xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 06:10:12 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix captions

Browse Source
This commit is contained in:
Conner Luker 2024-02-27 12:45:48 -05:00
parent 4fc802f965
commit d9ab668223
1 changed files with 21 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
yt_dlp/extractor/frontendmasters.py
View File

@ -19,6 +19,21 @@ class FrontendMastersBaseIE(InfoExtractor):
_NETRC_MACHINE = 'frontendmasters'
def _get_subtitles(self, lesson_data, course_data):
captions_base = "https://captions.frontendmasters.com/assets/courses/"
lesson_slug = lesson_data.get('slug')
lesson_index = lesson_data.get('index')
date_published = course_data.get('datePublished')
course_slug = course_data.get('slug')
subtitles_url = f'{captions_base}{date_published}-{course_slug}/{lesson_index}-{lesson_slug}.vtt'
return {
'en': [{
'url': subtitles_url
}]
}
def _perform_login(self, username, password):
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
@ -69,7 +84,7 @@ def _extract_chapters(course):
return chapters
@staticmethod
def _extract_lesson(chapters, lesson_id, lesson):
def _extract_lesson(chapters, lesson_id, lesson, subtitles):
title = lesson.get('title') or lesson_id
display_id = lesson.get('slug')
description = lesson.get('description')
@ -106,6 +121,7 @@ def _extract_lesson(chapters, lesson_id, lesson):
'duration': duration,
'chapter': chapter,
'chapter_number': chapter_number,
'subtitles': subtitles
}
@ -147,17 +163,10 @@ def _real_extract(self, url):
formats = self._extract_m3u8_formats(m3u8_url, lesson_id)
subtitles = {
'en': [{
'url': f'{self._API_BASE}/transcripts/{lesson_id}.vtt'
}]
}
return {
'id': lesson_id,
'title': lesson_id,
'formats': formats,
'subtitles': subtitles
}
@ -192,8 +201,9 @@ def _real_extract(self, url):
for video_id, data in course['lessonData'].items()
if data.get('slug') == lesson_name)
subtitles = self.extract_subtitles(lesson, course)
chapters = self._extract_chapters(course)
return self._extract_lesson(chapters, lesson_id, lesson)
return self._extract_lesson(chapters, lesson_id, lesson, subtitles)
class FrontendMastersCourseIE(FrontendMastersPageBaseIE):
@ -228,9 +238,10 @@ def _real_extract(self, url):
for lesson in lessons:
lesson_name = lesson.get('slug')
lesson_id = lesson.get('hash') or lesson.get('statsId')
subtitles = self.extract_subtitles(lesson, course)
if not lesson_id or not lesson_name:
continue
entries.append(self._extract_lesson(chapters, lesson_id, lesson))
entries.append(self._extract_lesson(chapters, lesson_id, lesson, subtitles))
title = course.get('title')
description = course.get('description')