1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-01 20:57:54 +01:00

Merge remote-tracking branch 'upstream/master' into fix/niconico

This commit is contained in:
tsukumijima 2020-02-17 17:18:02 +09:00
commit 653ce37517
29 changed files with 596 additions and 484 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: 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 2020.01.24. 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 Issues with outdated version will be REJECTED.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 2020.02.16. 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 Issues with outdated version will be REJECTED.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 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. - 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. - 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'm reporting a broken site support
- [ ] I've verified that I'm running youtube-dl version **2020.01.24** - [ ] I've verified that I'm running youtube-dl version **2020.02.16**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] 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 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 - [ ] 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] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [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] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2020.01.24 [debug] youtube-dl version 2020.02.16
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [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] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {} [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: 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 2020.01.24. 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 2020.02.16. 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 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. - 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. - 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'm reporting a new site support request
- [ ] I've verified that I'm running youtube-dl version **2020.01.24** - [ ] I've verified that I'm running youtube-dl version **2020.02.16**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] 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 checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones - [ ] 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: 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 2020.01.24. 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 2020.02.16. 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. - 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]) - Finally, put x into all relevant boxes (like this [x])
--> -->
- [ ] I'm reporting a site feature request - [ ] I'm reporting a site feature request
- [ ] I've verified that I'm running youtube-dl version **2020.01.24** - [ ] I've verified that I'm running youtube-dl version **2020.02.16**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones - [ ] 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: 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 2020.01.24. 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 2020.02.16. 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 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. - 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. - 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'm reporting a broken site support issue
- [ ] I've verified that I'm running youtube-dl version **2020.01.24** - [ ] I've verified that I'm running youtube-dl version **2020.02.16**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] 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 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 - [ ] 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] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [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] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2020.01.24 [debug] youtube-dl version 2020.02.16
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [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] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {} [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: 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 2020.01.24. 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 2020.02.16. 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. - 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]) - Finally, put x into all relevant boxes (like this [x])
--> -->
- [ ] I'm reporting a feature request - [ ] I'm reporting a feature request
- [ ] I've verified that I'm running youtube-dl version **2020.01.24** - [ ] I've verified that I'm running youtube-dl version **2020.02.16**
- [ ] I've searched the bugtracker for similar feature requests including closed ones - [ ] I've searched the bugtracker for similar feature requests including closed ones

View File

@ -1,3 +1,37 @@
version 2020.02.16
Core
* [YoutubeDL] Fix playlist entry indexing with --playlist-items (#10591,
#10622)
* [update] Fix updating via symlinks (#23991)
+ [compat] Introduce compat_realpath (#23991)
Extractors
+ [npr] Add support for streams (#24042)
+ [24video] Add support for porn.24video.net (#23779, #23784)
- [jpopsuki] Remove extractor (#23858)
* [nova] Improve extraction (#23690)
* [nova:embed] Improve (#23690)
* [nova:embed] Fix extraction (#23672)
+ [abc:iview] Add support for 720p (#22907, #22921)
* [nytimes] Improve format sorting (#24010)
+ [toggle] Add support for mewatch.sg (#23895, #23930)
* [thisoldhouse] Fix extraction (#23951)
+ [popcorntimes] Add support for popcorntimes.tv (#23949)
* [sportdeutschland] Update to new API
* [twitch:stream] Lowercase channel id for stream request (#23917)
* [tv5mondeplus] Fix extraction (#23907, #23911)
* [tva] Relax URL regular expression (#23903)
* [vimeo] Fix album extraction (#23864)
* [viewlift] Improve extraction
* Fix extraction (#23851)
+ Add support for authentication
+ Add support for more domains
* [svt] Fix series extraction (#22297)
* [svt] Fix article extraction (#22897, #22919)
* [soundcloud] Imporve private playlist/set tracks extraction (#3707)
version 2020.01.24 version 2020.01.24
Extractors Extractors

View File

@ -389,7 +389,6 @@
- **JeuxVideo** - **JeuxVideo**
- **Joj** - **Joj**
- **Jove** - **Jove**
- **jpopsuki.tv**
- **JWPlatform** - **JWPlatform**
- **Kakao** - **Kakao**
- **Kaltura** - **Kaltura**
@ -663,6 +662,7 @@
- **Pokemon** - **Pokemon**
- **PolskieRadio** - **PolskieRadio**
- **PolskieRadioCategory** - **PolskieRadioCategory**
- **Popcorntimes**
- **PopcornTV** - **PopcornTV**
- **PornCom** - **PornCom**
- **PornerBros** - **PornerBros**
@ -1004,8 +1004,8 @@
- **Vidzi** - **Vidzi**
- **vier**: vier.be and vijf.be - **vier**: vier.be and vijf.be
- **vier:videos** - **vier:videos**
- **ViewLift** - **viewlift**
- **ViewLiftEmbed** - **viewlift:embed**
- **Viidea** - **Viidea**
- **viki** - **viki**
- **viki:channel** - **viki:channel**

View File

@ -816,11 +816,15 @@ class TestYoutubeDL(unittest.TestCase):
'webpage_url': 'http://example.com', 'webpage_url': 'http://example.com',
} }
def get_ids(params): def get_downloaded_info_dicts(params):
ydl = YDL(params) ydl = YDL(params)
# make a copy because the dictionary can be modified # make a deep copy because the dictionary and nested entries
ydl.process_ie_result(playlist.copy()) # can be modified
return [int(v['id']) for v in ydl.downloaded_info_dicts] ydl.process_ie_result(copy.deepcopy(playlist))
return ydl.downloaded_info_dicts
def get_ids(params):
return [int(v['id']) for v in get_downloaded_info_dicts(params)]
result = get_ids({}) result = get_ids({})
self.assertEqual(result, [1, 2, 3, 4]) self.assertEqual(result, [1, 2, 3, 4])
@ -852,6 +856,22 @@ class TestYoutubeDL(unittest.TestCase):
result = get_ids({'playlist_items': '2-4,3-4,3'}) result = get_ids({'playlist_items': '2-4,3-4,3'})
self.assertEqual(result, [2, 3, 4]) self.assertEqual(result, [2, 3, 4])
# Tests for https://github.com/ytdl-org/youtube-dl/issues/10591
# @{
result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'})
self.assertEqual(result[0]['playlist_index'], 2)
self.assertEqual(result[1]['playlist_index'], 3)
result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'})
self.assertEqual(result[0]['playlist_index'], 2)
self.assertEqual(result[1]['playlist_index'], 3)
self.assertEqual(result[2]['playlist_index'], 4)
result = get_downloaded_info_dicts({'playlist_items': '4,2'})
self.assertEqual(result[0]['playlist_index'], 4)
self.assertEqual(result[1]['playlist_index'], 2)
# @}
def test_urlopen_no_file_protocol(self): def test_urlopen_no_file_protocol(self):
# see https://github.com/ytdl-org/youtube-dl/issues/8227 # see https://github.com/ytdl-org/youtube-dl/issues/8227
ydl = YDL() ydl = YDL()

View File

@ -990,7 +990,7 @@ class YoutubeDL(object):
'playlist_title': ie_result.get('title'), 'playlist_title': ie_result.get('title'),
'playlist_uploader': ie_result.get('uploader'), 'playlist_uploader': ie_result.get('uploader'),
'playlist_uploader_id': ie_result.get('uploader_id'), 'playlist_uploader_id': ie_result.get('uploader_id'),
'playlist_index': i + playliststart, 'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart,
'extractor': ie_result['extractor'], 'extractor': ie_result['extractor'],
'webpage_url': ie_result['webpage_url'], 'webpage_url': ie_result['webpage_url'],
'webpage_url_basename': url_basename(ie_result['webpage_url']), 'webpage_url_basename': url_basename(ie_result['webpage_url']),

View File

@ -2754,6 +2754,17 @@ else:
compat_expanduser = os.path.expanduser compat_expanduser = os.path.expanduser
if compat_os_name == 'nt' and sys.version_info < (3, 8):
# os.path.realpath on Windows does not follow symbolic links
# prior to Python 3.8 (see https://bugs.python.org/issue9949)
def compat_realpath(path):
while os.path.islink(path):
path = os.path.abspath(os.readlink(path))
return path
else:
compat_realpath = os.path.realpath
if sys.version_info < (3, 0): if sys.version_info < (3, 0):
def compat_print(s): def compat_print(s):
from .utils import preferredencoding from .utils import preferredencoding
@ -2998,6 +3009,7 @@ __all__ = [
'compat_os_name', 'compat_os_name',
'compat_parse_qs', 'compat_parse_qs',
'compat_print', 'compat_print',
'compat_realpath',
'compat_setenv', 'compat_setenv',
'compat_shlex_quote', 'compat_shlex_quote',
'compat_shlex_split', 'compat_shlex_split',

View File

@ -110,17 +110,17 @@ class ABCIViewIE(InfoExtractor):
# ABC iview programs are normally available for 14 days only. # ABC iview programs are normally available for 14 days only.
_TESTS = [{ _TESTS = [{
'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00', 'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
'md5': 'cde42d728b3b7c2b32b1b94b4a548afc', 'md5': '67715ce3c78426b11ba167d875ac6abf',
'info_dict': { 'info_dict': {
'id': 'ZX9371A050S00', 'id': 'LE1927H001S00',
'ext': 'mp4', 'ext': 'mp4',
'title': "Gaston's Birthday", 'title': "Series 11 Ep 1",
'series': "Ben And Holly's Little Kingdom", 'series': "Gruen",
'description': 'md5:f9de914d02f226968f598ac76f105bcf', 'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
'upload_date': '20180604', 'upload_date': '20190925',
'uploader_id': 'abc4kids', 'uploader_id': 'abc1',
'timestamp': 1528140219, 'timestamp': 1569445289,
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -148,7 +148,7 @@ class ABCIViewIE(InfoExtractor):
'hdnea': token, 'hdnea': token,
}) })
for sd in ('sd', 'sd-low'): for sd in ('720', 'sd', 'sd-low'):
sd_url = try_get( sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str) stream, lambda x: x['streams']['hls'][sd], compat_str)
if not sd_url: if not sd_url:

View File

@ -497,7 +497,6 @@ from .jeuxvideo import JeuxVideoIE
from .jove import JoveIE from .jove import JoveIE
from .joj import JojIE from .joj import JojIE
from .jwplatform import JWPlatformIE from .jwplatform import JWPlatformIE
from .jpopsukitv import JpopsukiIE
from .kakao import KakaoIE from .kakao import KakaoIE
from .kaltura import KalturaIE from .kaltura import KalturaIE
from .kanalplay import KanalPlayIE from .kanalplay import KanalPlayIE
@ -850,6 +849,7 @@ from .polskieradio import (
PolskieRadioIE, PolskieRadioIE,
PolskieRadioCategoryIE, PolskieRadioCategoryIE,
) )
from .popcorntimes import PopcorntimesIE
from .popcorntv import PopcornTVIE from .popcorntv import PopcornTVIE
from .porn91 import Porn91IE from .porn91 import Porn91IE
from .porncom import PornComIE from .porncom import PornComIE

View File

@ -1,68 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_strdate,
)
class JpopsukiIE(InfoExtractor):
IE_NAME = 'jpopsuki.tv'
_VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P<id>\S+)'
_TEST = {
'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
'md5': '88018c0c1a9b1387940e90ec9e7e198e',
'info_dict': {
'id': '00be659d23b0b40508169cdee4545771',
'ext': 'mp4',
'title': 'ayumi hamasaki - evolution',
'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution',
'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
'uploader': 'plama_chan',
'uploader_id': '404',
'upload_date': '20121101'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
r'<source src="(.*?)" type', webpage, 'video url')
video_title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._html_search_regex(
r'<li>from: <a href="/user/view/user/(.*?)/uid/',
webpage, 'video uploader', fatal=False)
uploader_id = self._html_search_regex(
r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)',
webpage, 'video uploader_id', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date',
fatal=False))
view_count_str = self._html_search_regex(
r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count',
fatal=False)
comment_count_str = self._html_search_regex(
r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count',
fatal=False)
return {
'id': video_id,
'url': video_url,
'title': video_title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'upload_date': upload_date,
'view_count': int_or_none(view_count_str),
'comment_count': int_or_none(comment_count_str),
}

View File

@ -18,7 +18,7 @@ class NovaEmbedIE(InfoExtractor):
_VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
_TEST = { _TEST = {
'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1', 'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
'md5': 'b3834f6de5401baabf31ed57456463f7', 'md5': 'ee009bafcc794541570edd44b71cbea3',
'info_dict': { 'info_dict': {
'id': '8o0n0r', 'id': '8o0n0r',
'ext': 'mp4', 'ext': 'mp4',
@ -44,11 +44,17 @@ class NovaEmbedIE(InfoExtractor):
formats = [] formats = []
for format_id, format_list in bitrates.items(): for format_id, format_list in bitrates.items():
if not isinstance(format_list, list): if not isinstance(format_list, list):
continue format_list = [format_list]
for format_url in format_list: for format_url in format_list:
format_url = url_or_none(format_url) format_url = url_or_none(format_url)
if not format_url: if not format_url:
continue continue
if format_id == 'hls':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False))
continue
f = { f = {
'url': format_url, 'url': format_url,
} }
@ -91,7 +97,7 @@ class NovaIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)' _VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
_TESTS = [{ _TESTS = [{
'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260', 'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
'md5': '1dd7b9d5ea27bc361f110cd855a19bd3', 'md5': '249baab7d0104e186e78b0899c7d5f28',
'info_dict': { 'info_dict': {
'id': '1757139', 'id': '1757139',
'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci', 'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
@ -113,7 +119,8 @@ class NovaIE(InfoExtractor):
'params': { 'params': {
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
} },
'skip': 'gone',
}, { }, {
# media.cms.nova.cz embed # media.cms.nova.cz embed
'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil', 'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil',
@ -128,6 +135,7 @@ class NovaIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
'add_ie': [NovaEmbedIE.ie_key()], 'add_ie': [NovaEmbedIE.ie_key()],
'skip': 'CHYBA 404: STRÁNKA NENALEZENA',
}, { }, {
'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html', 'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
'only_matching': True, 'only_matching': True,
@ -152,14 +160,29 @@ class NovaIE(InfoExtractor):
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
description = clean_html(self._og_search_description(webpage, default=None))
if site == 'novaplus':
upload_date = unified_strdate(self._search_regex(
r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
elif site == 'fanda':
upload_date = unified_strdate(self._search_regex(
r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
else:
upload_date = None
# novaplus # novaplus
embed_id = self._search_regex( embed_id = self._search_regex(
r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)', r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)',
webpage, 'embed url', default=None) webpage, 'embed url', default=None)
if embed_id: if embed_id:
return self.url_result( return {
'https://media.cms.nova.cz/embed/%s' % embed_id, '_type': 'url_transparent',
ie=NovaEmbedIE.ie_key(), video_id=embed_id) 'url': 'https://media.cms.nova.cz/embed/%s' % embed_id,
'ie_key': NovaEmbedIE.ie_key(),
'id': embed_id,
'description': description,
'upload_date': upload_date
}
video_id = self._search_regex( video_id = self._search_regex(
[r"(?:media|video_id)\s*:\s*'(\d+)'", [r"(?:media|video_id)\s*:\s*'(\d+)'",
@ -233,18 +256,8 @@ class NovaIE(InfoExtractor):
self._sort_formats(formats) self._sort_formats(formats)
title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage) title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
description = clean_html(self._og_search_description(webpage, default=None))
thumbnail = config.get('poster') thumbnail = config.get('poster')
if site == 'novaplus':
upload_date = unified_strdate(self._search_regex(
r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
elif site == 'fanda':
upload_date = unified_strdate(self._search_regex(
r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
else:
upload_date = None
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,

View File

@ -4,6 +4,7 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
qualities, qualities,
url_or_none,
) )
@ -48,6 +49,10 @@ class NprIE(InfoExtractor):
}, },
}], }],
'expected_warnings': ['Failed to download m3u8 information'], 'expected_warnings': ['Failed to download m3u8 information'],
}, {
# multimedia, no formats, stream
'url': 'https://www.npr.org/2020/02/14/805476846/laura-stevenson-tiny-desk-concert',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -95,6 +100,17 @@ class NprIE(InfoExtractor):
'format_id': format_id, 'format_id': format_id,
'quality': quality(format_id), 'quality': quality(format_id),
}) })
for stream_id, stream_entry in media.get('stream', {}).items():
if not isinstance(stream_entry, dict):
continue
if stream_id != 'hlsUrl':
continue
stream_url = url_or_none(stream_entry.get('$text'))
if not stream_url:
continue
formats.extend(self._extract_m3u8_formats(
stream_url, stream_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
self._sort_formats(formats) self._sort_formats(formats)
entries.append({ entries.append({

View File

@ -69,10 +69,10 @@ class NYTimesBaseIE(InfoExtractor):
'width': int_or_none(video.get('width')), 'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')), 'height': int_or_none(video.get('height')),
'filesize': get_file_size(video.get('file_size') or video.get('fileSize')), 'filesize': get_file_size(video.get('file_size') or video.get('fileSize')),
'tbr': int_or_none(video.get('bitrate'), 1000), 'tbr': int_or_none(video.get('bitrate'), 1000) or None,
'ext': ext, 'ext': ext,
}) })
self._sort_formats(formats) self._sort_formats(formats, ('height', 'width', 'filesize', 'tbr', 'fps', 'format_id'))
thumbnails = [] thumbnails = []
for image in video_data.get('images', []): for image in video_data.get('images', []):

View File

@ -0,0 +1,99 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_chr,
)
from ..utils import int_or_none
class PopcorntimesIE(InfoExtractor):
_VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
_TEST = {
'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy',
'md5': '93f210991ad94ba8c3485950a2453257',
'info_dict': {
'id': 'A1XCFvz',
'display_id': 'haensel-und-gretel-opera-fantasy',
'ext': 'mp4',
'title': 'Hänsel und Gretel',
'description': 'md5:1b8146791726342e7b22ce8125cf6945',
'thumbnail': r're:^https?://.*\.jpg$',
'creator': 'John Paul',
'release_date': '19541009',
'duration': 4260,
'tbr': 5380,
'width': 720,
'height': 540,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id, display_id = mobj.group('id', 'display_id')
webpage = self._download_webpage(url, display_id)
title = self._search_regex(
r'<h1>([^<]+)', webpage, 'title',
default=None) or self._html_search_meta(
'ya:ovs:original_name', webpage, 'title', fatal=True)
loc = self._search_regex(
r'PCTMLOC\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'loc',
group='value')
loc_b64 = ''
for c in loc:
c_ord = ord(c)
if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'):
upper = ord('Z') if c_ord <= ord('Z') else ord('z')
c_ord += 13
if upper < c_ord:
c_ord -= 26
loc_b64 += compat_chr(c_ord)
video_url = compat_b64decode(loc_b64).decode('utf-8')
description = self._html_search_regex(
r'(?s)<div[^>]+class=["\']pt-movie-desc[^>]+>(.+?)</div>', webpage,
'description', fatal=False)
thumbnail = self._search_regex(
r'<img[^>]+class=["\']video-preview[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1',
webpage, 'thumbnail', default=None,
group='value') or self._og_search_thumbnail(webpage)
creator = self._html_search_meta(
'video:director', webpage, 'creator', default=None)
release_date = self._html_search_meta(
'video:release_date', webpage, default=None)
if release_date:
release_date = release_date.replace('-', '')
def int_meta(name):
return int_or_none(self._html_search_meta(
name, webpage, default=None))
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'creator': creator,
'release_date': release_date,
'duration': int_meta('video:duration'),
'tbr': int_meta('ya:ovs:bitrate'),
'width': int_meta('og:video:width'),
'height': int_meta('og:video:height'),
'http_headers': {
'Referer': url,
},
}

View File

@ -13,36 +13,18 @@ from ..utils import (
class SportDeutschlandIE(InfoExtractor): class SportDeutschlandIE(InfoExtractor):
_VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])' _VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])'
_TESTS = [{ _TESTS = [{
'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
'info_dict': { 'info_dict': {
'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', 'id': 're-live-deutsche-meisterschaften-2020-halbfinals',
'ext': 'mp4', 'ext': 'mp4',
'title': 're:Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', 'title': 're:Re-live: Deutsche Meisterschaften 2020.*Halbfinals',
'categories': ['Badminton'], 'categories': ['Badminton-Deutschland'],
'view_count': int, 'view_count': int,
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
'description': r're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV',
'timestamp': int, 'timestamp': int,
'upload_date': 're:^201408[23][0-9]$', 'upload_date': '20200201',
'description': 're:.*', # meaningless description for THIS video
}, },
'params': {
'skip_download': 'Live stream',
},
}, {
'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
'info_dict': {
'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
'ext': 'mp4',
'upload_date': '20140825',
'description': 'md5:60a20536b57cee7d9a4ec005e8687504',
'timestamp': 1408976060,
'duration': 2732,
'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee',
'thumbnail': r're:^https?://.*\.jpg$',
'view_count': int,
'categories': ['Li-Ning Badminton WM 2014'],
}
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -50,7 +32,7 @@ class SportDeutschlandIE(InfoExtractor):
video_id = mobj.group('id') video_id = mobj.group('id')
sport_id = mobj.group('sport') sport_id = mobj.group('sport')
api_url = 'http://proxy.vidibusdynamic.net/sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % ( api_url = 'https://proxy.vidibusdynamic.net/ssl/backend.sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % (
sport_id, video_id) sport_id, video_id)
req = sanitized_Request(api_url, headers={ req = sanitized_Request(api_url, headers={
'Accept': 'application/vnd.vidibus.v2.html+json', 'Accept': 'application/vnd.vidibus.v2.html+json',

View File

@ -4,19 +4,14 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_str
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
dict_get, dict_get,
int_or_none, int_or_none,
orderedSet, str_or_none,
strip_or_none, strip_or_none,
try_get, try_get,
urljoin,
compat_str,
) )
@ -237,23 +232,23 @@ class SVTPlayIE(SVTPlayBaseIE):
class SVTSeriesIE(SVTPlayBaseIE): class SVTSeriesIE(SVTPlayBaseIE):
_VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)' _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)(?:.+?\btab=(?P<season_slug>[^&#]+))?'
_TESTS = [{ _TESTS = [{
'url': 'https://www.svtplay.se/rederiet', 'url': 'https://www.svtplay.se/rederiet',
'info_dict': { 'info_dict': {
'id': 'rederiet', 'id': '14445680',
'title': 'Rederiet', 'title': 'Rederiet',
'description': 'md5:505d491a58f4fcf6eb418ecab947e69e', 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039',
}, },
'playlist_mincount': 318, 'playlist_mincount': 318,
}, { }, {
'url': 'https://www.svtplay.se/rederiet?tab=sasong2', 'url': 'https://www.svtplay.se/rederiet?tab=season-2-14445680',
'info_dict': { 'info_dict': {
'id': 'rederiet-sasong2', 'id': 'season-2-14445680',
'title': 'Rederiet - Säsong 2', 'title': 'Rederiet - Säsong 2',
'description': 'md5:505d491a58f4fcf6eb418ecab947e69e', 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039',
}, },
'playlist_count': 12, 'playlist_mincount': 12,
}] }]
@classmethod @classmethod
@ -261,83 +256,87 @@ class SVTSeriesIE(SVTPlayBaseIE):
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url) return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
series_id = self._match_id(url) series_slug, season_id = re.match(self._VALID_URL, url).groups()
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query) series = self._download_json(
season_slug = qs.get('tab', [None])[0] 'https://api.svt.se/contento/graphql', series_slug,
'Downloading series page', query={
if season_slug: 'query': '''{
series_id += '-%s' % season_slug listablesBySlug(slugs: ["%s"]) {
associatedContent(include: [productionPeriod, season]) {
webpage = self._download_webpage( items {
url, series_id, 'Downloading series page') item {
... on Episode {
root = self._parse_json( videoSvtId
self._search_regex( }
self._SVTPLAY_RE, webpage, 'content', group='json'), }
series_id) }
id
name
}
id
longDescription
name
shortDescription
}
}''' % series_slug,
})['data']['listablesBySlug'][0]
season_name = None season_name = None
entries = [] entries = []
for season in root['relatedVideoContent']['relatedVideosAccordion']: for season in series['associatedContent']:
if not isinstance(season, dict): if not isinstance(season, dict):
continue continue
if season_slug: if season_id:
if season.get('slug') != season_slug: if season.get('id') != season_id:
continue continue
season_name = season.get('name') season_name = season.get('name')
videos = season.get('videos') items = season.get('items')
if not isinstance(videos, list): if not isinstance(items, list):
continue continue
for video in videos: for item in items:
content_url = video.get('contentUrl') video = item.get('item') or {}
if not content_url or not isinstance(content_url, compat_str): content_id = video.get('videoSvtId')
if not content_id or not isinstance(content_id, compat_str):
continue continue
entries.append( entries.append(self.url_result(
self.url_result( 'svt:' + content_id, SVTPlayIE.ie_key(), content_id))
urljoin(url, content_url),
ie=SVTPlayIE.ie_key(),
video_title=video.get('title')
))
metadata = root.get('metaData') title = series.get('name')
if not isinstance(metadata, dict): season_name = season_name or season_id
metadata = {}
title = metadata.get('title')
season_name = season_name or season_slug
if title and season_name: if title and season_name:
title = '%s - %s' % (title, season_name) title = '%s - %s' % (title, season_name)
elif season_slug: elif season_id:
title = season_slug title = season_id
return self.playlist_result( return self.playlist_result(
entries, series_id, title, metadata.get('description')) entries, season_id or series.get('id'), title,
dict_get(series, ('longDescription', 'shortDescription')))
class SVTPageIE(InfoExtractor): class SVTPageIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P<id>[^/?&#]+)' _VALID_URL = r'https?://(?:www\.)?svt\.se/(?P<path>(?:[^/]+/)*(?P<id>[^/?&#]+))'
_TESTS = [{ _TESTS = [{
'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill', 'url': 'https://www.svt.se/sport/ishockey/bakom-masken-lehners-kamp-mot-mental-ohalsa',
'info_dict': { 'info_dict': {
'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill', 'id': '25298267',
'title': 'GUIDE: Sommarträning du kan göra var och när du vill', 'title': 'Bakom masken Lehners kamp mot mental ohälsa',
}, },
'playlist_count': 7, 'playlist_count': 4,
}, { }, {
'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner', 'url': 'https://www.svt.se/nyheter/utrikes/svenska-andrea-ar-en-mil-fran-branderna-i-kalifornien',
'info_dict': { 'info_dict': {
'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner', 'id': '24243746',
'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”', 'title': 'Svenska Andrea redo att fly sitt hem i Kalifornien',
}, },
'playlist_count': 1, 'playlist_count': 2,
}, { }, {
# only programTitle # only programTitle
'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
'info_dict': { 'info_dict': {
'id': '2900353', 'id': '8439V2K',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Stjärnorna skojar till det - under SVT-intervjun', 'title': 'Stjärnorna skojar till det - under SVT-intervjun',
'duration': 27, 'duration': 27,
@ -356,16 +355,26 @@ class SVTPageIE(InfoExtractor):
return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url) return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
playlist_id = self._match_id(url) path, display_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, playlist_id) article = self._download_json(
'https://api.svt.se/nss-api/page/' + path, display_id,
query={'q': 'articles'})['articles']['content'][0]
entries = [ entries = []
self.url_result(
'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id)
for video_id in orderedSet(re.findall(
r'data-video-id=["\'](\d+)', webpage))]
title = strip_or_none(self._og_search_title(webpage, default=None)) def _process_content(content):
if content.get('_type') in ('VIDEOCLIP', 'VIDEOEPISODE'):
video_id = compat_str(content['image']['svtId'])
entries.append(self.url_result(
'svt:' + video_id, SVTPlayIE.ie_key(), video_id))
return self.playlist_result(entries, playlist_id, title) for media in article.get('media', []):
_process_content(media)
for obj in article.get('structuredBody', []):
_process_content(obj.get('content') or {})
return self.playlist_result(
entries, str_or_none(article.get('id')),
strip_or_none(article.get('title')))

View File

@ -2,43 +2,42 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import try_get
class ThisOldHouseIE(InfoExtractor): class ThisOldHouseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)' _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P<id>[^/?#]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench', 'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
'md5': '568acf9ca25a639f0c4ff905826b662f',
'info_dict': { 'info_dict': {
'id': '2REGtUDQ', 'id': '5dcdddf673c3f956ef5db202',
'ext': 'mp4', 'ext': 'mp4',
'title': 'How to Build a Storage Bench', 'title': 'How to Build a Storage Bench',
'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.', 'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.',
'timestamp': 1442548800, 'timestamp': 1442548800,
'upload_date': '20150918', 'upload_date': '20150918',
} },
'params': {
'skip_download': True,
},
}, { }, {
'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins', 'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric', 'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench',
'only_matching': True,
}, {
'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost',
'only_matching': True,
}] }]
_ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe'
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
video_id = self._search_regex( video_id = self._search_regex(
(r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', r'<iframe[^>]+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/videos/zype/([0-9a-f]{24})',
r'id=(["\'])inline-video-player-(?P<id>(?:(?!\1).)+)\1'), webpage, 'video id')
webpage, 'video id', default=None, group='id') return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id)
if not video_id:
drupal_settings = self._parse_json(self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
webpage, 'drupal settings'), display_id)
video_id = try_get(
drupal_settings, lambda x: x['jwplatform']['video_id'],
compat_str) or list(drupal_settings['comScore'])[0]
return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id)

View File

@ -17,9 +17,9 @@ from ..utils import (
class ToggleIE(InfoExtractor): class ToggleIE(InfoExtractor):
IE_NAME = 'toggle' IE_NAME = 'toggle'
_VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', 'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
'info_dict': { 'info_dict': {
'id': '343115', 'id': '343115',
'ext': 'mp4', 'ext': 'mp4',
@ -33,7 +33,7 @@ class ToggleIE(InfoExtractor):
} }
}, { }, {
'note': 'DRM-protected video', 'note': 'DRM-protected video',
'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413', 'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
'info_dict': { 'info_dict': {
'id': '341413', 'id': '341413',
'ext': 'wvm', 'ext': 'wvm',
@ -48,7 +48,7 @@ class ToggleIE(InfoExtractor):
}, { }, {
# this also tests correct video id extraction # this also tests correct video id extraction
'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay', 'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', 'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
'info_dict': { 'info_dict': {
'id': '332861', 'id': '332861',
'ext': 'mp4', 'ext': 'mp4',
@ -65,19 +65,22 @@ class ToggleIE(InfoExtractor):
'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367', 'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', 'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'http://video.toggle.sg/en/movies/seven-days/321936', 'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', 'url': 'http://www.mewatch.sg/en/movies/seven-days/321936',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585', 'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
'only_matching': True,
}, {
'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
'only_matching': True, 'only_matching': True,
}] }]

View File

@ -3,31 +3,51 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html,
determine_ext, determine_ext,
extract_attributes, extract_attributes,
get_element_by_class,
int_or_none, int_or_none,
parse_duration, parse_duration,
parse_iso8601,
) )
class TV5MondePlusIE(InfoExtractor): class TV5MondePlusIE(InfoExtractor):
IE_DESC = 'TV5MONDE+' IE_DESC = 'TV5MONDE+'
_VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)' _VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
_TEST = { _TESTS = [{
'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', # movie
'md5': '12130fc199f020673138a83466542ec6', 'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/rendez-vous-a-atlit',
'md5': '8cbde5ea7b296cf635073e27895e227f',
'info_dict': { 'info_dict': {
'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', 'id': '822a4756-0712-7329-1859-a13ac7fd1407',
'display_id': 'rendez-vous-a-atlit',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Tdah, mon amour - Enfants', 'title': 'Rendez-vous à Atlit',
'description': 'md5:230e3aca23115afcf8006d1bece6df74', 'description': 'md5:2893a4c5e1dbac3eedff2d87956e4efb',
'upload_date': '20170401', 'upload_date': '20200130',
'timestamp': 1491022860, },
} }, {
} # series episode
'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/c-est-la-vie-ennemie-juree',
'info_dict': {
'id': '0df7007c-4900-3936-c601-87a13a93a068',
'display_id': 'c-est-la-vie-ennemie-juree',
'ext': 'mp4',
'title': "C'est la vie - Ennemie jurée",
'description': 'md5:dfb5c63087b6f35fe0cc0af4fe44287e',
'upload_date': '20200130',
'series': "C'est la vie",
'episode': 'Ennemie jurée',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver',
'only_matching': True,
}, {
'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30',
'only_matching': True,
}]
_GEO_BYPASS = False _GEO_BYPASS = False
def _real_extract(self, url): def _real_extract(self, url):
@ -37,11 +57,7 @@ class TV5MondePlusIE(InfoExtractor):
if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage: if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
self.raise_geo_restricted(countries=['FR']) self.raise_geo_restricted(countries=['FR'])
series = get_element_by_class('video-detail__title', webpage) title = episode = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
title = episode = get_element_by_class(
'video-detail__subtitle', webpage) or series
if series and series != title:
title = '%s - %s' % (series, title)
vpl_data = extract_attributes(self._search_regex( vpl_data = extract_attributes(self._search_regex(
r'(<[^>]+class="video_player_loader"[^>]+>)', r'(<[^>]+class="video_player_loader"[^>]+>)',
webpage, 'video player loader')) webpage, 'video player loader'))
@ -65,15 +81,37 @@ class TV5MondePlusIE(InfoExtractor):
}) })
self._sort_formats(formats) self._sort_formats(formats)
description = self._html_search_regex(
r'(?s)<div[^>]+class=["\']episode-texte[^>]+>(.+?)</div>', webpage,
'description', fatal=False)
series = self._html_search_regex(
r'<p[^>]+class=["\']episode-emission[^>]+>([^<]+)', webpage,
'series', default=None)
if series and series != title:
title = '%s - %s' % (series, title)
upload_date = self._search_regex(
r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})',
webpage, 'upload date', default=None)
if upload_date:
upload_date = upload_date.replace('_', '')
video_id = self._search_regex(
(r'data-guid=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
r'id_contenu["\']\s:\s*(\d+)'), webpage, 'video id',
default=display_id)
return { return {
'id': display_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,
'description': clean_html(get_element_by_class('video-detail__description', webpage)), 'description': description,
'thumbnail': vpl_data.get('data-image'), 'thumbnail': vpl_data.get('data-image'),
'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)), 'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)),
'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)), 'upload_date': upload_date,
'formats': formats, 'formats': formats,
'episode': episode,
'series': series, 'series': series,
'episode': episode,
} }

View File

@ -9,8 +9,8 @@ from ..utils import (
class TVAIE(InfoExtractor): class TVAIE(InfoExtractor):
_VALID_URL = r'https?://videos\.tva\.ca/details/_(?P<id>\d+)' _VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P<id>\d+)'
_TEST = { _TESTS = [{
'url': 'https://videos.tva.ca/details/_5596811470001', 'url': 'https://videos.tva.ca/details/_5596811470001',
'info_dict': { 'info_dict': {
'id': '5596811470001', 'id': '5596811470001',
@ -24,7 +24,10 @@ class TVAIE(InfoExtractor):
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
} }
} }, {
'url': 'https://video.tva.ca/details/_5596811470001',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s' BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s'
def _real_extract(self, url): def _real_extract(self, url):

View File

@ -17,7 +17,7 @@ class TwentyFourVideoIE(InfoExtractor):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
https?:// https?://
(?P<host> (?P<host>
(?:(?:www|porno)\.)?24video\. (?:(?:www|porno?)\.)?24video\.
(?:net|me|xxx|sexy?|tube|adult|site|vip) (?:net|me|xxx|sexy?|tube|adult|site|vip)
)/ )/
(?: (?:
@ -62,6 +62,9 @@ class TwentyFourVideoIE(InfoExtractor):
}, { }, {
'url': 'https://www.24video.vip/video/view/1044982', 'url': 'https://www.24video.vip/video/view/1044982',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://porn.24video.net/video/2640421-vsya-takay',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):

View File

@ -575,8 +575,8 @@ class TwitchStreamIE(TwitchBaseIE):
channel_id = self._match_id(url) channel_id = self._match_id(url)
stream = self._call_api( stream = self._call_api(
'kraken/streams/%s?stream_type=all' % channel_id, channel_id, 'kraken/streams/%s?stream_type=all' % channel_id.lower(),
'Downloading stream JSON').get('stream') channel_id, 'Downloading stream JSON').get('stream')
if not stream: if not stream:
raise ExtractorError('%s is offline' % channel_id, expected=True) raise ExtractorError('%s is offline' % channel_id, expected=True)

View File

@ -1,28 +1,62 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import base64 import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote from ..compat import compat_HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
clean_html,
determine_ext,
int_or_none, int_or_none,
js_to_json,
parse_age_limit, parse_age_limit,
parse_duration,
try_get,
) )
class ViewLiftBaseIE(InfoExtractor): class ViewLiftBaseIE(InfoExtractor):
_DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv' _API_BASE = 'https://prod-api.viewlift.com/'
_DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm|failarmy|ftfnext|lnppass\.legapallacanestro|moviespree|app\.myoutdoortv|neoufitness|pflmma|theidentitytb)\.com|(?:hoichoi|app\.horseandcountry|kronon|marquee|supercrosslive)\.tv'
_SITE_MAP = {
'ftfnext': 'lax',
'funnyforfree': 'snagfilms',
'hoichoi': 'hoichoitv',
'kiddovid': 'snagfilms',
'laxsportsnetwork': 'lax',
'legapallacanestro': 'lnp',
'marquee': 'marquee-tv',
'monumentalsportsnetwork': 'monumental-network',
'moviespree': 'bingeflix',
'pflmma': 'pfl',
'snagxtreme': 'snagfilms',
'theidentitytb': 'tampabay',
'vayafilm': 'snagfilms',
}
_TOKENS = {}
def _call_api(self, site, path, video_id, query):
token = self._TOKENS.get(site)
if not token:
token_query = {'site': site}
email, password = self._get_login_info(netrc_machine=site)
if email:
resp = self._download_json(
self._API_BASE + 'identity/signin', video_id,
'Logging in', query=token_query, data=json.dumps({
'email': email,
'password': password,
}).encode())
else:
resp = self._download_json(
self._API_BASE + 'identity/anonymous-token', video_id,
'Downloading authorization token', query=token_query)
self._TOKENS[site] = token = resp['authorizationToken']
return self._download_json(
self._API_BASE + path, video_id,
headers={'Authorization': token}, query=query)
class ViewLiftEmbedIE(ViewLiftBaseIE): class ViewLiftEmbedIE(ViewLiftBaseIE):
_VALID_URL = r'https?://(?:(?:www|embed)\.)?(?:%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX IE_NAME = 'viewlift:embed'
_VALID_URL = r'https?://(?:(?:www|embed)\.)?(?P<domain>%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX
_TESTS = [{ _TESTS = [{
'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500', 'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
'md5': '2924e9215c6eff7a55ed35b72276bd93', 'md5': '2924e9215c6eff7a55ed35b72276bd93',
@ -30,6 +64,9 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
'id': '74849a00-85a9-11e1-9660-123139220831', 'id': '74849a00-85a9-11e1-9660-123139220831',
'ext': 'mp4', 'ext': 'mp4',
'title': '#whilewewatch', 'title': '#whilewewatch',
'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8',
'timestamp': 1334350096,
'upload_date': '20120413',
} }
}, { }, {
# invalid labels, 360p is better that 480p # invalid labels, 360p is better that 480p
@ -39,7 +76,8 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
'id': '17ca0950-a74a-11e0-a92a-0026bb61d036', 'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Life in Limbo', 'title': 'Life in Limbo',
} },
'skip': 'The video does not exist',
}, { }, {
'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017', 'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
'only_matching': True, 'only_matching': True,
@ -54,67 +92,68 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
return mobj.group('url') return mobj.group('url')
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) domain, film_id = re.match(self._VALID_URL, url).groups()
site = domain.split('.')[-2]
webpage = self._download_webpage(url, video_id) if site in self._SITE_MAP:
site = self._SITE_MAP[site]
if '>This film is not playable in your area.<' in webpage: try:
raise ExtractorError( content_data = self._call_api(
'Film %s is not playable in your area.' % video_id, expected=True) site, 'entitlement/video/status', film_id, {
'id': film_id
})['video']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error_message = self._parse_json(e.cause.read().decode(), film_id).get('errorMessage')
if error_message == 'User does not have a valid subscription or has not purchased this content.':
self.raise_login_required()
raise ExtractorError(error_message, expected=True)
raise
gist = content_data['gist']
title = gist['title']
video_assets = content_data['streamingInfo']['videoAssets']
formats = [] formats = []
has_bitrate = False mpeg_video_assets = video_assets.get('mpeg') or []
sources = self._parse_json(self._search_regex( for video_asset in mpeg_video_assets:
r'(?s)sources:\s*(\[.+?\]),', webpage, video_asset_url = video_asset.get('url')
'sources', default='[]'), video_id, js_to_json) if not video_asset:
for source in sources:
file_ = source.get('file')
if not file_:
continue continue
type_ = source.get('type') bitrate = int_or_none(video_asset.get('bitrate'))
ext = determine_ext(file_)
format_id = source.get('label') or ext
if all(v in ('m3u8', 'hls') for v in (type_, ext)):
formats.extend(self._extract_m3u8_formats(
file_, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
bitrate = int_or_none(self._search_regex(
[r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext],
file_, 'bitrate', default=None))
if not has_bitrate and bitrate:
has_bitrate = True
height = int_or_none(self._search_regex( height = int_or_none(self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)) r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
'height', default=None))
formats.append({ formats.append({
'url': file_, 'url': video_asset_url,
'format_id': 'http-%s%s' % (format_id, ('-%dk' % bitrate if bitrate else '')), 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
'tbr': bitrate, 'tbr': bitrate,
'height': height, 'height': height,
'vcodec': video_asset.get('codec'),
}) })
if not formats:
hls_url = self._parse_json(self._search_regex(
r'filmInfo\.src\s*=\s*({.+?});',
webpage, 'src'), video_id, js_to_json)['src']
formats = self._extract_m3u8_formats(
hls_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
field_preference = None if has_bitrate else ('height', 'tbr', 'format_id')
self._sort_formats(formats, field_preference)
title = self._search_regex( hls_url = video_assets.get('hls')
[r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'], if hls_url:
webpage, 'title') formats.extend(self._extract_m3u8_formats(
hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
self._sort_formats(formats, ('height', 'tbr', 'format_id'))
return { info = {
'id': video_id, 'id': film_id,
'title': title, 'title': title,
'description': gist.get('description'),
'thumbnail': gist.get('videoImageUrl'),
'duration': int_or_none(gist.get('runtime')),
'age_limit': parse_age_limit(content_data.get('parentalRating')),
'timestamp': int_or_none(gist.get('publishDate'), 1000),
'formats': formats, 'formats': formats,
} }
for k in ('categories', 'tags'):
info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')]
return info
class ViewLiftIE(ViewLiftBaseIE): class ViewLiftIE(ViewLiftBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX IE_NAME = 'viewlift'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX
_TESTS = [{ _TESTS = [{
'url': 'http://www.snagfilms.com/films/title/lost_for_life', 'url': 'http://www.snagfilms.com/films/title/lost_for_life',
'md5': '19844f897b35af219773fd63bdec2942', 'md5': '19844f897b35af219773fd63bdec2942',
@ -151,10 +190,13 @@ class ViewLiftIE(ViewLiftBaseIE):
'id': '00000148-7b53-de26-a9fb-fbf306f70020', 'id': '00000148-7b53-de26-a9fb-fbf306f70020',
'display_id': 'augie_alone/s_2_ep_12_love', 'display_id': 'augie_alone/s_2_ep_12_love',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Augie, Alone:S. 2 Ep. 12 - Love', 'title': 'S. 2 Ep. 12 - Love',
'description': 'md5:db2a5c72d994f16a780c1eb353a8f403', 'description': 'Augie finds love.',
'thumbnail': r're:^https?://.*\.jpg', 'thumbnail': r're:^https?://.*\.jpg',
'duration': 107, 'duration': 107,
'upload_date': '20141012',
'timestamp': 1413129540,
'age_limit': 17,
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -177,6 +219,9 @@ class ViewLiftIE(ViewLiftBaseIE):
# Was once Kaltura embed # Was once Kaltura embed
'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15', 'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters',
'only_matching': True,
}] }]
@classmethod @classmethod
@ -184,119 +229,22 @@ class ViewLiftIE(ViewLiftBaseIE):
return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url) return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
domain, display_id = re.match(self._VALID_URL, url).groups() domain, path, display_id = re.match(self._VALID_URL, url).groups()
site = domain.split('.')[-2]
webpage = self._download_webpage(url, display_id) if site in self._SITE_MAP:
site = self._SITE_MAP[site]
if ">Sorry, the Film you're looking for is not available.<" in webpage: modules = self._call_api(
raise ExtractorError( site, 'content/pages', display_id, {
'Film %s is not available.' % display_id, expected=True) 'includeContent': 'true',
'moduleOffset': 1,
initial_store_state = self._search_regex( 'path': path,
r"window\.initialStoreState\s*=.*?JSON\.parse\(unescape\(atob\('([^']+)'\)\)\)", 'site': site,
webpage, 'Initial Store State', default=None) })['modules']
if initial_store_state: film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule')
modules = self._parse_json(compat_urllib_parse_unquote(base64.b64decode(
initial_store_state).decode()), display_id)['page']['data']['modules']
content_data = next(m['contentData'][0] for m in modules if m.get('moduleType') == 'VideoDetailModule')
gist = content_data['gist']
film_id = gist['id']
title = gist['title']
video_assets = try_get(
content_data, lambda x: x['streamingInfo']['videoAssets'], dict)
if not video_assets:
token = self._download_json(
'https://prod-api.viewlift.com/identity/anonymous-token',
film_id, 'Downloading authorization token',
query={'site': 'snagfilms'})['authorizationToken']
video_assets = self._download_json(
'https://prod-api.viewlift.com/entitlement/video/status',
film_id, headers={
'Authorization': token,
'Referer': url,
}, query={
'id': film_id
})['video']['streamingInfo']['videoAssets']
formats = []
mpeg_video_assets = video_assets.get('mpeg') or []
for video_asset in mpeg_video_assets:
video_asset_url = video_asset.get('url')
if not video_asset:
continue
bitrate = int_or_none(video_asset.get('bitrate'))
height = int_or_none(self._search_regex(
r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
'height', default=None))
formats.append({
'url': video_asset_url,
'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
'tbr': bitrate,
'height': height,
'vcodec': video_asset.get('codec'),
})
hls_url = video_assets.get('hls')
if hls_url:
formats.extend(self._extract_m3u8_formats(
hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
self._sort_formats(formats, ('height', 'tbr', 'format_id'))
info = {
'id': film_id,
'display_id': display_id,
'title': title,
'description': gist.get('description'),
'thumbnail': gist.get('videoImageUrl'),
'duration': int_or_none(gist.get('runtime')),
'age_limit': parse_age_limit(content_data.get('parentalRating')),
'timestamp': int_or_none(gist.get('publishDate'), 1000),
'formats': formats,
}
for k in ('categories', 'tags'):
info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')]
return info
else:
film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
snag = self._parse_json(
self._search_regex(
r'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag', default='[]'),
display_id)
for item in snag:
if item.get('data', {}).get('film', {}).get('id') == film_id:
data = item['data']['film']
title = data['title']
description = clean_html(data.get('synopsis'))
thumbnail = data.get('image')
duration = int_or_none(data.get('duration') or data.get('runtime'))
categories = [
category['title'] for category in data.get('categories', [])
if category.get('title')]
break
else:
title = self._html_search_regex(
(r'itemprop="title">([^<]+)<',
r'(?s)itemprop="title">(.+?)<div'), webpage, 'title')
description = self._html_search_regex(
r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
webpage, 'description', default=None) or self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
duration = parse_duration(self._search_regex(
r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
webpage, 'duration', fatal=False))
categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id), 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
'id': film_id, 'id': film_id,
'display_id': display_id, 'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'categories': categories,
'ie_key': 'ViewLiftEmbed', 'ie_key': 'ViewLiftEmbed',
} }

View File

@ -841,33 +841,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
return self._TITLE or self._html_search_regex( return self._TITLE or self._html_search_regex(
self._TITLE_RE, webpage, 'list title', fatal=False) self._TITLE_RE, webpage, 'list title', fatal=False)
def _login_list_password(self, page_url, list_id, webpage):
login_form = self._search_regex(
r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
webpage, 'login form', default=None)
if not login_form:
return webpage
password = self._downloader.params.get('videopassword')
if password is None:
raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
fields = self._hidden_inputs(login_form)
token, vuid = self._extract_xsrft_and_vuid(webpage)
fields['token'] = token
fields['password'] = password
post = urlencode_postdata(fields)
password_path = self._search_regex(
r'action="([^"]+)"', login_form, 'password URL')
password_url = compat_urlparse.urljoin(page_url, password_path)
password_request = sanitized_Request(password_url, post)
password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
self._set_vimeo_cookie('vuid', vuid)
self._set_vimeo_cookie('xsrft', token)
return self._download_webpage(
password_request, list_id,
'Verifying the password', 'Wrong password')
def _title_and_entries(self, list_id, base_url): def _title_and_entries(self, list_id, base_url):
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
page_url = self._page_url(base_url, pagenum) page_url = self._page_url(base_url, pagenum)
@ -876,7 +849,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
'Downloading page %s' % pagenum) 'Downloading page %s' % pagenum)
if pagenum == 1: if pagenum == 1:
webpage = self._login_list_password(page_url, list_id, webpage)
yield self._extract_list_title(webpage) yield self._extract_list_title(webpage)
# Try extracting href first since not all videos are available via # Try extracting href first since not all videos are available via
@ -923,7 +895,7 @@ class VimeoUserIE(VimeoChannelIE):
_BASE_URL_TEMPL = 'https://vimeo.com/%s' _BASE_URL_TEMPL = 'https://vimeo.com/%s'
class VimeoAlbumIE(VimeoChannelIE): class VimeoAlbumIE(VimeoBaseInfoExtractor):
IE_NAME = 'vimeo:album' IE_NAME = 'vimeo:album'
_VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))' _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
@ -973,13 +945,39 @@ class VimeoAlbumIE(VimeoChannelIE):
def _real_extract(self, url): def _real_extract(self, url):
album_id = self._match_id(url) album_id = self._match_id(url)
webpage = self._download_webpage(url, album_id) webpage = self._download_webpage(url, album_id)
webpage = self._login_list_password(url, album_id, webpage) viewer = self._parse_json(self._search_regex(
api_config = self._extract_vimeo_config(webpage, album_id)['api'] r'bootstrap_data\s*=\s*({.+?})</script>',
webpage, 'bootstrap data'), album_id)['viewer']
jwt = viewer['jwt']
album = self._download_json(
'https://api.vimeo.com/albums/' + album_id,
album_id, headers={'Authorization': 'jwt ' + jwt},
query={'fields': 'description,name,privacy'})
hashed_pass = None
if try_get(album, lambda x: x['privacy']['view']) == 'password':
password = self._downloader.params.get('videopassword')
if not password:
raise ExtractorError(
'This album is protected by a password, use the --video-password option',
expected=True)
self._set_vimeo_cookie('vuid', viewer['vuid'])
try:
hashed_pass = self._download_json(
'https://vimeo.com/showcase/%s/auth' % album_id,
album_id, 'Verifying the password', data=urlencode_postdata({
'password': password,
'token': viewer['xsrft'],
}), headers={
'X-Requested-With': 'XMLHttpRequest',
})['hashed_pass']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
raise ExtractorError('Wrong password', expected=True)
raise
entries = OnDemandPagedList(functools.partial( entries = OnDemandPagedList(functools.partial(
self._fetch_page, album_id, api_config['jwt'], self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
api_config.get('hashed_pass')), self._PAGE_SIZE) return self.playlist_result(
return self.playlist_result(entries, album_id, self._html_search_regex( entries, album_id, album.get('name'), album.get('description'))
r'<title>\s*(.+?)(?:\s+on Vimeo)?</title>', webpage, 'title', fatal=False))
class VimeoGroupsIE(VimeoChannelIE): class VimeoGroupsIE(VimeoChannelIE):

View File

@ -9,6 +9,7 @@ import subprocess
import sys import sys
from zipimport import zipimporter from zipimport import zipimporter
from .compat import compat_realpath
from .utils import encode_compat_str from .utils import encode_compat_str
from .version import __version__ from .version import __version__
@ -84,7 +85,9 @@ def update_self(to_screen, verbose, opener):
print_notes(to_screen, versions_info['versions']) print_notes(to_screen, versions_info['versions'])
# sys.executable is set to the full pathname of the exe-file for py2exe # sys.executable is set to the full pathname of the exe-file for py2exe
filename = sys.executable if hasattr(sys, 'frozen') else sys.argv[0] # though symlinks are not followed so that we need to do this manually
# with help of realpath
filename = compat_realpath(sys.executable if hasattr(sys, 'frozen') else sys.argv[0])
if not os.access(filename, os.W_OK): if not os.access(filename, os.W_OK):
to_screen('ERROR: no write permissions on %s' % filename) to_screen('ERROR: no write permissions on %s' % filename)

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals from __future__ import unicode_literals
__version__ = '2020.01.24' __version__ = '2020.02.16'