lopar/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-16 22:37:35 +00:00
Code Releases Activity

Further improve extraction

Browse Source 
* detect when login required
* extract further metadata
This commit is contained in:
dirkf 2022-10-28 22:43:54 +00:00 committed by GitHub
parent 0235e627b9
commit 1ce8590329
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 22 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
youtube_dl/extractor/platzi.py
View File

@ -7,12 +7,15 @@ from ..compat import (
) )
from ..utils import ( from ..utils import (
clean_html, clean_html,
dict_get,
ExtractorError, ExtractorError,
get_element_by_class, get_element_by_class,
int_or_none, int_or_none,
parse_iso8601,
str_or_none, str_or_none,
strip_or_none, strip_or_none,
try_get, try_get,
url_or_none,
urlencode_postdata, urlencode_postdata,
urljoin, urljoin,
) )
@ -113,6 +116,13 @@ class PlatziIE(PlatziBaseIE):
video_player = try_get(data_preloaded_state, lambda x: x['videoPlayer'], dict) video_player = try_get(data_preloaded_state, lambda x: x['videoPlayer'], dict)
title = strip_or_none(video_player.get('name')) or self._og_search_title(webpage) title = strip_or_none(video_player.get('name')) or self._og_search_title(webpage)
servers = try_get(video_player, lambda x: x['video']['servers'], dict) or {} servers = try_get(video_player, lambda x: x['video']['servers'], dict) or {}
if not servers and try_get(video_player, lambda x: x['blockedInfo']['blocked']):
why = video_player['blockedInfo'].get('type') or 'unspecified'
if why == 'unlogged':
self.raise_login_required()
raise ExtractorError(
'All video formats blocked because ' + why, expected=True)
formats = [] formats = []
headers['Referer'] = url headers['Referer'] = url
extractions = { extractions = {
@ -137,13 +147,22 @@ class PlatziIE(PlatziBaseIE):
for f in formats: for f in formats:
f.setdefault('http_headers', {})['Referer'] = headers['Referer'] f.setdefault('http_headers', {})['Referer'] = headers['Referer']
def categories():
cat = strip_or_none(video_player.get('courseCategory'))
if cat:
return [cat]
return { return {
'id': lecture_id, 'id': lecture_id,
'title': title, 'title': title,
'description': self._og_search_description(webpage), 'description': clean_html(video_player.get('courseDescription')) or self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'duration': int_or_none(video_player.get('duration'), invscale=60), 'duration': int_or_none(video_player.get('duration'), invscale=60),
'creator': clean_html(get_element_by_class('TeacherDetails-name', webpage)), 'thumbnail': url_or_none(video_player.get('thumbnail')) or self._og_search_thumbnail(webpage),
'timestamp': parse_iso8601(dict_get(video_player, ('dataModified', 'dataPublished'))),
'creator': strip_or_none(video_player.get('teacherName')) or clean_html(get_element_by_class('TeacherDetails-name', webpage)),
'comment_count': int_or_none(video_player.get('commentsNumber')),
'categories': categories(),
'series': strip_or_none(video_player.get('courseTitle')) or None,
'formats': formats, 'formats': formats,
} }