Compare commits

...

20 Commits

Author SHA1 Message Date
epsilonSpider
da9a74d54a
Merge f7ca7e77be69b7028d68b92332d6de499d528601 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6 2025-04-01 08:20:48 +02:00
dirkf
3eb8d22ddb
[JSInterp] Temporary fix for #33102 2025-03-31 04:21:09 +01:00
dirkf
4e714f9df1 [Misc] Correct [_]IE_DESC/NAME in a few IEs
* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`
2025-03-26 12:47:19 +00:00
dirkf
c1ea7f5a24 [ITV] Mark ITVX not working
* update old shim
* correct [_]IE_DESC
2025-03-26 12:17:49 +00:00
Epsilon Spider
f7ca7e77be [safari] Refactor login check 2023-04-04 16:29:00 -04:00
dirkf
899af2ef61
Merge branch 'master' into oreilly-login 2023-03-31 15:50:47 +01:00
Epsilon Spider
d524ac1898 Check for oreilly login with new url
Resolves #30884
2023-02-11 14:42:25 -05:00
fonkap
70a4a8b752
[StreamsbIE] Add extractor for streamsb.com (viewsb.com) (#31517)
* Add extractor for streamsb.com (viewsb.com)

* make data url using app.js version

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-11 02:54:45 +00:00
fonkap
99c3cf6419
[KommunetvIE] Add extractor for kommunetv.no (#31516)
* Add extractor for kommunetv.no
* Using utils.update_url instead of regex

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-11 02:47:43 +00:00
fonkap
cf5fb7e139
[FileMoonIE] Add extractor for filemoon.sx (#31515)
---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-11 02:37:45 +00:00
teddy171
9256b026d0
[feat]: Add support to external downloader aria2p (#31500)
* feat: add class Aria2pFD

* feat: create call_downloader function

* feat: a colorful download interface to aria2pFD

* feat: change value name

* Apply suggestions from code review

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Typo in suggestion

* fix: remove unused value

* fix: add not function to return value(0 is normal); add total_seconds to download.eta(timedelta object); add waiting status when hook progress

* fix: remove unuse method ..utils.format_bytes

* fix: be up to flake8

* fix: be up to flake8

* Apply suggestions from code review

* [feat] test external downloader aria2p

* [feat] test external downloader aria2p

* [fix] test_external_downloader.py

* Apply suggestions from code review

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Apply suggestions from code review

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Update test/test_external_downloader.py

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Update test/test_external_downloader.py

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Update youtube_dl/downloader/external.py

Co-authored-by: dirkf <fieldhouse@gmx.net>

* refactoring code and fix bugs

* Apply suggestions from code review

* Rename test_external_downloader.py to test_downloader_external.py

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-09 20:19:27 +00:00
Valentin Metz
80c0228777
[rbgtum] Add new extractor (#31305)
* [rbgtum] Add new extractor

* Small update, force CI

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-09 11:25:28 +00:00
dirkf
bcf597ea17 [YouTube] Fix tests 2023-02-09 11:01:57 +00:00
dirkf
f640916de1 [YouTube] Refresh compat/utils usage
* import parse_qs()
* import parse_qs in lazy_extractors (clears old TODO)
* clean up old compiled lazy_extractors for Py2
* use update_url()
2023-02-09 11:01:57 +00:00
dirkf
b337af9c62 [compat] Update test_compat
[skip ci]
2023-02-09 11:01:57 +00:00
dirkf
a6f7d10d44 [utils] Add parse_qs, update_url
[skip ci]
2023-02-09 11:01:57 +00:00
dirkf
9ca224b697 [compat] Systematise compat_ naming
[skip ci]
2023-02-09 11:01:57 +00:00
dirkf
ce81ae3846 [test] Fix TestAgeRestriction
* age restriction may cause DownloadError
* update obsolete test URLs
[skip ci]
2023-02-09 11:01:57 +00:00
dirkf
2be0cd2616 [YouTube] Add signatureTimestamp for age-gate bypass 2023-02-09 11:01:57 +00:00
dirkf
b14b33a2e9 [YouTube] Bypass age-gating for certain restricted videos
* Use TVHTML5_SIMPLY_EMBEDDED_PLAYER client

* Also add and fix tests

* Introduce and use new utility function `update_url()`
2023-02-09 11:01:57 +00:00
7 changed files with 17 additions and 16 deletions

View File

@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
class BokeCCIE(BokeCCBaseIE): class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频' IE_DESC = 'CC视频'
_VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)' _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{ _TESTS = [{

View File

@ -9,7 +9,7 @@ from ..utils import (
class CloudyIE(InfoExtractor): class CloudyIE(InfoExtractor):
_IE_DESC = 'cloudy.ec' IE_DESC = 'cloudy.ec'
_VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)' _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.cloudy.ec/v/af511e2527aac', 'url': 'https://www.cloudy.ec/v/af511e2527aac',

View File

@ -422,6 +422,8 @@ class InfoExtractor(object):
_GEO_COUNTRIES = None _GEO_COUNTRIES = None
_GEO_IP_BLOCKS = None _GEO_IP_BLOCKS = None
_WORKING = True _WORKING = True
# supply this in public subclasses: used in supported sites list, etc
# IE_DESC = 'short description of IE'
def __init__(self, downloader=None): def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader.""" """Constructor. Receives an optional downloader."""

View File

@ -35,15 +35,6 @@ from ..utils import (
class ITVBaseIE(InfoExtractor): class ITVBaseIE(InfoExtractor):
def _search_nextjs_data(self, webpage, video_id, **kw):
transform_source = kw.pop('transform_source', None)
fatal = kw.pop('fatal', True)
return self._parse_json(
self._search_regex(
r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
webpage, 'next.js data', group='js', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True): def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
if errnote is False: if errnote is False:
return False return False
@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
class ITVIE(ITVBaseIE): class ITVIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)' _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
_IE_DESC = 'ITVX' IE_DESC = 'ITVX'
_WORKING = False
_TESTS = [{ _TESTS = [{
'note': 'Hub URLs redirect to ITVX', 'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012', 'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
'ext': determine_ext(href, 'vtt'), 'ext': determine_ext(href, 'vtt'),
}) })
next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}') next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {}) video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle') title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title) info = self._og_extract(webpage, require_title=not title)
@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
class ITVBTCCIE(ITVBaseIE): class ITVBTCCIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
_IE_DESC = 'ITV articles: News, British Touring Car Championship' IE_DESC = 'ITV articles: News, British Touring Car Championship'
_TESTS = [{ _TESTS = [{
'note': 'British Touring Car Championship', 'note': 'British Touring Car Championship',
'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch', 'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

View File

@ -38,7 +38,11 @@ class SafariBaseIE(InfoExtractor):
'Downloading login page') 'Downloading login page')
def is_logged(urlh): def is_logged(urlh):
return 'learning.oreilly.com/home/' in urlh.geturl() url = urlh.geturl()
parsed_url = compat_urlparse.urlparse(url)
return parsed_url.hostname.endswith('learning.oreilly.com') and (
parsed_url.path.startswith('/home/')
or (parsed_url.path == '/member/login/' and not parsed_url.query))
if is_logged(urlh): if is_logged(urlh):
self.LOGGED_IN = True self.LOGGED_IN = True

View File

@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
['vetaff', '76462', 'http://vetaff-f.akamaihd.net'], ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
['arch', '', 'http://ussenate-f.akamaihd.net/'] ['arch', '', 'http://ussenate-f.akamaihd.net/']
] ]
_IE_NAME = 'senate.gov' IE_NAME = 'senate.gov'
_VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)' _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png', 'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

View File

@ -686,6 +686,8 @@ class JSInterpreter(object):
raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e) raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
def _dump(self, obj, namespace): def _dump(self, obj, namespace):
if obj is JS_Undefined:
return 'undefined'
try: try:
return json.dumps(obj) return json.dumps(obj)
except TypeError: except TypeError: