mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-12-22 20:20:09 +09:00
Compare commits
15 Commits
2e47264235
...
13ec444a98
Author | SHA1 | Date | |
---|---|---|---|
|
13ec444a98 | ||
|
51579d87e4 | ||
|
e147619669 | ||
|
e7f93fbd85 | ||
|
58f7ada235 | ||
|
c67b33888f | ||
|
e8c0af04b7 | ||
|
5d769860c3 | ||
|
02b04785ee | ||
|
41c92b8d02 | ||
|
fe0c28f956 | ||
|
957c65b9ea | ||
|
5e95e18ce9 | ||
|
e91df0c550 | ||
|
c5636e9bca |
6
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
6
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
@ -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 2020.12.02. 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 Issues with outdated version will be REJECTED.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 2020.12.05. 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 Issues with outdated version will be REJECTED.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 **2020.12.02**
|
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
|
||||||
- [ ] 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 2020.12.02
|
[debug] youtube-dl version 2020.12.05
|
||||||
[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: {}
|
||||||
|
@ -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 2020.12.02. 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 2020.12.05. 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 **2020.12.02**
|
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
|
||||||
- [ ] 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
|
||||||
|
@ -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 2020.12.02. 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 2020.12.05. 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 **2020.12.02**
|
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
|
||||||
- [ ] 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
|
||||||
|
|
||||||
|
|
||||||
|
6
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
6
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
@ -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 2020.12.02. 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 2020.12.05. 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 **2020.12.02**
|
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
|
||||||
- [ ] 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 2020.12.02
|
[debug] youtube-dl version 2020.12.05
|
||||||
[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: {}
|
||||||
|
4
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
4
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
@ -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 2020.12.02. 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 2020.12.05. 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 **2020.12.02**
|
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
|
||||||
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
||||||
|
|
||||||
|
|
||||||
|
21
ChangeLog
21
ChangeLog
@ -1,3 +1,24 @@
|
|||||||
|
version 2020.12.05
|
||||||
|
|
||||||
|
Core
|
||||||
|
* [extractor/common] Improve Akamai HTTP format extraction
|
||||||
|
* Allow m3u8 manifest without an additional audio format
|
||||||
|
* Fix extraction for qualities starting with a number
|
||||||
|
|
||||||
|
Extractors
|
||||||
|
* [teachable:course] Improve extraction (#24507, #27286)
|
||||||
|
* [nrk] Improve error extraction
|
||||||
|
* [nrktv:series] Improve extraction (#21926)
|
||||||
|
* [nrktv:season] Improve extraction
|
||||||
|
* [nrk] Improve format extraction and geo-restriction detection (#24221)
|
||||||
|
* [pornhub] Handle HTTP errors gracefully (#26414)
|
||||||
|
* [nrktv] Relax URL regular expression (#27299, #26185)
|
||||||
|
+ [zdf] Extract webm formats (#26659)
|
||||||
|
+ [gamespot] Extract DASH and HTTP formats
|
||||||
|
+ [tver] Add support for tver.jp (#26662, #27284)
|
||||||
|
+ [pornhub] Add support for pornhub.org (#27276)
|
||||||
|
|
||||||
|
|
||||||
version 2020.12.02
|
version 2020.12.02
|
||||||
|
|
||||||
Extractors
|
Extractors
|
||||||
|
@ -308,6 +308,7 @@
|
|||||||
- **FrontendMasters**
|
- **FrontendMasters**
|
||||||
- **FrontendMastersCourse**
|
- **FrontendMastersCourse**
|
||||||
- **FrontendMastersLesson**
|
- **FrontendMastersLesson**
|
||||||
|
- **FujiTVFODPlus7**
|
||||||
- **Funimation**
|
- **Funimation**
|
||||||
- **Funk**
|
- **Funk**
|
||||||
- **Fusion**
|
- **Fusion**
|
||||||
@ -710,6 +711,7 @@
|
|||||||
- **qqmusic:singer**: QQ音乐 - 歌手
|
- **qqmusic:singer**: QQ音乐 - 歌手
|
||||||
- **qqmusic:toplist**: QQ音乐 - 排行榜
|
- **qqmusic:toplist**: QQ音乐 - 排行榜
|
||||||
- **QuantumTV**
|
- **QuantumTV**
|
||||||
|
- **Qub**
|
||||||
- **Quickline**
|
- **Quickline**
|
||||||
- **QuicklineLive**
|
- **QuicklineLive**
|
||||||
- **R7**
|
- **R7**
|
||||||
@ -952,6 +954,7 @@
|
|||||||
- **TVANouvellesArticle**
|
- **TVANouvellesArticle**
|
||||||
- **TVC**
|
- **TVC**
|
||||||
- **TVCArticle**
|
- **TVCArticle**
|
||||||
|
- **TVer**
|
||||||
- **tvigle**: Интернет-телевидение Tvigle.ru
|
- **tvigle**: Интернет-телевидение Tvigle.ru
|
||||||
- **tvland.com**
|
- **tvland.com**
|
||||||
- **TVN24**
|
- **TVN24**
|
||||||
|
@ -1,6 +1,7 @@
|
|||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import itertools
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
@ -17,6 +18,7 @@ from ..utils import (
|
|||||||
parse_age_limit,
|
parse_age_limit,
|
||||||
parse_duration,
|
parse_duration,
|
||||||
try_get,
|
try_get,
|
||||||
|
urljoin,
|
||||||
url_or_none,
|
url_or_none,
|
||||||
)
|
)
|
||||||
|
|
||||||
@ -24,6 +26,27 @@ from ..utils import (
|
|||||||
class NRKBaseIE(InfoExtractor):
|
class NRKBaseIE(InfoExtractor):
|
||||||
_GEO_COUNTRIES = ['NO']
|
_GEO_COUNTRIES = ['NO']
|
||||||
|
|
||||||
|
def _extract_nrk_formats(self, asset_url, video_id):
|
||||||
|
return self._extract_m3u8_formats(
|
||||||
|
re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url),
|
||||||
|
video_id, 'mp4', 'm3u8_native', fatal=False)
|
||||||
|
|
||||||
|
def _raise_error(self, data):
|
||||||
|
MESSAGES = {
|
||||||
|
'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
|
||||||
|
'ProgramRightsHasExpired': 'Programmet har gått ut',
|
||||||
|
'NoProgramRights': 'Ikke tilgjengelig',
|
||||||
|
'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
|
||||||
|
}
|
||||||
|
message_type = data.get('messageType', '')
|
||||||
|
# Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
|
||||||
|
if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is True:
|
||||||
|
self.raise_geo_restricted(
|
||||||
|
msg=MESSAGES.get('ProgramIsGeoBlocked'),
|
||||||
|
countries=self._GEO_COUNTRIES)
|
||||||
|
message = data.get('endUserMessage') or MESSAGES.get(message_type, message_type)
|
||||||
|
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
|
||||||
|
|
||||||
|
|
||||||
class NRKIE(NRKBaseIE):
|
class NRKIE(NRKBaseIE):
|
||||||
_VALID_URL = r'''(?x)
|
_VALID_URL = r'''(?x)
|
||||||
@ -82,6 +105,9 @@ class NRKIE(NRKBaseIE):
|
|||||||
'http://psapi.nrk.no/playback/manifest/%s' % video_id,
|
'http://psapi.nrk.no/playback/manifest/%s' % video_id,
|
||||||
video_id, 'Downloading manifest JSON')
|
video_id, 'Downloading manifest JSON')
|
||||||
|
|
||||||
|
if manifest.get('playability') == 'nonPlayable':
|
||||||
|
self._raise_error(manifest['nonPlayable'])
|
||||||
|
|
||||||
playable = manifest['playable']
|
playable = manifest['playable']
|
||||||
|
|
||||||
formats = []
|
formats = []
|
||||||
@ -94,9 +120,7 @@ class NRKIE(NRKBaseIE):
|
|||||||
if not format_url:
|
if not format_url:
|
||||||
continue
|
continue
|
||||||
if asset.get('format') == 'HLS' or determine_ext(format_url) == 'm3u8':
|
if asset.get('format') == 'HLS' or determine_ext(format_url) == 'm3u8':
|
||||||
formats.extend(self._extract_m3u8_formats(
|
formats.extend(self._extract_nrk_formats(format_url, video_id))
|
||||||
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
|
||||||
m3u8_id='hls', fatal=False))
|
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
data = self._download_json(
|
data = self._download_json(
|
||||||
@ -143,14 +167,7 @@ class NRKIE(NRKBaseIE):
|
|||||||
class NRKTVIE(NRKBaseIE):
|
class NRKTVIE(NRKBaseIE):
|
||||||
IE_DESC = 'NRK TV and NRK Radio'
|
IE_DESC = 'NRK TV and NRK Radio'
|
||||||
_EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
|
_EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
|
||||||
_VALID_URL = r'''(?x)
|
_VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*%s' % _EPISODE_RE
|
||||||
https?://
|
|
||||||
(?:tv|radio)\.nrk(?:super)?\.no/
|
|
||||||
(?:serie(?:/[^/]+){1,2}|program)/
|
|
||||||
(?![Ee]pisodes)%s
|
|
||||||
(?:/\d{2}-\d{2}-\d{4})?
|
|
||||||
(?:\#del=(?P<part_id>\d+))?
|
|
||||||
''' % _EPISODE_RE
|
|
||||||
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
|
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://tv.nrk.no/program/MDDP12000117',
|
'url': 'https://tv.nrk.no/program/MDDP12000117',
|
||||||
@ -275,6 +292,9 @@ class NRKTVIE(NRKBaseIE):
|
|||||||
}, {
|
}, {
|
||||||
'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
|
'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201507/NPUB21019315',
|
||||||
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
_api_host = None
|
_api_host = None
|
||||||
@ -295,6 +315,7 @@ class NRKTVIE(NRKBaseIE):
|
|||||||
title = data.get('fullTitle') or data.get('mainTitle') or data['title']
|
title = data.get('fullTitle') or data.get('mainTitle') or data['title']
|
||||||
video_id = data.get('id') or video_id
|
video_id = data.get('id') or video_id
|
||||||
|
|
||||||
|
urls = []
|
||||||
entries = []
|
entries = []
|
||||||
|
|
||||||
conviva = data.get('convivaStatistics') or {}
|
conviva = data.get('convivaStatistics') or {}
|
||||||
@ -311,19 +332,13 @@ class NRKTVIE(NRKBaseIE):
|
|||||||
else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
|
else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
|
||||||
for num, asset in enumerate(media_assets, 1):
|
for num, asset in enumerate(media_assets, 1):
|
||||||
asset_url = asset.get('url')
|
asset_url = asset.get('url')
|
||||||
if not asset_url:
|
if not asset_url or asset_url in urls:
|
||||||
continue
|
continue
|
||||||
formats = self._extract_akamai_formats(asset_url, video_id)
|
formats = self._extract_nrk_formats(asset_url, video_id)
|
||||||
if not formats:
|
if not formats:
|
||||||
continue
|
continue
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
# Some f4m streams may not work with hdcore in fragments' URLs
|
|
||||||
for f in formats:
|
|
||||||
extra_param = f.get('extra_param_to_segment_url')
|
|
||||||
if extra_param and 'hdcore' in extra_param:
|
|
||||||
del f['extra_param_to_segment_url']
|
|
||||||
|
|
||||||
entry_id, entry_title = video_id_and_title(num)
|
entry_id, entry_title = video_id_and_title(num)
|
||||||
duration = parse_duration(asset.get('duration'))
|
duration = parse_duration(asset.get('duration'))
|
||||||
subtitles = {}
|
subtitles = {}
|
||||||
@ -343,34 +358,20 @@ class NRKTVIE(NRKBaseIE):
|
|||||||
|
|
||||||
if not entries:
|
if not entries:
|
||||||
media_url = data.get('mediaUrl')
|
media_url = data.get('mediaUrl')
|
||||||
if media_url:
|
if media_url and media_url not in urls:
|
||||||
formats = self._extract_akamai_formats(media_url, video_id)
|
formats = self._extract_nrk_formats(media_url, video_id)
|
||||||
self._sort_formats(formats)
|
if formats:
|
||||||
duration = parse_duration(data.get('duration'))
|
self._sort_formats(formats)
|
||||||
entries = [{
|
duration = parse_duration(data.get('duration'))
|
||||||
'id': video_id,
|
entries = [{
|
||||||
'title': make_title(title),
|
'id': video_id,
|
||||||
'duration': duration,
|
'title': make_title(title),
|
||||||
'formats': formats,
|
'duration': duration,
|
||||||
}]
|
'formats': formats,
|
||||||
|
}]
|
||||||
|
|
||||||
if not entries:
|
if not entries:
|
||||||
MESSAGES = {
|
self._raise_error(data)
|
||||||
'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
|
|
||||||
'ProgramRightsHasExpired': 'Programmet har gått ut',
|
|
||||||
'NoProgramRights': 'Ikke tilgjengelig',
|
|
||||||
'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
|
|
||||||
}
|
|
||||||
message_type = data.get('messageType', '')
|
|
||||||
# Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
|
|
||||||
if 'IsGeoBlocked' in message_type:
|
|
||||||
self.raise_geo_restricted(
|
|
||||||
msg=MESSAGES.get('ProgramIsGeoBlocked'),
|
|
||||||
countries=self._GEO_COUNTRIES)
|
|
||||||
raise ExtractorError(
|
|
||||||
'%s said: %s' % (self.IE_NAME, MESSAGES.get(
|
|
||||||
message_type, message_type)),
|
|
||||||
expected=True)
|
|
||||||
|
|
||||||
series = conviva.get('seriesName') or data.get('seriesTitle')
|
series = conviva.get('seriesName') or data.get('seriesTitle')
|
||||||
episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
|
episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
|
||||||
@ -517,7 +518,8 @@ class NRKTVSerieBaseIE(InfoExtractor):
|
|||||||
config = self._parse_json(
|
config = self._parse_json(
|
||||||
self._search_regex(
|
self._search_regex(
|
||||||
(r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
|
(r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
|
||||||
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
|
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>',
|
||||||
|
r'PRELOADED_STATE_*\s*=\s*({.+?})\s*\n'),
|
||||||
webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
|
webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
|
||||||
display_id, fatal=False, transform_source=js_to_json)
|
display_id, fatal=False, transform_source=js_to_json)
|
||||||
if not config:
|
if not config:
|
||||||
@ -527,12 +529,26 @@ class NRKTVSerieBaseIE(InfoExtractor):
|
|||||||
(lambda x: x['initialState']['series'], lambda x: x['series']),
|
(lambda x: x['initialState']['series'], lambda x: x['series']),
|
||||||
dict)
|
dict)
|
||||||
|
|
||||||
def _extract_seasons(self, seasons):
|
def _extract_seasons(self, domain, series_id, seasons):
|
||||||
|
if isinstance(seasons, dict):
|
||||||
|
seasons = seasons.get('seasons')
|
||||||
if not isinstance(seasons, list):
|
if not isinstance(seasons, list):
|
||||||
return []
|
return []
|
||||||
entries = []
|
entries = []
|
||||||
for season in seasons:
|
for season in seasons:
|
||||||
entries.extend(self._extract_episodes(season))
|
if not isinstance(season, dict):
|
||||||
|
continue
|
||||||
|
episodes = self._extract_episodes(season)
|
||||||
|
if episodes:
|
||||||
|
entries.extend(episodes)
|
||||||
|
continue
|
||||||
|
season_name = season.get('name')
|
||||||
|
if season_name and isinstance(season_name, compat_str):
|
||||||
|
entries.append(self.url_result(
|
||||||
|
'https://%s.nrk.no/serie/%s/sesong/%s'
|
||||||
|
% (domain, series_id, season_name),
|
||||||
|
ie=NRKTVSeasonIE.ie_key(),
|
||||||
|
video_title=season.get('title')))
|
||||||
return entries
|
return entries
|
||||||
|
|
||||||
def _extract_episodes(self, season):
|
def _extract_episodes(self, season):
|
||||||
@ -545,24 +561,94 @@ class NRKTVSerieBaseIE(InfoExtractor):
|
|||||||
return []
|
return []
|
||||||
entries = []
|
entries = []
|
||||||
for episode in entry_list:
|
for episode in entry_list:
|
||||||
nrk_id = episode.get('prfId')
|
nrk_id = episode.get('prfId') or episode.get('episodeId')
|
||||||
if not nrk_id or not isinstance(nrk_id, compat_str):
|
if not nrk_id or not isinstance(nrk_id, compat_str):
|
||||||
continue
|
continue
|
||||||
|
if not re.match(NRKTVIE._EPISODE_RE, nrk_id):
|
||||||
|
continue
|
||||||
entries.append(self.url_result(
|
entries.append(self.url_result(
|
||||||
'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id))
|
'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id))
|
||||||
return entries
|
return entries
|
||||||
|
|
||||||
|
_ASSETS_KEYS = ('episodes', 'instalments',)
|
||||||
|
|
||||||
|
def _extract_assets_key(self, embedded):
|
||||||
|
for asset_key in self._ASSETS_KEYS:
|
||||||
|
if embedded.get(asset_key):
|
||||||
|
return asset_key
|
||||||
|
|
||||||
|
def _entries(self, data, display_id):
|
||||||
|
for page_num in itertools.count(1):
|
||||||
|
embedded = data.get('_embedded')
|
||||||
|
if not isinstance(embedded, dict):
|
||||||
|
break
|
||||||
|
assets_key = self._extract_assets_key(embedded)
|
||||||
|
if not assets_key:
|
||||||
|
break
|
||||||
|
# Extract entries
|
||||||
|
entries = try_get(
|
||||||
|
embedded,
|
||||||
|
(lambda x: x[assets_key]['_embedded'][assets_key],
|
||||||
|
lambda x: x[assets_key]),
|
||||||
|
list)
|
||||||
|
for e in self._extract_entries(entries):
|
||||||
|
yield e
|
||||||
|
# Find next URL
|
||||||
|
next_url = urljoin(
|
||||||
|
'https://psapi.nrk.no/',
|
||||||
|
try_get(
|
||||||
|
data,
|
||||||
|
(lambda x: x['_links']['next']['href'],
|
||||||
|
lambda x: x['_embedded'][assets_key]['_links']['next']['href']),
|
||||||
|
compat_str))
|
||||||
|
if not next_url:
|
||||||
|
break
|
||||||
|
data = self._download_json(
|
||||||
|
next_url, display_id,
|
||||||
|
'Downloading %s JSON page %d' % (assets_key, page_num),
|
||||||
|
fatal=False)
|
||||||
|
if not data:
|
||||||
|
break
|
||||||
|
|
||||||
|
|
||||||
class NRKTVSeasonIE(NRKTVSerieBaseIE):
|
class NRKTVSeasonIE(NRKTVSerieBaseIE):
|
||||||
_VALID_URL = r'https?://tv\.nrk\.no/serie/[^/]+/sesong/(?P<id>\d+)'
|
_VALID_URL = r'https?://(?P<domain>tv|radio)\.nrk\.no/serie/(?P<serie>[^/]+)/(?:sesong/)?(?P<id>\d+)'
|
||||||
_TEST = {
|
_TESTS = [{
|
||||||
'url': 'https://tv.nrk.no/serie/backstage/sesong/1',
|
'url': 'https://tv.nrk.no/serie/backstage/sesong/1',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '1',
|
'id': 'backstage/1',
|
||||||
'title': 'Sesong 1',
|
'title': 'Sesong 1',
|
||||||
},
|
},
|
||||||
'playlist_mincount': 30,
|
'playlist_mincount': 30,
|
||||||
}
|
}, {
|
||||||
|
# no /sesong/ in path
|
||||||
|
'url': 'https://tv.nrk.no/serie/lindmo/2016',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'lindmo/2016',
|
||||||
|
'title': '2016',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 29,
|
||||||
|
}, {
|
||||||
|
# weird nested _embedded in catalog JSON response
|
||||||
|
'url': 'https://radio.nrk.no/serie/dickie-dick-dickens/sesong/1',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'dickie-dick-dickens/1',
|
||||||
|
'title': 'Sesong 1',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 11,
|
||||||
|
}, {
|
||||||
|
# 841 entries, multi page
|
||||||
|
'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201509',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'dagsnytt/201509',
|
||||||
|
'title': 'September 2015',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 841,
|
||||||
|
}, {
|
||||||
|
# 180 entries, single page
|
||||||
|
'url': 'https://tv.nrk.no/serie/spangas/sesong/1',
|
||||||
|
'only_matching': True,
|
||||||
|
}]
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
def suitable(cls, url):
|
def suitable(cls, url):
|
||||||
@ -570,42 +656,26 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
|
|||||||
else super(NRKTVSeasonIE, cls).suitable(url))
|
else super(NRKTVSeasonIE, cls).suitable(url))
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
display_id = self._match_id(url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
domain = mobj.group('domain')
|
||||||
|
serie = mobj.group('serie')
|
||||||
|
season_id = mobj.group('id')
|
||||||
|
display_id = '%s/%s' % (serie, season_id)
|
||||||
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
data = self._download_json(
|
||||||
|
'https://psapi.nrk.no/%s/catalog/series/%s/seasons/%s'
|
||||||
|
% (domain, serie, season_id), display_id, query={'pageSize': 50})
|
||||||
|
|
||||||
series = self._extract_series(webpage, display_id)
|
title = try_get(data, lambda x: x['titles']['title'], compat_str) or display_id
|
||||||
|
|
||||||
season = next(
|
|
||||||
s for s in series['seasons']
|
|
||||||
if int(display_id) == s.get('seasonNumber'))
|
|
||||||
|
|
||||||
title = try_get(season, lambda x: x['titles']['title'], compat_str)
|
|
||||||
return self.playlist_result(
|
return self.playlist_result(
|
||||||
self._extract_episodes(season), display_id, title)
|
self._entries(data, display_id),
|
||||||
|
display_id, title)
|
||||||
|
|
||||||
|
|
||||||
class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
||||||
_VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
|
_VALID_URL = r'https?://(?P<domain>tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
|
||||||
_ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
|
_ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://tv.nrk.no/serie/blank',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'blank',
|
|
||||||
'title': 'Blank',
|
|
||||||
'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
|
|
||||||
},
|
|
||||||
'playlist_mincount': 30,
|
|
||||||
}, {
|
|
||||||
# new layout, seasons
|
|
||||||
'url': 'https://tv.nrk.no/serie/backstage',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'backstage',
|
|
||||||
'title': 'Backstage',
|
|
||||||
'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3',
|
|
||||||
},
|
|
||||||
'playlist_mincount': 60,
|
|
||||||
}, {
|
|
||||||
# new layout, instalments
|
# new layout, instalments
|
||||||
'url': 'https://tv.nrk.no/serie/groenn-glede',
|
'url': 'https://tv.nrk.no/serie/groenn-glede',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
@ -613,7 +683,30 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
|||||||
'title': 'Grønn glede',
|
'title': 'Grønn glede',
|
||||||
'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
|
'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
|
||||||
},
|
},
|
||||||
'playlist_mincount': 10,
|
'playlist_mincount': 90,
|
||||||
|
}, {
|
||||||
|
# new layout, instalments, more entries
|
||||||
|
'url': 'https://tv.nrk.no/serie/lindmo',
|
||||||
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://tv.nrk.no/serie/blank',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'blank',
|
||||||
|
'title': 'Blank',
|
||||||
|
'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 30,
|
||||||
|
'expected_warnings': ['HTTP Error 404: Not Found'],
|
||||||
|
}, {
|
||||||
|
# new layout, seasons
|
||||||
|
'url': 'https://tv.nrk.no/serie/backstage',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'backstage',
|
||||||
|
'title': 'Backstage',
|
||||||
|
'description': 'md5:63692ceb96813d9a207e9910483d948b',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 60,
|
||||||
|
'expected_warnings': ['HTTP Error 404: Not Found'],
|
||||||
}, {
|
}, {
|
||||||
# old layout
|
# old layout
|
||||||
'url': 'https://tv.nrksuper.no/serie/labyrint',
|
'url': 'https://tv.nrksuper.no/serie/labyrint',
|
||||||
@ -632,6 +725,13 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
|||||||
}, {
|
}, {
|
||||||
'url': 'https://tv.nrk.no/serie/postmann-pat',
|
'url': 'https://tv.nrk.no/serie/postmann-pat',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://radio.nrk.no/serie/dickie-dick-dickens',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'dickie-dick-dickens',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 8,
|
||||||
|
'expected_warnings': ['HTTP Error 404: Not Found'],
|
||||||
}]
|
}]
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
@ -642,18 +742,32 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
|||||||
else super(NRKTVSeriesIE, cls).suitable(url))
|
else super(NRKTVSeriesIE, cls).suitable(url))
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
series_id = self._match_id(url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
domain = mobj.group('domain')
|
||||||
|
series_id = mobj.group('id')
|
||||||
|
|
||||||
|
title = description = None
|
||||||
|
|
||||||
webpage = self._download_webpage(url, series_id)
|
webpage = self._download_webpage(url, series_id)
|
||||||
|
|
||||||
# New layout (e.g. https://tv.nrk.no/serie/backstage)
|
|
||||||
series = self._extract_series(webpage, series_id, fatal=False)
|
series = self._extract_series(webpage, series_id, fatal=False)
|
||||||
if series:
|
if series:
|
||||||
title = try_get(series, lambda x: x['titles']['title'], compat_str)
|
title = try_get(series, lambda x: x['titles']['title'], compat_str)
|
||||||
description = try_get(
|
description = try_get(
|
||||||
series, lambda x: x['titles']['subtitle'], compat_str)
|
series, lambda x: x['titles']['subtitle'], compat_str)
|
||||||
|
|
||||||
|
data = self._download_json(
|
||||||
|
'https://psapi.nrk.no/%s/catalog/series/%s/instalments'
|
||||||
|
% (domain, series_id), series_id, query={'pageSize': 50},
|
||||||
|
fatal=False)
|
||||||
|
if data:
|
||||||
|
return self.playlist_result(
|
||||||
|
self._entries(data, series_id), series_id, title, description)
|
||||||
|
|
||||||
|
# New layout (e.g. https://tv.nrk.no/serie/backstage)
|
||||||
|
if series:
|
||||||
entries = []
|
entries = []
|
||||||
entries.extend(self._extract_seasons(series.get('seasons')))
|
entries.extend(self._extract_seasons(domain, series_id, series.get('seasons')))
|
||||||
entries.extend(self._extract_entries(series.get('instalments')))
|
entries.extend(self._extract_entries(series.get('instalments')))
|
||||||
entries.extend(self._extract_episodes(series.get('extraMaterial')))
|
entries.extend(self._extract_episodes(series.get('extraMaterial')))
|
||||||
return self.playlist_result(entries, series_id, title, description)
|
return self.playlist_result(entries, series_id, title, description)
|
||||||
|
@ -541,6 +541,10 @@ class PeerTubeIE(InfoExtractor):
|
|||||||
'format_id': format_id,
|
'format_id': format_id,
|
||||||
'filesize': file_size,
|
'filesize': file_size,
|
||||||
})
|
})
|
||||||
|
if format_id == '0p':
|
||||||
|
f['vcodec'] = 'none'
|
||||||
|
else:
|
||||||
|
f['fps'] = int_or_none(file_.get('fps'))
|
||||||
formats.append(f)
|
formats.append(f)
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
@ -31,7 +31,12 @@ class PornHubBaseIE(InfoExtractor):
|
|||||||
def dl(*args, **kwargs):
|
def dl(*args, **kwargs):
|
||||||
return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
|
return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
|
||||||
|
|
||||||
webpage, urlh = dl(*args, **kwargs)
|
ret = dl(*args, **kwargs)
|
||||||
|
|
||||||
|
if not ret:
|
||||||
|
return ret
|
||||||
|
|
||||||
|
webpage, urlh = ret
|
||||||
|
|
||||||
if any(re.search(p, webpage) for p in (
|
if any(re.search(p, webpage) for p in (
|
||||||
r'<body\b[^>]+\bonload=["\']go\(\)',
|
r'<body\b[^>]+\bonload=["\']go\(\)',
|
||||||
|
@ -269,7 +269,7 @@ class TeachableCourseIE(TeachableBaseIE):
|
|||||||
r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
|
r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
|
||||||
webpage):
|
webpage):
|
||||||
li = mobj.group('li')
|
li = mobj.group('li')
|
||||||
if 'fa-youtube-play' not in li:
|
if 'fa-youtube-play' not in li and not re.search(r'\d{1,2}:\d{2}', li):
|
||||||
continue
|
continue
|
||||||
lecture_url = self._search_regex(
|
lecture_url = self._search_regex(
|
||||||
r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
|
r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
|
||||||
|
@ -1,3 +1,3 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
__version__ = '2020.12.02'
|
__version__ = '2020.12.05'
|
||||||
|
Loading…
Reference in New Issue
Block a user