Compare commits

..

1 Commits

Author SHA1 Message Date
HobbyistDev
4abd1fe3db
Merge 172bfb74b0 into a9f85670d0 2024-11-12 21:56:28 +08:00
11 changed files with 30 additions and 239 deletions

View File

@ -481,7 +481,7 @@ class TestTraversalHelpers:
'id': 'name',
'data': 'content',
'url': 'url',
}, all, {subs_list_to_dict(lang=None)}]) == {
}, all, {subs_list_to_dict}]) == {
'de': [{'url': 'https://example.com/subs/de.ass'}],
'en': [{'data': 'content'}],
}, 'subs with mandatory items missing should be filtered'
@ -507,54 +507,6 @@ class TestTraversalHelpers:
{'url': 'https://example.com/subs/en1', 'ext': 'ext'},
{'url': 'https://example.com/subs/en2', 'ext': 'ext'},
]}, '`quality` key should sort subtitle list accordingly'
assert traverse_obj([
{'name': 'de', 'url': 'https://example.com/subs/de.ass'},
{'name': 'de'},
{'name': 'en', 'content': 'content'},
{'url': 'https://example.com/subs/en'},
], [..., {
'id': 'name',
'url': 'url',
'data': 'content',
}, all, {subs_list_to_dict(lang='en')}]) == {
'de': [{'url': 'https://example.com/subs/de.ass'}],
'en': [
{'data': 'content'},
{'url': 'https://example.com/subs/en'},
],
}, 'optionally provided lang should be used if no id available'
assert traverse_obj([
{'name': 1, 'url': 'https://example.com/subs/de1'},
{'name': {}, 'url': 'https://example.com/subs/de2'},
{'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
{'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
], [..., {
'id': 'name',
'url': 'url',
'ext': 'ext',
}, all, {subs_list_to_dict(lang=None)}]) == {
'de': [
{'url': 'https://example.com/subs/de3'},
{'url': 'https://example.com/subs/de4'},
],
}, 'non str types should be ignored for id and ext'
assert traverse_obj([
{'name': 1, 'url': 'https://example.com/subs/de1'},
{'name': {}, 'url': 'https://example.com/subs/de2'},
{'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
{'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
], [..., {
'id': 'name',
'url': 'url',
'ext': 'ext',
}, all, {subs_list_to_dict(lang='de')}]) == {
'de': [
{'url': 'https://example.com/subs/de1'},
{'url': 'https://example.com/subs/de2'},
{'url': 'https://example.com/subs/de3'},
{'url': 'https://example.com/subs/de4'},
],
}, 'non str types should be replaced by default id'
def test_trim_str(self):
with pytest.raises(TypeError):
@ -573,7 +525,7 @@ class TestTraversalHelpers:
def test_unpack(self):
assert unpack(lambda *x: ''.join(map(str, x)))([1, 2, 3]) == '123'
assert unpack(join_nonempty)([1, 2, 3]) == '1-2-3'
assert unpack(join_nonempty, delim=' ')([1, 2, 3]) == '1 2 3'
assert unpack(join_nonempty(delim=' '))([1, 2, 3]) == '1 2 3'
with pytest.raises(TypeError):
unpack(join_nonempty)()
with pytest.raises(TypeError):

View File

@ -72,6 +72,7 @@ from yt_dlp.utils import (
intlist_to_bytes,
iri_to_uri,
is_html,
join_nonempty,
js_to_json,
limit_length,
locked_file,
@ -2157,6 +2158,10 @@ Line 1
assert int_or_none(v=10) == 10, 'keyword passed positional should call function'
assert int_or_none(scale=0.1)(10) == 100, 'call after partial application should call the function'
assert callable(join_nonempty(delim=', ')), 'varargs positional should apply partially'
assert callable(join_nonempty()), 'varargs positional should apply partially'
assert join_nonempty(None, delim=', ') == '', 'passed varargs should call the function'
if __name__ == '__main__':
unittest.main()

View File

@ -4381,9 +4381,7 @@ class YoutubeDL:
return None
for idx, t in list(enumerate(thumbnails))[::-1]:
thumb_ext = t.get('ext') or determine_ext(t['url'], 'jpg')
if multiple:
thumb_ext = f'{t["id"]}.{thumb_ext}'
thumb_ext = (f'{t["id"]}.' if multiple else '') + determine_ext(t['url'], 'jpg')
thumb_display_id = f'{label} thumbnail {t["id"]}'
thumb_filename = replace_extension(filename, thumb_ext, info_dict.get('ext'))
thumb_filename_final = replace_extension(thumb_filename_base, thumb_ext, info_dict.get('ext'))

View File

@ -1650,7 +1650,6 @@ from .radiokapital import (
RadioKapitalIE,
RadioKapitalShowIE,
)
from .radioradicale import RadioRadicaleIE
from .radiozet import RadioZetPodcastIE
from .radlive import (
RadLiveChannelIE,

View File

@ -66,14 +66,6 @@ class AfreecaTVBaseIE(InfoExtractor):
extensions={'legacy_ssl': True}), display_id,
'Downloading API JSON', 'Unable to download API JSON')
@staticmethod
def _fixup_thumb(thumb_url):
if not url_or_none(thumb_url):
return None
# Core would determine_ext as 'php' from the url, so we need to provide the real ext
# See: https://github.com/yt-dlp/yt-dlp/issues/11537
return [{'url': thumb_url, 'ext': 'jpg'}]
class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'soop'
@ -163,7 +155,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'uploader': ('writer_nick', {str}),
'uploader_id': ('bj_id', {str}),
'duration': ('total_file_duration', {int_or_none(scale=1000)}),
'thumbnails': ('thumb', {self._fixup_thumb}),
'thumbnail': ('thumb', {url_or_none}),
})
entries = []
@ -234,7 +226,8 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
return self.playlist_result(self._entries(data), video_id)
def _entries(self, data):
@staticmethod
def _entries(data):
# 'files' is always a list with 1 element
yield from traverse_obj(data, (
'data', lambda _, v: v['story_type'] == 'catch',
@ -245,7 +238,7 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
'title': ('title', {str}),
'uploader': ('writer_nick', {str}),
'uploader_id': ('writer_id', {str}),
'thumbnails': ('thumb', {self._fixup_thumb}),
'thumbnail': ('thumb', {url_or_none}),
'timestamp': ('write_timestamp', {int_or_none}),
}))

View File

@ -205,26 +205,6 @@ class ArchiveOrgIE(InfoExtractor):
},
},
],
}, {
# The reviewbody is None for one of the reviews; just need to extract data without crashing
'url': 'https://archive.org/details/gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn',
'info_dict': {
'id': 'gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn',
'ext': 'mp3',
'title': 'Stuck Inside of Mobile with the Memphis Blues Again',
'creators': ['Grateful Dead'],
'duration': 338.31,
'track': 'Stuck Inside of Mobile with the Memphis Blues Again',
'description': 'md5:764348a470b986f1217ffd38d6ac7b72',
'display_id': 'gd95-04-02d1t04.shn',
'location': 'Pyramid Arena',
'uploader': 'jon@archive.org',
'album': '1995-04-02 - Pyramid Arena',
'upload_date': '20040519',
'track_number': 4,
'release_date': '19950402',
'timestamp': 1084927901,
},
}]
@staticmethod
@ -355,7 +335,7 @@ class ArchiveOrgIE(InfoExtractor):
info['comments'].append({
'id': review.get('review_id'),
'author': review.get('reviewer'),
'text': join_nonempty('reviewtitle', 'reviewbody', from_dict=review, delim='\n\n'),
'text': str_or_none(review.get('reviewtitle'), '') + '\n\n' + review.get('reviewbody'),
'timestamp': unified_timestamp(review.get('createdate')),
'parent': 'root'})

View File

@ -279,7 +279,6 @@ class InfoExtractor:
thumbnails: A list of dictionaries, with the following entries:
* "id" (optional, string) - Thumbnail format ID
* "url"
* "ext" (optional, string) - actual image extension if not given in URL
* "preference" (optional, int) - quality of the image
* "width" (optional, int)
* "height" (optional, int)

View File

@ -563,13 +563,13 @@ class FacebookIE(InfoExtractor):
return extract_video_data(try_get(
js_data, lambda x: x['jsmods']['instances'], list) or [])
def extract_dash_manifest(vid_data, formats, mpd_url=None):
def extract_dash_manifest(video, formats):
dash_manifest = traverse_obj(
vid_data, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', 'manifest_xml', expected_type=str)
video, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', expected_type=str)
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(urllib.parse.unquote_plus(dash_manifest)),
mpd_url=url_or_none(video.get('dash_manifest_url')) or mpd_url))
mpd_url=url_or_none(video.get('dash_manifest_url'))))
def process_formats(info):
# Downloads with browser's User-Agent are rate limited. Working around
@ -619,12 +619,9 @@ class FacebookIE(InfoExtractor):
video = video['creation_story']
video['owner'] = traverse_obj(video, ('short_form_video_context', 'video_owner'))
video.update(reel_info)
fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video
formats = []
q = qualities(['sd', 'hd'])
# Legacy formats extraction
fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video
for key, format_id in (('playable_url', 'sd'), ('playable_url_quality_hd', 'hd'),
('playable_url_dash', ''), ('browser_native_hd_url', 'hd'),
('browser_native_sd_url', 'sd')):
@ -632,7 +629,7 @@ class FacebookIE(InfoExtractor):
if not playable_url:
continue
if determine_ext(playable_url) == 'mpd':
formats.extend(self._extract_mpd_formats(playable_url, video_id, fatal=False))
formats.extend(self._extract_mpd_formats(playable_url, video_id))
else:
formats.append({
'format_id': format_id,
@ -641,28 +638,6 @@ class FacebookIE(InfoExtractor):
'url': playable_url,
})
extract_dash_manifest(fmt_data, formats)
# New videoDeliveryResponse formats extraction
fmt_data = traverse_obj(video, ('videoDeliveryResponseFragment', 'videoDeliveryResponseResult'))
mpd_urls = traverse_obj(fmt_data, ('dash_manifest_urls', ..., 'manifest_url', {url_or_none}))
dash_manifests = traverse_obj(fmt_data, ('dash_manifests', lambda _, v: v['manifest_xml']))
for idx, dash_manifest in enumerate(dash_manifests):
extract_dash_manifest(dash_manifest, formats, mpd_url=traverse_obj(mpd_urls, idx))
if not dash_manifests:
# Only extract from MPD URLs if the manifests are not already provided
for mpd_url in mpd_urls:
formats.extend(self._extract_mpd_formats(mpd_url, video_id, fatal=False))
for prog_fmt in traverse_obj(fmt_data, ('progressive_urls', lambda _, v: v['progressive_url'])):
format_id = traverse_obj(prog_fmt, ('metadata', 'quality', {str.lower}))
formats.append({
'format_id': format_id,
# sd, hd formats w/o resolution info should be deprioritized below DASH
'quality': q(format_id) - 3,
'url': prog_fmt['progressive_url'],
})
for m3u8_url in traverse_obj(fmt_data, ('hls_playlist_urls', ..., 'hls_playlist_url', {url_or_none})):
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False, m3u8_id='hls'))
if not formats:
# Do not append false positive entry w/o any formats
return

View File

@ -1,105 +0,0 @@
from .common import InfoExtractor
from ..utils import url_or_none
from ..utils.traversal import traverse_obj
class RadioRadicaleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?radioradicale\.it/scheda/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.radioradicale.it/scheda/471591',
'md5': 'eb0fbe43a601f1a361cbd00f3c45af4a',
'info_dict': {
'id': '471591',
'ext': 'mp4',
'title': 'md5:e8fbb8de57011a3255db0beca69af73d',
'description': 'md5:5e15a789a2fe4d67da8d1366996e89ef',
'location': 'Napoli',
'duration': 2852.0,
'timestamp': 1459987200,
'upload_date': '20160407',
'thumbnail': 'https://www.radioradicale.it/photo400/0/0/9/0/1/00901768.jpg',
},
}, {
'url': 'https://www.radioradicale.it/scheda/742783/parlamento-riunito-in-seduta-comune-11a-della-xix-legislatura',
'info_dict': {
'id': '742783',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
'description': '-) Votazione per l\'elezione di un giudice della Corte Costituzionale (nono scrutinio)',
'location': 'CAMERA',
'duration': 5868.0,
'timestamp': 1730246400,
'upload_date': '20241030',
},
'playlist': [{
'md5': 'aa48de55dcc45478e4cd200f299aab7d',
'info_dict': {
'id': '742783-0',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}, {
'md5': 'be915c189c70ad2920e5810f32260ff5',
'info_dict': {
'id': '742783-1',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}, {
'md5': 'f0ee4047342baf8ed3128a8417ac5e0a',
'info_dict': {
'id': '742783-2',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}],
}]
def _entries(self, videos_info, page_id):
for idx, video in enumerate(traverse_obj(
videos_info, ('playlist', lambda _, v: v['sources']))):
video_id = f'{page_id}-{idx}'
formats = []
subtitles = {}
for m3u8_url in traverse_obj(video, ('sources', ..., 'src', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
for sub in traverse_obj(video, ('subtitles', ..., lambda _, v: url_or_none(v['src']))):
self._merge_subtitles({sub.get('srclang') or 'und': [{
'url': sub['src'],
'name': sub.get('label'),
}]}, target=subtitles)
yield {
'id': video_id,
'title': video.get('title'),
'formats': formats,
'subtitles': subtitles,
}
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
videos_info = self._search_json(
r'jQuery\.extend\(Drupal\.settings\s*,',
webpage, 'videos_info', page_id)['RRscheda']
entries = list(self._entries(videos_info, page_id))
common_info = {
'id': page_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'location': videos_info.get('luogo'),
**self._search_json_ld(webpage, page_id),
}
if len(entries) == 1:
return {
**entries[0],
**common_info,
}
return self.playlist_result(entries, multi_video=True, **common_info)

View File

@ -216,7 +216,7 @@ def partial_application(func):
sig = inspect.signature(func)
required_args = [
param.name for param in sig.parameters.values()
if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD)
if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.VAR_POSITIONAL)
if param.default is inspect.Parameter.empty
]
@ -4837,6 +4837,7 @@ def number_of_digits(number):
return len('%d' % number)
@partial_application
def join_nonempty(*values, delim='-', from_dict=None):
if from_dict is not None:
values = (traversal.traverse_obj(from_dict, variadic(v)) for v in values)

View File

@ -332,14 +332,14 @@ class _RequiredError(ExtractorError):
@typing.overload
def subs_list_to_dict(*, lang: str | None = 'und', ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ...
def subs_list_to_dict(*, ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ...
@typing.overload
def subs_list_to_dict(subs: list[dict] | None, /, *, lang: str | None = 'und', ext: str | None = None) -> dict[str, list[dict]]: ...
def subs_list_to_dict(subs: list[dict] | None, /, *, ext: str | None = None) -> dict[str, list[dict]]: ...
def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None):
def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None):
"""
Convert subtitles from a traversal into a subtitle dict.
The path should have an `all` immediately before this function.
@ -352,7 +352,7 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None
`quality` The sort order for each subtitle
"""
if subs is None:
return functools.partial(subs_list_to_dict, lang=lang, ext=ext)
return functools.partial(subs_list_to_dict, ext=ext)
result = collections.defaultdict(list)
@ -360,16 +360,10 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None
if not url_or_none(sub.get('url')) and not sub.get('data'):
continue
sub_id = sub.pop('id', None)
if not isinstance(sub_id, str):
if not lang:
continue
sub_id = lang
sub_ext = sub.get('ext')
if not isinstance(sub_ext, str):
if not ext:
sub.pop('ext', None)
else:
sub['ext'] = ext
if sub_id is None:
continue
if ext is not None and not sub.get('ext'):
sub['ext'] = ext
result[sub_id].append(sub)
result = dict(result)
@ -458,9 +452,9 @@ def trim_str(*, start=None, end=None):
return trim
def unpack(func, **kwargs):
def unpack(func):
@functools.wraps(func)
def inner(items):
def inner(items, **kwargs):
return func(*items, **kwargs)
return inner