('endTime')),
|
||||
current.get('text'))
|
||||
current.get('text'), current.get('lineAlign'),
|
||||
current.get('positionAlign'))
|
||||
if start is None or end is None or text is None:
|
||||
continue
|
||||
srt += os.linesep.join(
|
||||
(
|
||||
'%d' % num,
|
||||
'%s --> %s' % (
|
||||
srt_subtitles_timecode(start),
|
||||
srt_subtitles_timecode(end)),
|
||||
text,
|
||||
os.linesep,
|
||||
))
|
||||
alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0)
|
||||
ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % (
|
||||
self._ass_subtitles_timecode(start),
|
||||
self._ass_subtitles_timecode(end),
|
||||
'{\\a%d}' % alignment if alignment != 2 else '',
|
||||
text.replace('\n', '\\N').replace('<i>', '{\\i1}').replace('</i>', '{\\i0}'))
|
||||
|
||||
if sub_lang == 'vostf':
|
||||
sub_lang = 'fr'
|
||||
@ -91,8 +111,8 @@ class ADNIE(InfoExtractor):
|
||||
'ext': 'json',
|
||||
'data': json.dumps(sub),
|
||||
}, {
|
||||
'ext': 'srt',
|
||||
'data': srt,
|
||||
'ext': 'ssa',
|
||||
'data': ssa,
|
||||
}])
|
||||
return subtitles
|
||||
|
||||
@ -100,7 +120,15 @@ class ADNIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
player_config = self._parse_json(self._search_regex(
|
||||
r'playerConfig\s*=\s*({.+});', webpage, 'player config'), video_id)
|
||||
r'playerConfig\s*=\s*({.+});', webpage,
|
||||
'player config', default='{}'), video_id, fatal=False)
|
||||
if not player_config:
|
||||
config_url = urljoin(self._BASE_URL, self._search_regex(
|
||||
r'(?:id="player"|class="[^"]*adn-player-container[^"]*")[^>]+data-url="([^"]+)"',
|
||||
webpage, 'config url'))
|
||||
player_config = self._download_json(
|
||||
config_url, video_id,
|
||||
'Downloading player config JSON metadata')['player']
|
||||
|
||||
video_info = {}
|
||||
video_info_str = self._search_regex(
|
||||
@ -129,12 +157,15 @@ class ADNIE(InfoExtractor):
|
||||
encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
|
||||
authorization = base64.b64encode(encrypted_message).decode()
|
||||
links_data = self._download_json(
|
||||
urljoin(self._BASE_URL, links_url), video_id, headers={
|
||||
urljoin(self._BASE_URL, links_url), video_id,
|
||||
'Downloading links JSON metadata', headers={
|
||||
'Authorization': 'Bearer ' + authorization,
|
||||
})
|
||||
links = links_data.get('links') or {}
|
||||
metas = metas or links_data.get('meta') or {}
|
||||
sub_path = (sub_path or links_data.get('subtitles')) + '&token=' + token
|
||||
sub_path = sub_path or links_data.get('subtitles') or \
|
||||
'index.php?option=com_vodapi&task=subtitles.getJSON&format=json&id=' + video_id
|
||||
sub_path += '&token=' + token
|
||||
error = links_data.get('error')
|
||||
title = metas.get('title') or video_info['title']
|
||||
|
||||
@ -142,9 +173,11 @@ class ADNIE(InfoExtractor):
|
||||
for format_id, qualities in links.items():
|
||||
if not isinstance(qualities, dict):
|
||||
continue
|
||||
for load_balancer_url in qualities.values():
|
||||
for quality, load_balancer_url in qualities.items():
|
||||
load_balancer_data = self._download_json(
|
||||
load_balancer_url, video_id, fatal=False) or {}
|
||||
load_balancer_url, video_id,
|
||||
'Downloading %s %s JSON metadata' % (format_id, quality),
|
||||
fatal=False) or {}
|
||||
m3u8_url = load_balancer_data.get('location')
|
||||
if not m3u8_url:
|
||||
continue
|
||||
|
||||
37
youtube_dl/extractor/adobeconnect.py
Normal file
37
youtube_dl/extractor/adobeconnect.py
Normal file
@ -0,0 +1,37 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urlparse,
|
||||
)
|
||||
|
||||
|
||||
class AdobeConnectIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://\w+\.adobeconnect\.com/(?P<id>[\w-]+)'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
|
||||
qs = compat_parse_qs(self._search_regex(r"swfUrl\s*=\s*'([^']+)'", webpage, 'swf url').split('?')[1])
|
||||
is_live = qs.get('isLive', ['false'])[0] == 'true'
|
||||
formats = []
|
||||
for con_string in qs['conStrings'][0].split(','):
|
||||
formats.append({
|
||||
'format_id': con_string.split('://')[0],
|
||||
'app': compat_urlparse.quote('?' + con_string.split('?')[1] + 'flvplayerapp/' + qs['appInstance'][0]),
|
||||
'ext': 'flv',
|
||||
'play_path': 'mp4:' + qs['streamName'][0],
|
||||
'rtmp_conn': 'S:' + qs['ticket'][0],
|
||||
'rtmp_live': is_live,
|
||||
'url': con_string,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._live_title(title) if is_live else title,
|
||||
'formats': formats,
|
||||
'is_live': is_live,
|
||||
}
|
||||
@ -1,13 +1,19 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .turner import TurnerBaseIE
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
mimetype2ext,
|
||||
parse_age_limit,
|
||||
parse_iso8601,
|
||||
strip_or_none,
|
||||
url_or_none,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
@ -21,8 +27,8 @@ class AdultSwimIE(TurnerBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': 'Rick and Morty - Pilot',
|
||||
'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
|
||||
'timestamp': 1493267400,
|
||||
'upload_date': '20170427',
|
||||
'timestamp': 1543294800,
|
||||
'upload_date': '20181127',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
@ -43,6 +49,7 @@ class AdultSwimIE(TurnerBaseIE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': '404 Not Found',
|
||||
}, {
|
||||
'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
|
||||
'info_dict': {
|
||||
@ -61,9 +68,9 @@ class AdultSwimIE(TurnerBaseIE):
|
||||
}, {
|
||||
'url': 'http://www.adultswim.com/videos/attack-on-titan',
|
||||
'info_dict': {
|
||||
'id': 'b7A69dzfRzuaXIECdxW8XQ',
|
||||
'id': 'attack-on-titan',
|
||||
'title': 'Attack on Titan',
|
||||
'description': 'md5:6c8e003ea0777b47013e894767f5e114',
|
||||
'description': 'md5:41caa9416906d90711e31dc00cb7db7e',
|
||||
},
|
||||
'playlist_mincount': 12,
|
||||
}, {
|
||||
@ -78,83 +85,118 @@ class AdultSwimIE(TurnerBaseIE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': '404 Not Found',
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
show_path, episode_path = re.match(self._VALID_URL, url).groups()
|
||||
display_id = episode_path or show_path
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
initial_data = self._parse_json(self._search_regex(
|
||||
r'AS_INITIAL_DATA(?:__)?\s*=\s*({.+?});',
|
||||
webpage, 'initial data'), display_id)
|
||||
|
||||
is_stream = show_path == 'streams'
|
||||
if is_stream:
|
||||
if not episode_path:
|
||||
episode_path = 'live-stream'
|
||||
|
||||
video_data = next(stream for stream_path, stream in initial_data['streams'].items() if stream_path == episode_path)
|
||||
video_id = video_data.get('stream')
|
||||
|
||||
if not video_id:
|
||||
entries = []
|
||||
for episode in video_data.get('archiveEpisodes', []):
|
||||
episode_url = url_or_none(episode.get('url'))
|
||||
if not episode_url:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
episode_url, 'AdultSwim', episode.get('id')))
|
||||
return self.playlist_result(
|
||||
entries, video_data.get('id'), video_data.get('title'),
|
||||
strip_or_none(video_data.get('description')))
|
||||
query = '''query {
|
||||
getShowBySlug(slug:"%s") {
|
||||
%%s
|
||||
}
|
||||
}''' % show_path
|
||||
if episode_path:
|
||||
query = query % '''title
|
||||
getVideoBySlug(slug:"%s") {
|
||||
_id
|
||||
auth
|
||||
description
|
||||
duration
|
||||
episodeNumber
|
||||
launchDate
|
||||
mediaID
|
||||
seasonNumber
|
||||
poster
|
||||
title
|
||||
tvRating
|
||||
}''' % episode_path
|
||||
['getVideoBySlug']
|
||||
else:
|
||||
show_data = initial_data['show']
|
||||
query = query % '''metaDescription
|
||||
title
|
||||
videos(first:1000,sort:["episode_number"]) {
|
||||
edges {
|
||||
node {
|
||||
_id
|
||||
slug
|
||||
}
|
||||
}
|
||||
}'''
|
||||
show_data = self._download_json(
|
||||
'https://www.adultswim.com/api/search', display_id,
|
||||
data=json.dumps({'query': query}).encode(),
|
||||
headers={'Content-Type': 'application/json'})['data']['getShowBySlug']
|
||||
if episode_path:
|
||||
video_data = show_data['getVideoBySlug']
|
||||
video_id = video_data['_id']
|
||||
episode_title = title = video_data['title']
|
||||
series = show_data.get('title')
|
||||
if series:
|
||||
title = '%s - %s' % (series, title)
|
||||
info = {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': strip_or_none(video_data.get('description')),
|
||||
'duration': float_or_none(video_data.get('duration')),
|
||||
'formats': [],
|
||||
'subtitles': {},
|
||||
'age_limit': parse_age_limit(video_data.get('tvRating')),
|
||||
'thumbnail': video_data.get('poster'),
|
||||
'timestamp': parse_iso8601(video_data.get('launchDate')),
|
||||
'series': series,
|
||||
'season_number': int_or_none(video_data.get('seasonNumber')),
|
||||
'episode': episode_title,
|
||||
'episode_number': int_or_none(video_data.get('episodeNumber')),
|
||||
}
|
||||
|
||||
if not episode_path:
|
||||
auth = video_data.get('auth')
|
||||
media_id = video_data.get('mediaID')
|
||||
if media_id:
|
||||
info.update(self._extract_ngtv_info(media_id, {
|
||||
# CDN_TOKEN_APP_ID from:
|
||||
# https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
|
||||
'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
|
||||
}, {
|
||||
'url': url,
|
||||
'site_name': 'AdultSwim',
|
||||
'auth_required': auth,
|
||||
}))
|
||||
|
||||
if not auth:
|
||||
extract_data = self._download_json(
|
||||
'https://www.adultswim.com/api/shows/v1/videos/' + video_id,
|
||||
video_id, query={'fields': 'stream'}, fatal=False) or {}
|
||||
assets = try_get(extract_data, lambda x: x['data']['video']['stream']['assets'], list) or []
|
||||
for asset in assets:
|
||||
asset_url = asset.get('url')
|
||||
if not asset_url:
|
||||
continue
|
||||
ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
|
||||
if ext == 'm3u8':
|
||||
info['formats'].extend(self._extract_m3u8_formats(
|
||||
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
|
||||
elif ext == 'f4m':
|
||||
continue
|
||||
# info['formats'].extend(self._extract_f4m_formats(
|
||||
# asset_url, video_id, f4m_id='hds', fatal=False))
|
||||
elif ext in ('scc', 'ttml', 'vtt'):
|
||||
info['subtitles'].setdefault('en', []).append({
|
||||
'url': asset_url,
|
||||
})
|
||||
self._sort_formats(info['formats'])
|
||||
|
||||
return info
|
||||
else:
|
||||
entries = []
|
||||
for video in show_data.get('videos', []):
|
||||
for edge in show_data.get('videos', {}).get('edges', []):
|
||||
video = edge.get('node') or {}
|
||||
slug = video.get('slug')
|
||||
if not slug:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
'http://adultswim.com/videos/%s/%s' % (show_path, slug),
|
||||
'AdultSwim', video.get('id')))
|
||||
'AdultSwim', video.get('_id')))
|
||||
return self.playlist_result(
|
||||
entries, show_data.get('id'), show_data.get('title'),
|
||||
strip_or_none(show_data.get('metadata', {}).get('description')))
|
||||
|
||||
video_data = show_data['sluggedVideo']
|
||||
video_id = video_data['id']
|
||||
|
||||
info = self._extract_cvp_info(
|
||||
'http://www.adultswim.com/videos/api/v0/assets?platform=desktop&id=' + video_id,
|
||||
video_id, {
|
||||
'secure': {
|
||||
'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
|
||||
'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
|
||||
},
|
||||
}, {
|
||||
'url': url,
|
||||
'site_name': 'AdultSwim',
|
||||
'auth_required': video_data.get('auth'),
|
||||
})
|
||||
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'description': info.get('description') or strip_or_none(video_data.get('description')),
|
||||
})
|
||||
if not is_stream:
|
||||
info.update({
|
||||
'duration': info.get('duration') or int_or_none(video_data.get('duration')),
|
||||
'timestamp': info.get('timestamp') or int_or_none(video_data.get('launch_date')),
|
||||
'season_number': info.get('season_number') or int_or_none(video_data.get('season_number')),
|
||||
'episode': info['title'],
|
||||
'episode_number': info.get('episode_number') or int_or_none(video_data.get('episode_number')),
|
||||
})
|
||||
|
||||
info['series'] = video_data.get('collection_title') or info.get('series')
|
||||
if info['series'] and info['series'] != info['title']:
|
||||
info['title'] = '%s - %s' % (info['series'], info['title'])
|
||||
|
||||
return info
|
||||
entries, show_path, show_data.get('title'),
|
||||
strip_or_none(show_data.get('metaDescription')))
|
||||
|
||||
@ -1,14 +1,15 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .theplatform import ThePlatformIE
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
smuggle_url,
|
||||
update_url_query,
|
||||
unescapeHTML,
|
||||
extract_attributes,
|
||||
get_element_by_attribute,
|
||||
)
|
||||
from ..compat import (
|
||||
compat_urlparse,
|
||||
@ -19,6 +20,43 @@ class AENetworksBaseIE(ThePlatformIE):
|
||||
_THEPLATFORM_KEY = 'crazyjava'
|
||||
_THEPLATFORM_SECRET = 's3cr3t'
|
||||
|
||||
def _extract_aen_smil(self, smil_url, video_id, auth=None):
|
||||
query = {'mbr': 'true'}
|
||||
if auth:
|
||||
query['auth'] = auth
|
||||
TP_SMIL_QUERY = [{
|
||||
'assetTypes': 'high_video_ak',
|
||||
'switch': 'hls_high_ak'
|
||||
}, {
|
||||
'assetTypes': 'high_video_s3'
|
||||
}, {
|
||||
'assetTypes': 'high_video_s3',
|
||||
'switch': 'hls_ingest_fastly'
|
||||
}]
|
||||
formats = []
|
||||
subtitles = {}
|
||||
last_e = None
|
||||
for q in TP_SMIL_QUERY:
|
||||
q.update(query)
|
||||
m_url = update_url_query(smil_url, q)
|
||||
m_url = self._sign_url(m_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
|
||||
try:
|
||||
tp_formats, tp_subtitles = self._extract_theplatform_smil(
|
||||
m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes']))
|
||||
except ExtractorError as e:
|
||||
last_e = e
|
||||
continue
|
||||
formats.extend(tp_formats)
|
||||
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
|
||||
if last_e and not formats:
|
||||
raise last_e
|
||||
self._sort_formats(formats)
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
|
||||
class AENetworksIE(AENetworksBaseIE):
|
||||
IE_NAME = 'aenetworks'
|
||||
@ -33,22 +71,25 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
(?:
|
||||
shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
|
||||
movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
|
||||
specials/(?P<special_display_id>[^/]+)/full-special|
|
||||
specials/(?P<special_display_id>[^/]+)/(?:full-special|preview-)|
|
||||
collections/[^/]+/(?P<collection_display_id>[^/]+)
|
||||
)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
|
||||
'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
|
||||
'info_dict': {
|
||||
'id': '22253814',
|
||||
'ext': 'mp4',
|
||||
'title': 'Winter Is Coming',
|
||||
'title': 'Winter is Coming',
|
||||
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
|
||||
'timestamp': 1338306241,
|
||||
'upload_date': '20120529',
|
||||
'uploader': 'AENE-NEW',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': ['ThePlatform'],
|
||||
}, {
|
||||
'url': 'http://www.history.com/shows/ancient-aliens/season-1',
|
||||
@ -84,6 +125,9 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
}, {
|
||||
'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
|
||||
'only_matching': True
|
||||
}, {
|
||||
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
|
||||
'only_matching': True
|
||||
}]
|
||||
_DOMAIN_TO_REQUESTOR_ID = {
|
||||
'history.com': 'HISTORY',
|
||||
@ -124,11 +168,6 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
return self.playlist_result(
|
||||
entries, self._html_search_meta('aetn:SeasonId', webpage))
|
||||
|
||||
query = {
|
||||
'mbr': 'true',
|
||||
'assetTypes': 'high_video_ak',
|
||||
'switch': 'hls_high_ak',
|
||||
}
|
||||
video_id = self._html_search_meta('aetn:VideoID', webpage)
|
||||
media_url = self._search_regex(
|
||||
[r"media_url\s*=\s*'(?P<url>[^']+)'",
|
||||
@ -138,64 +177,39 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
|
||||
r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
|
||||
info = self._parse_theplatform_metadata(theplatform_metadata)
|
||||
auth = None
|
||||
if theplatform_metadata.get('AETN$isBehindWall'):
|
||||
requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
|
||||
resource = self._get_mvpd_resource(
|
||||
requestor_id, theplatform_metadata['title'],
|
||||
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
|
||||
theplatform_metadata['ratings'][0]['rating'])
|
||||
query['auth'] = self._extract_mvpd_auth(
|
||||
auth = self._extract_mvpd_auth(
|
||||
url, video_id, requestor_id, resource)
|
||||
info.update(self._search_json_ld(webpage, video_id, fatal=False))
|
||||
media_url = update_url_query(media_url, query)
|
||||
media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
|
||||
formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
|
||||
self._sort_formats(formats)
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
})
|
||||
info.update(self._extract_aen_smil(media_url, video_id, auth))
|
||||
return info
|
||||
|
||||
|
||||
class HistoryTopicIE(AENetworksBaseIE):
|
||||
IE_NAME = 'history:topic'
|
||||
IE_DESC = 'History.com Topic'
|
||||
_VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
|
||||
_VALID_URL = r'https?://(?:www\.)?history\.com/topics/[^/]+/(?P<id>[\w+-]+?)-video'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
|
||||
'url': 'https://www.history.com/topics/valentines-day/history-of-valentines-day-video',
|
||||
'info_dict': {
|
||||
'id': '40700995724',
|
||||
'ext': 'mp4',
|
||||
'title': "Bet You Didn't Know: Valentine's Day",
|
||||
'title': "History of Valentine’s Day",
|
||||
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
|
||||
'timestamp': 1375819729,
|
||||
'upload_date': '20130806',
|
||||
'uploader': 'AENE-NEW',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': ['ThePlatform'],
|
||||
}, {
|
||||
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
|
||||
'info_dict':
|
||||
{
|
||||
'id': 'world-war-i-history',
|
||||
'title': 'World War I History',
|
||||
},
|
||||
'playlist_mincount': 23,
|
||||
}, {
|
||||
'url': 'http://www.history.com/topics/world-war-i-history/videos',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def theplatform_url_result(self, theplatform_url, video_id, query):
|
||||
@ -215,27 +229,19 @@ class HistoryTopicIE(AENetworksBaseIE):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
|
||||
if video_display_id:
|
||||
webpage = self._download_webpage(url, video_display_id)
|
||||
release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
|
||||
release_url = unescapeHTML(release_url)
|
||||
|
||||
return self.theplatform_url_result(
|
||||
release_url, video_id, {
|
||||
'mbr': 'true',
|
||||
'switch': 'hls',
|
||||
'assetTypes': 'high_video_ak',
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._search_regex(
|
||||
r'<phoenix-iframe[^>]+src="[^"]+\btpid=(\d+)', webpage, 'tpid')
|
||||
result = self._download_json(
|
||||
'https://feeds.video.aetnd.com/api/v2/history/videos',
|
||||
video_id, query={'filter[id]': video_id})['results'][0]
|
||||
title = result['title']
|
||||
info = self._extract_aen_smil(result['publicUrl'], video_id)
|
||||
info.update({
|
||||
'title': title,
|
||||
'description': result.get('description'),
|
||||
'duration': int_or_none(result.get('duration')),
|
||||
'timestamp': int_or_none(result.get('added'), 1000),
|
||||
})
|
||||
else:
|
||||
webpage = self._download_webpage(url, topic_id)
|
||||
entries = []
|
||||
for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
|
||||
video_attributes = extract_attributes(episode_item)
|
||||
entries.append(self.theplatform_url_result(
|
||||
video_attributes['data-release-url'], video_attributes['data-id'], {
|
||||
'mbr': 'true',
|
||||
'switch': 'hls',
|
||||
'assetTypes': 'high_video_ak',
|
||||
}))
|
||||
return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))
|
||||
return info
|
||||
|
||||
@ -4,6 +4,10 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urllib_parse_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
@ -12,12 +16,12 @@ from ..utils import (
|
||||
|
||||
|
||||
class AolIE(InfoExtractor):
|
||||
IE_NAME = 'on.aol.com'
|
||||
_VALID_URL = r'(?:aol-video:|https?://(?:(?:www|on)\.)?aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
|
||||
IE_NAME = 'aol.com'
|
||||
_VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>[0-9a-f]+)'
|
||||
|
||||
_TESTS = [{
|
||||
# video with 5min ID
|
||||
'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
|
||||
'url': 'https://www.aol.com/video/view/u-s--official-warns-of-largest-ever-irs-phone-scam/518167793/',
|
||||
'md5': '18ef68f48740e86ae94b98da815eec42',
|
||||
'info_dict': {
|
||||
'id': '518167793',
|
||||
@ -34,7 +38,7 @@ class AolIE(InfoExtractor):
|
||||
}
|
||||
}, {
|
||||
# video with vidible ID
|
||||
'url': 'http://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
|
||||
'url': 'https://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
|
||||
'info_dict': {
|
||||
'id': '5707d6b8e4b090497b04f706',
|
||||
'ext': 'mp4',
|
||||
@ -49,17 +53,29 @@ class AolIE(InfoExtractor):
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://on.aol.com/partners/abc-551438d309eab105804dbfe8/sneak-peek-was-haley-really-framed-570eaebee4b0448640a5c944',
|
||||
'url': 'https://www.aol.com/video/view/park-bench-season-2-trailer/559a1b9be4b0c3bfad3357a7/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://on.aol.com/video/519442220',
|
||||
'url': 'https://www.aol.com/video/view/donald-trump-spokeswoman-tones-down-megyn-kelly-attacks/519442220/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'aol-video:5707d6b8e4b090497b04f706',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.aol.com/video/playlist/PL8245/5ca79d19d21f1a04035db606/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.aol.ca/video/view/u-s-woman-s-family-arrested-for-murder-first-pinned-on-panhandler-police/5c7ccf45bc03931fa04b2fe1/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.aol.co.uk/video/view/-one-dead-and-22-hurt-in-bus-crash-/5cb3a6f3d21f1a072b457347/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.aol.de/video/view/eva-braun-privataufnahmen-von-hitlers-geliebter-werden-digitalisiert/5cb2d49de98ab54c113d3d5d/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -73,7 +89,7 @@ class AolIE(InfoExtractor):
|
||||
|
||||
video_data = response['data']
|
||||
formats = []
|
||||
m3u8_url = video_data.get('videoMasterPlaylist')
|
||||
m3u8_url = url_or_none(video_data.get('videoMasterPlaylist'))
|
||||
if m3u8_url:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
|
||||
@ -96,6 +112,12 @@ class AolIE(InfoExtractor):
|
||||
'width': int(mobj.group(1)),
|
||||
'height': int(mobj.group(2)),
|
||||
})
|
||||
else:
|
||||
qs = compat_parse_qs(compat_urllib_parse_urlparse(video_url).query)
|
||||
f.update({
|
||||
'width': int_or_none(qs.get('w', [None])[0]),
|
||||
'height': int_or_none(qs.get('h', [None])[0]),
|
||||
})
|
||||
formats.append(f)
|
||||
self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
|
||||
|
||||
|
||||
37
youtube_dl/extractor/bfi.py
Normal file
37
youtube_dl/extractor/bfi.py
Normal file
@ -0,0 +1,37 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import extract_attributes
|
||||
|
||||
|
||||
class BFIPlayerIE(InfoExtractor):
|
||||
IE_NAME = 'bfi:player'
|
||||
_VALID_URL = r'https?://player\.bfi\.org\.uk/[^/]+/film/watch-(?P<id>[\w-]+)-online'
|
||||
_TEST = {
|
||||
'url': 'https://player.bfi.org.uk/free/film/watch-computer-doctor-1974-online',
|
||||
'md5': 'e8783ebd8e061ec4bc6e9501ed547de8',
|
||||
'info_dict': {
|
||||
'id': 'htNnhlZjE60C9VySkQEIBtU-cNV1Xx63',
|
||||
'ext': 'mp4',
|
||||
'title': 'Computer Doctor',
|
||||
'description': 'md5:fb6c240d40c4dbe40428bdd62f78203b',
|
||||
},
|
||||
'skip': 'BFI Player films cannot be played outside of the UK',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
entries = []
|
||||
for player_el in re.findall(r'(?s)<[^>]+class="player"[^>]*>', webpage):
|
||||
player_attr = extract_attributes(player_el)
|
||||
ooyala_id = player_attr.get('data-video-id')
|
||||
if not ooyala_id:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
'ooyala:' + ooyala_id, 'Ooyala',
|
||||
ooyala_id, player_attr.get('data-label')))
|
||||
return self.playlist_result(entries)
|
||||
@ -28,7 +28,7 @@ class BIQLEIE(InfoExtractor):
|
||||
'url': 'http://biqle.org/watch/-44781847_168547604',
|
||||
'md5': '7f24e72af1db0edf7c1aaba513174f97',
|
||||
'info_dict': {
|
||||
'id': '168547604',
|
||||
'id': '-44781847_168547604',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ребенок в шоке от автоматической мойки',
|
||||
'timestamp': 1396633454,
|
||||
|
||||
@ -1,6 +1,8 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .adobepass import AdobePassIE
|
||||
from ..utils import (
|
||||
smuggle_url,
|
||||
@ -12,16 +14,16 @@ from ..utils import (
|
||||
class BravoTVIE(AdobePassIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.bravotv.com/last-chance-kitchen/season-5/videos/lck-ep-12-fishy-finale',
|
||||
'md5': '9086d0b7ef0ea2aabc4781d75f4e5863',
|
||||
'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
|
||||
'md5': 'e34684cfea2a96cd2ee1ef3a60909de9',
|
||||
'info_dict': {
|
||||
'id': 'zHyk1_HU_mPy',
|
||||
'id': 'epL0pmK1kQlT',
|
||||
'ext': 'mp4',
|
||||
'title': 'LCK Ep 12: Fishy Finale',
|
||||
'description': 'S13/E12: Two eliminated chefs have just 12 minutes to cook up a delicious fish dish.',
|
||||
'title': 'The Top Chef Season 16 Winner Is...',
|
||||
'description': 'Find out who takes the title of Top Chef!',
|
||||
'uploader': 'NBCU-BRAV',
|
||||
'upload_date': '20160302',
|
||||
'timestamp': 1456945320,
|
||||
'upload_date': '20190314',
|
||||
'timestamp': 1552591860,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
|
||||
@ -32,30 +34,38 @@ class BravoTVIE(AdobePassIE):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
settings = self._parse_json(self._search_regex(
|
||||
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', webpage, 'drupal settings'),
|
||||
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>({.+?})</script>', webpage, 'drupal settings'),
|
||||
display_id)
|
||||
info = {}
|
||||
query = {
|
||||
'mbr': 'true',
|
||||
}
|
||||
account_pid, release_pid = [None] * 2
|
||||
tve = settings.get('sharedTVE')
|
||||
tve = settings.get('ls_tve')
|
||||
if tve:
|
||||
query['manifest'] = 'm3u'
|
||||
mobj = re.search(r'<[^>]+id="pdk-player"[^>]+data-url=["\']?(?:https?:)?//player\.theplatform\.com/p/([^/]+)/(?:[^/]+/)*select/([^?#&"\']+)', webpage)
|
||||
if mobj:
|
||||
account_pid, tp_path = mobj.groups()
|
||||
release_pid = tp_path.strip('/').split('/')[-1]
|
||||
else:
|
||||
account_pid = 'HNK2IC'
|
||||
release_pid = tve['release_pid']
|
||||
tp_path = release_pid = tve['release_pid']
|
||||
if tve.get('entitlement') == 'auth':
|
||||
adobe_pass = settings.get('adobePass', {})
|
||||
adobe_pass = settings.get('tve_adobe_auth', {})
|
||||
resource = self._get_mvpd_resource(
|
||||
adobe_pass.get('adobePassResourceId', 'bravo'),
|
||||
tve['title'], release_pid, tve.get('rating'))
|
||||
query['auth'] = self._extract_mvpd_auth(
|
||||
url, release_pid, adobe_pass.get('adobePassRequestorId', 'bravo'), resource)
|
||||
else:
|
||||
shared_playlist = settings['shared_playlist']
|
||||
shared_playlist = settings['ls_playlist']
|
||||
account_pid = shared_playlist['account_pid']
|
||||
metadata = shared_playlist['video_metadata'][shared_playlist['default_clip']]
|
||||
release_pid = metadata['release_pid']
|
||||
tp_path = release_pid = metadata.get('release_pid')
|
||||
if not release_pid:
|
||||
release_pid = metadata['guid']
|
||||
tp_path = 'media/guid/2140479951/' + release_pid
|
||||
info.update({
|
||||
'title': metadata['title'],
|
||||
'description': metadata.get('description'),
|
||||
@ -67,7 +77,7 @@ class BravoTVIE(AdobePassIE):
|
||||
'_type': 'url_transparent',
|
||||
'id': release_pid,
|
||||
'url': smuggle_url(update_url_query(
|
||||
'http://link.theplatform.com/s/%s/%s' % (account_pid, release_pid),
|
||||
'http://link.theplatform.com/s/%s/%s' % (account_pid, tp_path),
|
||||
query), {'force_smil_url': True}),
|
||||
'ie_key': 'ThePlatform',
|
||||
})
|
||||
|
||||
@ -13,13 +13,17 @@ from ..utils import (
|
||||
|
||||
class CBSBaseIE(ThePlatformFeedIE):
|
||||
def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
|
||||
closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
|
||||
return {
|
||||
'en': [{
|
||||
'ext': 'ttml',
|
||||
'url': closed_caption_e.attrib['value'],
|
||||
}]
|
||||
} if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
|
||||
subtitles = {}
|
||||
for k, ext in [('sMPTE-TTCCURL', 'tt'), ('ClosedCaptionURL', 'ttml'), ('webVTTCaptionURL', 'vtt')]:
|
||||
cc_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', k)
|
||||
if cc_e is not None:
|
||||
cc_url = cc_e.get('value')
|
||||
if cc_url:
|
||||
subtitles.setdefault(subtitles_lang, []).append({
|
||||
'ext': ext,
|
||||
'url': cc_url,
|
||||
})
|
||||
return subtitles
|
||||
|
||||
|
||||
class CBSIE(CBSBaseIE):
|
||||
|
||||
@ -2019,6 +2019,8 @@ class InfoExtractor(object):
|
||||
if res is False:
|
||||
return []
|
||||
mpd_doc, urlh = res
|
||||
if mpd_doc is None:
|
||||
return []
|
||||
mpd_base_url = base_url(urlh.geturl())
|
||||
|
||||
return self._parse_mpd_formats(
|
||||
|
||||
@ -58,10 +58,17 @@ class DigitallySpeakingIE(InfoExtractor):
|
||||
stream_name = xpath_text(a_format, 'streamName', fatal=True)
|
||||
video_path = re.match(r'mp4\:(?P<path>.*)', stream_name).group('path')
|
||||
url = video_root + video_path
|
||||
vbr = xpath_text(a_format, 'bitrate')
|
||||
bitrate = xpath_text(a_format, 'bitrate')
|
||||
tbr = int_or_none(bitrate)
|
||||
vbr = int_or_none(self._search_regex(
|
||||
r'-(\d+)\.mp4', video_path, 'vbr', default=None))
|
||||
abr = tbr - vbr if tbr and vbr else None
|
||||
video_formats.append({
|
||||
'format_id': bitrate,
|
||||
'url': url,
|
||||
'vbr': int_or_none(vbr),
|
||||
'tbr': tbr,
|
||||
'vbr': vbr,
|
||||
'abr': abr,
|
||||
})
|
||||
return video_formats
|
||||
|
||||
|
||||
@ -10,16 +10,16 @@ from ..utils import (
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
mimetype2ext,
|
||||
try_get,
|
||||
unescapeHTML,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
class DVTVIE(InfoExtractor):
|
||||
IE_NAME = 'dvtv'
|
||||
IE_DESC = 'http://video.aktualne.cz/'
|
||||
|
||||
_VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
|
||||
'md5': '67cb83e4a955d36e1b5d31993134a0c2',
|
||||
@ -28,11 +28,13 @@ class DVTVIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně',
|
||||
'duration': 1484,
|
||||
'upload_date': '20141217',
|
||||
'timestamp': 1418792400,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
|
||||
'info_dict': {
|
||||
'title': r're:^DVTV 16\. 12\. 2014: útok Talibanu, boj o kliniku, uprchlíci',
|
||||
'title': r'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci',
|
||||
'id': '973eb3bc854e11e498be002590604f2e',
|
||||
},
|
||||
'playlist': [{
|
||||
@ -84,6 +86,8 @@ class DVTVIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Zeman si jen léčí mindráky, Sobotku nenávidí a Babiš se mu teď hodí, tvrdí Kmenta',
|
||||
'duration': 1103,
|
||||
'upload_date': '20170511',
|
||||
'timestamp': 1494514200,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
@ -91,19 +95,35 @@ class DVTVIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Test live stream video (liveStarter) parsing
|
||||
'url': 'https://video.aktualne.cz/dvtv/zive-mistryne-sveta-eva-samkova-po-navratu-ze-sampionatu/r~182654c2288811e990fd0cc47ab5f122/',
|
||||
'md5': '2e552e483f2414851ca50467054f9d5d',
|
||||
'info_dict': {
|
||||
'id': '8d116360288011e98c840cc47ab5f122',
|
||||
'ext': 'mp4',
|
||||
'title': 'Živě: Mistryně světa Eva Samková po návratu ze šampionátu',
|
||||
'upload_date': '20190204',
|
||||
'timestamp': 1549289591,
|
||||
},
|
||||
'params': {
|
||||
# Video content is no longer available
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _parse_video_metadata(self, js, video_id, live_js=None):
|
||||
def _parse_video_metadata(self, js, video_id, timestamp):
|
||||
data = self._parse_json(js, video_id, transform_source=js_to_json)
|
||||
if live_js:
|
||||
data.update(self._parse_json(
|
||||
live_js, video_id, transform_source=js_to_json))
|
||||
|
||||
title = unescapeHTML(data['title'])
|
||||
|
||||
live_starter = try_get(data, lambda x: x['plugins']['liveStarter'], dict)
|
||||
if live_starter:
|
||||
data.update(live_starter)
|
||||
|
||||
formats = []
|
||||
for video in data['sources']:
|
||||
video_url = video.get('file')
|
||||
for tracks in data.get('tracks', {}).values():
|
||||
for video in tracks:
|
||||
video_url = video.get('src')
|
||||
if not video_url:
|
||||
continue
|
||||
video_type = video.get('type')
|
||||
@ -136,41 +156,29 @@ class DVTVIE(InfoExtractor):
|
||||
'description': data.get('description'),
|
||||
'thumbnail': data.get('image'),
|
||||
'duration': int_or_none(data.get('duration')),
|
||||
'timestamp': int_or_none(data.get('pubtime')),
|
||||
'timestamp': int_or_none(timestamp),
|
||||
'formats': formats
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
timestamp = parse_iso8601(self._html_search_meta(
|
||||
'article:published_time', webpage, 'published time', default=None))
|
||||
|
||||
# live content
|
||||
live_item = self._search_regex(
|
||||
r'(?s)embedData[0-9a-f]{32}\.asset\.liveStarter\s*=\s*(\{.+?\});',
|
||||
webpage, 'video', default=None)
|
||||
|
||||
# single video
|
||||
item = self._search_regex(
|
||||
r'(?s)embedData[0-9a-f]{32}\[["\']asset["\']\]\s*=\s*(\{.+?\});',
|
||||
webpage, 'video', default=None)
|
||||
|
||||
if item:
|
||||
return self._parse_video_metadata(item, video_id, live_item)
|
||||
|
||||
# playlist
|
||||
items = re.findall(
|
||||
r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);",
|
||||
webpage)
|
||||
if not items:
|
||||
items = re.findall(r'(?s)var\s+asset\s*=\s*({.+?});\n', webpage)
|
||||
|
||||
items = re.findall(r'(?s)playlist\.push\(({.+?})\);', webpage)
|
||||
if items:
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'entries': [self._parse_video_metadata(i, video_id) for i in items]
|
||||
}
|
||||
return self.playlist_result(
|
||||
[self._parse_video_metadata(i, video_id, timestamp) for i in items],
|
||||
video_id, self._html_search_meta('twitter:title', webpage))
|
||||
|
||||
item = self._search_regex(
|
||||
r'(?s)BBXPlayer\.setup\((.+?)\);',
|
||||
webpage, 'video', default=None)
|
||||
if item:
|
||||
# remove function calls (ex. htmldeentitize)
|
||||
# TODO this should be fixed in a general way in the js_to_json
|
||||
item = re.sub(r'\w+?\((.+)\)', r'\1', item)
|
||||
return self._parse_video_metadata(item, video_id, timestamp)
|
||||
|
||||
raise ExtractorError('Could not find neither video nor playlist')
|
||||
|
||||
@ -20,6 +20,7 @@ from .acast import (
|
||||
)
|
||||
from .addanime import AddAnimeIE
|
||||
from .adn import ADNIE
|
||||
from .adobeconnect import AdobeConnectIE
|
||||
from .adobetv import (
|
||||
AdobeTVIE,
|
||||
AdobeTVShowIE,
|
||||
@ -106,6 +107,7 @@ from .behindkink import BehindKinkIE
|
||||
from .bellmedia import BellMediaIE
|
||||
from .beatport import BeatportIE
|
||||
from .bet import BetIE
|
||||
from .bfi import BFIPlayerIE
|
||||
from .bigflix import BigflixIE
|
||||
from .bild import BildIE
|
||||
from .bilibili import (
|
||||
@ -440,10 +442,7 @@ from .goshgay import GoshgayIE
|
||||
from .gputechconf import GPUTechConfIE
|
||||
from .groupon import GrouponIE
|
||||
from .hark import HarkIE
|
||||
from .hbo import (
|
||||
HBOIE,
|
||||
HBOEpisodeIE,
|
||||
)
|
||||
from .hbo import HBOIE
|
||||
from .hearthisat import HearThisAtIE
|
||||
from .heise import HeiseIE
|
||||
from .hellporno import HellPornoIE
|
||||
@ -635,6 +634,7 @@ from .mediaset import MediasetIE
|
||||
from .mediasite import (
|
||||
MediasiteIE,
|
||||
MediasiteCatalogIE,
|
||||
MediasiteNamedCatalogIE,
|
||||
)
|
||||
from .medici import MediciIE
|
||||
from .megaphone import MegaphoneIE
|
||||
@ -808,6 +808,8 @@ from .nrk import (
|
||||
NRKTVSeasonIE,
|
||||
NRKTVSeriesIE,
|
||||
)
|
||||
from .nrl import NRLTVIE
|
||||
from .ntvcojp import NTVCoJpCUIE
|
||||
from .ntvde import NTVDeIE
|
||||
from .ntvru import NTVRuIE
|
||||
from .nytimes import (
|
||||
@ -868,6 +870,10 @@ from .picarto import (
|
||||
from .piksel import PikselIE
|
||||
from .pinkbike import PinkbikeIE
|
||||
from .pladform import PladformIE
|
||||
from .platzi import (
|
||||
PlatziIE,
|
||||
PlatziCourseIE,
|
||||
)
|
||||
from .playfm import PlayFMIE
|
||||
from .playplustv import PlayPlusTVIE
|
||||
from .plays import PlaysTVIE
|
||||
@ -1089,6 +1095,7 @@ from .streamcloud import StreamcloudIE
|
||||
from .streamcz import StreamCZIE
|
||||
from .streetvoice import StreetVoiceIE
|
||||
from .stretchinternet import StretchInternetIE
|
||||
from .stv import STVPlayerIE
|
||||
from .sunporno import SunPornoIE
|
||||
from .svt import (
|
||||
SVTIE,
|
||||
@ -1447,6 +1454,8 @@ from .xxxymovies import XXXYMoviesIE
|
||||
from .yahoo import (
|
||||
YahooIE,
|
||||
YahooSearchIE,
|
||||
YahooGyaOPlayerIE,
|
||||
YahooGyaOIE,
|
||||
)
|
||||
from .yandexdisk import YandexDiskIE
|
||||
from .yandexmusic import (
|
||||
|
||||
@ -4,12 +4,17 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urllib_parse_unquote,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
strip_or_none,
|
||||
try_get,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
@ -46,6 +51,29 @@ class GaiaIE(InfoExtractor):
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
_NETRC_MACHINE = 'gaia'
|
||||
_jwt = None
|
||||
|
||||
def _real_initialize(self):
|
||||
auth = self._get_cookies('https://www.gaia.com/').get('auth')
|
||||
if auth:
|
||||
auth = self._parse_json(
|
||||
compat_urllib_parse_unquote(auth.value),
|
||||
None, fatal=False)
|
||||
if not auth:
|
||||
username, password = self._get_login_info()
|
||||
if username is None:
|
||||
return
|
||||
auth = self._download_json(
|
||||
'https://auth.gaia.com/v1/login',
|
||||
None, data=urlencode_postdata({
|
||||
'username': username,
|
||||
'password': password
|
||||
}))
|
||||
if auth.get('success') is False:
|
||||
raise ExtractorError(', '.join(auth['messages']), expected=True)
|
||||
if auth:
|
||||
self._jwt = auth.get('jwt')
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id, vtype = re.search(self._VALID_URL, url).groups()
|
||||
@ -59,8 +87,12 @@ class GaiaIE(InfoExtractor):
|
||||
media_id = compat_str(vdata['nid'])
|
||||
title = node['title']
|
||||
|
||||
headers = None
|
||||
if self._jwt:
|
||||
headers = {'Authorization': 'Bearer ' + self._jwt}
|
||||
media = self._download_json(
|
||||
'https://brooklyn.gaia.com/media/' + media_id, media_id)
|
||||
'https://brooklyn.gaia.com/media/' + media_id,
|
||||
media_id, headers=headers)
|
||||
formats = self._extract_m3u8_formats(
|
||||
media['mediaUrls']['bcHLS'], media_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
@ -3,22 +3,24 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .kaltura import KalturaIE
|
||||
from ..utils import (
|
||||
HEADRequest,
|
||||
sanitized_Request,
|
||||
smuggle_url,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class GDCVaultIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)?'
|
||||
_VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)(?:/(?P<name>[\w-]+))?'
|
||||
_NETRC_MACHINE = 'gdcvault'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
|
||||
'md5': '7ce8388f544c88b7ac11c7ab1b593704',
|
||||
'info_dict': {
|
||||
'id': '1019721',
|
||||
'id': '201311826596_AWNY',
|
||||
'display_id': 'Doki-Doki-Universe-Sweet-Simple',
|
||||
'ext': 'mp4',
|
||||
'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
|
||||
@ -27,7 +29,7 @@ class GDCVaultIE(InfoExtractor):
|
||||
{
|
||||
'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
|
||||
'info_dict': {
|
||||
'id': '1015683',
|
||||
'id': '201203272_1330951438328RSXR',
|
||||
'display_id': 'Embracing-the-Dark-Art-of',
|
||||
'ext': 'flv',
|
||||
'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
|
||||
@ -56,7 +58,7 @@ class GDCVaultIE(InfoExtractor):
|
||||
'url': 'http://gdcvault.com/play/1023460/Tenacious-Design-and-The-Interface',
|
||||
'md5': 'a8efb6c31ed06ca8739294960b2dbabd',
|
||||
'info_dict': {
|
||||
'id': '1023460',
|
||||
'id': '840376_BQRC',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'Tenacious-Design-and-The-Interface',
|
||||
'title': 'Tenacious Design and The Interface of \'Destiny\'',
|
||||
@ -66,26 +68,38 @@ class GDCVaultIE(InfoExtractor):
|
||||
# Multiple audios
|
||||
'url': 'http://www.gdcvault.com/play/1014631/Classic-Game-Postmortem-PAC',
|
||||
'info_dict': {
|
||||
'id': '1014631',
|
||||
'ext': 'flv',
|
||||
'id': '12396_1299111843500GMPX',
|
||||
'ext': 'mp4',
|
||||
'title': 'How to Create a Good Game - From My Experience of Designing Pac-Man',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # Requires rtmpdump
|
||||
'format': 'jp', # The japanese audio
|
||||
}
|
||||
# 'params': {
|
||||
# 'skip_download': True, # Requires rtmpdump
|
||||
# 'format': 'jp', # The japanese audio
|
||||
# }
|
||||
},
|
||||
{
|
||||
# gdc-player.html
|
||||
'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo',
|
||||
'info_dict': {
|
||||
'id': '1435',
|
||||
'id': '9350_1238021887562UHXB',
|
||||
'display_id': 'An-American-engine-in-Tokyo',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT',
|
||||
},
|
||||
},
|
||||
{
|
||||
# Kaltura Embed
|
||||
'url': 'https://www.gdcvault.com/play/1026180/Mastering-the-Apex-of-Scaling',
|
||||
'info_dict': {
|
||||
'id': '0_h1fg8j3p',
|
||||
'ext': 'mp4',
|
||||
'title': 'Mastering the Apex of Scaling Game Servers (Presented by Multiplay)',
|
||||
'timestamp': 1554401811,
|
||||
'upload_date': '20190404',
|
||||
'uploader_id': 'joe@blazestreaming.com',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # Requires rtmpdump
|
||||
'format': 'mp4-408',
|
||||
},
|
||||
},
|
||||
]
|
||||
@ -114,10 +128,8 @@ class GDCVaultIE(InfoExtractor):
|
||||
return start_page
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('name') or video_id
|
||||
video_id, name = re.match(self._VALID_URL, url).groups()
|
||||
display_id = name or video_id
|
||||
|
||||
webpage_url = 'http://www.gdcvault.com/play/' + video_id
|
||||
start_page = self._download_webpage(webpage_url, display_id)
|
||||
@ -127,12 +139,12 @@ class GDCVaultIE(InfoExtractor):
|
||||
start_page, 'url', default=None)
|
||||
if direct_url:
|
||||
title = self._html_search_regex(
|
||||
r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>',
|
||||
r'<td><strong>Session Name:?</strong></td>\s*<td>(.*?)</td>',
|
||||
start_page, 'title')
|
||||
video_url = 'http://www.gdcvault.com' + direct_url
|
||||
# resolve the url so that we can detect the correct extension
|
||||
head = self._request_webpage(HEADRequest(video_url), video_id)
|
||||
video_url = head.geturl()
|
||||
video_url = self._request_webpage(
|
||||
HEADRequest(video_url), video_id).geturl()
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
@ -141,6 +153,11 @@ class GDCVaultIE(InfoExtractor):
|
||||
'title': title,
|
||||
}
|
||||
|
||||
embed_url = KalturaIE._extract_url(start_page)
|
||||
if embed_url:
|
||||
embed_url = smuggle_url(embed_url, {'source_url': url})
|
||||
ie_key = 'Kaltura'
|
||||
else:
|
||||
PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>'
|
||||
|
||||
xml_root = self._html_search_regex(
|
||||
@ -157,18 +174,15 @@ class GDCVaultIE(InfoExtractor):
|
||||
PLAYER_REGEX, start_page, 'xml root')
|
||||
|
||||
xml_name = self._html_search_regex(
|
||||
r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>',
|
||||
start_page, 'xml filename', default=None)
|
||||
if xml_name is None:
|
||||
# Fallback to the older format
|
||||
xml_name = self._html_search_regex(
|
||||
r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>',
|
||||
r'<iframe src=".*?\?xml(?:=|URL=xml/)(.+?\.xml).*?".*?</iframe>',
|
||||
start_page, 'xml filename')
|
||||
embed_url = '%s/xml/%s' % (xml_root, xml_name)
|
||||
ie_key = 'DigitallySpeaking'
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': '%s/xml/%s' % (xml_root, xml_name),
|
||||
'ie_key': 'DigitallySpeaking',
|
||||
'url': embed_url,
|
||||
'ie_key': ie_key,
|
||||
}
|
||||
|
||||
@ -4,16 +4,28 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
xpath_text,
|
||||
xpath_element,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class HBOBaseIE(InfoExtractor):
|
||||
class HBOIE(InfoExtractor):
|
||||
IE_NAME = 'hbo'
|
||||
_VALID_URL = r'https?://(?:www\.)?hbo\.com/(?:video|embed)(?:/[^/]+)*/(?P<id>[^/?#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.hbo.com/video/game-of-thrones/seasons/season-8/videos/trailer',
|
||||
'md5': '8126210656f433c452a21367f9ad85b3',
|
||||
'info_dict': {
|
||||
'id': '22113301',
|
||||
'ext': 'mp4',
|
||||
'title': 'Game of Thrones - Trailer',
|
||||
},
|
||||
'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'],
|
||||
}
|
||||
_FORMATS_INFO = {
|
||||
'pro7': {
|
||||
'width': 1280,
|
||||
@ -53,10 +65,17 @@ class HBOBaseIE(InfoExtractor):
|
||||
},
|
||||
}
|
||||
|
||||
def _extract_from_id(self, video_id):
|
||||
video_data = self._download_xml(
|
||||
'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id)
|
||||
title = xpath_text(video_data, 'title', 'title', True)
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
location_path = self._parse_json(self._html_search_regex(
|
||||
r'data-state="({.+?})"', webpage, 'state'), display_id)['video']['locationUrl']
|
||||
video_data = self._download_xml(urljoin(url, location_path), display_id)
|
||||
video_id = xpath_text(video_data, 'id', fatal=True)
|
||||
episode_title = title = xpath_text(video_data, 'title', fatal=True)
|
||||
series = xpath_text(video_data, 'program')
|
||||
if series:
|
||||
title = '%s - %s' % (series, title)
|
||||
|
||||
formats = []
|
||||
for source in xpath_element(video_data, 'videos', 'sources', True):
|
||||
@ -128,68 +147,23 @@ class HBOBaseIE(InfoExtractor):
|
||||
'width': width,
|
||||
})
|
||||
|
||||
subtitles = None
|
||||
caption_url = xpath_text(video_data, 'captionUrl')
|
||||
if caption_url:
|
||||
subtitles = {
|
||||
'en': [{
|
||||
'url': caption_url,
|
||||
'ext': 'ttml'
|
||||
}],
|
||||
}
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'duration': parse_duration(xpath_text(video_data, 'duration/tv14')),
|
||||
'series': series,
|
||||
'episode': episode_title,
|
||||
'formats': formats,
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
|
||||
class HBOIE(HBOBaseIE):
|
||||
IE_NAME = 'hbo'
|
||||
_VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
|
||||
'md5': '2c6a6bc1222c7e91cb3334dad1746e5a',
|
||||
'info_dict': {
|
||||
'id': '1437839',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ep. 64 Clip: Encryption',
|
||||
'thumbnail': r're:https?://.*\.jpg$',
|
||||
'duration': 1072,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
return self._extract_from_id(video_id)
|
||||
|
||||
|
||||
class HBOEpisodeIE(HBOBaseIE):
|
||||
IE_NAME = 'hbo:episode'
|
||||
_VALID_URL = r'https?://(?:www\.)?hbo\.com/(?P<path>(?!video)(?:(?:[^/]+/)+video|watch-free-episodes)/(?P<id>[0-9a-z-]+))(?:\.html)?'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true',
|
||||
'md5': '61ead79b9c0dfa8d3d4b07ef4ac556fb',
|
||||
'info_dict': {
|
||||
'id': '1439518',
|
||||
'display_id': 'ep-52-inside-the-episode',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ep. 52: Inside the Episode',
|
||||
'thumbnail': r're:https?://.*\.jpg$',
|
||||
'duration': 240,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.hbo.com/game-of-thrones/about/video/season-5-invitation-to-the-set.html?autoplay=true',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.hbo.com/watch-free-episodes/last-week-tonight-with-john-oliver',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
path, display_id = re.match(self._VALID_URL, url).groups()
|
||||
|
||||
content = self._download_json(
|
||||
'http://www.hbo.com/api/content/' + path, display_id)['content']
|
||||
|
||||
video_id = compat_str((content.get('parsed', {}).get(
|
||||
'common:FullBleedVideo', {}) or content['selectedEpisode'])['videoId'])
|
||||
|
||||
info_dict = self._extract_from_id(video_id)
|
||||
info_dict['display_id'] = display_id
|
||||
|
||||
return info_dict
|
||||
|
||||
@ -7,7 +7,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class JWPlatformIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
|
||||
_VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
|
||||
_TESTS = [{
|
||||
'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
|
||||
'md5': 'fa8899fa601eb7c83a64e9d568bdf325',
|
||||
|
||||
@ -145,6 +145,8 @@ class KalturaIE(InfoExtractor):
|
||||
)
|
||||
if mobj:
|
||||
embed_info = mobj.groupdict()
|
||||
for k, v in embed_info.items():
|
||||
embed_info[k] = v.strip()
|
||||
url = 'kaltura:%(partner_id)s:%(id)s' % embed_info
|
||||
escaped_pid = re.escape(embed_info['partner_id'])
|
||||
service_url = re.search(
|
||||
|
||||
@ -9,11 +9,13 @@ from ..utils import (
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
urlencode_postdata,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class LinkedInLearningBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'linkedin'
|
||||
_LOGIN_URL = 'https://www.linkedin.com/uas/login?trk=learning'
|
||||
|
||||
def _call_api(self, course_slug, fields, video_slug=None, resolution=None):
|
||||
query = {
|
||||
@ -50,11 +52,10 @@ class LinkedInLearningBaseIE(InfoExtractor):
|
||||
return
|
||||
|
||||
login_page = self._download_webpage(
|
||||
'https://www.linkedin.com/uas/login?trk=learning',
|
||||
None, 'Downloading login page')
|
||||
action_url = self._search_regex(
|
||||
self._LOGIN_URL, None, 'Downloading login page')
|
||||
action_url = urljoin(self._LOGIN_URL, self._search_regex(
|
||||
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, 'post url',
|
||||
default='https://www.linkedin.com/uas/login-submit', group='url')
|
||||
default='https://www.linkedin.com/uas/login-submit', group='url'))
|
||||
data = self._hidden_inputs(login_page)
|
||||
data.update({
|
||||
'session_key': email,
|
||||
|
||||
@ -22,7 +22,7 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
_ID_RE = r'[0-9a-f]{32,34}'
|
||||
_ID_RE = r'(?:[0-9a-f]{32,34}|[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12,14})'
|
||||
|
||||
|
||||
class MediasiteIE(InfoExtractor):
|
||||
@ -98,6 +98,11 @@ class MediasiteIE(InfoExtractor):
|
||||
'url': 'https://mediasite.ntnu.no/Mediasite/Showcase/default/Presentation/7d8b913259334b688986e970fae6fcb31d',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# dashed id
|
||||
'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271-681e-4f19-9af3-c60d1f82869b1d',
|
||||
'only_matching': True,
|
||||
}
|
||||
]
|
||||
|
||||
# look in Mediasite.Core.js (Mediasite.ContentStreamType[*])
|
||||
@ -264,6 +269,10 @@ class MediasiteCatalogIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://medaudio.medicine.iu.edu/Mediasite/Catalog/Full/9518c4a6c5cf4993b21cbd53e828a92521/97a9db45f7ab47428c77cd2ed74bb98f14/9518c4a6c5cf4993b21cbd53e828a92521',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# dashed id
|
||||
'url': 'http://events7.mediasite.com/Mediasite/Catalog/Full/631f9e48-530d-4543-8154-9f955d08c75e',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -333,3 +342,25 @@ class MediasiteCatalogIE(InfoExtractor):
|
||||
catalog, lambda x: x['CurrentFolder']['Name'], compat_str)
|
||||
|
||||
return self.playlist_result(entries, catalog_id, title,)
|
||||
|
||||
|
||||
class MediasiteNamedCatalogIE(InfoExtractor):
|
||||
_VALID_URL = r'(?xi)(?P<url>https?://[^/]+/Mediasite)/Catalog/catalogs/(?P<catalog_name>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://msite.misis.ru/Mediasite/Catalog/catalogs/2016-industrial-management-skriabin-o-o',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
mediasite_url = mobj.group('url')
|
||||
catalog_name = mobj.group('catalog_name')
|
||||
|
||||
webpage = self._download_webpage(url, catalog_name)
|
||||
|
||||
catalog_id = self._search_regex(
|
||||
r'CatalogId\s*:\s*["\'](%s)' % _ID_RE, webpage, 'catalog id')
|
||||
|
||||
return self.url_result(
|
||||
'%s/Catalog/Full/%s' % (mediasite_url, catalog_id),
|
||||
ie=MediasiteCatalogIE.ie_key(), video_id=catalog_id)
|
||||
|
||||
@ -1,22 +1,32 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import base64
|
||||
import time
|
||||
import uuid
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import int_or_none
|
||||
from ..compat import (
|
||||
compat_HTTPError,
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class MGTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
IE_DESC = '芒果TV'
|
||||
_GEO_COUNTRIES = ['CN']
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
|
||||
'md5': 'b1ffc0fc163152acf6beaa81832c9ee7',
|
||||
'info_dict': {
|
||||
'id': '3116640',
|
||||
'ext': 'mp4',
|
||||
'title': '我是歌手第四季双年巅峰会：韩红李玟“双王”领军对抗',
|
||||
'title': '我是歌手 第四季',
|
||||
'description': '我是歌手第四季双年巅峰会',
|
||||
'duration': 7461,
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
@ -28,16 +38,30 @@ class MGTVIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
try:
|
||||
api_data = self._download_json(
|
||||
'http://pcweb.api.mgtv.com/player/video', video_id,
|
||||
query={'video_id': video_id},
|
||||
headers=self.geo_verification_headers())['data']
|
||||
'https://pcweb.api.mgtv.com/player/video', video_id, query={
|
||||
'tk2': base64.urlsafe_b64encode(b'did=%s|pno=1030|ver=0.3.0301|clit=%d' % (compat_str(uuid.uuid4()).encode(), time.time()))[::-1],
|
||||
'video_id': video_id,
|
||||
}, headers=self.geo_verification_headers())['data']
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
|
||||
error = self._parse_json(e.cause.read().decode(), None)
|
||||
if error.get('code') == 40005:
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
raise ExtractorError(error['msg'], expected=True)
|
||||
raise
|
||||
info = api_data['info']
|
||||
title = info['title'].strip()
|
||||
stream_domain = api_data['stream_domain'][0]
|
||||
stream_data = self._download_json(
|
||||
'https://pcweb.api.mgtv.com/player/getSource', video_id, query={
|
||||
'pm2': api_data['atc']['pm2'],
|
||||
'video_id': video_id,
|
||||
}, headers=self.geo_verification_headers())['data']
|
||||
stream_domain = stream_data['stream_domain'][0]
|
||||
|
||||
formats = []
|
||||
for idx, stream in enumerate(api_data['stream']):
|
||||
for idx, stream in enumerate(stream_data['stream']):
|
||||
stream_path = stream.get('url')
|
||||
if not stream_path:
|
||||
continue
|
||||
@ -47,7 +71,7 @@ class MGTVIE(InfoExtractor):
|
||||
format_url = format_data.get('info')
|
||||
if not format_url:
|
||||
continue
|
||||
tbr = int_or_none(self._search_regex(
|
||||
tbr = int_or_none(stream.get('filebitrate') or self._search_regex(
|
||||
r'_(\d+)_mp4/', format_url, 'tbr', default=None))
|
||||
formats.append({
|
||||
'format_id': compat_str(tbr or idx),
|
||||
|
||||
@ -1,12 +1,17 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import base64
|
||||
import hashlib
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..aes import aes_cbc_decrypt
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
bytes_to_intlist,
|
||||
int_or_none,
|
||||
intlist_to_bytes,
|
||||
parse_codecs,
|
||||
parse_duration,
|
||||
)
|
||||
|
||||
|
||||
@ -14,7 +19,7 @@ class NewstubeIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?newstube\.ru/media/(?P<id>.+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.newstube.ru/media/telekanal-cnn-peremestil-gorod-slavyansk-v-krym',
|
||||
'md5': '801eef0c2a9f4089fa04e4fe3533abdc',
|
||||
'md5': '9d10320ad473444352f72f746ccb8b8c',
|
||||
'info_dict': {
|
||||
'id': '728e0ef2-e187-4012-bac0-5a081fdcb1f6',
|
||||
'ext': 'mp4',
|
||||
@ -25,64 +30,30 @@ class NewstubeIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
video_id = self._match_id(url)
|
||||
|
||||
page = self._download_webpage(url, video_id, 'Downloading page')
|
||||
page = self._download_webpage(url, video_id)
|
||||
title = self._html_search_meta(['og:title', 'twitter:title'], page, fatal=True)
|
||||
|
||||
video_guid = self._html_search_regex(
|
||||
r'<meta property="og:video:url" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
|
||||
r'<meta\s+property="og:video(?::(?:(?:secure_)?url|iframe))?"\s+content="https?://(?:www\.)?newstube\.ru/embed/(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
|
||||
page, 'video GUID')
|
||||
|
||||
player = self._download_xml(
|
||||
'http://p.newstube.ru/v2/player.asmx/GetAutoPlayInfo6?state=&url=%s&sessionId=&id=%s&placement=profile&location=n2' % (url, video_guid),
|
||||
video_guid, 'Downloading player XML')
|
||||
|
||||
def ns(s):
|
||||
return s.replace('/', '/%(ns)s') % {'ns': '{http://app1.newstube.ru/N2SiteWS/player.asmx}'}
|
||||
|
||||
error_message = player.find(ns('./ErrorMessage'))
|
||||
if error_message is not None:
|
||||
raise ExtractorError('%s returned error: %s' % (self.IE_NAME, error_message.text), expected=True)
|
||||
|
||||
session_id = player.find(ns('./SessionId')).text
|
||||
media_info = player.find(ns('./Medias/MediaInfo'))
|
||||
title = media_info.find(ns('./Name')).text
|
||||
description = self._og_search_description(page)
|
||||
thumbnail = media_info.find(ns('./KeyFrame')).text
|
||||
duration = int(media_info.find(ns('./Duration')).text) / 1000.0
|
||||
enc_data = base64.b64decode(self._download_webpage(
|
||||
'https://www.newstube.ru/embed/api/player/getsources2',
|
||||
video_guid, query={
|
||||
'guid': video_guid,
|
||||
'ff': 3,
|
||||
}))
|
||||
key = hashlib.pbkdf2_hmac(
|
||||
'sha1', video_guid.replace('-', '').encode(), enc_data[:16], 1)[:16]
|
||||
dec_data = aes_cbc_decrypt(
|
||||
bytes_to_intlist(enc_data[32:]), bytes_to_intlist(key),
|
||||
bytes_to_intlist(enc_data[16:32]))
|
||||
sources = self._parse_json(intlist_to_bytes(dec_data[:-dec_data[-1]]), video_guid)
|
||||
|
||||
formats = []
|
||||
|
||||
for stream_info in media_info.findall(ns('./Streams/StreamInfo')):
|
||||
media_location = stream_info.find(ns('./MediaLocation'))
|
||||
if media_location is None:
|
||||
continue
|
||||
|
||||
server = media_location.find(ns('./Server')).text
|
||||
app = media_location.find(ns('./App')).text
|
||||
media_id = stream_info.find(ns('./Id')).text
|
||||
name = stream_info.find(ns('./Name')).text
|
||||
width = int(stream_info.find(ns('./Width')).text)
|
||||
height = int(stream_info.find(ns('./Height')).text)
|
||||
|
||||
formats.append({
|
||||
'url': 'rtmp://%s/%s' % (server, app),
|
||||
'app': app,
|
||||
'play_path': '01/%s' % video_guid.upper(),
|
||||
'rtmp_conn': ['S:%s' % session_id, 'S:%s' % media_id, 'S:n2'],
|
||||
'page_url': url,
|
||||
'ext': 'flv',
|
||||
'format_id': 'rtmp' + ('-%s' % name if name else ''),
|
||||
'width': width,
|
||||
'height': height,
|
||||
})
|
||||
|
||||
sources_data = self._download_json(
|
||||
'http://www.newstube.ru/player2/getsources?guid=%s' % video_guid,
|
||||
video_guid, fatal=False)
|
||||
if sources_data:
|
||||
for source in sources_data.get('Sources', []):
|
||||
for source in sources:
|
||||
source_url = source.get('Src')
|
||||
if not source_url:
|
||||
continue
|
||||
@ -95,13 +66,8 @@ class NewstubeIE(InfoExtractor):
|
||||
}
|
||||
source_type = source.get('Type')
|
||||
if source_type:
|
||||
mobj = re.search(r'codecs="([^,]+),\s*([^"]+)"', source_type)
|
||||
if mobj:
|
||||
vcodec, acodec = mobj.groups()
|
||||
f.update({
|
||||
'vcodec': vcodec,
|
||||
'acodec': acodec,
|
||||
})
|
||||
f.update(parse_codecs(self._search_regex(
|
||||
r'codecs="([^"]+)"', source_type, 'codecs', fatal=False)))
|
||||
formats.append(f)
|
||||
|
||||
self._check_formats(formats, video_guid)
|
||||
@ -110,8 +76,8 @@ class NewstubeIE(InfoExtractor):
|
||||
return {
|
||||
'id': video_guid,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'description': self._html_search_meta(['description', 'og:description'], page),
|
||||
'thumbnail': self._html_search_meta(['og:image:secure_url', 'og:image', 'twitter:image'], page),
|
||||
'duration': parse_duration(self._html_search_meta('duration', page)),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -1,54 +1,81 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
|
||||
class NhkVodIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/(?:vod|ondemand)/(?P<id>[^/]+/[^/?#&]+)'
|
||||
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)'
|
||||
# Content available only for a limited period of time. Visit
|
||||
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
|
||||
_TESTS = [{
|
||||
# Videos available only for a limited period of time. Visit
|
||||
# http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
|
||||
'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815',
|
||||
'info_dict': {
|
||||
'id': 'A1bnNiNTE6nY3jLllS-BIISfcC_PpvF5',
|
||||
'ext': 'flv',
|
||||
'title': 'TOKYO FASHION EXPRESS - The Kimono as Global Fashion',
|
||||
'description': 'md5:db338ee6ce8204f415b754782f819824',
|
||||
'series': 'TOKYO FASHION EXPRESS',
|
||||
'episode': 'The Kimono as Global Fashion',
|
||||
},
|
||||
'skip': 'Videos available only for a limited period of time',
|
||||
}, {
|
||||
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/plugin-20190404-1/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k'
|
||||
_API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sodesdlist/v7/episode/%s/%s/all%s.json'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
data = self._download_json(self._API_URL, video_id)
|
||||
|
||||
try:
|
||||
episode = next(
|
||||
e for e in data['data']['episodes']
|
||||
if e.get('url') and video_id in e['url'])
|
||||
except StopIteration:
|
||||
raise ExtractorError('Unable to find episode')
|
||||
|
||||
embed_code = episode['vod_id']
|
||||
lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
|
||||
if episode_id.isdigit():
|
||||
episode_id = episode_id[:4] + '-' + episode_id[4:]
|
||||
|
||||
is_video = m_type == 'video'
|
||||
episode = self._download_json(
|
||||
self._API_URL_TEMPLATE % ('v' if is_video else 'r', episode_id, lang, '/all' if is_video else ''),
|
||||
episode_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'][0]
|
||||
title = episode.get('sub_title_clean') or episode['sub_title']
|
||||
description = episode.get('description_clean') or episode.get('description')
|
||||
series = episode.get('title_clean') or episode.get('title')
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'Ooyala',
|
||||
'url': 'ooyala:%s' % embed_code,
|
||||
def get_clean_field(key):
|
||||
return episode.get(key + '_clean') or episode.get(key)
|
||||
|
||||
series = get_clean_field('title')
|
||||
|
||||
thumbnails = []
|
||||
for s, w, h in [('', 640, 360), ('_l', 1280, 720)]:
|
||||
img_path = episode.get('image' + s)
|
||||
if not img_path:
|
||||
continue
|
||||
thumbnails.append({
|
||||
'id': '%dp' % h,
|
||||
'height': h,
|
||||
'width': w,
|
||||
'url': 'https://www3.nhk.or.jp' + img_path,
|
||||
})
|
||||
|
||||
info = {
|
||||
'id': episode_id + '-' + lang,
|
||||
'title': '%s - %s' % (series, title) if series and title else title,
|
||||
'description': description,
|
||||
'description': get_clean_field('description'),
|
||||
'thumbnails': thumbnails,
|
||||
'series': series,
|
||||
'episode': title,
|
||||
}
|
||||
if is_video:
|
||||
info.update({
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'Ooyala',
|
||||
'url': 'ooyala:' + episode['vod_id'],
|
||||
})
|
||||
else:
|
||||
audio = episode['audio']
|
||||
audio_path = audio['audio']
|
||||
info['formats'] = self._extract_m3u8_formats(
|
||||
'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
|
||||
episode_id, 'm4a', m3u8_id='hls', fatal=False)
|
||||
for proto in ('rtmpt', 'rtmp'):
|
||||
info['formats'].append({
|
||||
'ext': 'flv',
|
||||
'format_id': proto,
|
||||
'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path),
|
||||
'vcodec': 'none',
|
||||
})
|
||||
for f in info['formats']:
|
||||
f['language'] = lang
|
||||
return info
|
||||
|
||||
30
youtube_dl/extractor/nrl.py
Normal file
30
youtube_dl/extractor/nrl.py
Normal file
@ -0,0 +1,30 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class NRLTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?nrl\.com/tv(/[^/]+)*/(?P<id>[^/?&#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.nrl.com/tv/news/match-highlights-titans-v-knights-862805/',
|
||||
'info_dict': {
|
||||
'id': 'YyNnFuaDE6kPJqlDhG4CGQ_w89mKTau4',
|
||||
'ext': 'mp4',
|
||||
'title': 'Match Highlights: Titans v Knights',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
q_data = self._parse_json(self._search_regex(
|
||||
r"(?s)q-data='({.+?})'", webpage, 'player data'), display_id)
|
||||
ooyala_id = q_data['videoId']
|
||||
return self.url_result(
|
||||
'ooyala:' + ooyala_id, 'Ooyala', ooyala_id, q_data.get('title'))
|
||||
49
youtube_dl/extractor/ntvcojp.py
Normal file
49
youtube_dl/extractor/ntvcojp.py
Normal file
@ -0,0 +1,49 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
js_to_json,
|
||||
smuggle_url,
|
||||
)
|
||||
|
||||
|
||||
class NTVCoJpCUIE(InfoExtractor):
|
||||
IE_NAME = 'cu.ntv.co.jp'
|
||||
IE_DESC = 'Nippon Television Network'
|
||||
_VALID_URL = r'https?://cu\.ntv\.co\.jp/(?!program)(?P<id>[^/?&#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://cu.ntv.co.jp/televiva-chill-gohan_181031/',
|
||||
'info_dict': {
|
||||
'id': '5978891207001',
|
||||
'ext': 'mp4',
|
||||
'title': '桜エビと炒り卵がポイント！ 「中華風 エビチリおにぎり」──『美虎』五十嵐美幸',
|
||||
'upload_date': '20181213',
|
||||
'description': 'md5:211b52f4fd60f3e0e72b68b0c6ba52a9',
|
||||
'uploader_id': '3855502814001',
|
||||
'timestamp': 1544669941,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
player_config = self._parse_json(self._search_regex(
|
||||
r'(?s)PLAYER_CONFIG\s*=\s*({.+?})',
|
||||
webpage, 'player config'), display_id, js_to_json)
|
||||
video_id = player_config['videoId']
|
||||
account_id = player_config.get('account') or '3855502814001'
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': self._search_regex(r'<h1[^>]+class="title"[^>]*>([^<]+)', webpage, 'title').strip(),
|
||||
'description': self._html_search_meta(['description', 'og:description'], webpage),
|
||||
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), {'geo_countries': ['JP']}),
|
||||
'ie_key': 'BrightcoveNew',
|
||||
}
|
||||
@ -36,7 +36,7 @@ class OoyalaBaseIE(InfoExtractor):
|
||||
'domain': domain,
|
||||
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
|
||||
'embedToken': embed_token,
|
||||
}), video_id)
|
||||
}), video_id, headers=self.geo_verification_headers())
|
||||
|
||||
cur_auth_data = auth_data['authorization_data'][embed_code]
|
||||
|
||||
|
||||
@ -3,6 +3,7 @@ from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import re
|
||||
import subprocess
|
||||
import tempfile
|
||||
@ -243,7 +244,7 @@ class PhantomJSwrapper(object):
|
||||
|
||||
|
||||
class OpenloadIE(InfoExtractor):
|
||||
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space))'
|
||||
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space|services)|oladblock\.(?:services|xyz|me)|openloed\.co)'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?P<host>
|
||||
@ -350,9 +351,24 @@ class OpenloadIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://oload.space/f/IY4eZSst3u8/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://oload.services/embed/bs1NWj1dCag/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://oladblock.services/f/b8NWEgkqNLI/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://oladblock.xyz/f/b8NWEgkqNLI/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://oladblock.me/f/b8NWEgkqNLI/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://openloed.co/f/b8NWEgkqNLI/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
|
||||
_USER_AGENT_TPL = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/{major}.0.{build}.{patch} Safari/537.36'
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
@ -367,7 +383,11 @@ class OpenloadIE(InfoExtractor):
|
||||
|
||||
url_pattern = 'https://%s/%%s/%s/' % (host, video_id)
|
||||
headers = {
|
||||
'User-Agent': self._USER_AGENT,
|
||||
'User-Agent': self._USER_AGENT_TPL % {
|
||||
'major': random.randint(63, 73),
|
||||
'build': random.randint(3239, 3683),
|
||||
'patch': random.randint(0, 100),
|
||||
},
|
||||
}
|
||||
|
||||
for path in ('embed', 'f'):
|
||||
|
||||
217
youtube_dl/extractor/platzi.py
Normal file
217
youtube_dl/extractor/platzi.py
Normal file
@ -0,0 +1,217 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_b64decode,
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
try_get,
|
||||
url_or_none,
|
||||
urlencode_postdata,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class PlatziIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
platzi\.com/clases| # es version
|
||||
courses\.platzi\.com/classes # en version
|
||||
)/[^/]+/(?P<id>\d+)-[^/?\#&]+
|
||||
'''
|
||||
_LOGIN_URL = 'https://platzi.com/login/'
|
||||
_NETRC_MACHINE = 'platzi'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/',
|
||||
'md5': '8f56448241005b561c10f11a595b37e3',
|
||||
'info_dict': {
|
||||
'id': '12074',
|
||||
'ext': 'mp4',
|
||||
'title': 'Creando nuestra primera página',
|
||||
'description': 'md5:4c866e45034fc76412fbf6e60ae008bc',
|
||||
'duration': 420,
|
||||
},
|
||||
'skip': 'Requires platzi account credentials',
|
||||
}, {
|
||||
'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/',
|
||||
'info_dict': {
|
||||
'id': '13430',
|
||||
'ext': 'mp4',
|
||||
'title': 'Background',
|
||||
'description': 'md5:49c83c09404b15e6e71defaf87f6b305',
|
||||
'duration': 360,
|
||||
},
|
||||
'skip': 'Requires platzi account credentials',
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
if username is None:
|
||||
return
|
||||
|
||||
login_page = self._download_webpage(
|
||||
self._LOGIN_URL, None, 'Downloading login page')
|
||||
|
||||
login_form = self._hidden_inputs(login_page)
|
||||
|
||||
login_form.update({
|
||||
'email': username,
|
||||
'password': password,
|
||||
})
|
||||
|
||||
urlh = self._request_webpage(
|
||||
self._LOGIN_URL, None, 'Logging in',
|
||||
data=urlencode_postdata(login_form),
|
||||
headers={'Referer': self._LOGIN_URL})
|
||||
|
||||
# login succeeded
|
||||
if 'platzi.com/login' not in compat_str(urlh.geturl()):
|
||||
return
|
||||
|
||||
login_error = self._webpage_read_content(
|
||||
urlh, self._LOGIN_URL, None, 'Downloading login error page')
|
||||
|
||||
login = self._parse_json(
|
||||
self._search_regex(
|
||||
r'login\s*=\s*({.+?})(?:\s*;|\s*</script)', login_error, 'login'),
|
||||
None)
|
||||
|
||||
for kind in ('error', 'password', 'nonFields'):
|
||||
error = str_or_none(login.get('%sError' % kind))
|
||||
if error:
|
||||
raise ExtractorError(
|
||||
'Unable to login: %s' % error, expected=True)
|
||||
raise ExtractorError('Unable to log in')
|
||||
|
||||
def _real_extract(self, url):
|
||||
lecture_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, lecture_id)
|
||||
|
||||
data = self._parse_json(
|
||||
self._search_regex(
|
||||
r'client_data\s*=\s*({.+?})\s*;', webpage, 'client data'),
|
||||
lecture_id)
|
||||
|
||||
material = data['initialState']['material']
|
||||
desc = material['description']
|
||||
title = desc['title']
|
||||
|
||||
formats = []
|
||||
for server_id, server in material['videos'].items():
|
||||
if not isinstance(server, dict):
|
||||
continue
|
||||
for format_id in ('hls', 'dash'):
|
||||
format_url = url_or_none(server.get(format_id))
|
||||
if not format_url:
|
||||
continue
|
||||
if format_id == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, lecture_id, 'mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id=format_id,
|
||||
note='Downloading %s m3u8 information' % server_id,
|
||||
fatal=False))
|
||||
elif format_id == 'dash':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
format_url, lecture_id, mpd_id=format_id,
|
||||
note='Downloading %s MPD manifest' % server_id,
|
||||
fatal=False))
|
||||
self._sort_formats(formats)
|
||||
|
||||
content = str_or_none(desc.get('content'))
|
||||
description = (clean_html(compat_b64decode(content).decode('utf-8'))
|
||||
if content else None)
|
||||
duration = int_or_none(material.get('duration'), invscale=60)
|
||||
|
||||
return {
|
||||
'id': lecture_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class PlatziCourseIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
platzi\.com/clases| # es version
|
||||
courses\.platzi\.com/classes # en version
|
||||
)/(?P<id>[^/?\#&]+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'https://platzi.com/clases/next-js/',
|
||||
'info_dict': {
|
||||
'id': '1311',
|
||||
'title': 'Curso de Next.js',
|
||||
},
|
||||
'playlist_count': 22,
|
||||
}, {
|
||||
'url': 'https://courses.platzi.com/classes/communication-codestream/',
|
||||
'info_dict': {
|
||||
'id': '1367',
|
||||
'title': 'Codestream Course',
|
||||
},
|
||||
'playlist_count': 14,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if PlatziIE.suitable(url) else super(PlatziCourseIE, cls).suitable(url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
course_name = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, course_name)
|
||||
|
||||
props = self._parse_json(
|
||||
self._search_regex(r'data\s*=\s*({.+?})\s*;', webpage, 'data'),
|
||||
course_name)['initialProps']
|
||||
|
||||
entries = []
|
||||
for chapter_num, chapter in enumerate(props['concepts'], 1):
|
||||
if not isinstance(chapter, dict):
|
||||
continue
|
||||
materials = chapter.get('materials')
|
||||
if not materials or not isinstance(materials, list):
|
||||
continue
|
||||
chapter_title = chapter.get('title')
|
||||
chapter_id = str_or_none(chapter.get('id'))
|
||||
for material in materials:
|
||||
if not isinstance(material, dict):
|
||||
continue
|
||||
if material.get('material_type') != 'video':
|
||||
continue
|
||||
video_url = urljoin(url, material.get('url'))
|
||||
if not video_url:
|
||||
continue
|
||||
entries.append({
|
||||
'_type': 'url_transparent',
|
||||
'url': video_url,
|
||||
'title': str_or_none(material.get('name')),
|
||||
'id': str_or_none(material.get('id')),
|
||||
'ie_key': PlatziIE.ie_key(),
|
||||
'chapter': chapter_title,
|
||||
'chapter_number': chapter_num,
|
||||
'chapter_id': chapter_id,
|
||||
})
|
||||
|
||||
course_id = compat_str(try_get(props, lambda x: x['course']['id']))
|
||||
course_title = try_get(props, lambda x: x['course']['name'], compat_str)
|
||||
|
||||
return self.playlist_result(entries, course_id, course_title)
|
||||
@ -21,7 +21,7 @@ from ..utils import (
|
||||
|
||||
class RTL2IE(InfoExtractor):
|
||||
IE_NAME = 'rtl2'
|
||||
_VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
|
||||
_VALID_URL = r'https?://(?:www\.)?rtl2\.de/sendung/[^/]+/(?:video/(?P<vico_id>\d+)[^/]+/(?P<vivi_id>\d+)-|folge/)(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
|
||||
'info_dict': {
|
||||
@ -34,10 +34,11 @@ class RTL2IE(InfoExtractor):
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
|
||||
}, {
|
||||
'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
|
||||
'info_dict': {
|
||||
'id': '21040-anna-erwischt-alex',
|
||||
'id': 'anna-erwischt-alex',
|
||||
'ext': 'mp4',
|
||||
'title': 'Anna erwischt Alex!',
|
||||
'description': 'Anna nimmt ihrem Vater nicht ab, dass er nicht spielt. Und tatsächlich erwischt sie ihn auf frischer Tat.'
|
||||
@ -46,18 +47,16 @@ class RTL2IE(InfoExtractor):
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Some rtl2 urls have no slash at the end, so append it.
|
||||
if not url.endswith('/'):
|
||||
url += '/'
|
||||
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
vico_id, vivi_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
if not vico_id:
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
mobj = re.search(
|
||||
r'<div[^>]+data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"',
|
||||
r'data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"',
|
||||
webpage)
|
||||
if mobj:
|
||||
vico_id = mobj.group('vico_id')
|
||||
@ -69,8 +68,8 @@ class RTL2IE(InfoExtractor):
|
||||
r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
|
||||
|
||||
info = self._download_json(
|
||||
'http://www.rtl2.de/sites/default/modules/rtl2/mediathek/php/get_video_jw.php',
|
||||
video_id, query={
|
||||
'https://service.rtl2.de/api-player-vipo/video.php',
|
||||
display_id, query={
|
||||
'vico_id': vico_id,
|
||||
'vivi_id': vivi_id,
|
||||
})
|
||||
@ -89,7 +88,7 @@ class RTL2IE(InfoExtractor):
|
||||
'format_id': 'rtmp',
|
||||
'url': rtmp_url,
|
||||
'play_path': stream_url,
|
||||
'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
|
||||
'player_url': 'https://www.rtl2.de/sites/default/modules/rtl2/jwplayer/jwplayer-7.6.0/jwplayer.flash.swf',
|
||||
'page_url': url,
|
||||
'flash_version': 'LNX 11,2,202,429',
|
||||
'rtmp_conn': rtmp_conn,
|
||||
@ -99,12 +98,12 @@ class RTL2IE(InfoExtractor):
|
||||
|
||||
m3u8_url = video_info.get('streamurl_hls')
|
||||
if m3u8_url:
|
||||
formats.extend(self._extract_akamai_formats(m3u8_url, video_id))
|
||||
formats.extend(self._extract_akamai_formats(m3u8_url, display_id))
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'id': display_id,
|
||||
'title': title,
|
||||
'thumbnail': video_info.get('image'),
|
||||
'description': video_info.get('beschreibung'),
|
||||
|
||||
@ -59,6 +59,20 @@ class RuutuIE(InfoExtractor):
|
||||
'url': 'http://www.ruutu.fi/video/3193728',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# audio podcast
|
||||
'url': 'https://www.supla.fi/supla/3382410',
|
||||
'md5': 'b9d7155fed37b2ebf6021d74c4b8e908',
|
||||
'info_dict': {
|
||||
'id': '3382410',
|
||||
'ext': 'mp3',
|
||||
'title': 'Mikä ihmeen poltergeist?',
|
||||
'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'age_limit': 0,
|
||||
},
|
||||
'expected_warnings': ['HTTP Error 502: Bad Gateway'],
|
||||
}
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -94,6 +108,12 @@ class RuutuIE(InfoExtractor):
|
||||
continue
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
video_url, video_id, mpd_id='dash', fatal=False))
|
||||
elif ext == 'mp3' or child.tag == 'AudioMediaFile':
|
||||
formats.append({
|
||||
'format_id': 'audio',
|
||||
'url': video_url,
|
||||
'vcodec': 'none',
|
||||
})
|
||||
else:
|
||||
proto = compat_urllib_parse_urlparse(video_url).scheme
|
||||
if not child.tag.startswith('HTTP') and proto != 'rtmp':
|
||||
|
||||
@ -15,7 +15,12 @@ from ..compat import (
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
KNOWN_EXTENSIONS,
|
||||
merge_dicts,
|
||||
mimetype2ext,
|
||||
str_or_none,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
update_url_query,
|
||||
@ -57,7 +62,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'E.T. ExTerrestrial Music',
|
||||
'timestamp': 1349920598,
|
||||
'upload_date': '20121011',
|
||||
'duration': 143,
|
||||
'duration': 143.216,
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -100,7 +105,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'jaimeMF',
|
||||
'timestamp': 1386604920,
|
||||
'upload_date': '20131209',
|
||||
'duration': 9,
|
||||
'duration': 9.927,
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -120,7 +125,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'jaimeMF',
|
||||
'timestamp': 1386604920,
|
||||
'upload_date': '20131209',
|
||||
'duration': 9,
|
||||
'duration': 9.927,
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -140,7 +145,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'oddsamples',
|
||||
'timestamp': 1389232924,
|
||||
'upload_date': '20140109',
|
||||
'duration': 17,
|
||||
'duration': 17.346,
|
||||
'license': 'cc-by-sa',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -160,7 +165,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'Ori Uplift Music',
|
||||
'timestamp': 1504206263,
|
||||
'upload_date': '20170831',
|
||||
'duration': 7449,
|
||||
'duration': 7449.096,
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -180,7 +185,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'garyvee',
|
||||
'timestamp': 1488152409,
|
||||
'upload_date': '20170226',
|
||||
'duration': 207,
|
||||
'duration': 207.012,
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
@ -192,9 +197,31 @@ class SoundcloudIE(InfoExtractor):
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
# not avaialble via api.soundcloud.com/i1/tracks/id/streams
|
||||
{
|
||||
'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer',
|
||||
'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7',
|
||||
'info_dict': {
|
||||
'id': '583011102',
|
||||
'ext': 'mp3',
|
||||
'title': 'Mezzo Valzer',
|
||||
'description': 'md5:4138d582f81866a530317bae316e8b61',
|
||||
'uploader': 'Giovanni Sarani',
|
||||
'timestamp': 1551394171,
|
||||
'upload_date': '20190228',
|
||||
'duration': 180.157,
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
},
|
||||
'expected_warnings': ['Unable to download JSON metadata'],
|
||||
}
|
||||
]
|
||||
|
||||
_CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK'
|
||||
_CLIENT_ID = 'FweeGBOOEOYJWLJN3oEyToGLKhmSz0I7'
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
@ -202,10 +229,6 @@ class SoundcloudIE(InfoExtractor):
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1',
|
||||
webpage)]
|
||||
|
||||
def report_resolve(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self.to_screen('%s: Resolving id' % video_id)
|
||||
|
||||
@classmethod
|
||||
def _resolv_url(cls, url):
|
||||
return 'https://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
|
||||
@ -224,6 +247,10 @@ class SoundcloudIE(InfoExtractor):
|
||||
def extract_count(key):
|
||||
return int_or_none(info.get('%s_count' % key))
|
||||
|
||||
like_count = extract_count('favoritings')
|
||||
if like_count is None:
|
||||
like_count = extract_count('likes')
|
||||
|
||||
result = {
|
||||
'id': track_id,
|
||||
'uploader': username,
|
||||
@ -231,15 +258,17 @@ class SoundcloudIE(InfoExtractor):
|
||||
'title': title,
|
||||
'description': info.get('description'),
|
||||
'thumbnail': thumbnail,
|
||||
'duration': int_or_none(info.get('duration'), 1000),
|
||||
'duration': float_or_none(info.get('duration'), 1000),
|
||||
'webpage_url': info.get('permalink_url'),
|
||||
'license': info.get('license'),
|
||||
'view_count': extract_count('playback'),
|
||||
'like_count': extract_count('favoritings'),
|
||||
'like_count': like_count,
|
||||
'comment_count': extract_count('comment'),
|
||||
'repost_count': extract_count('reposts'),
|
||||
'genre': info.get('genre'),
|
||||
}
|
||||
|
||||
format_urls = set()
|
||||
formats = []
|
||||
query = {'client_id': self._CLIENT_ID}
|
||||
if secret_token is not None:
|
||||
@ -248,6 +277,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
# We can build a direct link to the song
|
||||
format_url = update_url_query(
|
||||
'https://api.soundcloud.com/tracks/%s/download' % track_id, query)
|
||||
format_urls.add(format_url)
|
||||
formats.append({
|
||||
'format_id': 'download',
|
||||
'ext': info.get('original_format', 'mp3'),
|
||||
@ -256,12 +286,17 @@ class SoundcloudIE(InfoExtractor):
|
||||
'preference': 10,
|
||||
})
|
||||
|
||||
# We have to retrieve the url
|
||||
# Old API, does not work for some tracks (e.g.
|
||||
# https://soundcloud.com/giovannisarani/mezzo-valzer)
|
||||
format_dict = self._download_json(
|
||||
'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
|
||||
track_id, 'Downloading track url', query=query)
|
||||
track_id, 'Downloading track url', query=query, fatal=False)
|
||||
|
||||
if format_dict:
|
||||
for key, stream_url in format_dict.items():
|
||||
if stream_url in format_urls:
|
||||
continue
|
||||
format_urls.add(stream_url)
|
||||
ext, abr = 'mp3', None
|
||||
mobj = re.search(r'_([^_]+)_(\d+)_url', key)
|
||||
if mobj:
|
||||
@ -295,6 +330,48 @@ class SoundcloudIE(InfoExtractor):
|
||||
|
||||
formats.extend(stream_formats)
|
||||
|
||||
# New API
|
||||
transcodings = try_get(
|
||||
info, lambda x: x['media']['transcodings'], list) or []
|
||||
for t in transcodings:
|
||||
if not isinstance(t, dict):
|
||||
continue
|
||||
format_url = url_or_none(t.get('url'))
|
||||
if not format_url:
|
||||
continue
|
||||
stream = self._download_json(
|
||||
update_url_query(format_url, query), track_id, fatal=False)
|
||||
if not isinstance(stream, dict):
|
||||
continue
|
||||
stream_url = url_or_none(stream.get('url'))
|
||||
if not stream_url:
|
||||
continue
|
||||
if stream_url in format_urls:
|
||||
continue
|
||||
format_urls.add(stream_url)
|
||||
protocol = try_get(t, lambda x: x['format']['protocol'], compat_str)
|
||||
if protocol != 'hls' and '/hls' in format_url:
|
||||
protocol = 'hls'
|
||||
ext = None
|
||||
preset = str_or_none(t.get('preset'))
|
||||
if preset:
|
||||
ext = preset.split('_')[0]
|
||||
if ext not in KNOWN_EXTENSIONS:
|
||||
mimetype = try_get(
|
||||
t, lambda x: x['format']['mime_type'], compat_str)
|
||||
ext = mimetype2ext(mimetype) or 'mp3'
|
||||
format_id_list = []
|
||||
if protocol:
|
||||
format_id_list.append(protocol)
|
||||
format_id_list.append(ext)
|
||||
format_id = '_'.join(format_id_list)
|
||||
formats.append({
|
||||
'url': stream_url,
|
||||
'format_id': format_id,
|
||||
'ext': ext,
|
||||
'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
|
||||
})
|
||||
|
||||
if not formats:
|
||||
# We fallback to the stream_url in the original info, this
|
||||
# cannot be always used, sometimes it can give an HTTP 404 error
|
||||
@ -303,11 +380,11 @@ class SoundcloudIE(InfoExtractor):
|
||||
'url': update_url_query(info['stream_url'], query),
|
||||
'ext': 'mp3',
|
||||
})
|
||||
self._check_formats(formats, track_id)
|
||||
|
||||
for f in formats:
|
||||
f['vcodec'] = 'none'
|
||||
|
||||
self._check_formats(formats, track_id)
|
||||
self._sort_formats(formats)
|
||||
result['formats'] = formats
|
||||
|
||||
@ -319,6 +396,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
raise ExtractorError('Invalid URL: %s' % url)
|
||||
|
||||
track_id = mobj.group('track_id')
|
||||
new_info = {}
|
||||
|
||||
if track_id is not None:
|
||||
info_json_url = 'https://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
|
||||
@ -344,13 +422,31 @@ class SoundcloudIE(InfoExtractor):
|
||||
if token:
|
||||
resolve_title += '/%s' % token
|
||||
|
||||
self.report_resolve(full_title)
|
||||
webpage = self._download_webpage(url, full_title, fatal=False)
|
||||
if webpage:
|
||||
entries = self._parse_json(
|
||||
self._search_regex(
|
||||
r'var\s+c\s*=\s*(\[.+?\])\s*,\s*o\s*=Date\b', webpage,
|
||||
'data', default='[]'), full_title, fatal=False)
|
||||
if entries:
|
||||
for e in entries:
|
||||
if not isinstance(e, dict):
|
||||
continue
|
||||
if e.get('id') != 67:
|
||||
continue
|
||||
data = try_get(e, lambda x: x['data'][0], dict)
|
||||
if data:
|
||||
new_info = data
|
||||
break
|
||||
info_json_url = self._resolv_url(
|
||||
'https://soundcloud.com/%s' % resolve_title)
|
||||
|
||||
url = 'https://soundcloud.com/%s' % resolve_title
|
||||
info_json_url = self._resolv_url(url)
|
||||
info = self._download_json(info_json_url, full_title, 'Downloading info JSON')
|
||||
# Contains some additional info missing from new_info
|
||||
info = self._download_json(
|
||||
info_json_url, full_title, 'Downloading info JSON')
|
||||
|
||||
return self._extract_info_dict(info, full_title, secret_token=token)
|
||||
return self._extract_info_dict(
|
||||
merge_dicts(info, new_info), full_title, secret_token=token)
|
||||
|
||||
|
||||
class SoundcloudPlaylistBaseIE(SoundcloudIE):
|
||||
@ -396,8 +492,6 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
|
||||
full_title += '/' + token
|
||||
url += '/' + token
|
||||
|
||||
self.report_resolve(full_title)
|
||||
|
||||
resolv_url = self._resolv_url(url)
|
||||
info = self._download_json(resolv_url, full_title)
|
||||
|
||||
|
||||
@ -14,7 +14,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class StreamangoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net)/(?:f|embed)/(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net|streamcherry\.com)/(?:f|embed)/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4',
|
||||
'md5': 'e992787515a182f55e38fc97588d802a',
|
||||
@ -41,6 +41,9 @@ class StreamangoIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://streamcherry.com/f/clapasobsptpkdfe/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
94
youtube_dl/extractor/stv.py
Normal file
94
youtube_dl/extractor/stv.py
Normal file
@ -0,0 +1,94 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urllib_parse_urlparse
|
||||
)
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
)
|
||||
|
||||
|
||||
class STVPlayerIE(InfoExtractor):
|
||||
IE_NAME = 'stv:player'
|
||||
_VALID_URL = r'https?://player\.stv\.tv/(?P<type>episode|video)/(?P<id>[a-z0-9]{4})'
|
||||
_TEST = {
|
||||
'url': 'https://player.stv.tv/video/7srz/victoria/interview-with-the-cast-ahead-of-new-victoria/',
|
||||
'md5': '2ad867d4afd641fa14187596e0fbc91b',
|
||||
'info_dict': {
|
||||
'id': '6016487034001',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20190321',
|
||||
'title': 'Interview with the cast ahead of new Victoria',
|
||||
'description': 'Nell Hudson and Lily Travers tell us what to expect in the new season of Victoria.',
|
||||
'timestamp': 1553179628,
|
||||
'uploader_id': '1486976045',
|
||||
},
|
||||
'skip': 'this resource is unavailable outside of the UK',
|
||||
}
|
||||
_PUBLISHER_ID = '1486976045'
|
||||
_PTYPE_MAP = {
|
||||
'episode': 'episodes',
|
||||
'video': 'shortform',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
ptype, video_id = re.match(self._VALID_URL, url).groups()
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
qs = compat_parse_qs(compat_urllib_parse_urlparse(self._search_regex(
|
||||
r'itemprop="embedURL"[^>]+href="([^"]+)',
|
||||
webpage, 'embed URL', default=None)).query)
|
||||
publisher_id = qs.get('publisherID', [None])[0] or self._PUBLISHER_ID
|
||||
|
||||
player_attr = extract_attributes(self._search_regex(
|
||||
r'(<[^>]+class="bcplayer"[^>]+>)', webpage, 'player', default=None)) or {}
|
||||
|
||||
info = {}
|
||||
duration = ref_id = series = video_id = None
|
||||
api_ref_id = player_attr.get('data-player-api-refid')
|
||||
if api_ref_id:
|
||||
resp = self._download_json(
|
||||
'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], api_ref_id),
|
||||
api_ref_id, fatal=False)
|
||||
if resp:
|
||||
result = resp.get('results') or {}
|
||||
video = result.get('video') or {}
|
||||
video_id = str_or_none(video.get('id'))
|
||||
ref_id = video.get('guid')
|
||||
duration = video.get('length')
|
||||
programme = result.get('programme') or {}
|
||||
series = programme.get('name') or programme.get('shortName')
|
||||
subtitles = {}
|
||||
_subtitles = result.get('_subtitles') or {}
|
||||
for ext, sub_url in _subtitles.items():
|
||||
subtitles.setdefault('en', []).append({
|
||||
'ext': 'vtt' if ext == 'webvtt' else ext,
|
||||
'url': sub_url,
|
||||
})
|
||||
info.update({
|
||||
'description': result.get('summary'),
|
||||
'subtitles': subtitles,
|
||||
'view_count': int_or_none(result.get('views')),
|
||||
})
|
||||
if not video_id:
|
||||
video_id = qs.get('videoId', [None])[0] or self._search_regex(
|
||||
r'<link\s+itemprop="url"\s+href="(\d+)"',
|
||||
webpage, 'video id', default=None) or 'ref:' + (ref_id or player_attr['data-refid'])
|
||||
|
||||
info.update({
|
||||
'_type': 'url_transparent',
|
||||
'duration': float_or_none(duration or player_attr.get('data-duration'), 1000),
|
||||
'id': video_id,
|
||||
'ie_key': 'BrightcoveNew',
|
||||
'series': series or player_attr.get('data-programme-name'),
|
||||
'url': 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id),
|
||||
})
|
||||
return info
|
||||
@ -16,7 +16,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class TeamcocoIE(TurnerBaseIE):
|
||||
_VALID_URL = r'https?://teamcoco\.com/(?P<id>([^/]+/)*[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:\w+\.)?teamcoco\.com/(?P<id>([^/]+/)*[^/?#]+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://teamcoco.com/video/mary-kay-remote',
|
||||
@ -79,15 +79,20 @@ class TeamcocoIE(TurnerBaseIE):
|
||||
}, {
|
||||
'url': 'http://teamcoco.com/israel/conan-hits-the-streets-beaches-of-tel-aviv',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://conan25.teamcoco.com/video/ice-cube-kevin-hart-conan-share-lyft',
|
||||
'only_matching': True,
|
||||
}
|
||||
]
|
||||
|
||||
def _graphql_call(self, query_template, object_type, object_id):
|
||||
find_object = 'find' + object_type
|
||||
return self._download_json(
|
||||
'http://teamcoco.com/graphql/', object_id, data=json.dumps({
|
||||
'https://teamcoco.com/graphql', object_id, data=json.dumps({
|
||||
'query': query_template % (find_object, object_id)
|
||||
}))['data'][find_object]
|
||||
}).encode(), headers={
|
||||
'Content-Type': 'application/json',
|
||||
})['data'][find_object]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
@ -145,6 +150,11 @@ class TeamcocoIE(TurnerBaseIE):
|
||||
'accessTokenType': 'jws',
|
||||
}))
|
||||
else:
|
||||
d = self._download_json(
|
||||
'https://teamcoco.com/_truman/d/' + video_id,
|
||||
video_id, fatal=False) or {}
|
||||
video_sources = d.get('meta') or {}
|
||||
if not video_sources:
|
||||
video_sources = self._graphql_call('''{
|
||||
%s(id: "%s") {
|
||||
src
|
||||
|
||||
@ -65,8 +65,15 @@ class TikTokBaseIE(InfoExtractor):
|
||||
|
||||
|
||||
class TikTokIE(TikTokBaseIE):
|
||||
_VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
(?:m\.)?tiktok\.com/v|
|
||||
(?:www\.)?tiktok\.com/share/video
|
||||
)
|
||||
/(?P<id>\d+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'https://m.tiktok.com/v/6606727368545406213.html',
|
||||
'md5': 'd584b572e92fcd48888051f238022420',
|
||||
'info_dict': {
|
||||
@ -81,25 +88,39 @@ class TikTokIE(TikTokBaseIE):
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.tiktok.com/share/video/6606727368545406213',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
webpage = self._download_webpage(
|
||||
'https://m.tiktok.com/v/%s.html' % video_id, video_id)
|
||||
data = self._parse_json(self._search_regex(
|
||||
r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id)
|
||||
return self._extract_aweme(data)
|
||||
|
||||
|
||||
class TikTokUserIE(TikTokBaseIE):
|
||||
_VALID_URL = r'https?://(?:m\.)?tiktok\.com/h5/share/usr/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
(?:m\.)?tiktok\.com/h5/share/usr|
|
||||
(?:www\.)?tiktok\.com/share/user
|
||||
)
|
||||
/(?P<id>\d+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html',
|
||||
'info_dict': {
|
||||
'id': '188294915489964032',
|
||||
},
|
||||
'playlist_mincount': 24,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.tiktok.com/share/user/188294915489964032',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
user_id = self._match_id(url)
|
||||
|
||||
@ -66,7 +66,12 @@ class TouTvIE(RadioCanadaIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
path = self._match_id(url)
|
||||
metadata = self._download_json('http://ici.tou.tv/presentation/%s' % path, path)
|
||||
metadata = self._download_json(
|
||||
'https://services.radio-canada.ca/toutv/presentation/%s' % path, path, query={
|
||||
'client_key': self._CLIENT_KEY,
|
||||
'device': 'web',
|
||||
'version': 4,
|
||||
})
|
||||
# IsDrm does not necessarily mean the video is DRM protected (see
|
||||
# https://github.com/ytdl-org/youtube-dl/issues/13994).
|
||||
if metadata.get('IsDrm'):
|
||||
@ -77,6 +82,12 @@ class TouTvIE(RadioCanadaIE):
|
||||
return merge_dicts({
|
||||
'id': video_id,
|
||||
'title': details.get('OriginalTitle'),
|
||||
'description': details.get('Description'),
|
||||
'thumbnail': details.get('ImageUrl'),
|
||||
'duration': int_or_none(details.get('LengthInSeconds')),
|
||||
'series': metadata.get('ProgramTitle'),
|
||||
'season_number': int_or_none(metadata.get('SeasonNumber')),
|
||||
'season': metadata.get('SeasonTitle'),
|
||||
'episode_number': int_or_none(metadata.get('EpisodeNumber')),
|
||||
'episode': metadata.get('EpisodeTitle'),
|
||||
}, self._extract_info(metadata.get('AppCode', 'toutv'), video_id))
|
||||
|
||||
@ -76,7 +76,10 @@ class UdemyIE(InfoExtractor):
|
||||
webpage, 'course', default='{}')),
|
||||
video_id, fatal=False) or {}
|
||||
course_id = course.get('id') or self._search_regex(
|
||||
r'data-course-id=["\'](\d+)', webpage, 'course id')
|
||||
[
|
||||
r'data-course-id=["\'](\d+)',
|
||||
r'"courseId"\s*:\s*(\d+)'
|
||||
], webpage, 'course id')
|
||||
return course_id, course.get('title')
|
||||
|
||||
def _enroll_course(self, base_url, webpage, course_id):
|
||||
|
||||
@ -109,23 +109,9 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
|
||||
def _parse_config(self, config, video_id):
|
||||
video_data = config['video']
|
||||
# Extract title
|
||||
video_title = video_data['title']
|
||||
|
||||
# Extract uploader, uploader_url and uploader_id
|
||||
video_uploader = video_data.get('owner', {}).get('name')
|
||||
video_uploader_url = video_data.get('owner', {}).get('url')
|
||||
video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
|
||||
|
||||
# Extract video thumbnail
|
||||
video_thumbnail = video_data.get('thumbnail')
|
||||
if video_thumbnail is None:
|
||||
video_thumbs = video_data.get('thumbs')
|
||||
if video_thumbs and isinstance(video_thumbs, dict):
|
||||
_, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
|
||||
|
||||
# Extract video duration
|
||||
video_duration = int_or_none(video_data.get('duration'))
|
||||
live_event = video_data.get('live_event') or {}
|
||||
is_live = live_event.get('status') == 'started'
|
||||
|
||||
formats = []
|
||||
config_files = video_data.get('files') or config['request'].get('files', {})
|
||||
@ -142,6 +128,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
'tbr': int_or_none(f.get('bitrate')),
|
||||
})
|
||||
|
||||
# TODO: fix handling of 308 status code returned for live archive manifest requests
|
||||
for files_type in ('hls', 'dash'):
|
||||
for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
|
||||
manifest_url = cdn_data.get('url')
|
||||
@ -151,7 +138,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
if files_type == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
manifest_url, video_id, 'mp4',
|
||||
'm3u8_native', m3u8_id=format_id,
|
||||
'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id,
|
||||
note='Downloading %s m3u8 information' % cdn_name,
|
||||
fatal=False))
|
||||
elif files_type == 'dash':
|
||||
@ -164,6 +151,10 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
else:
|
||||
mpd_manifest_urls = [(format_id, manifest_url)]
|
||||
for f_id, m_url in mpd_manifest_urls:
|
||||
if 'json=1' in m_url:
|
||||
real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
|
||||
if real_m_url:
|
||||
m_url = real_m_url
|
||||
mpd_formats = self._extract_mpd_formats(
|
||||
m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
|
||||
'Downloading %s MPD information' % cdn_name,
|
||||
@ -175,6 +166,15 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
f['preference'] = -40
|
||||
formats.extend(mpd_formats)
|
||||
|
||||
live_archive = live_event.get('archive') or {}
|
||||
live_archive_source_url = live_archive.get('source_url')
|
||||
if live_archive_source_url and live_archive.get('status') == 'done':
|
||||
formats.append({
|
||||
'format_id': 'live-archive-source',
|
||||
'url': live_archive_source_url,
|
||||
'preference': 1,
|
||||
})
|
||||
|
||||
subtitles = {}
|
||||
text_tracks = config['request'].get('text_tracks')
|
||||
if text_tracks:
|
||||
@ -184,15 +184,33 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
'url': 'https://vimeo.com' + tt['url'],
|
||||
}]
|
||||
|
||||
thumbnails = []
|
||||
if not is_live:
|
||||
for key, thumb in video_data.get('thumbs', {}).items():
|
||||
thumbnails.append({
|
||||
'id': key,
|
||||
'width': int_or_none(key),
|
||||
'url': thumb,
|
||||
})
|
||||
thumbnail = video_data.get('thumbnail')
|
||||
if thumbnail:
|
||||
thumbnails.append({
|
||||
'url': thumbnail,
|
||||
})
|
||||
|
||||
owner = video_data.get('owner') or {}
|
||||
video_uploader_url = owner.get('url')
|
||||
|
||||
return {
|
||||
'title': video_title,
|
||||
'uploader': video_uploader,
|
||||
'uploader_id': video_uploader_id,
|
||||
'title': self._live_title(video_title) if is_live else video_title,
|
||||
'uploader': owner.get('name'),
|
||||
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
|
||||
'uploader_url': video_uploader_url,
|
||||
'thumbnail': video_thumbnail,
|
||||
'duration': video_duration,
|
||||
'thumbnails': thumbnails,
|
||||
'duration': int_or_none(video_data.get('duration')),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'is_live': is_live,
|
||||
}
|
||||
|
||||
def _extract_original_format(self, url, video_id):
|
||||
|
||||
@ -6,10 +6,7 @@ import re
|
||||
import sys
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
ExtractorError,
|
||||
@ -103,7 +100,7 @@ class VKIE(VKBaseIE):
|
||||
'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
|
||||
'md5': '7babad3b85ea2e91948005b1b8b0cb84',
|
||||
'info_dict': {
|
||||
'id': '162222515',
|
||||
'id': '-77521_162222515',
|
||||
'ext': 'mp4',
|
||||
'title': 'ProtivoGunz - Хуёвая песня',
|
||||
'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
|
||||
@ -117,7 +114,7 @@ class VKIE(VKBaseIE):
|
||||
'url': 'http://vk.com/video205387401_165548505',
|
||||
'md5': '6c0aeb2e90396ba97035b9cbde548700',
|
||||
'info_dict': {
|
||||
'id': '165548505',
|
||||
'id': '205387401_165548505',
|
||||
'ext': 'mp4',
|
||||
'title': 'No name',
|
||||
'uploader': 'Tom Cruise',
|
||||
@ -132,7 +129,7 @@ class VKIE(VKBaseIE):
|
||||
'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
|
||||
'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
|
||||
'info_dict': {
|
||||
'id': '162925554',
|
||||
'id': '32194266_162925554',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'Vladimir Gavrin',
|
||||
'title': 'Lin Dan',
|
||||
@ -149,7 +146,7 @@ class VKIE(VKBaseIE):
|
||||
'md5': 'a590bcaf3d543576c9bd162812387666',
|
||||
'note': 'Only available for registered users',
|
||||
'info_dict': {
|
||||
'id': '164049491',
|
||||
'id': '-8871596_164049491',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'Триллеры',
|
||||
'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
|
||||
@ -163,7 +160,7 @@ class VKIE(VKBaseIE):
|
||||
'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
|
||||
'md5': '4d7a5ef8cf114dfa09577e57b2993202',
|
||||
'info_dict': {
|
||||
'id': '168067957',
|
||||
'id': '-43215063_168067957',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'Киномания - лучшее из мира кино',
|
||||
'title': ' ',
|
||||
@ -177,7 +174,7 @@ class VKIE(VKBaseIE):
|
||||
'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
|
||||
'note': 'ivi.ru embed',
|
||||
'info_dict': {
|
||||
'id': '60690',
|
||||
'id': '-43215063_169084319',
|
||||
'ext': 'mp4',
|
||||
'title': 'Книга Илая',
|
||||
'duration': 6771,
|
||||
@ -191,7 +188,7 @@ class VKIE(VKBaseIE):
|
||||
'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
|
||||
'md5': '091287af5402239a1051c37ec7b92913',
|
||||
'info_dict': {
|
||||
'id': '171201961',
|
||||
'id': '30481095_171201961',
|
||||
'ext': 'mp4',
|
||||
'title': 'ТюменцевВВ_09.07.2015',
|
||||
'uploader': 'Anton Ivanov',
|
||||
@ -206,10 +203,10 @@ class VKIE(VKBaseIE):
|
||||
'url': 'https://vk.com/video276849682_170681728',
|
||||
'info_dict': {
|
||||
'id': 'V3K4mi0SYkc',
|
||||
'ext': 'webm',
|
||||
'ext': 'mp4',
|
||||
'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
|
||||
'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
|
||||
'duration': 179,
|
||||
'duration': 178,
|
||||
'upload_date': '20130116',
|
||||
'uploader': "Children's Joy Foundation Inc.",
|
||||
'uploader_id': 'thecjf',
|
||||
@ -239,7 +236,7 @@ class VKIE(VKBaseIE):
|
||||
'url': 'http://vk.com/video-110305615_171782105',
|
||||
'md5': 'e13fcda136f99764872e739d13fac1d1',
|
||||
'info_dict': {
|
||||
'id': '171782105',
|
||||
'id': '-110305615_171782105',
|
||||
'ext': 'mp4',
|
||||
'title': 'S-Dance, репетиции к The way show',
|
||||
'uploader': 'THE WAY SHOW | 17 апреля',
|
||||
@ -254,14 +251,17 @@ class VKIE(VKBaseIE):
|
||||
{
|
||||
# finished live stream, postlive_mp4
|
||||
'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
|
||||
'md5': '90d22d051fccbbe9becfccc615be6791',
|
||||
'info_dict': {
|
||||
'id': '456242764',
|
||||
'id': '-387766_456242764',
|
||||
'ext': 'mp4',
|
||||
'title': 'ИгроМир 2016 — день 1',
|
||||
'title': 'ИгроМир 2016 День 1 — Игромания Утром',
|
||||
'uploader': 'Игромания',
|
||||
'duration': 5239,
|
||||
'view_count': int,
|
||||
# TODO: use act=show to extract view_count
|
||||
# 'view_count': int,
|
||||
'upload_date': '20160929',
|
||||
'uploader_id': '-387766',
|
||||
'timestamp': 1475137527,
|
||||
},
|
||||
},
|
||||
{
|
||||
@ -474,7 +474,7 @@ class VKIE(VKBaseIE):
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': compat_str(data.get('vid') or video_id),
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'thumbnail': data.get('jpg'),
|
||||
|
||||
@ -102,6 +102,15 @@ class VRVIE(VRVBaseIE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# movie listing
|
||||
'url': 'https://vrv.co/watch/G6NQXZ1J6/Lily-CAT',
|
||||
'info_dict': {
|
||||
'id': 'G6NQXZ1J6',
|
||||
'title': 'Lily C.A.T',
|
||||
'description': 'md5:988b031e7809a6aeb60968be4af7db07',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}]
|
||||
_NETRC_MACHINE = 'vrv'
|
||||
|
||||
@ -123,23 +132,23 @@ class VRVIE(VRVBaseIE):
|
||||
def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang):
|
||||
if not url or stream_format not in ('hls', 'dash'):
|
||||
return []
|
||||
assert audio_lang or hardsub_lang
|
||||
stream_id_list = []
|
||||
if audio_lang:
|
||||
stream_id_list.append('audio-%s' % audio_lang)
|
||||
if hardsub_lang:
|
||||
stream_id_list.append('hardsub-%s' % hardsub_lang)
|
||||
stream_id = '-'.join(stream_id_list)
|
||||
format_id = '%s-%s' % (stream_format, stream_id)
|
||||
format_id = stream_format
|
||||
if stream_id_list:
|
||||
format_id += '-' + '-'.join(stream_id_list)
|
||||
if stream_format == 'hls':
|
||||
adaptive_formats = self._extract_m3u8_formats(
|
||||
url, video_id, 'mp4', m3u8_id=format_id,
|
||||
note='Downloading %s m3u8 information' % stream_id,
|
||||
note='Downloading %s information' % format_id,
|
||||
fatal=False)
|
||||
elif stream_format == 'dash':
|
||||
adaptive_formats = self._extract_mpd_formats(
|
||||
url, video_id, mpd_id=format_id,
|
||||
note='Downloading %s MPD information' % stream_id,
|
||||
note='Downloading %s information' % format_id,
|
||||
fatal=False)
|
||||
if audio_lang:
|
||||
for f in adaptive_formats:
|
||||
@ -150,10 +159,28 @@ class VRVIE(VRVBaseIE):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
episode_path = self._get_cms_resource(
|
||||
'cms:/episodes/' + video_id, video_id)
|
||||
video_data = self._call_cms(episode_path, video_id, 'video')
|
||||
object_data = self._call_cms(self._get_cms_resource(
|
||||
'cms:/objects/' + video_id, video_id), video_id, 'object')['items'][0]
|
||||
resource_path = object_data['__links__']['resource']['href']
|
||||
video_data = self._call_cms(resource_path, video_id, 'video')
|
||||
title = video_data['title']
|
||||
description = video_data.get('description')
|
||||
|
||||
if video_data.get('__class__') == 'movie_listing':
|
||||
items = self._call_cms(
|
||||
video_data['__links__']['movie_listing/movies']['href'],
|
||||
video_id, 'movie listing').get('items') or []
|
||||
if len(items) != 1:
|
||||
entries = []
|
||||
for item in items:
|
||||
item_id = item.get('id')
|
||||
if not item_id:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
'https://vrv.co/watch/' + item_id,
|
||||
self.ie_key(), item_id, item.get('title')))
|
||||
return self.playlist_result(entries, video_id, title, description)
|
||||
video_data = items[0]
|
||||
|
||||
streams_path = video_data['__links__'].get('streams', {}).get('href')
|
||||
if not streams_path:
|
||||
@ -197,7 +224,7 @@ class VRVIE(VRVBaseIE):
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'thumbnails': thumbnails,
|
||||
'description': video_data.get('description'),
|
||||
'description': description,
|
||||
'duration': float_or_none(video_data.get('duration_ms'), 1000),
|
||||
'uploader_id': video_data.get('channel_id'),
|
||||
'series': video_data.get('series_title'),
|
||||
|
||||
@ -57,10 +57,17 @@ class XVideosIE(InfoExtractor):
|
||||
webpage, 'title', default=None,
|
||||
group='title') or self._og_search_title(webpage)
|
||||
|
||||
thumbnail = self._search_regex(
|
||||
(r'setThumbUrl\(\s*(["\'])(?P<thumbnail>(?:(?!\1).)+)\1',
|
||||
r'url_bigthumb=(?P<thumbnail>.+?)&'),
|
||||
webpage, 'thumbnail', fatal=False, group='thumbnail')
|
||||
thumbnails = []
|
||||
for preference, thumbnail in enumerate(('', '169')):
|
||||
thumbnail_url = self._search_regex(
|
||||
r'setThumbUrl%s\(\s*(["\'])(?P<thumbnail>(?:(?!\1).)+)\1' % thumbnail,
|
||||
webpage, 'thumbnail', default=None, group='thumbnail')
|
||||
if thumbnail_url:
|
||||
thumbnails.append({
|
||||
'url': thumbnail_url,
|
||||
'preference': preference,
|
||||
})
|
||||
|
||||
duration = int_or_none(self._og_search_property(
|
||||
'duration', webpage, default=None)) or parse_duration(
|
||||
self._search_regex(
|
||||
@ -98,6 +105,6 @@ class XVideosIE(InfoExtractor):
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'duration': duration,
|
||||
'thumbnail': thumbnail,
|
||||
'thumbnails': thumbnails,
|
||||
'age_limit': 18,
|
||||
}
|
||||
|
||||
@ -477,3 +477,77 @@ class YahooSearchIE(SearchInfoExtractor):
|
||||
'id': query,
|
||||
'entries': entries,
|
||||
}
|
||||
|
||||
|
||||
class YahooGyaOPlayerIE(InfoExtractor):
|
||||
IE_NAME = 'yahoo:gyao:player'
|
||||
_VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/(?:player|episode/[^/]+)|streaming\.yahoo\.co\.jp/c/y)/(?P<id>\d+/v\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
|
||||
_TESTS = [{
|
||||
'url': 'https://gyao.yahoo.co.jp/player/00998/v00818/v0000000000000008564/',
|
||||
'info_dict': {
|
||||
'id': '5993125228001',
|
||||
'ext': 'mp4',
|
||||
'title': 'フューリー 【字幕版】',
|
||||
'description': 'md5:21e691c798a15330eda4db17a8fe45a5',
|
||||
'uploader_id': '4235717419001',
|
||||
'upload_date': '20190124',
|
||||
'timestamp': 1548294365,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://streaming.yahoo.co.jp/c/y/01034/v00133/v0000000000000000706/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://gyao.yahoo.co.jp/episode/%E3%81%8D%E3%81%AE%E3%81%86%E4%BD%95%E9%A3%9F%E3%81%B9%E3%81%9F%EF%BC%9F%20%E7%AC%AC2%E8%A9%B1%202019%2F4%2F12%E6%94%BE%E9%80%81%E5%88%86/5cb02352-b725-409e-9f8d-88f947a9f682',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url).replace('/', ':')
|
||||
video = self._download_json(
|
||||
'https://gyao.yahoo.co.jp/dam/v1/videos/' + video_id,
|
||||
video_id, query={
|
||||
'fields': 'longDescription,title,videoId',
|
||||
})
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'title': video['title'],
|
||||
'url': smuggle_url(
|
||||
'http://players.brightcove.net/4235717419001/default_default/index.html?videoId=' + video['videoId'],
|
||||
{'geo_countries': ['JP']}),
|
||||
'description': video.get('longDescription'),
|
||||
'ie_key': BrightcoveNewIE.ie_key(),
|
||||
}
|
||||
|
||||
|
||||
class YahooGyaOIE(InfoExtractor):
|
||||
IE_NAME = 'yahoo:gyao'
|
||||
_VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/p|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/',
|
||||
'info_dict': {
|
||||
'id': '00449:v03102',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}, {
|
||||
'url': 'https://streaming.yahoo.co.jp/p/y/01034/v00133/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
program_id = self._match_id(url).replace('/', ':')
|
||||
videos = self._download_json(
|
||||
'https://gyao.yahoo.co.jp/api/programs/%s/videos' % program_id, program_id)['videos']
|
||||
entries = []
|
||||
for video in videos:
|
||||
video_id = video.get('id')
|
||||
if not video_id:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
'https://gyao.yahoo.co.jp/player/%s/' % video_id.replace(':', '/'),
|
||||
YahooGyaOPlayerIE.ie_key(), video_id))
|
||||
return self.playlist_result(entries, program_id)
|
||||
|
||||
@ -8,8 +8,8 @@ from ..utils import (
|
||||
|
||||
|
||||
class YourPornIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P<id>[^/?#&.]+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:yourporn\.sexy|sxyprn\.com)/post/(?P<id>[^/?#&.]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html',
|
||||
'md5': '6f8682b6464033d87acaa7a8ff0c092e',
|
||||
'info_dict': {
|
||||
@ -23,7 +23,10 @@ class YourPornIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
@ -484,7 +484,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
# RTMP (unnamed)
|
||||
'_rtmp': {'protocol': 'rtmp'},
|
||||
}
|
||||
_SUBTITLE_FORMATS = ('ttml', 'vtt')
|
||||
_SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
|
||||
|
||||
_GEO_BYPASS = False
|
||||
|
||||
@ -1652,7 +1652,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
view_count = extract_view_count(get_video_info)
|
||||
if not video_info:
|
||||
video_info = get_video_info
|
||||
if 'token' in get_video_info:
|
||||
get_token = get_video_info.get('token') or get_video_info.get('account_playback_token')
|
||||
if get_token:
|
||||
# Different get_video_info requests may report different results, e.g.
|
||||
# some may report video unavailability, but some may serve it without
|
||||
# any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
|
||||
@ -1662,7 +1663,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
# due to YouTube measures against IP ranges of hosting providers.
|
||||
# Working around by preferring the first succeeded video_info containing
|
||||
# the token if no such video_info yet was found.
|
||||
if 'token' not in video_info:
|
||||
token = video_info.get('token') or video_info.get('account_playback_token')
|
||||
if not token:
|
||||
video_info = get_video_info
|
||||
break
|
||||
|
||||
@ -1671,7 +1673,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
|
||||
video_webpage, 'unavailable message', default=None)
|
||||
|
||||
if 'token' not in video_info:
|
||||
if not video_info:
|
||||
unavailable_message = extract_unavailable_message()
|
||||
if not unavailable_message:
|
||||
unavailable_message = 'Unable to extract video data'
|
||||
raise ExtractorError(
|
||||
'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
|
||||
|
||||
token = video_info.get('token') or video_info.get('account_playback_token')
|
||||
if not token:
|
||||
if 'reason' in video_info:
|
||||
if 'The uploader has not made this video available in your country.' in video_info['reason']:
|
||||
regions_allowed = self._html_search_meta(
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = 'vc.2019.03.28'
|
||||
__version__ = 'vc.2019.04.24'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user