lopar/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-16 14:27:53 +00:00
Code Releases Activity

refactor and fix

Browse Source
This commit is contained in:
EduTel 2022-01-23 14:36:00 -06:00
parent 6abc344f22
commit 3ee378c099
1 changed files with 18 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
youtube_dl/extractor/platzi.py
View File

@ -3,16 +3,13 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_b64decode,
compat_str, compat_str,
) )
from ..utils import ( from ..utils import (
clean_html,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
str_or_none, str_or_none,
try_get, try_get,
url_or_none,
urlencode_postdata, urlencode_postdata,
urljoin, urljoin,
) )
@ -105,39 +102,35 @@ class PlatziIE(PlatziBaseIE):
webpage = self._download_webpage(url, lecture_id) webpage = self._download_webpage(url, lecture_id)
data_preloaded_state = self._parse_json( data_preloaded_state = self._parse_json(
self._search_regex((r'window.__PRELOADED_STATE__ = (.*)\<\/script'), webpage, 'client data'), self._search_regex(
(r'window\s*.\s*__PRELOADED_STATE__\s*=\s*({.*?});?\s*</script'), webpage, 'client data'),
lecture_id) lecture_id)
# desc = data_preloaded_state['videoPlayer']['courseDescription'] video_player = try_get(data_preloaded_state, lambda x: x['videoPlayer'], dict)
title = data_preloaded_state['videoPlayer']['name'] title = video_player.get('name', '')
duration = data_preloaded_state['videoPlayer']['duration'] duration = video_player.get('duration', '')
servers = data_preloaded_state['videoPlayer']['video']['servers'] servers = video_player.get('video', '').get('servers', {})
formats = [] formats = []
for server in servers.keys(): for server in servers.keys():
for format_id in ('hls', 'dash'): server_json = servers.get(server, {})
server_json = servers[server] if 'hls' in server_json.keys():
if 'hls' in server_json.keys(): formats.extend(self._extract_m3u8_formats(
formats.extend(self._extract_m3u8_formats( server_json['hls'], lecture_id, 'mp4',
server_json['hls'], lecture_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls',
entry_protocol='m3u8_native', m3u8_id=format_id, note='Downloading %s m3u8 information' % server_json.get('id', ''),
note='Downloading %s m3u8 information' % server_json['id'], fatal=False))
fatal=False)) elif 'dash' in server_json.keys():
elif 'dash' in server_json.keys(): formats.extend(self._extract_mpd_formats(
formats.extend(self._extract_mpd_formats( server_json['dash'], lecture_id, mpd_id='dash',
server_json['dash'], lecture_id, mpd_id=format_id, note='Downloading %s MPD manifest' % server_json.get('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(data['videoPlayer']['content'])
# description = (clean_html(compat_b64decode(content).decode('utf-8'))
# if content else None)
duration = int_or_none(duration, invscale=60) duration = int_or_none(duration, invscale=60)
return { return {
'id': lecture_id, 'id': lecture_id,
'title': title, 'title': title,
'description': '',
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
} }