Compare commits

...

10 Commits

Author SHA1 Message Date
Glenn Slayden
c6d1fac82d
Merge 112e8e497068205af8fbc1698f61bc3b9dc52e96 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6 2025-04-01 10:04:24 +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
Glenn Slayden
112e8e4970
Early extraction of duration metadata via playlist thumbnail overlay
Early gathering of item video durations from playlist metadata, prior to downloading individual item metadata pages, so that video duration values are (e.g.) shown in `--flat-playlist` or `--simulate`, and/or can be used as a download filtering criterion.
2021-07-06 15:11:46 -07:00
Glenn Slayden
3da4918c8b
lint indentation compliance 2021-07-06 14:51:18 -07:00
Glenn Slayden
d8aa72b006
I'll get this right sooner or later... 2021-07-06 14:37:21 -07:00
Glenn Slayden
6c43aeea5c
...or is this what the linter wants? 2021-07-06 14:19:52 -07:00
Glenn Slayden
a80c44ea8e
Adjust hanging alignment, if you prefer? 2021-07-06 14:10:41 -07:00
Glenn Slayden
6a09bcde7c
Early extraction of duration metadata via playlist thumbnail overlay
Early gathering of item video durations from playlist metadata, prior to downloading individual item metadata pages, so that video duration values are (e.g.) shown in `--flat-playlist` or `--simulate`, and/or can be used as a download filtering criterion.
2021-07-06 14:02:30 -07:00
7 changed files with 18 additions and 17 deletions

View File

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

View File

@ -9,7 +9,7 @@ from ..utils import (
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]+)'
_TESTS = [{
'url': 'https://www.cloudy.ec/v/af511e2527aac',

View File

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

View File

@ -35,15 +35,6 @@ from ..utils import (
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):
if errnote is False:
return False
@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
class ITVIE(ITVBaseIE):
_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 = [{
'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
'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 {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title)
@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
class ITVBTCCIE(ITVBaseIE):
_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 = [{
'note': 'British Touring Car Championship',
'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

View File

@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
['vetaff', '76462', 'http://vetaff-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>.+)'
_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',

View File

@ -440,8 +440,12 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
description = try_get(
renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
compat_str)
duration = parse_duration(try_get(
renderer, lambda x: x['lengthText']['simpleText'], compat_str))
duration_text = try_get(
renderer,
(lambda x: x['lengthText']['simpleText'],
lambda x: x['thumbnailOverlays'][0]['thumbnailOverlayTimeStatusRenderer']['text']['simpleText']),
compat_str)
duration = parse_duration(duration_text)
view_count_text = try_get(
renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
view_count = str_to_int(self._search_regex(

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)
def _dump(self, obj, namespace):
if obj is JS_Undefined:
return 'undefined'
try:
return json.dumps(obj)
except TypeError: