ytdl/youtube_dl/extractor/pluralsight.py

292 lines
12 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
import re
import json
import random
import collections
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
parse_duration,
qualities,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
sanitized_Request,
)
2015-11-21 16:37:29 +01:00
class PluralsightBaseIE(InfoExtractor):
_API_BASE = 'http://app.pluralsight.com'
class PluralsightIE(PluralsightBaseIE):
IE_NAME = 'pluralsight'
_VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/training/player\?'
2015-11-21 16:25:48 +01:00
_LOGIN_URL = 'https://app.pluralsight.com/id/'
2015-11-21 16:37:29 +01:00
_NETRC_MACHINE = 'pluralsight'
_TESTS = [{
'url': 'http://www.pluralsight.com/training/player?author=mike-mckeown&name=hosting-sql-server-windows-azure-iaas-m7-mgmt&mode=live&clip=3&course=hosting-sql-server-windows-azure-iaas',
'md5': '4d458cf5cf4c593788672419a8dd4cf8',
'info_dict': {
'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
'ext': 'mp4',
'title': 'Management of SQL Server - Demo Monitoring',
'duration': 338,
},
'skip': 'Requires pluralsight account credentials',
}, {
'url': 'https://app.pluralsight.com/training/player?course=angularjs-get-started&author=scott-allen&name=angularjs-get-started-m1-introduction&clip=0&mode=live',
'only_matching': True,
}, {
# available without pluralsight account
'url': 'http://app.pluralsight.com/training/player?author=scott-allen&name=angularjs-get-started-m1-introduction&mode=live&clip=0&course=angularjs-get-started',
'only_matching': True,
}]
def _real_initialize(self):
self._login()
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
login_form = self._hidden_inputs(login_page)
login_form.update({
'Username': username.encode('utf-8'),
'Password': password.encode('utf-8'),
})
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
request = sanitized_Request(
post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
error = self._search_regex(
r'<span[^>]+class="field-validation-error"[^>]*>([^<]+)</span>',
response, 'error message', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
2015-11-21 16:49:37 +01:00
if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
raise ExtractorError('Unable to log in')
def _real_extract(self, url):
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
author = qs.get('author', [None])[0]
name = qs.get('name', [None])[0]
clip_id = qs.get('clip', [None])[0]
course = qs.get('course', [None])[0]
if any(not f for f in (author, name, clip_id, course,)):
raise ExtractorError('Invalid URL', expected=True)
display_id = '%s-%s' % (name, clip_id)
webpage = self._download_webpage(url, display_id)
modules = self._search_regex(
r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)',
webpage, 'modules', default=None)
if modules:
collection = self._parse_json(modules, display_id)
else:
# Webpage may be served in different layout (see
# https://github.com/rg3/youtube-dl/issues/7607)
collection = self._parse_json(
self._search_regex(
r'var\s+initialState\s*=\s*({.+?});\n', webpage, 'initial state'),
display_id)['course']['modules']
module, clip = None, None
for module_ in collection:
if name in (module_.get('moduleName'), module_.get('name')):
module = module_
for clip_ in module_.get('clips', []):
clip_index = clip_.get('clipIndex')
if clip_index is None:
clip_index = clip_.get('index')
if clip_index is None:
continue
if compat_str(clip_index) == clip_id:
clip = clip_
break
if not clip:
raise ExtractorError('Unable to resolve clip')
QUALITIES = {
'low': {'width': 640, 'height': 480},
'medium': {'width': 848, 'height': 640},
'high': {'width': 1024, 'height': 768},
'high-widescreen': {'width': 1280, 'height': 720},
}
QUALITIES_PREFERENCE = ('low', 'medium', 'high', 'high-widescreen',)
quality_key = qualities(QUALITIES_PREFERENCE)
AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities'])
ALLOWED_QUALITIES = (
AllowedQuality('webm', ['high', ]),
AllowedQuality('mp4', ['low', 'medium', 'high', ]),
)
# Some courses also offer widescreen resolution for high quality (see
# https://github.com/rg3/youtube-dl/issues/7766)
widescreen = True if re.search(
r'courseSupportsWidescreenVideoFormats\s*:\s*true', webpage) else False
best_quality = 'high-widescreen' if widescreen else 'high'
if widescreen:
for allowed_quality in ALLOWED_QUALITIES:
allowed_quality.qualities.append(best_quality)
# In order to minimize the number of calls to ViewClip API and reduce
# the probability of being throttled or banned by Pluralsight we will request
2015-11-21 19:58:25 +01:00
# only single format until formats listing was explicitly requested.
if self._downloader.params.get('listformats', False):
allowed_qualities = ALLOWED_QUALITIES
else:
def guess_allowed_qualities():
req_format = self._downloader.params.get('format') or 'best'
req_format_split = req_format.split('-', 1)
if len(req_format_split) > 1:
req_ext, req_quality = req_format_split
for allowed_quality in ALLOWED_QUALITIES:
if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities:
return (AllowedQuality(req_ext, (req_quality, )), )
req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4'
return (AllowedQuality(req_ext, (best_quality, )), )
allowed_qualities = guess_allowed_qualities()
formats = []
for ext, qualities_ in allowed_qualities:
for quality in qualities_:
f = QUALITIES[quality].copy()
clip_post = {
'a': author,
'cap': 'false',
'cn': clip_id,
'course': course,
'lc': 'en',
'm': name,
'mt': ext,
'q': '%dx%d' % (f['width'], f['height']),
}
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
request = sanitized_Request(
2015-11-21 16:35:08 +01:00
'%s/training/Player/ViewClip' % self._API_BASE,
json.dumps(clip_post).encode('utf-8'))
request.add_header('Content-Type', 'application/json;charset=utf-8')
format_id = '%s-%s' % (ext, quality)
clip_url = self._download_webpage(
request, display_id, 'Downloading %s URL' % format_id, fatal=False)
# Pluralsight tracks multiple sequential calls to ViewClip API and start
# to return 429 HTTP errors after some time (see
# https://github.com/rg3/youtube-dl/pull/6989). Moreover it may even lead
# to account ban (see https://github.com/rg3/youtube-dl/issues/6842).
# To somewhat reduce the probability of these consequences
# we will sleep random amount of time before each call to ViewClip.
self._sleep(
random.randint(2, 5), display_id,
'%(video_id)s: Waiting for %(timeout)s seconds to avoid throttling')
if not clip_url:
continue
f.update({
'url': clip_url,
'ext': ext,
'format_id': format_id,
'quality': quality_key(quality),
})
formats.append(f)
self._sort_formats(formats)
# TODO: captions
# http://www.pluralsight.com/training/Player/ViewClip + cap = true
# or
# http://www.pluralsight.com/training/Player/Captions
# { a = author, cn = clip_id, lc = end, m = name }
return {
'id': clip['clipName'],
'title': '%s - %s' % (module['title'], clip['title']),
'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')),
'creator': author,
'formats': formats
}
2015-11-21 16:37:29 +01:00
class PluralsightCourseIE(PluralsightBaseIE):
IE_NAME = 'pluralsight:course'
_VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/(?:library/)?courses/(?P<id>[^/]+)'
_TESTS = [{
# Free course from Pluralsight Starter Subscription for Microsoft TechNet
# https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz
'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas',
'info_dict': {
'id': 'hosting-sql-server-windows-azure-iaas',
'title': 'Hosting SQL Server in Microsoft Azure IaaS Fundamentals',
'description': 'md5:61b37e60f21c4b2f91dc621a977d0986',
},
'playlist_count': 31,
}, {
# available without pluralsight account
'url': 'https://www.pluralsight.com/courses/angularjs-get-started',
'only_matching': True,
}, {
'url': 'https://app.pluralsight.com/library/courses/understanding-microsoft-azure-amazon-aws/table-of-contents',
'only_matching': True,
}]
def _real_extract(self, url):
course_id = self._match_id(url)
# TODO: PSM cookie
course = self._download_json(
2015-11-21 16:35:08 +01:00
'%s/data/course/%s' % (self._API_BASE, course_id),
course_id, 'Downloading course JSON')
title = course['title']
description = course.get('description') or course.get('shortDescription')
course_data = self._download_json(
2015-11-21 16:35:08 +01:00
'%s/data/course/content/%s' % (self._API_BASE, course_id),
course_id, 'Downloading course data JSON')
entries = []
for module in course_data:
for clip in module.get('clips', []):
player_parameters = clip.get('playerParameters')
if not player_parameters:
continue
entries.append(self.url_result(
2015-11-21 16:35:08 +01:00
'%s/training/player?%s' % (self._API_BASE, player_parameters),
'Pluralsight'))
return self.playlist_result(entries, course_id, title, description)