etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-22 06:00:00 +00:00
Code Issues Projects Releases Wiki Activity

[ie/craftsy] Fix extractor (#9384)

Browse source 
Closes #9383
Authored by: bashonly
This commit is contained in:
bashonly 2024-03-07 17:12:43 -06:00 committed by GitHub
parent 0fcefb92f3
commit 96f3924bac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 29 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
yt_dlp/extractor/craftsy.py
View file

@ -1,12 +1,13 @@
import json
from .brightcove import BrightcoveNewIE from .brightcove import BrightcoveNewIE
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
dict_get, extract_attributes,
get_element_by_id, get_element_html_by_class,
js_to_json, get_element_text_and_html_by_tag,
traverse_obj,
) )
from ..utils.traversal import traverse_obj
class CraftsyIE(InfoExtractor): class CraftsyIE(InfoExtractor):
@ -41,28 +42,34 @@ def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(self._search_regex( video_player = get_element_html_by_class('class-video-player', webpage)
r'class_video_player_vars\s*=\s*({.*})\s*;', video_data = traverse_obj(video_player, (
get_element_by_id('vidstore-classes_class-video-player-js-extra', webpage), {extract_attributes}, 'wire:snapshot', {json.loads}, 'data', {dict})) or {}
'video data'), video_id, transform_source=js_to_json) video_js = traverse_obj(video_player, (
{lambda x: get_element_text_and_html_by_tag('video-js', x)}, 1, {extract_attributes})) or {}
account_id = traverse_obj(video_data, ('video_player', 'bc_account_id')) has_access = video_data.get('userHasAccess')
lessons = traverse_obj(video_data, ('lessons', ..., ..., lambda _, v: v['video_id']))
entries = [] preview_id = video_js.get('data-video-id')
class_preview = traverse_obj(video_data, ('video_player', 'class_preview')) if preview_id and preview_id not in traverse_obj(lessons, (..., 'video_id')):
if class_preview: if not lessons and not has_access:
v_id = class_preview.get('video_id') self.report_warning(
entries.append(self.url_result( 'Only extracting preview. For the full class, pass cookies '
f'http://players.brightcove.net/{account_id}/default_default/index.html?videoId={v_id}', + f'from an account that has access. {self._login_hint()}')
BrightcoveNewIE, v_id, class_preview.get('title'))) lessons.append({'video_id': preview_id})
if dict_get(video_data, ('is_free', 'user_has_access')): if not lessons and not has_access:
entries += [ self.raise_login_required('You do not have access to this class')
self.url_result(
account_id = video_data.get('accountId') or video_js['data-account']
def entries(lessons):
for lesson in lessons:
yield self.url_result(
f'http://players.brightcove.net/{account_id}/default_default/index.html?videoId={lesson["video_id"]}', f'http://players.brightcove.net/{account_id}/default_default/index.html?videoId={lesson["video_id"]}',
BrightcoveNewIE, lesson['video_id'], lesson.get('title')) BrightcoveNewIE, lesson['video_id'], lesson.get('title'))
for lesson in video_data['lessons']]
return self.playlist_result( return self.playlist_result(
entries, video_id, video_data.get('class_title'), entries(lessons), video_id, self._html_search_meta(('og:title', 'twitter:title'), webpage),
self._html_search_meta(('og:description', 'description'), webpage, default=None)) self._html_search_meta(('og:description', 'description'), webpage, default=None))