Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-07-03 10:39:12 +02:00
Code Issues Releases Activity

Ran hatch fmt

Browse Source
This commit is contained in:
zer0-delta 2024-06-12 05:49:31 +01:00
parent c0edd1c194
commit 2f66504571
1 changed files with 20 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
yt_dlp/extractor/bbcmaestro.py
View File

@ -1,9 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
import re import re
from ..utils import orderedSet, smuggle_url, unsmuggle_url
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import orderedSet, smuggle_url, unsmuggle_url
class BBCMaestroComIE(InfoExtractor): class BBCMaestroComIE(InfoExtractor):
@ -15,11 +13,11 @@ class BBCMaestroComIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': 'julia-donaldson/writing-children-s-picture-books/trailer', 'id': 'julia-donaldson/writing-children-s-picture-books/trailer',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Course trailer' 'title': 'Course trailer',
}, },
'params': { 'params': {
'skip_download': True 'skip_download': True,
} },
}] }]
def _do_extract_video(self, url, webpage, video_id): def _do_extract_video(self, url, webpage, video_id):
@ -30,13 +28,13 @@ def _do_extract_video(self, url, webpage, video_id):
r'<h1\b[^>]*lesson[^>]*title[^>]*>\s*(.+?)\s*</h1>', r'<h1\b[^>]*lesson[^>]*title[^>]*>\s*(.+?)\s*</h1>',
webpage, webpage,
name='title', name='title',
flags=re.RegexFlag.S flags=re.RegexFlag.S,
) )
m3u8_url = self._html_search_regex( m3u8_url = self._html_search_regex(
r'<source[^>]+src="?\'?(\S+\.m3u8)', r'<source[^>]+src="?\'?(\S+\.m3u8)',
webpage, webpage,
'video URL' 'video URL',
) )
formats = [] formats = []
if m3u8_url: if m3u8_url:
@ -45,23 +43,21 @@ def _do_extract_video(self, url, webpage, video_id):
video_id=video_id, video_id=video_id,
ext='mp4', ext='mp4',
m3u8_id='hls', m3u8_id='hls',
fatal=False fatal=False,
) )
video_dict = { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'formats': formats 'formats': formats,
} }
return video_dict
def _do_extract_playlist(self, url, webpage): def _do_extract_playlist(self, url, webpage):
# Twitter Title usually: <Lesson Title> - <Author> | <Course Title> # Twitter Title usually: <Lesson Title> - <Author> | <Course Title>
twitter_title = self._html_search_meta( twitter_title = self._html_search_meta(
['twitter:title'], ['twitter:title'],
webpage, webpage,
fatal=True fatal=True,
) )
playlist_title = ( playlist_title = (
twitter_title twitter_title
@ -70,32 +66,32 @@ def _do_extract_playlist(self, url, webpage):
) )
url_without_query_parameters = url.split('?', maxsplit=1)[0] url_without_query_parameters = url.split('?', maxsplit=1)[0]
self.write_debug('url_without_query_parameters: %r' % url_without_query_parameters) self.write_debug(f'url_without_query_parameters: {url_without_query_parameters}')
playlist_id = self._search_regex( playlist_id = self._search_regex(
pattern=r'.*/courses/([^/]+/[^/]+).*', pattern=r'.*/courses/([^/]+/[^/]+).*',
string=url_without_query_parameters, string=url_without_query_parameters,
name='Playlist ID (from URL)', name='Playlist ID (from URL)',
fatal=True fatal=True,
) )
self.write_debug('playlist_id: %r' % playlist_id) self.write_debug(f'playlist_id: {playlist_id}')
entries = [ entries = [
self.url_result( self.url_result(
smuggle_url( smuggle_url(
f'https://www.bbcmaestro.com/courses/{playlist_id}/lessons/{item_video_id}', f'https://www.bbcmaestro.com/courses/{playlist_id}/lessons/{item_video_id}',
{'forcevideo': True} {'forcevideo': True},
), ),
ie=BBCMaestroComIE.ie_key() ie=BBCMaestroComIE.ie_key(),
) )
for item_video_id in orderedSet(re.findall( for item_video_id in orderedSet(re.findall(
r'href=[^>]*/courses/' + re.escape(playlist_id) + r'/lessons/([^?]+)', r'href=[^>]*/courses/' + re.escape(playlist_id) + r'/lessons/([^?]+)',
webpage webpage,
)) ))
] ]
# self.write_debug('entries: %r' % entries) # self.write_debug('entries: %r' % entries)
return self.playlist_result( return self.playlist_result(
entries=entries, entries=entries,
playlist_id=playlist_id, playlist_id=playlist_id,
playlist_title=playlist_title playlist_title=playlist_title,
) )
def _check_login_provided(self): def _check_login_provided(self):
@ -104,9 +100,9 @@ def _check_login_provided(self):
def _real_extract(self, url): def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {}) url, smuggled_data = unsmuggle_url(url, {})
self.write_debug('Extracting from: %r' % url) self.write_debug(f'Extracting from: {url}')
video_id = self._match_id(url) video_id = self._match_id(url)
self.write_debug('Video ID: %r' % video_id) self.write_debug(f'Video ID: {video_id}')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
is_private_course_content = ('/lessons/' in url) is_private_course_content = ('/lessons/' in url)
@ -115,7 +111,7 @@ def _real_extract(self, url):
# Note: We can only download the course trailer without login # Note: We can only download the course trailer without login
self._check_login_provided() self._check_login_provided()
is_playlist = ( is_playlist = (
is_private_course_content is_private_course_content
and not smuggled_data.get('forcevideo') and not smuggled_data.get('forcevideo')
and not self.get_param('noplaylist') and not self.get_param('noplaylist')