mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'yt-dlp:master' into telemb
doe1080
3 months ago
committed by
GitHub
commit
ce2fb298f3
@ -0,0 +1,235 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
|
||||
import datetime as dt
|
||||
import json
|
||||
import math
|
||||
import re
|
||||
import unittest
|
||||
|
||||
from yt_dlp.utils.jslib import devalue
|
||||
|
||||
|
||||
TEST_CASES_EQUALS = [{
|
||||
'name': 'int',
|
||||
'unparsed': [-42],
|
||||
'parsed': -42,
|
||||
}, {
|
||||
'name': 'str',
|
||||
'unparsed': ['woo!!!'],
|
||||
'parsed': 'woo!!!',
|
||||
}, {
|
||||
'name': 'Number',
|
||||
'unparsed': [['Object', 42]],
|
||||
'parsed': 42,
|
||||
}, {
|
||||
'name': 'String',
|
||||
'unparsed': [['Object', 'yar']],
|
||||
'parsed': 'yar',
|
||||
}, {
|
||||
'name': 'Infinity',
|
||||
'unparsed': -4,
|
||||
'parsed': math.inf,
|
||||
}, {
|
||||
'name': 'negative Infinity',
|
||||
'unparsed': -5,
|
||||
'parsed': -math.inf,
|
||||
}, {
|
||||
'name': 'negative zero',
|
||||
'unparsed': -6,
|
||||
'parsed': -0.0,
|
||||
}, {
|
||||
'name': 'RegExp',
|
||||
'unparsed': [['RegExp', 'regexp', 'gim']], # XXX: flags are ignored
|
||||
'parsed': re.compile('regexp'),
|
||||
}, {
|
||||
'name': 'Date',
|
||||
'unparsed': [['Date', '2001-09-09T01:46:40.000Z']],
|
||||
'parsed': dt.datetime.fromtimestamp(1e9, tz=dt.timezone.utc),
|
||||
}, {
|
||||
'name': 'Array',
|
||||
'unparsed': [[1, 2, 3], 'a', 'b', 'c'],
|
||||
'parsed': ['a', 'b', 'c'],
|
||||
}, {
|
||||
'name': 'Array (empty)',
|
||||
'unparsed': [[]],
|
||||
'parsed': [],
|
||||
}, {
|
||||
'name': 'Array (sparse)',
|
||||
'unparsed': [[-2, 1, -2], 'b'],
|
||||
'parsed': [None, 'b', None],
|
||||
}, {
|
||||
'name': 'Object',
|
||||
'unparsed': [{'foo': 1, 'x-y': 2}, 'bar', 'z'],
|
||||
'parsed': {'foo': 'bar', 'x-y': 'z'},
|
||||
}, {
|
||||
'name': 'Set',
|
||||
'unparsed': [['Set', 1, 2, 3], 1, 2, 3],
|
||||
'parsed': [1, 2, 3],
|
||||
}, {
|
||||
'name': 'Map',
|
||||
'unparsed': [['Map', 1, 2], 'a', 'b'],
|
||||
'parsed': [['a', 'b']],
|
||||
}, {
|
||||
'name': 'BigInt',
|
||||
'unparsed': [['BigInt', '1']],
|
||||
'parsed': 1,
|
||||
}, {
|
||||
'name': 'Uint8Array',
|
||||
'unparsed': [['Uint8Array', 'AQID']],
|
||||
'parsed': [1, 2, 3],
|
||||
}, {
|
||||
'name': 'ArrayBuffer',
|
||||
'unparsed': [['ArrayBuffer', 'AQID']],
|
||||
'parsed': [1, 2, 3],
|
||||
}, {
|
||||
'name': 'str (repetition)',
|
||||
'unparsed': [[1, 1], 'a string'],
|
||||
'parsed': ['a string', 'a string'],
|
||||
}, {
|
||||
'name': 'None (repetition)',
|
||||
'unparsed': [[1, 1], None],
|
||||
'parsed': [None, None],
|
||||
}, {
|
||||
'name': 'dict (repetition)',
|
||||
'unparsed': [[1, 1], {}],
|
||||
'parsed': [{}, {}],
|
||||
}, {
|
||||
'name': 'Object without prototype',
|
||||
'unparsed': [['null']],
|
||||
'parsed': {},
|
||||
}, {
|
||||
'name': 'cross-realm POJO',
|
||||
'unparsed': [{}],
|
||||
'parsed': {},
|
||||
}]
|
||||
|
||||
TEST_CASES_IS = [{
|
||||
'name': 'bool',
|
||||
'unparsed': [True],
|
||||
'parsed': True,
|
||||
}, {
|
||||
'name': 'Boolean',
|
||||
'unparsed': [['Object', False]],
|
||||
'parsed': False,
|
||||
}, {
|
||||
'name': 'undefined',
|
||||
'unparsed': -1,
|
||||
'parsed': None,
|
||||
}, {
|
||||
'name': 'null',
|
||||
'unparsed': [None],
|
||||
'parsed': None,
|
||||
}, {
|
||||
'name': 'NaN',
|
||||
'unparsed': -3,
|
||||
'parsed': math.nan,
|
||||
}]
|
||||
|
||||
TEST_CASES_INVALID = [{
|
||||
'name': 'empty string',
|
||||
'unparsed': '',
|
||||
'error': ValueError,
|
||||
'pattern': r'expected int or list as input',
|
||||
}, {
|
||||
'name': 'hole',
|
||||
'unparsed': -2,
|
||||
'error': ValueError,
|
||||
'pattern': r'invalid integer input',
|
||||
}, {
|
||||
'name': 'string',
|
||||
'unparsed': 'hello',
|
||||
'error': ValueError,
|
||||
'pattern': r'expected int or list as input',
|
||||
}, {
|
||||
'name': 'number',
|
||||
'unparsed': 42,
|
||||
'error': ValueError,
|
||||
'pattern': r'invalid integer input',
|
||||
}, {
|
||||
'name': 'boolean',
|
||||
'unparsed': True,
|
||||
'error': ValueError,
|
||||
'pattern': r'expected int or list as input',
|
||||
}, {
|
||||
'name': 'null',
|
||||
'unparsed': None,
|
||||
'error': ValueError,
|
||||
'pattern': r'expected int or list as input',
|
||||
}, {
|
||||
'name': 'object',
|
||||
'unparsed': {},
|
||||
'error': ValueError,
|
||||
'pattern': r'expected int or list as input',
|
||||
}, {
|
||||
'name': 'empty array',
|
||||
'unparsed': [],
|
||||
'error': ValueError,
|
||||
'pattern': r'expected a non-empty list as input',
|
||||
}, {
|
||||
'name': 'Python negative indexing',
|
||||
'unparsed': [[1, 2, 3, 4, 5, 6, 7, -7], 1, 2, 3, 4, 5, 6, 7],
|
||||
'error': IndexError,
|
||||
'pattern': r'invalid index: -7',
|
||||
}]
|
||||
|
||||
|
||||
class TestDevalue(unittest.TestCase):
|
||||
def test_devalue_parse_equals(self):
|
||||
for tc in TEST_CASES_EQUALS:
|
||||
self.assertEqual(devalue.parse(tc['unparsed']), tc['parsed'], tc['name'])
|
||||
|
||||
def test_devalue_parse_is(self):
|
||||
for tc in TEST_CASES_IS:
|
||||
self.assertIs(devalue.parse(tc['unparsed']), tc['parsed'], tc['name'])
|
||||
|
||||
def test_devalue_parse_invalid(self):
|
||||
for tc in TEST_CASES_INVALID:
|
||||
with self.assertRaisesRegex(tc['error'], tc['pattern'], msg=tc['name']):
|
||||
devalue.parse(tc['unparsed'])
|
||||
|
||||
def test_devalue_parse_cyclical(self):
|
||||
name = 'Map (cyclical)'
|
||||
result = devalue.parse([['Map', 1, 0], 'self'])
|
||||
self.assertEqual(result[0][0], 'self', name)
|
||||
self.assertIs(result, result[0][1], name)
|
||||
|
||||
name = 'Set (cyclical)'
|
||||
result = devalue.parse([['Set', 0, 1], 42])
|
||||
self.assertEqual(result[1], 42, name)
|
||||
self.assertIs(result, result[0], name)
|
||||
|
||||
result = devalue.parse([[0]])
|
||||
self.assertIs(result, result[0], 'Array (cyclical)')
|
||||
|
||||
name = 'Object (cyclical)'
|
||||
result = devalue.parse([{'self': 0}])
|
||||
self.assertIs(result, result['self'], name)
|
||||
|
||||
name = 'Object with null prototype (cyclical)'
|
||||
result = devalue.parse([['null', 'self', 0]])
|
||||
self.assertIs(result, result['self'], name)
|
||||
|
||||
name = 'Objects (cyclical)'
|
||||
result = devalue.parse([[1, 2], {'second': 2}, {'first': 1}])
|
||||
self.assertIs(result[0], result[1]['first'], name)
|
||||
self.assertIs(result[1], result[0]['second'], name)
|
||||
|
||||
def test_devalue_parse_revivers(self):
|
||||
self.assertEqual(
|
||||
devalue.parse([['indirect', 1], {'a': 2}, 'b'], revivers={'indirect': lambda x: x}),
|
||||
{'a': 'b'}, 'revivers (indirect)')
|
||||
|
||||
self.assertEqual(
|
||||
devalue.parse([['parse', 1], '{"a":0}'], revivers={'parse': lambda x: json.loads(x)}),
|
||||
{'a': 0}, 'revivers (parse)')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
@ -1,32 +1,66 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import js_to_json, traverse_obj
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
clean_html,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import subs_list_to_dict, traverse_obj
|
||||
|
||||
|
||||
class MonsterSirenHypergryphMusicIE(InfoExtractor):
|
||||
IE_NAME = 'monstersiren'
|
||||
IE_DESC = '塞壬唱片'
|
||||
_API_BASE = 'https://monster-siren.hypergryph.com/api'
|
||||
_VALID_URL = r'https?://monster-siren\.hypergryph\.com/music/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://monster-siren.hypergryph.com/music/514562',
|
||||
'info_dict': {
|
||||
'id': '514562',
|
||||
'ext': 'wav',
|
||||
'artists': ['塞壬唱片-MSR'],
|
||||
'album': 'Flame Shadow',
|
||||
'title': 'Flame Shadow',
|
||||
'album': 'Flame Shadow',
|
||||
'artists': ['塞壬唱片-MSR'],
|
||||
'description': 'md5:19e2acfcd1b65b41b29e8079ab948053',
|
||||
'thumbnail': r're:https?://web\.hycdn\.cn/siren/pic/.+\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://monster-siren.hypergryph.com/music/514518',
|
||||
'info_dict': {
|
||||
'id': '514518',
|
||||
'ext': 'wav',
|
||||
'title': 'Heavenly Me (Instrumental)',
|
||||
'album': 'Heavenly Me',
|
||||
'artists': ['塞壬唱片-MSR', 'AIYUE blessed : 理名'],
|
||||
'description': 'md5:ce790b41c932d1ad72eb791d1d8ae598',
|
||||
'thumbnail': r're:https?://web\.hycdn\.cn/siren/pic/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
audio_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, audio_id)
|
||||
json_data = self._search_json(
|
||||
r'window\.g_initialProps\s*=', webpage, 'data', audio_id, transform_source=js_to_json)
|
||||
song = self._download_json(f'{self._API_BASE}/song/{audio_id}', audio_id)
|
||||
if traverse_obj(song, 'code') != 0:
|
||||
msg = traverse_obj(song, ('msg', {str}, filter))
|
||||
raise ExtractorError(
|
||||
msg or 'API returned an error response', expected=bool(msg))
|
||||
|
||||
album = None
|
||||
if album_id := traverse_obj(song, ('data', 'albumCid', {str})):
|
||||
album = self._download_json(
|
||||
f'{self._API_BASE}/album/{album_id}/detail', album_id, fatal=False)
|
||||
|
||||
return {
|
||||
'id': audio_id,
|
||||
'title': traverse_obj(json_data, ('player', 'songDetail', 'name')),
|
||||
'url': traverse_obj(json_data, ('player', 'songDetail', 'sourceUrl')),
|
||||
'ext': 'wav',
|
||||
'vcodec': 'none',
|
||||
'artists': traverse_obj(json_data, ('player', 'songDetail', 'artists', ...)),
|
||||
'album': traverse_obj(json_data, ('musicPlay', 'albumDetail', 'name')),
|
||||
**traverse_obj(song, ('data', {
|
||||
'title': ('name', {str}),
|
||||
'artists': ('artists', ..., {str}),
|
||||
'subtitles': ({'url': 'lyricUrl'}, all, {subs_list_to_dict(lang='en')}),
|
||||
'url': ('sourceUrl', {url_or_none}),
|
||||
})),
|
||||
**traverse_obj(album, ('data', {
|
||||
'album': ('name', {str}),
|
||||
'description': ('intro', {clean_html}),
|
||||
'thumbnail': ('coverUrl', {url_or_none}),
|
||||
})),
|
||||
}
|
||||
|
||||
@ -1,59 +1,57 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
get_element_by_attribute,
|
||||
UnsupportedError,
|
||||
clean_html,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
mimetype2ext,
|
||||
update_url_query,
|
||||
parse_duration,
|
||||
parse_qs,
|
||||
str_or_none,
|
||||
update_url,
|
||||
)
|
||||
from ..utils.traversal import find_element, traverse_obj
|
||||
|
||||
|
||||
class NobelPrizeIE(InfoExtractor):
|
||||
_WORKING = False
|
||||
_VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.nobelprize.org/mediaplayer/?id=2636',
|
||||
'md5': '04c81e5714bb36cc4e2232fee1d8157f',
|
||||
_VALID_URL = r'https?://(?:(?:mediaplayer|www)\.)?nobelprize\.org/mediaplayer/'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.nobelprize.org/mediaplayer/?id=2636',
|
||||
'info_dict': {
|
||||
'id': '2636',
|
||||
'ext': 'mp4',
|
||||
'title': 'Announcement of the 2016 Nobel Prize in Physics',
|
||||
'description': 'md5:05beba57f4f5a4bbd4cf2ef28fcff739',
|
||||
'description': 'md5:1a2d8a6ca80c88fb3b9a326e0b0e8e43',
|
||||
'duration': 1560.0,
|
||||
'thumbnail': r're:https?://www\.nobelprize\.org/images/.+\.jpg',
|
||||
'timestamp': 1504883793,
|
||||
'upload_date': '20170908',
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'https://mediaplayer.nobelprize.org/mediaplayer/?qid=12693',
|
||||
'info_dict': {
|
||||
'id': '12693',
|
||||
'ext': 'mp4',
|
||||
'title': 'Nobel Lecture by Peter Higgs',
|
||||
'description': 'md5:9b12e275dbe3a8138484e70e00673a05',
|
||||
'duration': 1800.0,
|
||||
'thumbnail': r're:https?://www\.nobelprize\.org/images/.+\.jpg',
|
||||
'timestamp': 1504883793,
|
||||
'upload_date': '20170908',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
media = self._parse_json(self._search_regex(
|
||||
r'(?s)var\s*config\s*=\s*({.+?});', webpage,
|
||||
'config'), video_id, js_to_json)['media']
|
||||
title = media['title']
|
||||
|
||||
formats = []
|
||||
for source in media.get('source', []):
|
||||
source_src = source.get('src')
|
||||
if not source_src:
|
||||
continue
|
||||
ext = mimetype2ext(source.get('type')) or determine_ext(source_src)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
source_src, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
elif ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
update_url_query(source_src, {'hdcore': '3.7.0'}),
|
||||
video_id, f4m_id='hds', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'url': source_src,
|
||||
})
|
||||
video_id = traverse_obj(parse_qs(url), (
|
||||
('id', 'qid'), -1, {int_or_none}, {str_or_none}, any))
|
||||
if not video_id:
|
||||
raise UnsupportedError(url)
|
||||
webpage = self._download_webpage(
|
||||
update_url(url, netloc='mediaplayer.nobelprize.org'), video_id)
|
||||
|
||||
return {
|
||||
**self._search_json_ld(webpage, video_id),
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': get_element_by_attribute('itemprop', 'description', webpage),
|
||||
'duration': int_or_none(media.get('duration')),
|
||||
'formats': formats,
|
||||
'title': self._html_search_meta('caption', webpage),
|
||||
'description': traverse_obj(webpage, (
|
||||
{find_element(tag='span', attr='itemprop', value='description')}, {clean_html})),
|
||||
'duration': parse_duration(self._html_search_meta('duration', webpage)),
|
||||
}
|
||||
|
||||
@ -1,55 +1,82 @@
|
||||
from .common import InfoExtractor
|
||||
from .streaks import StreaksBaseIE
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
smuggle_url,
|
||||
traverse_obj,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import require, traverse_obj
|
||||
|
||||
|
||||
class NTVCoJpCUIE(InfoExtractor):
|
||||
class NTVCoJpCUIE(StreaksBaseIE):
|
||||
IE_NAME = 'cu.ntv.co.jp'
|
||||
IE_DESC = 'Nippon Television Network'
|
||||
_VALID_URL = r'https?://cu\.ntv\.co\.jp/(?!program)(?P<id>[^/?&#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://cu.ntv.co.jp/televiva-chill-gohan_181031/',
|
||||
IE_DESC = '日テレ無料TADA!'
|
||||
_VALID_URL = r'https?://cu\.ntv\.co\.jp/(?!program-list|search)(?P<id>[\w-]+)/?(?:[?#]|$)'
|
||||
_TESTS = [{
|
||||
'url': 'https://cu.ntv.co.jp/gaki_20250525/',
|
||||
'info_dict': {
|
||||
'id': '5978891207001',
|
||||
'id': 'gaki_20250525',
|
||||
'ext': 'mp4',
|
||||
'title': '桜エビと炒り卵がポイント！ 「中華風 エビチリおにぎり」──『美虎』五十嵐美幸',
|
||||
'upload_date': '20181213',
|
||||
'description': 'md5:1985b51a9abc285df0104d982a325f2a',
|
||||
'uploader_id': '3855502814001',
|
||||
'timestamp': 1544669941,
|
||||
'title': '放送開始36年!方正ココリコが選ぶ神回&地獄回!',
|
||||
'cast': 'count:2',
|
||||
'description': 'md5:1e1db556224d627d4d2f74370c650927',
|
||||
'display_id': 'ref:gaki_20250525',
|
||||
'duration': 1450,
|
||||
'episode': '放送開始36年!方正ココリコが選ぶ神回&地獄回!',
|
||||
'episode_id': '000000010172808',
|
||||
'episode_number': 255,
|
||||
'genres': ['variety'],
|
||||
'live_status': 'not_live',
|
||||
'modified_date': '20250525',
|
||||
'modified_timestamp': 1748145537,
|
||||
'release_date': '20250525',
|
||||
'release_timestamp': 1748145539,
|
||||
'series': 'ダウンタウンのガキの使いやあらへんで！',
|
||||
'series_id': 'gaki',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'timestamp': 1748145197,
|
||||
'upload_date': '20250525',
|
||||
'uploader': '日本テレビ放送網',
|
||||
'uploader_id': '0x7FE2',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
player_config = self._search_nuxt_data(webpage, display_id)
|
||||
video_id = traverse_obj(player_config, ('movie', 'video_id'))
|
||||
if not video_id:
|
||||
raise ExtractorError('Failed to extract video ID for Brightcove')
|
||||
account_id = traverse_obj(player_config, ('player', 'account')) or '3855502814001'
|
||||
title = traverse_obj(player_config, ('movie', 'name'))
|
||||
if not title:
|
||||
og_title = self._og_search_title(webpage, fatal=False) or traverse_obj(player_config, ('player', 'title'))
|
||||
if og_title:
|
||||
title = og_title.split('(', 1)[0].strip()
|
||||
description = (traverse_obj(player_config, ('movie', 'description'))
|
||||
or self._html_search_meta(['description', 'og:description'], webpage))
|
||||
|
||||
info = self._search_json(
|
||||
r'window\.app\s*=', webpage, 'video info',
|
||||
display_id)['falcorCache']['catalog']['episode'][display_id]['value']
|
||||
media_id = traverse_obj(info, (
|
||||
'streaks_data', 'mediaid', {str_or_none}, {require('Streaks media ID')}))
|
||||
non_phonetic = (lambda _, v: v['is_phonetic'] is False, 'value', {str})
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), {'geo_countries': ['JP']}),
|
||||
'ie_key': 'BrightcoveNew',
|
||||
**self._extract_from_streaks_api('ntv-tada', media_id, headers={
|
||||
'X-Streaks-Api-Key': 'df497719056b44059a0483b8faad1f4a',
|
||||
}),
|
||||
**traverse_obj(info, {
|
||||
'id': ('content_id', {str_or_none}),
|
||||
'title': ('title', *non_phonetic, any),
|
||||
'age_limit': ('is_adult_only_content', {lambda x: 18 if x else None}),
|
||||
'cast': ('credit', ..., 'name', *non_phonetic),
|
||||
'genres': ('genre', ..., {str}),
|
||||
'release_timestamp': ('pub_date', {parse_iso8601}),
|
||||
'tags': ('tags', ..., {str}),
|
||||
'thumbnail': ('artwork', ..., 'url', any, {url_or_none}),
|
||||
}),
|
||||
**traverse_obj(info, ('tv_episode_info', {
|
||||
'duration': ('duration', {int_or_none}),
|
||||
'episode_number': ('episode_number', {int}),
|
||||
'series': ('parent_show_title', *non_phonetic, any),
|
||||
'series_id': ('show_content_id', {str}),
|
||||
})),
|
||||
**traverse_obj(info, ('custom_data', {
|
||||
'description': ('program_detail', {str}),
|
||||
'episode': ('episode_title', {str}),
|
||||
'episode_id': ('episode_id', {str_or_none}),
|
||||
'uploader': ('network_name', {str}),
|
||||
'uploader_id': ('network_id', {str}),
|
||||
})),
|
||||
}
|
||||
|
||||
@ -1,57 +1,102 @@
|
||||
from .ard import ARDMediathekBaseIE
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
get_element_by_attribute,
|
||||
clean_html,
|
||||
extract_attributes,
|
||||
parse_duration,
|
||||
parse_qs,
|
||||
unified_strdate,
|
||||
)
|
||||
from ..utils.traversal import (
|
||||
find_element,
|
||||
require,
|
||||
traverse_obj,
|
||||
)
|
||||
|
||||
|
||||
class SRMediathekIE(ARDMediathekBaseIE):
|
||||
_WORKING = False
|
||||
IE_NAME = 'sr:mediathek'
|
||||
IE_DESC = 'Saarländischer Rundfunk'
|
||||
_VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
|
||||
|
||||
_CLS_COMMON = 'teaser__image__caption__text teaser__image__caption__text--'
|
||||
_VALID_URL = r'https?://(?:www\.)?sr-mediathek\.de/index\.php\?.*?&id=(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
|
||||
'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=141317',
|
||||
'info_dict': {
|
||||
'id': '28455',
|
||||
'id': '141317',
|
||||
'ext': 'mp4',
|
||||
'title': 'sportarena (26.10.2014)',
|
||||
'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'title': 'Kärnten, da will ich hin!',
|
||||
'channel': 'SR Fernsehen',
|
||||
'description': 'md5:7732e71e803379a499732864a572a456',
|
||||
'duration': 1788.0,
|
||||
'release_date': '20250525',
|
||||
'series': 'da will ich hin!',
|
||||
'series_id': 'DWIH',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
},
|
||||
'skip': 'no longer available',
|
||||
}, {
|
||||
'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=37682',
|
||||
'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=153853',
|
||||
'info_dict': {
|
||||
'id': '37682',
|
||||
'ext': 'mp4',
|
||||
'title': 'Love, Cakes and Rock\'n\'Roll',
|
||||
'description': 'md5:18bf9763631c7d326c22603681e1123d',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
'id': '153853',
|
||||
'ext': 'mp3',
|
||||
'title': 'Kappes, Klöße, Kokosmilch: Bruschetta mit Nduja',
|
||||
'channel': 'SR 3',
|
||||
'description': 'md5:3935798de3562b10c4070b408a15e225',
|
||||
'duration': 139.0,
|
||||
'release_date': '20250523',
|
||||
'series': 'Kappes, Klöße, Kokosmilch',
|
||||
'series_id': 'SR3_KKK_A',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://sr-mediathek.de/index.php?seite=7&id=7480',
|
||||
'only_matching': True,
|
||||
'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=31406&pnr=&tbl=pf',
|
||||
'info_dict': {
|
||||
'id': '31406',
|
||||
'ext': 'mp3',
|
||||
'title': 'Das Leben schwer nehmen, ist einfach zu anstrengend',
|
||||
'channel': 'SR 1',
|
||||
'description': 'md5:3e03fd556af831ad984d0add7175fb0c',
|
||||
'duration': 1769.0,
|
||||
'release_date': '20230717',
|
||||
'series': 'Abendrot',
|
||||
'series_id': 'SR1_AB_P',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
description = self._og_search_description(webpage)
|
||||
|
||||
if '>Der gewünschte Beitrag ist leider nicht mehr verfügbar.<' in webpage:
|
||||
if description == 'Der gewünschte Beitrag ist leider nicht mehr vorhanden.':
|
||||
raise ExtractorError(f'Video {video_id} is no longer available', expected=True)
|
||||
|
||||
media_collection_url = self._search_regex(
|
||||
r'data-mediacollection-ardplayer="([^"]+)"', webpage, 'media collection url')
|
||||
info = self._extract_media_info(media_collection_url, webpage, video_id)
|
||||
info.update({
|
||||
player_url = traverse_obj(webpage, (
|
||||
{find_element(tag='div', id=f'player{video_id}', html=True)},
|
||||
{extract_attributes}, 'data-mediacollection-ardplayer',
|
||||
{self._proto_relative_url}, {require('player URL')}))
|
||||
article = traverse_obj(webpage, (
|
||||
{find_element(cls='article__content')},
|
||||
{find_element(tag='p')}, {clean_html}))
|
||||
|
||||
return {
|
||||
**self._extract_media_info(player_url, webpage, video_id),
|
||||
'id': video_id,
|
||||
'title': get_element_by_attribute('class', 'ardplayer-title', webpage),
|
||||
'description': self._og_search_description(webpage),
|
||||
'title': traverse_obj(webpage, (
|
||||
{find_element(cls='ardplayer-title')}, {clean_html})),
|
||||
'channel': traverse_obj(webpage, (
|
||||
{find_element(cls=f'{self._CLS_COMMON}subheadline')},
|
||||
{lambda x: x.split('|')[0]}, {clean_html})),
|
||||
'description': description,
|
||||
'duration': parse_duration(self._search_regex(
|
||||
r'(\d{2}:\d{2}:\d{2})', article, 'duration')),
|
||||
'release_date': unified_strdate(self._search_regex(
|
||||
r'(\d{2}\.\d{2}\.\d{4})', article, 'release_date')),
|
||||
'series': traverse_obj(webpage, (
|
||||
{find_element(cls=f'{self._CLS_COMMON}headline')}, {clean_html})),
|
||||
'series_id': traverse_obj(webpage, (
|
||||
{find_element(cls='teaser__link', html=True)},
|
||||
{extract_attributes}, 'href', {parse_qs}, 'sen', ..., {str}, any)),
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
})
|
||||
return info
|
||||
}
|
||||
|
||||
@ -1,76 +1,76 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none, urljoin
|
||||
from .youtube import YoutubeIE
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
parse_iso8601,
|
||||
update_url,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import subs_list_to_dict, traverse_obj
|
||||
|
||||
|
||||
class StarTrekIE(InfoExtractor):
|
||||
_WORKING = False
|
||||
_VALID_URL = r'(?P<base>https?://(?:intl|www)\.startrek\.com)/videos/(?P<id>[^/]+)'
|
||||
IE_NAME = 'startrek'
|
||||
IE_DESC = 'STAR TREK'
|
||||
_VALID_URL = r'https?://(?:www\.)?startrek\.com(?:/en-(?:ca|un))?/videos/(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://intl.startrek.com/videos/watch-welcoming-jess-bush-to-the-ready-room',
|
||||
'md5': '491df5035c9d4dc7f63c79caaf9c839e',
|
||||
'url': 'https://www.startrek.com/en-un/videos/official-trailer-star-trek-lower-decks-season-4',
|
||||
'info_dict': {
|
||||
'id': 'watch-welcoming-jess-bush-to-the-ready-room',
|
||||
'id': 'official-trailer-star-trek-lower-decks-season-4',
|
||||
'ext': 'mp4',
|
||||
'title': 'WATCH: Welcoming Jess Bush to The Ready Room',
|
||||
'duration': 1888,
|
||||
'timestamp': 1655388000,
|
||||
'upload_date': '20220616',
|
||||
'description': 'md5:1ffee884e3920afbdd6dd04e926a1221',
|
||||
'thumbnail': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14794_rr_thumb_107_yt_16x9\.jpg(?:\?.+)?',
|
||||
'subtitles': {'en-US': [{
|
||||
'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_107_v4\.vtt',
|
||||
}, {
|
||||
'url': 'https://media.startrek.com/2022/06/16/2043801155561/1069981_hls/trr_snw_107_v4-c4bfc25d/stream_vtt.m3u8',
|
||||
}]},
|
||||
'title': 'Official Trailer | Star Trek: Lower Decks - Season 4',
|
||||
'alt_title': 'md5:dd7e3191aaaf9e95db16fc3abd5ef68b',
|
||||
'categories': ['TRAILERS'],
|
||||
'description': 'md5:563d7856ddab99bee7a5e50f45531757',
|
||||
'release_date': '20230722',
|
||||
'release_timestamp': 1690033200,
|
||||
'series': 'Star Trek: Lower Decks',
|
||||
'series_id': 'star-trek-lower-decks',
|
||||
'thumbnail': r're:https?://.+\.(?:jpg|png)',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.startrek.com/videos/watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
|
||||
'md5': 'f5ad74fbb86e91e0882fc0a333178d1d',
|
||||
'url': 'https://www.startrek.com/en-ca/videos/my-first-contact-senator-cory-booker',
|
||||
'info_dict': {
|
||||
'id': 'watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
|
||||
'id': 'my-first-contact-senator-cory-booker',
|
||||
'ext': 'mp4',
|
||||
'title': 'WATCH: Ethan Peck and Gia Sandhu Beam Down to The Ready Room',
|
||||
'duration': 1986,
|
||||
'timestamp': 1654221600,
|
||||
'upload_date': '20220603',
|
||||
'description': 'md5:b3aa0edacfe119386567362dec8ed51b',
|
||||
'thumbnail': r're:https://www\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14792_rr_thumb_105_yt_16x9_1.jpg(?:\?.+)?',
|
||||
'subtitles': {'en-US': [{
|
||||
'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_105_v5\.vtt',
|
||||
}]},
|
||||
'title': 'My First Contact: Senator Cory Booker',
|
||||
'alt_title': 'md5:fe74a8bdb0afab421c6e159a7680db4d',
|
||||
'categories': ['MY FIRST CONTACT'],
|
||||
'description': 'md5:a3992ab3b3e0395925d71156bbc018ce',
|
||||
'release_date': '20250401',
|
||||
'release_timestamp': 1743512400,
|
||||
'series': 'Star Trek: The Original Series',
|
||||
'series_id': 'star-trek-the-original-series',
|
||||
'thumbnail': r're:https?://.+\.(?:jpg|png)',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
urlbase, video_id = self._match_valid_url(url).group('base', 'id')
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
player = self._search_regex(
|
||||
r'(<\s*div\s+id\s*=\s*"cvp-player-[^<]+<\s*/div\s*>)', webpage, 'player')
|
||||
page_props = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
|
||||
video_data = page_props['video']['data']
|
||||
if youtube_id := video_data.get('youtube_video_id'):
|
||||
return self.url_result(youtube_id, YoutubeIE)
|
||||
|
||||
hls = self._html_search_regex(r'\bdata-hls\s*=\s*"([^"]+)"', player, 'HLS URL')
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls, video_id, 'mp4')
|
||||
|
||||
captions = self._html_search_regex(
|
||||
r'\bdata-captions-url\s*=\s*"([^"]+)"', player, 'captions URL', fatal=False)
|
||||
if captions:
|
||||
subtitles.setdefault('en-US', [])[:0] = [{'url': urljoin(urlbase, captions)}]
|
||||
|
||||
# NB: Most of the data in the json_ld is undesirable
|
||||
json_ld = self._search_json_ld(webpage, video_id, fatal=False)
|
||||
series_id = traverse_obj(video_data, (
|
||||
'series_and_movies', ..., 'series_or_movie', 'slug', {str}, any))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._html_search_regex(
|
||||
r'\bdata-title\s*=\s*"([^"]+)"', player, 'title', json_ld.get('title')),
|
||||
'description': self._html_search_regex(
|
||||
r'(?s)<\s*div\s+class\s*=\s*"header-body"\s*>(.+?)<\s*/div\s*>',
|
||||
webpage, 'description', fatal=False),
|
||||
'duration': int_or_none(self._html_search_regex(
|
||||
r'\bdata-duration\s*=\s*"(\d+)"', player, 'duration', fatal=False)),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'thumbnail': urljoin(urlbase, self._html_search_regex(
|
||||
r'\bdata-poster-url\s*=\s*"([^"]+)"', player, 'thumbnail', fatal=False)),
|
||||
'timestamp': json_ld.get('timestamp'),
|
||||
'series': traverse_obj(page_props, (
|
||||
'queried', 'header', 'tab3', 'slices', ..., 'items',
|
||||
lambda _, v: v['link']['slug'] == series_id, 'link_copy', {str}, any)),
|
||||
'series_id': series_id,
|
||||
**traverse_obj(video_data, {
|
||||
'title': ('title', ..., 'text', {clean_html}, any),
|
||||
'alt_title': ('subhead', ..., 'text', {clean_html}, any),
|
||||
'categories': ('category', 'data', 'category_name', {str.upper}, filter, all),
|
||||
'description': ('slices', ..., 'primary', 'content', ..., 'text', {clean_html}, any),
|
||||
'release_timestamp': ('published', {parse_iso8601}),
|
||||
'subtitles': ({'url': 'legacy_subtitle_file'}, all, {subs_list_to_dict(lang='en')}),
|
||||
'thumbnail': ('poster_frame', 'url', {url_or_none}, {update_url(query=None)}),
|
||||
'url': ('legacy_video_url', {url_or_none}),
|
||||
}),
|
||||
}
|
||||
|
||||
@ -0,0 +1 @@
|
||||
# Utility functions for handling web input based on commonly used JavaScript libraries
|
||||
@ -0,0 +1,167 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import array
|
||||
import base64
|
||||
import datetime as dt
|
||||
import math
|
||||
import re
|
||||
|
||||
from .._utils import parse_iso8601
|
||||
|
||||
TYPE_CHECKING = False
|
||||
if TYPE_CHECKING:
|
||||
import collections.abc
|
||||
import typing
|
||||
|
||||
T = typing.TypeVar('T')
|
||||
|
||||
|
||||
_ARRAY_TYPE_LOOKUP = {
|
||||
'Int8Array': 'b',
|
||||
'Uint8Array': 'B',
|
||||
'Uint8ClampedArray': 'B',
|
||||
'Int16Array': 'h',
|
||||
'Uint16Array': 'H',
|
||||
'Int32Array': 'i',
|
||||
'Uint32Array': 'I',
|
||||
'Float32Array': 'f',
|
||||
'Float64Array': 'd',
|
||||
'BigInt64Array': 'l',
|
||||
'BigUint64Array': 'L',
|
||||
'ArrayBuffer': 'B',
|
||||
}
|
||||
|
||||
|
||||
def parse_iter(parsed: typing.Any, /, *, revivers: dict[str, collections.abc.Callable[[list], typing.Any]] | None = None):
|
||||
# based on https://github.com/Rich-Harris/devalue/blob/f3fd2aa93d79f21746555671f955a897335edb1b/src/parse.js
|
||||
resolved = {
|
||||
-1: None,
|
||||
-2: None,
|
||||
-3: math.nan,
|
||||
-4: math.inf,
|
||||
-5: -math.inf,
|
||||
-6: -0.0,
|
||||
}
|
||||
|
||||
if isinstance(parsed, int) and not isinstance(parsed, bool):
|
||||
if parsed not in resolved or parsed == -2:
|
||||
raise ValueError('invalid integer input')
|
||||
return resolved[parsed]
|
||||
elif not isinstance(parsed, list):
|
||||
raise ValueError('expected int or list as input')
|
||||
elif not parsed:
|
||||
raise ValueError('expected a non-empty list as input')
|
||||
|
||||
if revivers is None:
|
||||
revivers = {}
|
||||
return_value = [None]
|
||||
stack: list[tuple] = [(return_value, 0, 0)]
|
||||
|
||||
while stack:
|
||||
target, index, source = stack.pop()
|
||||
if isinstance(source, tuple):
|
||||
name, source, reviver = source
|
||||
try:
|
||||
resolved[source] = target[index] = reviver(target[index])
|
||||
except Exception as error:
|
||||
yield TypeError(f'failed to parse {source} as {name!r}: {error}')
|
||||
resolved[source] = target[index] = None
|
||||
continue
|
||||
|
||||
if source in resolved:
|
||||
target[index] = resolved[source]
|
||||
continue
|
||||
|
||||
# guard against Python negative indexing
|
||||
if source < 0:
|
||||
yield IndexError(f'invalid index: {source!r}')
|
||||
continue
|
||||
|
||||
try:
|
||||
value = parsed[source]
|
||||
except IndexError as error:
|
||||
yield error
|
||||
continue
|
||||
|
||||
if isinstance(value, list):
|
||||
if value and isinstance(value[0], str):
|
||||
# TODO: implement zips `strict=True`
|
||||
if reviver := revivers.get(value[0]):
|
||||
if value[1] == source:
|
||||
# XXX: avoid infinite loop
|
||||
yield IndexError(f'{value[0]!r} cannot point to itself (index: {source})')
|
||||
continue
|
||||
# inverse order: resolve index, revive value
|
||||
stack.append((target, index, (value[0], value[1], reviver)))
|
||||
stack.append((target, index, value[1]))
|
||||
continue
|
||||
|
||||
elif value[0] == 'Date':
|
||||
try:
|
||||
result = dt.datetime.fromtimestamp(parse_iso8601(value[1]), tz=dt.timezone.utc)
|
||||
except Exception:
|
||||
yield ValueError(f'invalid date: {value[1]!r}')
|
||||
result = None
|
||||
|
||||
elif value[0] == 'Set':
|
||||
result = [None] * (len(value) - 1)
|
||||
for offset, new_source in enumerate(value[1:]):
|
||||
stack.append((result, offset, new_source))
|
||||
|
||||
elif value[0] == 'Map':
|
||||
result = []
|
||||
for key, new_source in zip(*(iter(value[1:]),) * 2):
|
||||
pair = [None, None]
|
||||
stack.append((pair, 0, key))
|
||||
stack.append((pair, 1, new_source))
|
||||
result.append(pair)
|
||||
|
||||
elif value[0] == 'RegExp':
|
||||
# XXX: use jsinterp to translate regex flags
|
||||
# currently ignores `value[2]`
|
||||
result = re.compile(value[1])
|
||||
|
||||
elif value[0] == 'Object':
|
||||
result = value[1]
|
||||
|
||||
elif value[0] == 'BigInt':
|
||||
result = int(value[1])
|
||||
|
||||
elif value[0] == 'null':
|
||||
result = {}
|
||||
for key, new_source in zip(*(iter(value[1:]),) * 2):
|
||||
stack.append((result, key, new_source))
|
||||
|
||||
elif value[0] in _ARRAY_TYPE_LOOKUP:
|
||||
typecode = _ARRAY_TYPE_LOOKUP[value[0]]
|
||||
data = base64.b64decode(value[1])
|
||||
result = array.array(typecode, data).tolist()
|
||||
|
||||
else:
|
||||
yield TypeError(f'invalid type at {source}: {value[0]!r}')
|
||||
result = None
|
||||
else:
|
||||
result = len(value) * [None]
|
||||
for offset, new_source in enumerate(value):
|
||||
stack.append((result, offset, new_source))
|
||||
|
||||
elif isinstance(value, dict):
|
||||
result = {}
|
||||
for key, new_source in value.items():
|
||||
stack.append((result, key, new_source))
|
||||
|
||||
else:
|
||||
result = value
|
||||
|
||||
target[index] = resolved[source] = result
|
||||
|
||||
return return_value[0]
|
||||
|
||||
|
||||
def parse(parsed: typing.Any, /, *, revivers: dict[str, collections.abc.Callable[[typing.Any], typing.Any]] | None = None):
|
||||
generator = parse_iter(parsed, revivers=revivers)
|
||||
while True:
|
||||
try:
|
||||
raise generator.send(None)
|
||||
except StopIteration as error:
|
||||
return error.value
|
||||
Loading…
Reference in New Issue