Compare commits

...

35 Commits

Author SHA1 Message Date
Remita Amine
aed617e311 [amcnetworks] improve auth only video detection(closes #27548) 2020-12-27 09:00:08 +01:00
Remita Amine
0fa67c1d68 [generic] Add support for VHX Embeds(#27546) 2020-12-27 09:00:07 +01:00
Sergey M․
365b3cc72d release 2020.12.26 2020-12-26 23:17:35 +07:00
Sergey M․
a272fe21a8 [ChangeLog] Actualize
[ci skip]
2020-12-26 23:13:26 +07:00
Sergey M․
cec1c2f211 [instagram] Fix test 2020-12-26 23:00:15 +07:00
Sergey M․
12053450dc [instagram] Fix comment count extraction 2020-12-26 23:00:15 +07:00
Sergey M․
46cffb0c47 [instagram] Add support for reel URLs (closes #26234, closes #26250) 2020-12-26 23:00:15 +07:00
Remita Amine
c32a059f52 [bbc] switch to media selector v6
closes #23232
closes #23933
closes #26303
closes #26432
closes #26821
closes #27538
2020-12-26 16:57:02 +01:00
Sergey M․
6911312e53 [instagram] Improve thumbnail extraction 2020-12-26 22:42:58 +07:00
Sergey M․
f22b5a6b96 [instagram] Improve extraction (closes #22880) 2020-12-26 22:37:41 +07:00
Andrew Udvare
58e55198c1 [instagram] Fix extraction when authenticated (closes #27422) 2020-12-26 22:31:55 +07:00
Sergey M․
d61ed9f2f1 [spankbang] Remove unused import 2020-12-26 22:14:31 +07:00
Sergey M․
8bc4c6350e [spangbang:playlist] Fix extraction (closes #24087) 2020-12-26 21:58:26 +07:00
Sergey M․
cfa4ffa23b [spangbang] Add support for playlist videos 2020-12-26 21:55:12 +07:00
Sergey M․
4f1dc1463d [pornhub] Improve like and dislike count extraction (closes #27356) 2020-12-26 21:24:43 +07:00
Sergey M․
17e0f41d34 [pornhub] Fix review issues (closes #27393) 2020-12-26 21:17:17 +07:00
JChris246
b57b27ff8f [pornhub] Fix lq formats extraction (closes #27386) 2020-12-26 21:17:11 +07:00
Marco Fantauzzo
bbe8cc6662 [README.md] Update reference to cookie export extension for Chrome (closes #26885) (#27433)
The cookies.txt extension doesn't exist anymore on the Chrome Web Store (see https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg), so I propose to change the link in the README.md to another similar extension called Get cookies.txt (https://chrome.google.com/webstore/detail/get-cookiestxt/bgaddhkoddajcdgocldbbfleckgcbcid/) with the same functions and utility of the old one.

This PR close #26885
2020-12-26 20:50:39 +07:00
Sergey M․
98106accb6 [bongacams] Add extractor (closes #27440) 2020-12-26 20:30:19 +07:00
Sergey M․
af1312bfc3 [youtube:tab] Extend _VALID_URL (closes #27501) 2020-12-26 19:59:57 +07:00
Remita Amine
4c7d7215cd [theweatherchannel] fix extraction (closes #25930)(closes #26051) 2020-12-26 09:37:40 +01:00
Remita Amine
0370d9eb3d [sprout] correct typo 2020-12-25 21:35:55 +01:00
Remita Amine
1434651d20 [sprout] Add support for Universal Kids (closes #22518) 2020-12-25 21:17:44 +01:00
Remita Amine
2c312ab84a [theplatform] allow passing geo bypass countries from other extractors 2020-12-25 21:16:36 +01:00
Remita Amine
0ee78d62d5 [wistia] Add support for playlists (closes #27533) 2020-12-25 17:00:30 +01:00
Remita Amine
7f3c90ab25 [ctv] Add new extractor (closes #27525) 2020-12-24 19:40:08 +01:00
Remita Amine
1d3cd29730 [9c9media] improve info extraction 2020-12-24 17:39:13 +01:00
Remita Amine
4ef1fc9707 [youtube] fix automatic captions extraction(closes #27162)(closes #27388) 2020-12-24 16:05:03 +01:00
Remita Amine
f9e6aa1dcf [sonyliv] fix title for movies 2020-12-24 13:33:12 +01:00
Remita Amine
f83db9064b [sonyliv] fix extraction(closes #25667) 2020-12-24 13:10:20 +01:00
Remita Amine
2da9a86399 [streetvoice] fix extraction(closes #27455)(closes #27492) 2020-12-24 13:10:20 +01:00
Remita Amine
ecaa535cf4 [facebook] add support for watchparty pages(closes #27507) 2020-12-24 13:10:20 +01:00
Remita Amine
79dd92b1fe [cbslocal] fix video extraction 2020-12-24 13:10:20 +01:00
Remita Amine
bd3844c9c2 [brightcove] add another method to extract policyKey 2020-12-24 13:10:20 +01:00
Sergey M․
7bf5e3a84a [mewatch] Relax _VALID_URL (closes #27506) 2020-12-22 23:27:05 +07:00
32 changed files with 935 additions and 466 deletions

View File

@@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support
- [ ] I've verified that I'm running youtube-dl version **2020.12.22**
- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[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 2020.12.22
[debug] youtube-dl version 2020.12.26
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@@ -19,7 +19,7 @@ labels: 'site-support-request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
- Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a new site support request
- [ ] I've verified that I'm running youtube-dl version **2020.12.22**
- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones

View File

@@ -18,13 +18,13 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a site feature request
- [ ] I've verified that I'm running youtube-dl version **2020.12.22**
- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones

View File

@@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support issue
- [ ] I've verified that I'm running youtube-dl version **2020.12.22**
- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[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 2020.12.22
[debug] youtube-dl version 2020.12.26
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@@ -19,13 +19,13 @@ labels: 'request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a feature request
- [ ] I've verified that I'm running youtube-dl version **2020.12.22**
- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

View File

@@ -1,3 +1,35 @@
version 2020.12.26
Extractors
* [instagram] Fix comment count extraction
+ [instagram] Add support for reel URLs (#26234, #26250)
* [bbc] Switch to media selector v6 (#23232, #23933, #26303, #26432, #26821,
#27538)
* [instagram] Improve thumbnail extraction
* [instagram] Fix extraction when authenticated (#22880, #26377, #26981,
#27422)
* [spankbang:playlist] Fix extraction (#24087)
+ [spankbang] Add support for playlist videos
* [pornhub] Improve like and dislike count extraction (#27356)
* [pornhub] Fix lq formats extraction (#27386, #27393)
+ [bongacams] Add support for bongacams.com (#27440)
* [youtube:tab] Extend URL regular expression (#27501)
* [theweatherchannel] Fix extraction (#25930, #26051)
+ [sprout] Add support for Universal Kids (#22518)
* [theplatform] Allow passing geo bypass countries from other extractors
+ [wistia] Add support for playlists (#27533)
+ [ctv] Add support for ctv.ca (#27525)
* [9c9media] Improve info extraction
* [youtube] Fix automatic captions extraction (#27162, #27388)
* [sonyliv] Fix title for movies
* [sonyliv] Fix extraction (#25667)
* [streetvoice] Fix extraction (#27455, #27492)
+ [facebook] Add support for watchparty pages (#27507)
* [cbslocal] Fix video extraction
+ [brightcove] Add another method to extract policyKey
* [mewatch] Relax URL regular expression (#27506)
version 2020.12.22
Core

View File

@@ -880,7 +880,7 @@ Either prepend `https://www.youtube.com/watch?v=` or separate the ID from the op
Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [cookies.txt](https://addons.mozilla.org/en-US/firefox/addon/cookies-txt/) (for Firefox).
In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [Get cookies.txt](https://chrome.google.com/webstore/detail/get-cookiestxt/bgaddhkoddajcdgocldbbfleckgcbcid/) (for Chrome) or [cookies.txt](https://addons.mozilla.org/en-US/firefox/addon/cookies-txt/) (for Firefox).
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, macOS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.

View File

@@ -112,6 +112,7 @@
- **blinkx**
- **Bloomberg**
- **BokeCC**
- **BongaCams**
- **BostonGlobe**
- **Box**
- **Bpb**: Bundeszentrale für politische Bildung
@@ -146,6 +147,7 @@
- **CBS**
- **CBSInteractive**
- **CBSLocal**
- **CBSLocalArticle**
- **cbsnews**: CBS News
- **cbsnews:embed**
- **cbsnews:livevideo**: CBS News Live Videos
@@ -198,6 +200,7 @@
- **CSNNE**
- **CSpan**: C-SPAN
- **CtsNews**: 華視新聞
- **CTV**
- **CTVNews**
- **cu.ntv.co.jp**: Nippon Television Network
- **Culturebox**
@@ -1108,6 +1111,7 @@
- **WeiboMobile**
- **WeiqiTV**: WQTV
- **Wistia**
- **WistiaPlaylist**
- **wnl**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
- **WorldStarHipHop**
- **WSJ**: Wall Street Journal

View File

@@ -36,7 +36,7 @@ class TestAllURLsMatching(unittest.TestCase):
assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585
assertPlaylist('PL63F0C78739B09958')
assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertTab('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
assertTab('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668
self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
@@ -57,8 +57,8 @@ class TestAllURLsMatching(unittest.TestCase):
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
# def test_youtube_user_matching(self):
# self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:tab'])
def test_youtube_user_matching(self):
self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:tab'])
def test_youtube_feeds(self):
self.assertMatch('https://www.youtube.com/feed/library', ['youtube:tab'])

View File

@@ -80,7 +80,8 @@ class AMCNetworksIE(ThePlatformIE):
title = theplatform_metadata['title']
rating = try_get(
theplatform_metadata, lambda x: x['ratings'][0]['rating'])
if properties.get('videoCategory') == 'TVE-Auth':
video_category = properties.get('videoCategory')
if video_category and video_category.endswith('-Auth'):
resource = self._get_mvpd_resource(
requestor_id, title, video_id, rating)
query['auth'] = self._extract_mvpd_auth(

View File

@@ -49,22 +49,17 @@ class BBCCoUkIE(InfoExtractor):
_LOGIN_URL = 'https://account.bbc.com/signin'
_NETRC_MACHINE = 'bbc'
_MEDIASELECTOR_URLS = [
_MEDIA_SELECTOR_URL_TEMPL = 'https://open.live.bbc.co.uk/mediaselector/6/select/version/2.0/mediaset/%s/vpid/%s'
_MEDIA_SETS = [
# Provides HQ HLS streams with even better quality that pc mediaset but fails
# with geolocation in some cases when it's even not geo restricted at all (e.g.
# http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable.
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
'iptv-all',
'pc',
]
_MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection'
_EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist'
_NAMESPACES = (
_MEDIASELECTION_NS,
_EMP_PLAYLIST_NS,
)
_TESTS = [
{
'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
@@ -261,8 +256,6 @@ class BBCCoUkIE(InfoExtractor):
'only_matching': True,
}]
_USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
def _login(self):
username, password = self._get_login_info()
if username is None:
@@ -307,22 +300,14 @@ class BBCCoUkIE(InfoExtractor):
def _extract_items(self, playlist):
return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
def _findall_ns(self, element, xpath):
elements = []
for ns in self._NAMESPACES:
elements.extend(element.findall(xpath % ns))
return elements
def _extract_medias(self, media_selection):
error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS)
if error is None:
media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS)
if error is not None:
raise BBCCoUkIE.MediaSelectionError(error.get('id'))
return self._findall_ns(media_selection, './{%s}media')
error = media_selection.get('result')
if error:
raise BBCCoUkIE.MediaSelectionError(error)
return media_selection.get('media') or []
def _extract_connections(self, media):
return self._findall_ns(media, './{%s}connection')
return media.get('connection') or []
def _get_subtitles(self, media, programme_id):
subtitles = {}
@@ -334,13 +319,13 @@ class BBCCoUkIE(InfoExtractor):
cc_url, programme_id, 'Downloading captions', fatal=False)
if not isinstance(captions, compat_etree_Element):
continue
lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
subtitles[lang] = [
subtitles['en'] = [
{
'url': connection.get('href'),
'ext': 'ttml',
},
]
break
return subtitles
def _raise_extractor_error(self, media_selection_error):
@@ -350,10 +335,10 @@ class BBCCoUkIE(InfoExtractor):
def _download_media_selector(self, programme_id):
last_exception = None
for mediaselector_url in self._MEDIASELECTOR_URLS:
for media_set in self._MEDIA_SETS:
try:
return self._download_media_selector_url(
mediaselector_url % programme_id, programme_id)
self._MEDIA_SELECTOR_URL_TEMPL % (media_set, programme_id), programme_id)
except BBCCoUkIE.MediaSelectionError as e:
if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
last_exception = e
@@ -362,8 +347,8 @@ class BBCCoUkIE(InfoExtractor):
self._raise_extractor_error(last_exception)
def _download_media_selector_url(self, url, programme_id=None):
media_selection = self._download_xml(
url, programme_id, 'Downloading media selection XML',
media_selection = self._download_json(
url, programme_id, 'Downloading media selection JSON',
expected_status=(403, 404))
return self._process_media_selector(media_selection, programme_id)
@@ -377,7 +362,6 @@ class BBCCoUkIE(InfoExtractor):
if kind in ('video', 'audio'):
bitrate = int_or_none(media.get('bitrate'))
encoding = media.get('encoding')
service = media.get('service')
width = int_or_none(media.get('width'))
height = int_or_none(media.get('height'))
file_size = int_or_none(media.get('media_file_size'))
@@ -392,8 +376,6 @@ class BBCCoUkIE(InfoExtractor):
supplier = connection.get('supplier')
transfer_format = connection.get('transferFormat')
format_id = supplier or conn_kind or protocol
if service:
format_id = '%s_%s' % (service, format_id)
# ASX playlist
if supplier == 'asx':
for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
@@ -408,20 +390,11 @@ class BBCCoUkIE(InfoExtractor):
formats.extend(self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False))
if re.search(self._USP_RE, href):
usp_formats = self._extract_m3u8_formats(
re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href),
programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
for f in usp_formats:
if f.get('height') and f['height'] > 720:
continue
formats.append(f)
elif transfer_format == 'hds':
formats.extend(self._extract_f4m_formats(
href, programme_id, f4m_id=format_id, fatal=False))
else:
if not service and not supplier and bitrate:
if not supplier and bitrate:
format_id += '-%d' % bitrate
fmt = {
'format_id': format_id,
@@ -554,7 +527,7 @@ class BBCCoUkIE(InfoExtractor):
webpage = self._download_webpage(url, group_id, 'Downloading video page')
error = self._search_regex(
r'<div\b[^>]+\bclass=["\']smp__message delta["\'][^>]*>([^<]+)<',
r'<div\b[^>]+\bclass=["\'](?:smp|playout)__message delta["\'][^>]*>\s*([^<]+?)\s*<',
webpage, 'error', default=None)
if error:
raise ExtractorError(error, expected=True)
@@ -607,16 +580,9 @@ class BBCIE(BBCCoUkIE):
IE_DESC = 'BBC'
_VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
_MEDIASELECTOR_URLS = [
# Provides HQ HLS streams but fails with geolocation in some cases when it's
# even not geo restricted at all
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
# Provides more formats, namely direct mp4 links, but fails on some videos with
# notukerror for non UK (?) users (e.g.
# http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
# Provides fewer formats, but works everywhere for everybody (hopefully)
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
_MEDIA_SETS = [
'mobile-tablet-main',
'pc',
]
_TESTS = [{

View File

@@ -0,0 +1,60 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
try_get,
urlencode_postdata,
)
class BongaCamsIE(InfoExtractor):
_VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.com)/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://de.bongacams.com/azumi-8',
'only_matching': True,
}, {
'url': 'https://cn.bongacams.com/azumi-8',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
channel_id = mobj.group('id')
amf = self._download_json(
'https://%s/tools/amf.php' % host, channel_id,
data=urlencode_postdata((
('method', 'getRoomData'),
('args[]', channel_id),
('args[]', 'false'),
)), headers={'X-Requested-With': 'XMLHttpRequest'})
server_url = amf['localData']['videoServerUrl']
uploader_id = try_get(
amf, lambda x: x['performerData']['username'], compat_str) or channel_id
uploader = try_get(
amf, lambda x: x['performerData']['displayName'], compat_str)
like_count = int_or_none(try_get(
amf, lambda x: x['performerData']['loversCount']))
formats = self._extract_m3u8_formats(
'%s/hls/stream_%s/playlist.m3u8' % (server_url, uploader_id),
channel_id, 'mp4', m3u8_id='hls', live=True)
self._sort_formats(formats)
return {
'id': channel_id,
'title': self._live_title(uploader or uploader_id),
'uploader': uploader,
'uploader_id': uploader_id,
'like_count': like_count,
'age_limit': 18,
'is_live': True,
'formats': formats,
}

View File

@@ -28,6 +28,7 @@ from ..utils import (
parse_iso8601,
smuggle_url,
str_or_none,
try_get,
unescapeHTML,
unsmuggle_url,
UnsupportedError,
@@ -600,24 +601,27 @@ class BrightcoveNewIE(AdobePassIE):
store_pk = lambda x: self._downloader.cache.store('brightcove', policy_key_id, x)
def extract_policy_key():
webpage = self._download_webpage(
'http://players.brightcove.net/%s/%s_%s/index.min.js'
% (account_id, player_id, embed), video_id)
policy_key = None
catalog = self._search_regex(
r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
if catalog:
catalog = self._parse_json(
js_to_json(catalog), video_id, fatal=False)
if catalog:
policy_key = catalog.get('policyKey')
base_url = 'http://players.brightcove.net/%s/%s_%s/' % (account_id, player_id, embed)
config = self._download_json(
base_url + 'config.json', video_id, fatal=False) or {}
policy_key = try_get(
config, lambda x: x['video_cloud']['policy_key'])
if not policy_key:
policy_key = self._search_regex(
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
webpage = self._download_webpage(
base_url + 'index.min.js', video_id)
catalog = self._search_regex(
r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
if catalog:
catalog = self._parse_json(
js_to_json(catalog), video_id, fatal=False)
if catalog:
policy_key = catalog.get('policyKey')
if not policy_key:
policy_key = self._search_regex(
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
store_pk(policy_key)
return policy_key

View File

@@ -11,7 +11,47 @@ from ..utils import (
class CBSLocalIE(AnvatoIE):
_VALID_URL = r'https?://[a-z]+\.cbslocal\.com/(?:\d+/\d+/\d+|video)/(?P<id>[0-9a-z-]+)'
_VALID_URL_BASE = r'https?://[a-z]+\.cbslocal\.com/'
_VALID_URL = _VALID_URL_BASE + r'video/(?P<id>\d+)'
_TESTS = [{
'url': 'http://newyork.cbslocal.com/video/3580809-a-very-blue-anniversary/',
'info_dict': {
'id': '3580809',
'ext': 'mp4',
'title': 'A Very Blue Anniversary',
'description': 'CBS2s Cindy Hsu has more.',
'thumbnail': 're:^https?://.*',
'timestamp': int,
'upload_date': r're:^\d{8}$',
'uploader': 'CBS',
'subtitles': {
'en': 'mincount:5',
},
'categories': [
'Stations\\Spoken Word\\WCBSTV',
'Syndication\\AOL',
'Syndication\\MSN',
'Syndication\\NDN',
'Syndication\\Yahoo',
'Content\\News',
'Content\\News\\Local News',
],
'tags': ['CBS 2 News Weekends', 'Cindy Hsu', 'Blue Man Group'],
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
mcp_id = self._match_id(url)
return self.url_result(
'anvato:anvato_cbslocal_app_web_prod_547f3e49241ef0e5d30c79b2efbca5d92c698f67:' + mcp_id, 'Anvato', mcp_id)
class CBSLocalArticleIE(AnvatoIE):
_VALID_URL = CBSLocalIE._VALID_URL_BASE + r'\d+/\d+/\d+/(?P<id>[0-9a-z-]+)'
_TESTS = [{
# Anvato backend
@@ -52,31 +92,6 @@ class CBSLocalIE(AnvatoIE):
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://newyork.cbslocal.com/video/3580809-a-very-blue-anniversary/',
'info_dict': {
'id': '3580809',
'ext': 'mp4',
'title': 'A Very Blue Anniversary',
'description': 'CBS2s Cindy Hsu has more.',
'thumbnail': 're:^https?://.*',
'timestamp': int,
'upload_date': r're:^\d{8}$',
'uploader': 'CBS',
'subtitles': {
'en': 'mincount:5',
},
'categories': [
'Stations\\Spoken Word\\WCBSTV',
'Syndication\\AOL',
'Syndication\\MSN',
'Syndication\\NDN',
'Syndication\\Yahoo',
'Content\\News',
'Content\\News\\Local News',
],
'tags': ['CBS 2 News Weekends', 'Cindy Hsu', 'Blue Man Group'],
},
}]
def _real_extract(self, url):

View File

@@ -0,0 +1,52 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class CTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ctv\.ca/(?P<id>(?:show|movie)s/[^/]+/[^/?#&]+)'
_TESTS = [{
'url': 'https://www.ctv.ca/shows/your-morning/wednesday-december-23-2020-s5e88',
'info_dict': {
'id': '2102249',
'ext': 'flv',
'title': 'Wednesday, December 23, 2020',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'Your Morning delivers original perspectives and unique insights into the headlines of the day.',
'timestamp': 1608732000,
'upload_date': '20201223',
'series': 'Your Morning',
'season': '2020-2021',
'season_number': 5,
'episode_number': 88,
'tags': ['Your Morning'],
'categories': ['Talk Show'],
'duration': 7467.126,
},
}, {
'url': 'https://www.ctv.ca/movies/adam-sandlers-eight-crazy-nights/adam-sandlers-eight-crazy-nights',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
content = self._download_json(
'https://www.ctv.ca/space-graphql/graphql', display_id, query={
'query': '''{
resolvedPath(path: "/%s") {
lastSegment {
content {
... on AxisContent {
axisId
videoPlayerDestCode
}
}
}
}
}''' % display_id,
})['data']['resolvedPath']['lastSegment']['content']
video_id = content['axisId']
return self.url_result(
'9c9media:%s:%s' % (content['videoPlayerDestCode'], video_id),
'NineCNineMedia', video_id)

View File

@@ -119,6 +119,7 @@ from .bleacherreport import (
from .blinkx import BlinkxIE
from .bloomberg import BloombergIE
from .bokecc import BokeCCIE
from .bongacams import BongaCamsIE
from .bostonglobe import BostonGlobeIE
from .box import BoxIE
from .bpb import BpbIE
@@ -163,7 +164,10 @@ from .cbc import (
CBCOlympicsIE,
)
from .cbs import CBSIE
from .cbslocal import CBSLocalIE
from .cbslocal import (
CBSLocalIE,
CBSLocalArticleIE,
)
from .cbsinteractive import CBSInteractiveIE
from .cbsnews import (
CBSNewsEmbedIE,
@@ -241,6 +245,7 @@ from .crunchyroll import (
)
from .cspan import CSpanIE
from .ctsnews import CtsNewsIE
from .ctv import CTVIE
from .ctvnews import CTVNewsIE
from .cultureunplugged import CultureUnpluggedIE
from .curiositystream import (
@@ -1451,7 +1456,10 @@ from .weibo import (
WeiboMobileIE
)
from .weiqitv import WeiqiTVIE
from .wistia import WistiaIE
from .wistia import (
WistiaIE,
WistiaPlaylistIE,
)
from .worldstarhiphop import WorldStarHipHopIE
from .wsj import (
WSJIE,

View File

@@ -1,6 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
import socket
@@ -8,6 +9,7 @@ from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_http_client,
compat_str,
compat_urllib_error,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
@@ -47,7 +49,8 @@ class FacebookIE(InfoExtractor):
)\?(?:.*?)(?:v|video_id|story_fbid)=|
[^/]+/videos/(?:[^/]+/)?|
[^/]+/posts/|
groups/[^/]+/permalink/
groups/[^/]+/permalink/|
watchparty/
)|
facebook:
)
@@ -280,8 +283,18 @@ class FacebookIE(InfoExtractor):
# data.video.creation_story.attachments[].media
'url': 'https://www.facebook.com/watch/live/?v=1823658634322275',
'only_matching': True,
}, {
'url': 'https://www.facebook.com/watchparty/211641140192478',
'info_dict': {
'id': '211641140192478',
},
'playlist_count': 1,
'skip': 'Requires logging in',
}]
_SUPPORTED_PAGLETS_REGEX = r'(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_[0-9a-f]+)'
_api_config = {
'graphURI': '/api/graphql/'
}
@staticmethod
def _extract_urls(webpage):
@@ -405,6 +418,17 @@ class FacebookIE(InfoExtractor):
self._sort_formats(formats)
def extract_relay_data(_filter):
return self._parse_json(self._search_regex(
r'handleWithCustomApplyEach\([^,]+,\s*({.*?%s.*?})\);' % _filter,
webpage, 'replay data', default='{}'), video_id, fatal=False) or {}
def extract_relay_prefetched_data(_filter):
replay_data = extract_relay_data(_filter)
for require in (replay_data.get('require') or []):
if require[0] == 'RelayPrefetchedStreamCache':
return try_get(require, lambda x: x[3][1]['__bbox']['result']['data'], dict) or {}
if not video_data:
server_js_data = self._parse_json(self._search_regex([
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+' + self._SUPPORTED_PAGLETS_REGEX,
@@ -413,87 +437,83 @@ class FacebookIE(InfoExtractor):
video_data = extract_from_jsmods_instances(server_js_data)
if not video_data:
graphql_data = self._parse_json(self._search_regex(
r'handleWithCustomApplyEach\([^,]+,\s*({.*?"(?:dash_manifest|playable_url(?:_quality_hd)?)"\s*:\s*"[^"]+".*?})\);',
webpage, 'graphql data', default='{}'), video_id, fatal=False) or {}
for require in (graphql_data.get('require') or []):
if require[0] == 'RelayPrefetchedStreamCache':
entries = []
data = extract_relay_prefetched_data(
r'"(?:dash_manifest|playable_url(?:_quality_hd)?)"\s*:\s*"[^"]+"')
if data:
entries = []
def parse_graphql_video(video):
formats = []
q = qualities(['sd', 'hd'])
for (suffix, format_id) in [('', 'sd'), ('_quality_hd', 'hd')]:
playable_url = video.get('playable_url' + suffix)
if not playable_url:
continue
formats.append({
'format_id': format_id,
'quality': q(format_id),
'url': playable_url,
})
extract_dash_manifest(video, formats)
process_formats(formats)
v_id = video.get('videoId') or video.get('id') or video_id
info = {
'id': v_id,
'formats': formats,
'thumbnail': try_get(video, lambda x: x['thumbnailImage']['uri']),
'uploader_id': try_get(video, lambda x: x['owner']['id']),
'timestamp': int_or_none(video.get('publish_time')),
'duration': float_or_none(video.get('playable_duration_in_ms'), 1000),
}
description = try_get(video, lambda x: x['savable_description']['text'])
title = video.get('name')
if title:
info.update({
'title': title,
'description': description,
})
else:
info['title'] = description or 'Facebook video #%s' % v_id
entries.append(info)
def parse_graphql_video(video):
formats = []
q = qualities(['sd', 'hd'])
for (suffix, format_id) in [('', 'sd'), ('_quality_hd', 'hd')]:
playable_url = video.get('playable_url' + suffix)
if not playable_url:
continue
formats.append({
'format_id': format_id,
'quality': q(format_id),
'url': playable_url,
})
extract_dash_manifest(video, formats)
process_formats(formats)
v_id = video.get('videoId') or video.get('id') or video_id
info = {
'id': v_id,
'formats': formats,
'thumbnail': try_get(video, lambda x: x['thumbnailImage']['uri']),
'uploader_id': try_get(video, lambda x: x['owner']['id']),
'timestamp': int_or_none(video.get('publish_time')),
'duration': float_or_none(video.get('playable_duration_in_ms'), 1000),
}
description = try_get(video, lambda x: x['savable_description']['text'])
title = video.get('name')
if title:
info.update({
'title': title,
'description': description,
})
else:
info['title'] = description or 'Facebook video #%s' % v_id
entries.append(info)
def parse_attachment(attachment, key='media'):
media = attachment.get(key) or {}
if media.get('__typename') == 'Video':
return parse_graphql_video(media)
def parse_attachment(attachment, key='media'):
media = attachment.get(key) or {}
if media.get('__typename') == 'Video':
return parse_graphql_video(media)
data = try_get(require, lambda x: x[3][1]['__bbox']['result']['data'], dict) or {}
nodes = data.get('nodes') or []
node = data.get('node') or {}
if not nodes and node:
nodes.append(node)
for node in nodes:
story = try_get(node, lambda x: x['comet_sections']['content']['story'], dict) or {}
attachments = try_get(story, [
lambda x: x['attached_story']['attachments'],
lambda x: x['attachments']
], list) or []
for attachment in attachments:
attachment = try_get(attachment, lambda x: x['style_type_renderer']['attachment'], dict)
ns = try_get(attachment, lambda x: x['all_subattachments']['nodes'], list) or []
for n in ns:
parse_attachment(n)
parse_attachment(attachment)
nodes = data.get('nodes') or []
node = data.get('node') or {}
if not nodes and node:
nodes.append(node)
for node in nodes:
story = try_get(node, lambda x: x['comet_sections']['content']['story'], dict) or {}
attachments = try_get(story, [
lambda x: x['attached_story']['attachments'],
lambda x: x['attachments']
], list) or []
for attachment in attachments:
attachment = try_get(attachment, lambda x: x['style_type_renderer']['attachment'], dict)
ns = try_get(attachment, lambda x: x['all_subattachments']['nodes'], list) or []
for n in ns:
parse_attachment(n)
parse_attachment(attachment)
edges = try_get(data, lambda x: x['mediaset']['currMedia']['edges'], list) or []
for edge in edges:
parse_attachment(edge, key='node')
edges = try_get(data, lambda x: x['mediaset']['currMedia']['edges'], list) or []
for edge in edges:
parse_attachment(edge, key='node')
video = data.get('video') or {}
if video:
attachments = try_get(video, [
lambda x: x['story']['attachments'],
lambda x: x['creation_story']['attachments']
], list) or []
for attachment in attachments:
parse_attachment(attachment)
if not entries:
parse_graphql_video(video)
video = data.get('video') or {}
if video:
attachments = try_get(video, [
lambda x: x['story']['attachments'],
lambda x: x['creation_story']['attachments']
], list) or []
for attachment in attachments:
parse_attachment(attachment)
if not entries:
parse_graphql_video(video)
return self.playlist_result(entries, video_id)
return self.playlist_result(entries, video_id)
if not video_data:
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
@@ -504,6 +524,43 @@ class FacebookIE(InfoExtractor):
elif '>You must log in to continue' in webpage:
self.raise_login_required()
if not video_data and '/watchparty/' in url:
post_data = {
'doc_id': 3731964053542869,
'variables': json.dumps({
'livingRoomID': video_id,
}),
}
prefetched_data = extract_relay_prefetched_data(r'"login_data"\s*:\s*{')
if prefetched_data:
lsd = try_get(prefetched_data, lambda x: x['login_data']['lsd'], dict)
if lsd:
post_data[lsd['name']] = lsd['value']
relay_data = extract_relay_data(r'\[\s*"RelayAPIConfigDefaults"\s*,')
for define in (relay_data.get('define') or []):
if define[0] == 'RelayAPIConfigDefaults':
self._api_config = define[2]
living_room = self._download_json(
urljoin(url, self._api_config['graphURI']), video_id,
data=urlencode_postdata(post_data))['data']['living_room']
entries = []
for edge in (try_get(living_room, lambda x: x['recap']['watched_content']['edges']) or []):
video = try_get(edge, lambda x: x['node']['video']) or {}
v_id = video.get('id')
if not v_id:
continue
v_id = compat_str(v_id)
entries.append(self.url_result(
self._VIDEO_PAGE_TEMPLATE % v_id,
self.ie_key(), v_id, video.get('name')))
return self.playlist_result(entries, video_id)
if not video_data:
# Video info not in first request, do a secondary request using
# tahoe player specific URL
tahoe_data = self._download_webpage(

View File

@@ -67,7 +67,10 @@ from .tube8 import Tube8IE
from .mofosex import MofosexEmbedIE
from .spankwire import SpankwireIE
from .youporn import YouPornIE
from .vimeo import VimeoIE
from .vimeo import (
VimeoIE,
VHXEmbedIE,
)
from .dailymotion import DailymotionIE
from .dailymail import DailyMailIE
from .onionstudios import OnionStudiosIE
@@ -2024,22 +2027,6 @@ class GenericIE(InfoExtractor):
},
'add_ie': [SpringboardPlatformIE.ie_key()],
},
{
'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
'info_dict': {
'id': 'uPDB5I9wfp8',
'ext': 'webm',
'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
'upload_date': '20160219',
'uploader': 'Pocoyo - Português (BR)',
'uploader_id': 'PocoyoBrazil',
},
'add_ie': [YoutubeIE.ie_key()],
'params': {
'skip_download': True,
},
},
{
'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
'info_dict': {
@@ -2209,7 +2196,18 @@ class GenericIE(InfoExtractor):
# 'params': {
# 'force_generic_extractor': True,
# },
# }
# },
{
# VHX Embed
'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
'info_dict': {
'id': '858208',
'ext': 'mp4',
'title': 'Untitled',
'uploader_id': 'user80538407',
'uploader': 'OTT Videos',
},
},
]
def report_following_redirect(self, new_url):
@@ -2587,6 +2585,10 @@ class GenericIE(InfoExtractor):
if vimeo_urls:
return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
vhx_url = VHXEmbedIE._extract_url(webpage)
if vhx_url:
return self.url_result(vhx_url, VHXEmbedIE.ie_key())
vid_me_embed_url = self._search_regex(
r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
webpage, 'vid.me embed', default=None)

View File

@@ -22,7 +22,7 @@ from ..utils import (
class InstagramIE(InfoExtractor):
_VALID_URL = r'(?P<url>https?://(?:www\.)?instagram\.com/(?:p|tv)/(?P<id>[^/?#&]+))'
_VALID_URL = r'(?P<url>https?://(?:www\.)?instagram\.com/(?:p|tv|reel)/(?P<id>[^/?#&]+))'
_TESTS = [{
'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
'md5': '0d2da106a9d2631273e192b372806516',
@@ -35,7 +35,7 @@ class InstagramIE(InfoExtractor):
'timestamp': 1371748545,
'upload_date': '20130620',
'uploader_id': 'naomipq',
'uploader': 'Naomi Leonor Phan-Quang',
'uploader': 'B E A U T Y F O R A S H E S',
'like_count': int,
'comment_count': int,
'comments': list,
@@ -95,6 +95,9 @@ class InstagramIE(InfoExtractor):
}, {
'url': 'https://www.instagram.com/tv/aye83DjauH/',
'only_matching': True,
}, {
'url': 'https://www.instagram.com/reel/CDUMkliABpa/',
'only_matching': True,
}]
@staticmethod
@@ -122,9 +125,9 @@ class InstagramIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
(video_url, description, thumbnail, timestamp, uploader,
(media, video_url, description, thumbnail, timestamp, uploader,
uploader_id, like_count, comment_count, comments, height,
width) = [None] * 11
width) = [None] * 12
shared_data = self._parse_json(
self._search_regex(
@@ -137,59 +140,77 @@ class InstagramIE(InfoExtractor):
(lambda x: x['entry_data']['PostPage'][0]['graphql']['shortcode_media'],
lambda x: x['entry_data']['PostPage'][0]['media']),
dict)
if media:
video_url = media.get('video_url')
height = int_or_none(media.get('dimensions', {}).get('height'))
width = int_or_none(media.get('dimensions', {}).get('width'))
description = try_get(
media, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'],
compat_str) or media.get('caption')
thumbnail = media.get('display_src')
timestamp = int_or_none(media.get('taken_at_timestamp') or media.get('date'))
uploader = media.get('owner', {}).get('full_name')
uploader_id = media.get('owner', {}).get('username')
# _sharedData.entry_data.PostPage is empty when authenticated (see
# https://github.com/ytdl-org/youtube-dl/pull/22880)
if not media:
additional_data = self._parse_json(
self._search_regex(
r'window\.__additionalDataLoaded\s*\(\s*[^,]+,\s*({.+?})\s*\)\s*;',
webpage, 'additional data', default='{}'),
video_id, fatal=False)
if additional_data:
media = try_get(
additional_data, lambda x: x['graphql']['shortcode_media'],
dict)
if media:
video_url = media.get('video_url')
height = int_or_none(media.get('dimensions', {}).get('height'))
width = int_or_none(media.get('dimensions', {}).get('width'))
description = try_get(
media, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'],
compat_str) or media.get('caption')
thumbnail = media.get('display_src') or media.get('display_url')
timestamp = int_or_none(media.get('taken_at_timestamp') or media.get('date'))
uploader = media.get('owner', {}).get('full_name')
uploader_id = media.get('owner', {}).get('username')
def get_count(key, kind):
return int_or_none(try_get(
def get_count(keys, kind):
if not isinstance(keys, (list, tuple)):
keys = [keys]
for key in keys:
count = int_or_none(try_get(
media, (lambda x: x['edge_media_%s' % key]['count'],
lambda x: x['%ss' % kind]['count'])))
like_count = get_count('preview_like', 'like')
comment_count = get_count('to_comment', 'comment')
if count is not None:
return count
like_count = get_count('preview_like', 'like')
comment_count = get_count(
('preview_comment', 'to_comment', 'to_parent_comment'), 'comment')
comments = [{
'author': comment.get('user', {}).get('username'),
'author_id': comment.get('user', {}).get('id'),
'id': comment.get('id'),
'text': comment.get('text'),
'timestamp': int_or_none(comment.get('created_at')),
} for comment in media.get(
'comments', {}).get('nodes', []) if comment.get('text')]
if not video_url:
edges = try_get(
media, lambda x: x['edge_sidecar_to_children']['edges'],
list) or []
if edges:
entries = []
for edge_num, edge in enumerate(edges, start=1):
node = try_get(edge, lambda x: x['node'], dict)
if not node:
continue
node_video_url = url_or_none(node.get('video_url'))
if not node_video_url:
continue
entries.append({
'id': node.get('shortcode') or node['id'],
'title': 'Video %d' % edge_num,
'url': node_video_url,
'thumbnail': node.get('display_url'),
'width': int_or_none(try_get(node, lambda x: x['dimensions']['width'])),
'height': int_or_none(try_get(node, lambda x: x['dimensions']['height'])),
'view_count': int_or_none(node.get('video_view_count')),
})
return self.playlist_result(
entries, video_id,
'Post by %s' % uploader_id if uploader_id else None,
description)
comments = [{
'author': comment.get('user', {}).get('username'),
'author_id': comment.get('user', {}).get('id'),
'id': comment.get('id'),
'text': comment.get('text'),
'timestamp': int_or_none(comment.get('created_at')),
} for comment in media.get(
'comments', {}).get('nodes', []) if comment.get('text')]
if not video_url:
edges = try_get(
media, lambda x: x['edge_sidecar_to_children']['edges'],
list) or []
if edges:
entries = []
for edge_num, edge in enumerate(edges, start=1):
node = try_get(edge, lambda x: x['node'], dict)
if not node:
continue
node_video_url = url_or_none(node.get('video_url'))
if not node_video_url:
continue
entries.append({
'id': node.get('shortcode') or node['id'],
'title': 'Video %d' % edge_num,
'url': node_video_url,
'thumbnail': node.get('display_url'),
'width': int_or_none(try_get(node, lambda x: x['dimensions']['width'])),
'height': int_or_none(try_get(node, lambda x: x['dimensions']['height'])),
'view_count': int_or_none(node.get('video_view_count')),
})
return self.playlist_result(
entries, video_id,
'Post by %s' % uploader_id if uploader_id else None,
description)
if not video_url:
video_url = self._og_search_video_url(webpage, secure=False)

View File

@@ -5,10 +5,11 @@ import re
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
float_or_none,
ExtractorError,
float_or_none,
int_or_none,
parse_iso8601,
try_get,
)
@@ -35,7 +36,7 @@ class NineCNineMediaIE(InfoExtractor):
'$include': '[HasClosedCaptions]',
})
if content_package.get('Constraints', {}).get('Security', {}).get('Type'):
if try_get(content_package, lambda x: x['Constraints']['Security']['Type']):
raise ExtractorError('This video is DRM protected.', expected=True)
manifest_base_url = content_package_url + 'manifest.'
@@ -52,7 +53,7 @@ class NineCNineMediaIE(InfoExtractor):
self._sort_formats(formats)
thumbnails = []
for image in content.get('Images', []):
for image in (content.get('Images') or []):
image_url = image.get('Url')
if not image_url:
continue
@@ -70,7 +71,7 @@ class NineCNineMediaIE(InfoExtractor):
continue
container.append(e_name)
season = content.get('Season', {})
season = content.get('Season') or {}
info = {
'id': content_id,
@@ -79,13 +80,14 @@ class NineCNineMediaIE(InfoExtractor):
'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
'episode_number': int_or_none(content.get('Episode')),
'season': season.get('Name'),
'season_number': season.get('Number'),
'season_number': int_or_none(season.get('Number')),
'season_id': season.get('Id'),
'series': content.get('Media', {}).get('Name'),
'series': try_get(content, lambda x: x['Media']['Name']),
'tags': tags,
'categories': categories,
'duration': float_or_none(content_package.get('Duration')),
'formats': formats,
'thumbnails': thumbnails,
}
if content_package.get('HasClosedCaptions'):

View File

@@ -288,14 +288,24 @@ class PornHubIE(PornHubBaseIE):
video_urls.append((v_url, None))
video_urls_set.add(v_url)
def parse_quality_items(quality_items):
q_items = self._parse_json(quality_items, video_id, fatal=False)
if not isinstance(q_items, list):
return
for item in q_items:
if isinstance(item, dict):
add_video_url(item.get('url'))
if not video_urls:
FORMAT_PREFIXES = ('media', 'quality')
FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
js_vars = extract_js_vars(
webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
default=None)
if js_vars:
for key, format_url in js_vars.items():
if any(key.startswith(p) for p in FORMAT_PREFIXES):
if key.startswith(FORMAT_PREFIXES[-1]):
parse_quality_items(format_url)
elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
add_video_url(format_url)
if not video_urls and re.search(
r'<[^>]+\bid=["\']lockedPlayer', webpage):
@@ -351,12 +361,16 @@ class PornHubIE(PornHubBaseIE):
r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
webpage, 'uploader', default=None)
def extract_vote_count(kind, name):
return self._extract_count(
(r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind,
r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind),
webpage, name)
view_count = self._extract_count(
r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
like_count = self._extract_count(
r'<span[^>]+class="votesUp"[^>]*>([\d,\.]+)</span>', webpage, 'like')
dislike_count = self._extract_count(
r'<span[^>]+class="votesDown"[^>]*>([\d,\.]+)</span>', webpage, 'dislike')
like_count = extract_vote_count('Up', 'like')
dislike_count = extract_vote_count('Down', 'dislike')
comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')

View File

@@ -1,40 +1,112 @@
# coding: utf-8
from __future__ import unicode_literals
import time
import uuid
from .common import InfoExtractor
from ..utils import smuggle_url
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
)
class SonyLIVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sonyliv\.com/details/[^/]+/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?sonyliv\.com/(?:s(?:how|port)s/[^/]+|movies|clip|trailer|music-videos)/[^/?#&]+-(?P<id>\d+)'
_TESTS = [{
'url': "http://www.sonyliv.com/details/episodes/5024612095001/Ep.-1---Achaari-Cheese-Toast---Bachelor's-Delight",
'url': 'https://www.sonyliv.com/shows/bachelors-delight-1700000113/achaari-cheese-toast-1000022678?watch=true',
'info_dict': {
'title': "Ep. 1 - Achaari Cheese Toast - Bachelor's Delight",
'id': 'ref:5024612095001',
'title': 'Bachelors Delight - Achaari Cheese Toast',
'id': '1000022678',
'ext': 'mp4',
'upload_date': '20170923',
'description': 'md5:7f28509a148d5be9d0782b4d5106410d',
'uploader_id': '5182475815001',
'timestamp': 1506200547,
'upload_date': '20200411',
'description': 'md5:3957fa31d9309bf336ceb3f37ad5b7cb',
'timestamp': 1586632091,
'duration': 185,
'season_number': 1,
'episode': 'Achaari Cheese Toast',
'episode_number': 1,
'release_year': 2016,
},
'params': {
'skip_download': True,
},
'add_ie': ['BrightcoveNew'],
}, {
'url': 'http://www.sonyliv.com/details/full%20movie/4951168986001/Sei-Raat-(Bangla)',
'url': 'https://www.sonyliv.com/movies/tahalka-1000050121?watch=true',
'only_matching': True,
}, {
'url': 'https://www.sonyliv.com/clip/jigarbaaz-1000098925',
'only_matching': True,
}, {
'url': 'https://www.sonyliv.com/trailer/sandwiched-forever-1000100286?watch=true',
'only_matching': True,
}, {
'url': 'https://www.sonyliv.com/sports/india-tour-of-australia-2020-21-1700000286/cricket-hls-day-3-1st-test-aus-vs-ind-19-dec-2020-1000100959?watch=true',
'only_matching': True,
}, {
'url': 'https://www.sonyliv.com/music-videos/yeh-un-dinon-ki-baat-hai-1000018779',
'only_matching': True,
}]
_GEO_COUNTRIES = ['IN']
_TOKEN = None
# BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4338955589001/default_default/index.html?videoId=%s'
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5182475815001/default_default/index.html?videoId=ref:%s'
def _call_api(self, version, path, video_id):
headers = {}
if self._TOKEN:
headers['security_token'] = self._TOKEN
try:
return self._download_json(
'https://apiv2.sonyliv.com/AGL/%s/A/ENG/WEB/%s' % (version, path),
video_id, headers=headers)['resultObj']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
message = self._parse_json(
e.cause.read().decode(), video_id)['message']
if message == 'Geoblocked Country':
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
raise ExtractorError(message)
raise
def _real_initialize(self):
self._TOKEN = self._call_api('1.4', 'ALL/GETTOKEN', None)
def _real_extract(self, url):
brightcove_id = self._match_id(url)
return self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {
'geo_countries': ['IN'],
'referrer': url,
}),
'BrightcoveNew', brightcove_id)
video_id = self._match_id(url)
content = self._call_api(
'1.5', 'IN/CONTENT/VIDEOURL/VOD/' + video_id, video_id)
if content.get('isEncrypted'):
raise ExtractorError('This video is DRM protected.', expected=True)
dash_url = content['videoURL']
headers = {
'x-playback-session-id': '%s-%d' % (uuid.uuid4().hex, time.time() * 1000)
}
formats = self._extract_mpd_formats(
dash_url, video_id, mpd_id='dash', headers=headers, fatal=False)
formats.extend(self._extract_m3u8_formats(
dash_url.replace('.mpd', '.m3u8').replace('/DASH/', '/HLS/'),
video_id, 'mp4', m3u8_id='hls', headers=headers, fatal=False))
for f in formats:
f.setdefault('http_headers', {}).update(headers)
self._sort_formats(formats)
metadata = self._call_api(
'1.6', 'IN/DETAIL/' + video_id, video_id)['containers'][0]['metadata']
title = metadata['title']
episode = metadata.get('episodeTitle')
if episode and title != episode:
title += ' - ' + episode
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': content.get('posterURL'),
'description': metadata.get('longDescription') or metadata.get('shortDescription'),
'timestamp': int_or_none(metadata.get('creationDate'), 1000),
'duration': int_or_none(metadata.get('duration')),
'season_number': int_or_none(metadata.get('season')),
'episode': episode,
'episode_number': int_or_none(metadata.get('episodeNumber')),
'release_year': int_or_none(metadata.get('year')),
}

View File

@@ -7,17 +7,24 @@ from ..utils import (
determine_ext,
ExtractorError,
merge_dicts,
orderedSet,
parse_duration,
parse_resolution,
str_to_int,
url_or_none,
urlencode_postdata,
urljoin,
)
class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
_VALID_URL = r'''(?x)
https?://
(?:[^/]+\.)?spankbang\.com/
(?:
(?P<id>[\da-z]+)/(?:video|play|embed)\b|
[\da-z]+-(?P<id_2>[\da-z]+)/playlist/[^/?#&]+
)
'''
_TESTS = [{
'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7',
@@ -57,10 +64,14 @@ class SpankBangIE(InfoExtractor):
}, {
'url': 'https://spankbang.com/2y3td/embed/',
'only_matching': True,
}, {
'url': 'https://spankbang.com/2v7ik-7ecbgu/playlist/latina+booty',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') or mobj.group('id_2')
webpage = self._download_webpage(
url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
video_id, headers={'Cookie': 'country=US'})
@@ -155,30 +166,33 @@ class SpankBangIE(InfoExtractor):
class SpankBangPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/(?P<display_id>[^/]+)'
_TEST = {
'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
'info_dict': {
'id': 'ug0k',
'title': 'Big Ass Titties',
},
'playlist_mincount': 50,
'playlist_mincount': 40,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(
url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
entries = [self.url_result(
'https://spankbang.com/%s/video' % video_id,
ie=SpankBangIE.ie_key(), video_id=video_id)
for video_id in orderedSet(re.findall(
r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
urljoin(url, mobj.group('path')),
ie=SpankBangIE.ie_key(), video_id=mobj.group('id'))
for mobj in re.finditer(
r'<a[^>]+\bhref=(["\'])(?P<path>/?[\da-z]+-(?P<id>[\da-z]+)/playlist/%s(?:(?!\1).)*)\1'
% re.escape(display_id), webpage)]
title = self._html_search_regex(
r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
r'<h1>([^<]+)\s+playlist\s*<', webpage, 'playlist title',
fatal=False)
return self.playlist_result(entries, playlist_id, title)

View File

@@ -3,50 +3,62 @@ from __future__ import unicode_literals
from .adobepass import AdobePassIE
from ..utils import (
extract_attributes,
update_url_query,
int_or_none,
smuggle_url,
update_url_query,
)
class SproutIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?sproutonline\.com/watch/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://www.sproutonline.com/watch/cowboy-adventure',
'md5': '74bf14128578d1e040c3ebc82088f45f',
_VALID_URL = r'https?://(?:www\.)?(?:sproutonline|universalkids)\.com/(?:watch|(?:[^/]+/)*videos)/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.universalkids.com/shows/remy-and-boo/season/1/videos/robot-bike-race',
'info_dict': {
'id': '9dexnwtmh8_X',
'id': 'bm0foJFaTKqb',
'ext': 'mp4',
'title': 'A Cowboy Adventure',
'description': 'Ruff-Ruff, Tweet and Dave get to be cowboys for the day at Six Cow Corral.',
'timestamp': 1437758640,
'upload_date': '20150724',
'uploader': 'NBCU-SPROUT-NEW',
}
}
'title': 'Robot Bike Race',
'description': 'md5:436b1d97117cc437f54c383f4debc66d',
'timestamp': 1606148940,
'upload_date': '20201123',
'uploader': 'NBCU-MPAT',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.sproutonline.com/watch/cowboy-adventure',
'only_matching': True,
}, {
'url': 'https://www.universalkids.com/watch/robot-bike-race',
'only_matching': True,
}]
_GEO_COUNTRIES = ['US']
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_component = self._search_regex(
r'(?s)(<div[^>]+data-component="video"[^>]*?>)',
webpage, 'video component', default=None)
if video_component:
options = self._parse_json(extract_attributes(
video_component)['data-options'], video_id)
theplatform_url = options['video']
query = {
'mbr': 'true',
'manifest': 'm3u',
}
if options.get('protected'):
query['auth'] = self._extract_mvpd_auth(url, options['pid'], 'sprout', 'sprout')
theplatform_url = smuggle_url(update_url_query(
theplatform_url, query), {'force_smil_url': True})
else:
iframe = self._search_regex(
r'(<iframe[^>]+id="sproutVideoIframe"[^>]*?>)',
webpage, 'iframe')
theplatform_url = extract_attributes(iframe)['src']
return self.url_result(theplatform_url, 'ThePlatform')
display_id = self._match_id(url)
mpx_metadata = self._download_json(
# http://nbcuunikidsprod.apps.nbcuni.com/networks/universalkids/content/videos/
'https://www.universalkids.com/_api/videos/' + display_id,
display_id)['mpxMetadata']
media_pid = mpx_metadata['mediaPid']
theplatform_url = 'https://link.theplatform.com/s/HNK2IC/' + media_pid
query = {
'mbr': 'true',
'manifest': 'm3u',
}
if mpx_metadata.get('entitlement') == 'auth':
query['auth'] = self._extract_mvpd_auth(url, media_pid, 'sprout', 'sprout')
theplatform_url = smuggle_url(
update_url_query(theplatform_url, query), {
'force_smil_url': True,
'geo_countries': self._GEO_COUNTRIES,
})
return {
'_type': 'url_transparent',
'id': media_pid,
'url': theplatform_url,
'series': mpx_metadata.get('seriesName'),
'season_number': int_or_none(mpx_metadata.get('seasonNumber')),
'episode_number': int_or_none(mpx_metadata.get('episodeNumber')),
'ie_key': 'ThePlatform',
}

View File

@@ -2,25 +2,40 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import unified_strdate
from ..utils import (
int_or_none,
parse_iso8601,
str_or_none,
strip_or_none,
try_get,
urljoin,
)
class StreetVoiceIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?streetvoice\.com/[^/]+/songs/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://streetvoice.com/skippylu/songs/94440/',
'md5': '15974627fc01a29e492c98593c2fd472',
'url': 'https://streetvoice.com/skippylu/songs/123688/',
'md5': '0eb535970629a5195685355f3ed60bfd',
'info_dict': {
'id': '94440',
'id': '123688',
'ext': 'mp3',
'title': '',
'description': 'Crispy脆樂團 - 輸',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 260,
'upload_date': '20091018',
'title': '流浪',
'description': 'md5:8eb0bfcc9dcd8aa82bd6efca66e3fea6',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 270,
'upload_date': '20100923',
'uploader': 'Crispy脆樂團',
'uploader_id': '627810',
'uploader_url': 're:^https?://streetvoice.com/skippylu/',
'timestamp': 1285261661,
'view_count': int,
'like_count': int,
'comment_count': int,
'repost_count': int,
'track': '流浪',
'track_id': '123688',
'album': '2010',
}
}, {
'url': 'http://tw.streetvoice.com/skippylu/songs/94440/',
@@ -29,21 +44,57 @@ class StreetVoiceIE(InfoExtractor):
def _real_extract(self, url):
song_id = self._match_id(url)
song = self._download_json(
'https://streetvoice.com/api/v1/public/song/%s/' % song_id, song_id, data=b'')
base_url = 'https://streetvoice.com/api/v4/song/%s/' % song_id
song = self._download_json(base_url, song_id, query={
'fields': 'album,comments_count,created_at,id,image,length,likes_count,name,nickname,plays_count,profile,share_count,synopsis,user,username',
})
title = song['name']
author = song['user']['nickname']
formats = []
for suffix, format_id in [('hls/file', 'hls'), ('file', 'http'), ('file/original', 'original')]:
f_url = (self._download_json(
base_url + suffix + '/', song_id,
'Downloading %s format URL' % format_id,
data=b'', fatal=False) or {}).get('file')
if not f_url:
continue
f = {
'ext': 'mp3',
'format_id': format_id,
'url': f_url,
'vcodec': 'none',
}
if format_id == 'hls':
f['protocol'] = 'm3u8_native'
abr = self._search_regex(r'\.mp3\.(\d+)k', f_url, 'bitrate', default=None)
if abr:
abr = int(abr)
f.update({
'abr': abr,
'tbr': abr,
})
formats.append(f)
user = song.get('user') or {}
username = user.get('username')
get_count = lambda x: int_or_none(song.get(x + '_count'))
return {
'id': song_id,
'url': song['file'],
'formats': formats,
'title': title,
'description': '%s - %s' % (author, title),
'thumbnail': self._proto_relative_url(song.get('image'), 'http:'),
'duration': song.get('length'),
'upload_date': unified_strdate(song.get('created_at')),
'uploader': author,
'uploader_id': compat_str(song['user']['id']),
'description': strip_or_none(song.get('synopsis')),
'thumbnail': song.get('image'),
'duration': int_or_none(song.get('length')),
'timestamp': parse_iso8601(song.get('created_at')),
'uploader': try_get(user, lambda x: x['profile']['nickname']),
'uploader_id': str_or_none(user.get('id')),
'uploader_url': urljoin(url, '/%s/' % username) if username else None,
'view_count': get_count('plays'),
'like_count': get_count('likes'),
'comment_count': get_count('comments'),
'repost_count': get_count('share'),
'track': title,
'track_id': song_id,
'album': try_get(song, lambda x: x['album']['name']),
}

View File

@@ -234,6 +234,9 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
})
mobj = re.match(self._VALID_URL, url)
provider_id = mobj.group('provider_id')

View File

@@ -1,18 +1,22 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .theplatform import ThePlatformIE
from ..utils import (
determine_ext,
parse_duration,
parse_iso8601,
)
class TheWeatherChannelIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?weather\.com/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?weather\.com(?P<asset_name>(?:/(?P<locale>[a-z]{2}-[A-Z]{2}))?/(?:[^/]+/)*video/(?P<id>[^/?#]+))'
_TESTS = [{
'url': 'https://weather.com/series/great-outdoors/video/ice-climber-is-in-for-a-shock',
'md5': 'ab924ac9574e79689c24c6b95e957def',
'md5': 'c4cbe74c9c17c5676b704b950b73dd92',
'info_dict': {
'id': 'cc82397e-cc3f-4d11-9390-a785add090e8',
'ext': 'mp4',
@@ -20,18 +24,33 @@ class TheWeatherChannelIE(ThePlatformIE):
'description': 'md5:55606ce1378d4c72e6545e160c9d9695',
'uploader': 'TWC - Digital (No Distro)',
'uploader_id': '6ccd5455-16bb-46f2-9c57-ff858bb9f62c',
'upload_date': '20160720',
'timestamp': 1469018835,
}
}, {
'url': 'https://weather.com/en-CA/international/videos/video/unidentified-object-falls-from-sky-in-india',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
drupal_settings = self._parse_json(self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
webpage, 'drupal settings'), display_id)
video_id = drupal_settings['twc']['contexts']['node']['uuid']
video_data = self._download_json(
'https://dsx.weather.com/cms/v4/asset-collection/en_US/' + video_id, video_id)
asset_name, locale, display_id = re.match(self._VALID_URL, url).groups()
if not locale:
locale = 'en-US'
video_data = list(self._download_json(
'https://weather.com/api/v1/p/redux-dal', display_id, data=json.dumps([{
'name': 'getCMSAssetsUrlConfig',
'params': {
'language': locale.replace('-', '_'),
'query': {
'assetName': {
'$in': asset_name,
},
},
}
}]).encode(), headers={
'Content-Type': 'application/json',
})['dal']['getCMSAssetsUrlConfig'].values())[0]['data'][0]
video_id = video_data['id']
seo_meta = video_data.get('seometa', {})
title = video_data.get('title') or seo_meta['title']
@@ -66,6 +85,8 @@ class TheWeatherChannelIE(ThePlatformIE):
})
self._sort_formats(formats)
cc_url = video_data.get('cc_url')
return {
'id': video_id,
'display_id': display_id,
@@ -74,6 +95,8 @@ class TheWeatherChannelIE(ThePlatformIE):
'duration': parse_duration(video_data.get('duration')),
'uploader': video_data.get('providername'),
'uploader_id': video_data.get('providerid'),
'timestamp': parse_iso8601(video_data.get('publishdate')),
'subtitles': {locale[:2]: [{'url': cc_url}]} if cc_url else None,
'thumbnails': thumbnails,
'formats': formats,
}

View File

@@ -200,7 +200,7 @@ class ToggleIE(InfoExtractor):
class MeWatchIE(InfoExtractor):
IE_NAME = 'mewatch'
_VALID_URL = r'https?://(?:www\.)?mewatch\.sg/watch/[0-9a-zA-Z-]+-(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371',
'info_dict': {
@@ -214,6 +214,12 @@ class MeWatchIE(InfoExtractor):
'params': {
'skip_download': 'm3u8 download',
},
}, {
'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-搜密。打卡。小红点-S2-E1-176232',
'only_matching': True,
}, {
'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@@ -1119,6 +1119,12 @@ class VHXEmbedIE(VimeoBaseInfoExtractor):
IE_NAME = 'vhx:embed'
_VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
return unescapeHTML(mobj.group(1)) if mobj else None
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
@@ -1127,5 +1133,6 @@ class VHXEmbedIE(VimeoBaseInfoExtractor):
'ott data'), video_id, js_to_json)['config_url']
config = self._download_json(config_url, video_id)
info = self._parse_config(config, video_id)
info['id'] = video_id
self._vimeo_sort_formats(info['formats'])
return info

View File

@@ -5,79 +5,34 @@ import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
int_or_none,
try_get,
unescapeHTML,
)
class WistiaIE(InfoExtractor):
_VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]{10})'
class WistiaBaseIE(InfoExtractor):
_VALID_ID_REGEX = r'(?P<id>[a-z0-9]{10})'
_VALID_URL_BASE = r'https?://(?:fast\.)?wistia\.(?:net|com)/embed/'
_EMBED_BASE_URL = 'http://fast.wistia.com/embed/'
_TESTS = [{
'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
'md5': 'cafeb56ec0c53c18c97405eecb3133df',
'info_dict': {
'id': 'sh7fpupwlt',
'ext': 'mov',
'title': 'Being Resourceful',
'description': 'a Clients From Hell Video Series video from worldwidewebhosting',
'upload_date': '20131204',
'timestamp': 1386185018,
'duration': 117,
},
}, {
'url': 'wistia:sh7fpupwlt',
'only_matching': True,
}, {
# with hls video
'url': 'wistia:807fafadvk',
'only_matching': True,
}, {
'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
'only_matching': True,
}, {
'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json',
'only_matching': True,
}]
# https://wistia.com/support/embed-and-share/video-on-your-website
@staticmethod
def _extract_url(webpage):
urls = WistiaIE._extract_urls(webpage)
return urls[0] if urls else None
@staticmethod
def _extract_urls(webpage):
urls = []
for match in re.finditer(
r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage):
urls.append(unescapeHTML(match.group('url')))
for match in re.finditer(
r'''(?sx)
<div[^>]+class=(["'])(?:(?!\1).)*?\bwistia_async_(?P<id>[a-z0-9]{10})\b(?:(?!\1).)*?\1
''', webpage):
urls.append('wistia:%s' % match.group('id'))
for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
urls.append('wistia:%s' % match.group('id'))
return urls
def _real_extract(self, url):
video_id = self._match_id(url)
data_json = self._download_json(
self._EMBED_BASE_URL + 'medias/%s.json' % video_id, video_id,
# Some videos require this.
headers={
'Referer': url if url.startswith('http') else self._EMBED_BASE_URL + 'iframe/' + video_id,
def _download_embed_config(self, config_type, config_id, referer):
base_url = self._EMBED_BASE_URL + '%ss/%s' % (config_type, config_id)
embed_config = self._download_json(
base_url + '.json', config_id, headers={
'Referer': referer if referer.startswith('http') else base_url, # Some videos require this.
})
if data_json.get('error'):
if isinstance(embed_config, dict) and embed_config.get('error'):
raise ExtractorError(
'Error while getting the playlist', expected=True)
data = data_json['media']
return embed_config
def _extract_media(self, embed_config):
data = embed_config['media']
video_id = data['hashedId']
title = data['name']
formats = []
@@ -160,3 +115,85 @@ class WistiaIE(InfoExtractor):
'timestamp': int_or_none(data.get('createdAt')),
'subtitles': subtitles,
}
class WistiaIE(WistiaBaseIE):
_VALID_URL = r'(?:wistia:|%s(?:iframe|medias)/)%s' % (WistiaBaseIE._VALID_URL_BASE, WistiaBaseIE._VALID_ID_REGEX)
_TESTS = [{
# with hls video
'url': 'wistia:807fafadvk',
'md5': 'daff0f3687a41d9a71b40e0e8c2610fe',
'info_dict': {
'id': '807fafadvk',
'ext': 'mp4',
'title': 'Drip Brennan Dunn Workshop',
'description': 'a JV Webinars video',
'upload_date': '20160518',
'timestamp': 1463607249,
'duration': 4987.11,
},
}, {
'url': 'wistia:sh7fpupwlt',
'only_matching': True,
}, {
'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
'only_matching': True,
}, {
'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
'only_matching': True,
}, {
'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json',
'only_matching': True,
}]
# https://wistia.com/support/embed-and-share/video-on-your-website
@staticmethod
def _extract_url(webpage):
urls = WistiaIE._extract_urls(webpage)
return urls[0] if urls else None
@staticmethod
def _extract_urls(webpage):
urls = []
for match in re.finditer(
r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage):
urls.append(unescapeHTML(match.group('url')))
for match in re.finditer(
r'''(?sx)
<div[^>]+class=(["'])(?:(?!\1).)*?\bwistia_async_(?P<id>[a-z0-9]{10})\b(?:(?!\1).)*?\1
''', webpage):
urls.append('wistia:%s' % match.group('id'))
for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
urls.append('wistia:%s' % match.group('id'))
return urls
def _real_extract(self, url):
video_id = self._match_id(url)
embed_config = self._download_embed_config('media', video_id, url)
return self._extract_media(embed_config)
class WistiaPlaylistIE(WistiaBaseIE):
_VALID_URL = r'%splaylists/%s' % (WistiaIE._VALID_URL_BASE, WistiaIE._VALID_ID_REGEX)
_TEST = {
'url': 'https://fast.wistia.net/embed/playlists/aodt9etokc',
'info_dict': {
'id': 'aodt9etokc',
},
'playlist_count': 3,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
playlist = self._download_embed_config('playlist', playlist_id, url)
entries = []
for media in (try_get(playlist, lambda x: x[0]['medias']) or []):
embed_config = media.get('embed_config')
if not embed_config:
continue
entries.append(self._extract_media(embed_config))
return self.playlist_result(entries, playlist_id)

View File

@@ -1322,17 +1322,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return self._parse_json(
uppercase_escape(config), video_id, fatal=False)
def _get_automatic_captions(self, video_id, webpage):
def _get_automatic_captions(self, video_id, player_response, player_config):
"""We need the webpage for getting the captions url, pass it as an
argument to speed up the process."""
self.to_screen('%s: Looking for automatic captions' % video_id)
player_config = self._get_ytplayer_config(video_id, webpage)
err_msg = 'Couldn\'t find automatic captions for %s' % video_id
if not player_config:
if not (player_response or player_config):
self._downloader.report_warning(err_msg)
return {}
try:
args = player_config['args']
args = player_config.get('args') if player_config else {}
caption_url = args.get('ttsurl')
if caption_url:
timestamp = args['timestamp']
@@ -1391,19 +1390,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return captions
# New captions format as of 22.06.2017
player_response = args.get('player_response')
if player_response and isinstance(player_response, compat_str):
player_response = self._parse_json(
player_response, video_id, fatal=False)
if player_response:
renderer = player_response['captions']['playerCaptionsTracklistRenderer']
base_url = renderer['captionTracks'][0]['baseUrl']
sub_lang_list = []
for lang in renderer['translationLanguages']:
lang_code = lang.get('languageCode')
if lang_code:
sub_lang_list.append(lang_code)
return make_captions(base_url, sub_lang_list)
if player_response:
renderer = player_response['captions']['playerCaptionsTracklistRenderer']
base_url = renderer['captionTracks'][0]['baseUrl']
sub_lang_list = []
for lang in renderer['translationLanguages']:
lang_code = lang.get('languageCode')
if lang_code:
sub_lang_list.append(lang_code)
return make_captions(base_url, sub_lang_list)
# Some videos don't provide ttsurl but rather caption_tracks and
# caption_translation_languages (e.g. 20LmZk1hakA)
@@ -1652,6 +1647,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# Get video info
video_info = {}
embed_webpage = None
ytplayer_config = None
if re.search(r'["\']status["\']\s*:\s*["\']LOGIN_REQUIRED', video_webpage) is not None:
age_gate = True
@@ -2276,7 +2272,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# subtitles
video_subtitles = self.extract_subtitles(video_id, video_webpage)
automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
automatic_captions = self.extract_automatic_captions(video_id, player_response, ytplayer_config)
video_duration = try_get(
video_info, lambda x: int_or_none(x['length_seconds'][0]))
@@ -2446,7 +2442,8 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
)/
(?:
(?:channel|c|user|feed)/|
(?:playlist|watch)\?.*?\blist=
(?:playlist|watch)\?.*?\blist=|
(?!(?:watch|embed|v|e)\b)
)
(?P<id>[^/?\#&]+)
'''
@@ -2715,13 +2712,22 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
# inline playlist with not always working continuations
'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
'only_matching': True,
}
# TODO
# {
# 'url': 'https://www.youtube.com/TheYoungTurks/live',
# 'only_matching': True,
# }
]
}, {
'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/course',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/zsecurity',
'only_matching': True,
}, {
'url': 'http://www.youtube.com/NASAgovVideo/videos',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/TheYoungTurks/live',
'only_matching': True,
}]
def _extract_channel_id(self, webpage):
channel_id = self._html_search_meta(

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2020.12.22'
__version__ = '2020.12.26'