github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-29 15:50:46 +00:00
Code Issues Projects Releases Packages Wiki Activity

[lynda] Fix successful login regex and fix formats extraction (Closes #2520)

Browse source
This commit is contained in:
Sergey M․ 2014-03-07 06:56:48 +07:00
parent c361c505b0
commit 16ff7ebc77
1 changed files with 24 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
youtube_dl/extractor/lynda.py
View file

@ -8,7 +8,8 @@
from ..utils import ( from ..utils import (
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request, compat_urllib_request,
ExtractorError ExtractorError,
int_or_none,
) )
@ -19,7 +20,7 @@ class LyndaIE(SubtitlesInfoExtractor):
_LOGIN_URL = 'https://www.lynda.com/login/login.aspx' _LOGIN_URL = 'https://www.lynda.com/login/login.aspx'
_NETRC_MACHINE = 'lynda' _NETRC_MACHINE = 'lynda'
_SUCCESSFUL_LOGIN_REGEX = r'<a href="https://www.lynda.com/home/userAccount/ChangeContactInfo.aspx" data-qa="eyebrow_account_menu">My account' _SUCCESSFUL_LOGIN_REGEX = r'isLoggedIn: true'
_TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]' _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.' ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
@ -55,13 +56,29 @@ def _real_extract(self, url):
duration = video_json['DurationInSeconds'] duration = video_json['DurationInSeconds']
title = video_json['Title'] title = video_json['Title']
formats = [{'url': fmt['Url'], formats = []
fmts = video_json.get('Formats')
if fmts:
formats.extend([
{
'url': fmt['Url'],
'ext': fmt['Extension'], 'ext': fmt['Extension'],
'width': fmt['Width'], 'width': fmt['Width'],
'height': fmt['Height'], 'height': fmt['Height'],
'filesize': fmt['FileSize'], 'filesize': fmt['FileSize'],
'format_id': str(fmt['Resolution']) 'format_id': str(fmt['Resolution'])
} for fmt in video_json['Formats']] } for fmt in fmts])
prioritized_streams = video_json.get('PrioritizedStreams')
if prioritized_streams:
formats.extend([
{
'url': video_url,
'width': int_or_none(format_id),
'format_id': format_id,
} for format_id, video_url in prioritized_streams['0'].items()
])
self._sort_formats(formats) self._sort_formats(formats)
@ -179,6 +196,9 @@ def _real_extract(self, url):
videos = [] videos = []
(username, _) = self._get_login_info() (username, _) = self._get_login_info()
# Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
# by single video API anymore
for chapter in course_json['Chapters']: for chapter in course_json['Chapters']:
for video in chapter['Videos']: for video in chapter['Videos']:
if username is None and video['HasAccess'] is False: if username is None and video['HasAccess'] is False: