paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fix platzi

Browse Source
This commit is contained in:
EduTel 2022-01-21 18:01:06 -06:00
parent 5014bd67c2
commit 6abc344f22
1 changed files with 24 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
youtube_dl/extractor/platzi.py
View File

@ -104,50 +104,40 @@ class PlatziIE(PlatziBaseIE):
lecture_id = self._match_id(url) lecture_id = self._match_id(url)
webpage = self._download_webpage(url, lecture_id) webpage = self._download_webpage(url, lecture_id)
data_preloaded_state = self._parse_json(
data = self._parse_json( self._search_regex((r'window.__PRELOADED_STATE__ = (.*)\<\/script'), webpage, 'client data'),
self._search_regex(
# client_data may contain "};" so that we have to try more
# strict regex first
(r'client_data\s*=\s*({.+?})\s*;\s*\n',
r'client_data\s*=\s*({.+?})\s*;'),
webpage, 'client data'),
lecture_id) lecture_id)
material = data['initialState']['material'] # desc = data_preloaded_state['videoPlayer']['courseDescription']
desc = material['description'] title = data_preloaded_state['videoPlayer']['name']
title = desc['title'] duration = data_preloaded_state['videoPlayer']['duration']
servers = data_preloaded_state['videoPlayer']['video']['servers']
formats = [] formats = []
for server_id, server in material['videos'].items(): for server in servers.keys():
if not isinstance(server, dict):
continue
for format_id in ('hls', 'dash'): for format_id in ('hls', 'dash'):
format_url = url_or_none(server.get(format_id)) server_json = servers[server]
if not format_url: if 'hls' in server_json.keys():
continue
if format_id == 'hls':
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
format_url, lecture_id, 'mp4', server_json['hls'], lecture_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id=format_id, entry_protocol='m3u8_native', m3u8_id=format_id,
note='Downloading %s m3u8 information' % server_id, note='Downloading %s m3u8 information' % server_json['id'],
fatal=False)) fatal=False))
elif format_id == 'dash': elif 'dash' in server_json.keys():
formats.extend(self._extract_mpd_formats( formats.extend(self._extract_mpd_formats(
format_url, lecture_id, mpd_id=format_id, server_json['dash'], lecture_id, mpd_id=format_id,
note='Downloading %s MPD manifest' % server_id, note='Downloading %s MPD manifest' % server_json['id'],
fatal=False)) fatal=False))
self._sort_formats(formats) self._sort_formats(formats)
content = str_or_none(desc.get('content')) # content = str_or_none(data['videoPlayer']['content'])
description = (clean_html(compat_b64decode(content).decode('utf-8')) # description = (clean_html(compat_b64decode(content).decode('utf-8'))
if content else None) # if content else None)
duration = int_or_none(material.get('duration'), invscale=60) duration = int_or_none(duration, invscale=60)
return { return {
'id': lecture_id, 'id': lecture_id,
'title': title, 'title': title,
'description': description, 'description': '',
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
} }
@ -186,10 +176,12 @@ class PlatziCourseIE(PlatziBaseIE):
webpage = self._download_webpage(url, course_name) webpage = self._download_webpage(url, course_name)
initialData = self._search_regex(
(r'window.initialData\s*=\s*({.+?})\s*;\s*\n', r'window.initialData\s*=\s*({.+?})\s*;'),
webpage, 'window.initialData')
props = self._parse_json( props = self._parse_json(
self._search_regex(r'data\s*=\s*({.+?})\s*;', webpage, 'data'), initialData,
course_name)['initialProps'] course_name)['initialState']
entries = [] entries = []
for chapter_num, chapter in enumerate(props['concepts'], 1): for chapter_num, chapter in enumerate(props['concepts'], 1):
if not isinstance(chapter, dict): if not isinstance(chapter, dict):