Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-23 00:54:31 +01:00
Code Issues Releases Wiki Activity

[BrainPOP] Trim code and make optional metadata less brittle

Browse Source
This commit is contained in:
Nehal Patel 2016-07-12 19:51:50 -05:00
parent 7022e24b1d
commit f02b57d5a7
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
youtube_dl/extractor/brainpop.py
View File

@ -26,20 +26,20 @@ class BrainPOPIE(InfoExtractor):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
content = self._parse_json(self._html_search_regex(r'var content = ([^;]*)', webpage, 'content'), display_id) content = self._parse_json(self._html_search_regex(r'var content = ([^;]*)', webpage, 'content JSON'), display_id)
topic = content['category']['unit']['topic']
if content['category']['unit']['topic']['free'] == 'no': if topic['free'] == 'no':
self.raise_login_required('%s is only available for users with Subscriptions' % display_id) self.raise_login_required('%s is only available for users with Subscriptions' % display_id)
global_content = self._parse_json(self._html_search_regex(r'var global_content = ([^;]*)', webpage, 'global content').replace("'", '"'), display_id) global_content = self._parse_json(self._html_search_regex(r'var global_content = ([^;]*)', webpage, 'global content JSON').replace("'", '"'), display_id)
cdn_path = global_content.get('cdn_path', 'https://cdn.brainpop.com') cdn_path = global_content.get('cdn_path', 'https://cdn.brainpop.com')
movie_cdn_path = global_content.get('movie_cdn_path', 'https://svideos.brainpop.com') movie_cdn_path = global_content.get('movie_cdn_path', 'https://svideos.brainpop.com')
ec_token = self._html_search_regex(r"ec_token : '([^']*)'", webpage, 'token') ec_token = self._html_search_regex(r"ec_token : '([^']*)'", webpage, 'token')
screenshots = content['category']['unit']['topic'].get('screenshots', {}) thumbnails = [{'url': cdn_path + screenshot} for screenshot in topic.get('screenshots', {})]
thumbnails = [{'url': cdn_path + screenshot} for screenshot in screenshots]
movies = content['category']['unit']['topic']['movies'] movies = topic['movies']
formats = [] formats = []
formats.append({ formats.append({
'url': movie_cdn_path + movies['mp4'] + '?' + ec_token, 'url': movie_cdn_path + movies['mp4'] + '?' + ec_token,
@ -53,13 +53,13 @@ class BrainPOPIE(InfoExtractor):
}) })
self._sort_formats(formats) self._sort_formats(formats)
settings = self._parse_json(self._html_search_regex(r'var settings = ([^;]*)', webpage, 'settings'), display_id) settings = self._parse_json(self._html_search_regex(r'var settings = ([^;]*)', webpage, 'settings JSON', '{}'), display_id)
return { return {
'id': content['category']['unit']['topic']['EntryID'], 'id': topic['EntryID'],
'display_id': display_id, 'display_id': display_id,
'title': remove_end(settings['title'], ' - BrainPOP'), 'title': remove_end(settings.get('title', display_id), ' - BrainPOP'),
'description': settings['description'], 'description': settings.get('description', ''),
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'formats': formats, 'formats': formats,
} }