From 8d1ddb0805c7c56bd03a5c0837c55602473d213f Mon Sep 17 00:00:00 2001 From: pukkandan Date: Sat, 31 Dec 2022 09:45:12 +0530 Subject: [PATCH] [extractor/udemy] Fix lectures that have no URL and detect DRM Closes #5662 --- yt_dlp/extractor/udemy.py | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/yt_dlp/extractor/udemy.py b/yt_dlp/extractor/udemy.py index 8b99c59cf..329e5da2d 100644 --- a/yt_dlp/extractor/udemy.py +++ b/yt_dlp/extractor/udemy.py @@ -11,8 +11,10 @@ int_or_none, js_to_json, sanitized_Request, + smuggle_url, try_get, unescapeHTML, + unsmuggle_url, url_or_none, urlencode_postdata, ) @@ -106,7 +108,7 @@ def _download_lecture(self, course_id, lecture_id): % (course_id, lecture_id), lecture_id, 'Downloading lecture JSON', query={ 'fields[lecture]': 'title,description,view_html,asset', - 'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,stream_urls,captions,data', + 'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,stream_urls,captions,data,course_is_drmed', }) def _handle_error(self, response): @@ -199,16 +201,19 @@ def is_logged(webpage): def _real_extract(self, url): lecture_id = self._match_id(url) + course_id = unsmuggle_url(url, {})[1].get('course_id') - webpage = self._download_webpage(url, lecture_id) - - course_id, _ = self._extract_course_info(webpage, lecture_id) + webpage = None + if not course_id: + webpage = self._download_webpage(url, lecture_id) + course_id, _ = self._extract_course_info(webpage, lecture_id) try: lecture = self._download_lecture(course_id, lecture_id) except ExtractorError as e: # Error could possibly mean we are not enrolled in the course if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + webpage = webpage or self._download_webpage(url, lecture_id) self._enroll_course(url, webpage, course_id) lecture = self._download_lecture(course_id, lecture_id) else: @@ -391,6 +396,9 @@ def extract_subtitles(track_list): if f.get('url'): formats.append(f) + if not formats and asset.get('course_is_drmed'): + self.report_drm(video_id) + return { 'id': video_id, 'title': title, @@ -449,7 +457,9 @@ def _real_extract(self, url): if lecture_id: entry = { '_type': 'url_transparent', - 'url': 'https://www.udemy.com/%s/learn/v4/t/lecture/%s' % (course_path, entry['id']), + 'url': smuggle_url( + f'https://www.udemy.com/{course_path}/learn/v4/t/lecture/{entry["id"]}', + {'course_id': course_id}), 'title': entry.get('title'), 'ie_key': UdemyIE.ie_key(), }