mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-07-10 07:18:33 +00:00
Code Issues Projects Releases Wiki Activity

Apply suggestions

Browse Source
This commit is contained in:
doe1080 2025-05-27 19:41:23 +09:00
parent d940f11ae5
commit 989dfdfbfc
1 changed files with 46 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
yt_dlp/extractor/dw.py
View File

@ -4,6 +4,7 @@
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
parse_iso8601, parse_iso8601,
url_basename,
url_or_none, url_or_none,
variadic, variadic,
) )
@ -14,7 +15,19 @@ class DWIE(InfoExtractor):
IE_NAME = 'dw' IE_NAME = 'dw'
IE_DESC = 'Deutsche Welle' IE_DESC = 'Deutsche Welle'
_VALID_URL = r'https?://(?:(?:amp|www)\.)?dw\.com/(?P<lang>[^/]+)/[^/]+/(?P<type>a(?:udio)?|live|program|video)-(?P<id>\d+)' _ENTRIES_PATH_MAP = {
'a': 'videos',
'live': ('posts', ..., 'videos'),
'program': 'moreContentsFromUnifiedProgram',
}
_PATH_MAP = {
'a': 'article',
'audio': 'audio',
'live': 'liveblog',
'program': 'unified-program',
'video': 'video',
}
_VALID_URL = fr'https?://(?:(?:amp|www)\.)?dw\.com/(?P<lang>[^/?#]+)/[^/?#]+/(?P<type>{"|".join(_PATH_MAP)})-(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.dw.com/en/intelligent-light/video-19112290', 'url': 'https://www.dw.com/en/intelligent-light/video-19112290',
'info_dict': { 'info_dict': {
@ -81,11 +94,7 @@ class DWIE(InfoExtractor):
}] }]
def _entries(self, url, graph_api, media_type): def _entries(self, url, graph_api, media_type):
if path := { path = self._ENTRIES_PATH_MAP[media_type]
'a': 'videos',
'live': ('posts', ..., 'videos'),
'program': 'moreContentsFromUnifiedProgram',
}.get(media_type):
for dct in traverse_obj(graph_api, ( for dct in traverse_obj(graph_api, (
*variadic(path), lambda _, v: v['namedUrl'] not in url, *variadic(path), lambda _, v: v['namedUrl'] not in url,
)): )):
@ -94,51 +103,47 @@ def _entries(self, url, graph_api, media_type):
if media_type == 'a': if media_type == 'a':
for dct in traverse_obj(graph_api, ('audios', lambda _, v: v['mp3Src'])): for dct in traverse_obj(graph_api, ('audios', lambda _, v: v['mp3Src'])):
m3u8_url = traverse_obj(dct, 'mp3Src', {url_or_none}) mp3_url = traverse_obj(dct, 'mp3Src', {url_or_none})
yield from [{ yield from [{
'id': m3u8_url.rpartition('/')[2].removesuffix('.mp3'), 'id': url_basename(mp3_url).removesuffix('.mp3'),
'ext': 'mp3', 'ext': 'mp3',
'title': dct.get('title'), 'title': dct.get('title'),
'url': m3u8_url, 'url': mp3_url,
'vcodec': 'none',
}] }]
def _real_extract(self, url): def _real_extract(self, url):
lang, media_type, media_id = self._match_valid_url(url).groups() lang, media_type, media_id = self._match_valid_url(url).group('lang', 'type', 'id')
webpage = self._download_webpage(url, media_id) webpage = self._download_webpage(url, media_id)
path = { app_state = self._search_json(
'a': 'article', r'window\.__APP_STATE__\s*=\s*', webpage, 'app state', media_id, default={})
'audio': 'audio', if not app_state:
'live': 'liveblog',
'program': 'unified-program',
'video': 'video',
}[media_type]
if not (app_state := self._search_json(
r'window\.__APP_STATE__\s*=\s*', webpage, 'app state', media_id, default={},
)):
title = self._html_search_meta('twitter:title', webpage) title = self._html_search_meta('twitter:title', webpage)
pattern = re.compile(r'<source[^>]+src\s*=\s*(["\'])(?P<url>.+?)\1') pattern = re.compile(r'<source[^>]+src\s*=\s*(["\'])(?P<url>.+?)\1')
entries = [{ entries = [{
'id': m.group('url').rpartition('/')[2].removesuffix('.mp3'), 'id': url_basename(m.group('url')).removesuffix('.mp3'),
'ext': 'mp3', 'ext': 'mp3',
'title': title, 'title': title,
'url': m.group('url'), 'url': m.group('url'),
'vcodec': 'none',
} for m in pattern.finditer(webpage)] } for m in pattern.finditer(webpage)]
return self.playlist_result(entries, media_id, title) return self.playlist_result(entries, media_id, title)
else:
path = self._PATH_MAP[media_type]
graph_api = traverse_obj(app_state, ( graph_api = traverse_obj(app_state, (
f'/graph-api/{lang}/content/{path}/{media_id}', 'data', 'content', {dict})) f'/graph-api/{lang}/content/{path}/{media_id}', 'data', 'content', {dict}))
if media_type in {'a', 'live', 'program'}: if media_type in self._ENTRIES_PATH_MAP:
return self.playlist_result( return self.playlist_result(
self._entries(url, graph_api, media_type), media_id, graph_api.get('title')) self._entries(url, graph_api, media_type), media_id, graph_api.get('title'))
elif media_type == 'audio': elif media_type == 'audio':
formats = [{ formats = [{
'ext': 'mp3', 'ext': 'mp3',
'url': traverse_obj(graph_api, 'mp3Src', {url_or_none}), 'url': traverse_obj(graph_api, 'mp3Src', {url_or_none}),
'vcodec': 'none',
}] }]
else: else:
m3u8_url = traverse_obj(graph_api, 'hlsVideoSrc', {url_or_none}) m3u8_url = traverse_obj(graph_api, 'hlsVideoSrc', {url_or_none})