Ashish/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-01-05 00:47:42 -05:00
Code Issues 7 Projects Releases Wiki Activity

[ie/createacademy] extract course

Browse Source
This commit is contained in:
Greg Rotter 2024-12-17 14:18:48 -08:00
parent ed0ecfe56d
commit 6eb69a3e12
2 changed files with 49 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
yt_dlp/extractor/_extractors.py
View File

@ -436,6 +436,7 @@ from .crackle import CrackleIE
from .craftsy import CraftsyIE
from .createacademy import (
CreateAcademyIE,
CreateAcademyCourseIE,
)
from .crooksandliars import CrooksAndLiarsIE
from .crowdbunker import (

52
yt_dlp/extractor/createacademy.py
View File

@ -18,6 +18,10 @@ class CreateAcademyIE(InfoExtractor):
'ext': 'mp4',
'title': 'Create Academy - s10e01 - Meet Dan',
'description': 'md5:48c8af37219020571a84d5f406e75d86',
'display_id': 'meet-dan',
'chapter': 'Introduction',
'chapter_id': '34',
'chapter_number': 1,
'thumbnail': 'https://cf-images.eu-west-1.prod.boltdns.net/v1/static/6222962662001/22f75006-c49f-4d95-8673-1b60df4223d2/45d953e0-fa58-4cb6-9217-1c7b3c80c932/1280x720/match/image.jpg',
},
},
@ -70,14 +74,17 @@ class CreateAcademyIE(InfoExtractor):
if 'master.m3u8' in source['src']:
return source['src']
def _real_extract(self, url):
video_id = self._match_id(url)
def _get_page_data(self, url, video_id):
webpage = self._download_webpage(url, video_id)
# parse
page_elem = self._search_regex(r'(<div[^>]+>)', webpage, 'div')
attributes = extract_attributes(page_elem)
data = json.loads(attributes['data-page'])
return json.loads(attributes['data-page'])
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._get_page_data(url, video_id)
createacademy_id = data['props']['lesson']['id']
# get media from manifest
@ -103,3 +110,40 @@ class CreateAcademyIE(InfoExtractor):
'chapter_number': lesson_metadata['section_data']['number'],
'chapter_id': str(lesson_metadata['section_data']['id']),
}
class CreateAcademyCourseIE(CreateAcademyIE):
_VALID_URL = r'https://www.createacademy.com/courses/(?P<id>[^/?#]+)'
_TESTS = [
{
'url': 'https://www.createacademy.com/courses/dan-pearson',
'info_dict': {
'id': '265',
'ext': 'mp4',
'chapter_id': '34',
'description': 'md5:48c8af37219020571a84d5f406e75d86',
'chapter_number': 1,
'thumbnail': 'https://cf-images.eu-west-1.prod.boltdns.net/v1/static/6222962662001/22f75006-c49f-4d95-8673-1b60df4223d2/45d953e0-fa58-4cb6-9217-1c7b3c80c932/1280x720/match/image.jpg',
'title': 'Create Academy - s10e01 - Meet Dan',
'display_id': 'dan-pearson',
'chapter': 'Introduction',
},
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._get_page_data(url, video_id)
# iterate lessons
entries = []
for section in data['props']['curriculum']['sections']:
for lesson in section['lessons']:
entries.append(super()._real_extract('https://www.createacademy.com' + lesson['lessonPath']))
return {
'_type': 'multi_video',
'entries': entries,
}