_ Git - youtube-dl/blob - youtube_dl/extractor/pluralsight.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11     compat_urlparse,
  12 )
  13 from ..utils import (
  14     ExtractorError,
  15     int_or_none,
  16     parse_duration,
  17 )
  18
  19
  20 class PluralsightIE(InfoExtractor):
  21     IE_NAME = 'pluralsight'
  22     _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/training/player\?author=(?P<author>[^&]+)&name=(?P<name>[^&]+)(?:&mode=live)?&clip=(?P<clip>\d+)&course=(?P<course>[^&]+)'
  23     _LOGIN_URL = 'https://www.pluralsight.com/id/'
  24     _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
  25     _NETRC_MACHINE = 'pluralsight'
  26
  27     _TEST = {
  28         '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',
  29         'md5': '4d458cf5cf4c593788672419a8dd4cf8',
  30         'info_dict': {
  31             'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
  32             'ext': 'mp4',
  33             'title': 'Management of SQL Server - Demo Monitoring',
  34             'duration': 338,
  35         },
  36         'skip': 'Requires pluralsight account credentials',
  37     }
  38
  39     def _real_initialize(self):
  40         self._login()
  41
  42     def _login(self):
  43         (username, password) = self._get_login_info()
  44         if username is None:
  45             raise ExtractorError(
  46                 'Pluralsight account is required, use --username and --password options to provide account credentials.',
  47                 expected=True)
  48
  49         login_page = self._download_webpage(
  50             self._LOGIN_URL, None, 'Downloading login page')
  51
  52         login_form = self._hidden_inputs(login_page)
  53
  54         login_form.update({
  55             'Username': username.encode('utf-8'),
  56             'Password': password.encode('utf-8'),
  57         })
  58
  59         post_url = self._search_regex(
  60             r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
  61             'post url', default=self._LOGIN_URL, group='url')
  62
  63         if not post_url.startswith('http'):
  64             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
  65
  66         request = compat_urllib_request.Request(
  67             post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
  68         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  69
  70         response = self._download_webpage(
  71             request, None, 'Logging in as %s' % username)
  72
  73         error = self._search_regex(
  74             r'<span[^>]+class="field-validation-error"[^>]*>([^<]+)</span>',
  75             response, 'error message', default=None)
  76         if error:
  77             raise ExtractorError('Unable to login: %s' % error, expected=True)
  78
  79     def _real_extract(self, url):
  80         mobj = re.match(self._VALID_URL, url)
  81         author = mobj.group('author')
  82         name = mobj.group('name')
  83         clip_id = mobj.group('clip')
  84         course = mobj.group('course')
  85
  86         display_id = '%s-%s' % (name, clip_id)
  87
  88         webpage = self._download_webpage(url, display_id)
  89
  90         collection = self._parse_json(
  91             self._search_regex(
  92                 r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)',
  93                 webpage, 'modules'),
  94             display_id)
  95
  96         module, clip = None, None
  97
  98         for module_ in collection:
  99             if module_.get('moduleName') == name:
 100                 module = module_
 101                 for clip_ in module_.get('clips', []):
 102                     clip_index = clip_.get('clipIndex')
 103                     if clip_index is None:
 104                         continue
 105                     if compat_str(clip_index) == clip_id:
 106                         clip = clip_
 107                         break
 108
 109         if not clip:
 110             raise ExtractorError('Unable to resolve clip')
 111
 112         QUALITIES = {
 113             'low': {'width': 640, 'height': 480},
 114             'medium': {'width': 848, 'height': 640},
 115             'high': {'width': 1024, 'height': 768},
 116         }
 117
 118         ALLOWED_QUALITIES = (
 119             ('webm', ('high',)),
 120             ('mp4', ('low', 'medium', 'high',)),
 121         )
 122
 123         formats = []
 124         for ext, qualities in ALLOWED_QUALITIES:
 125             for quality in qualities:
 126                 f = QUALITIES[quality].copy()
 127                 clip_post = {
 128                     'a': author,
 129                     'cap': 'false',
 130                     'cn': clip_id,
 131                     'course': course,
 132                     'lc': 'en',
 133                     'm': name,
 134                     'mt': ext,
 135                     'q': '%dx%d' % (f['width'], f['height']),
 136                 }
 137                 request = compat_urllib_request.Request(
 138                     'http://www.pluralsight.com/training/Player/ViewClip',
 139                     json.dumps(clip_post).encode('utf-8'))
 140                 request.add_header('Content-Type', 'application/json;charset=utf-8')
 141                 format_id = '%s-%s' % (ext, quality)
 142                 clip_url = self._download_webpage(
 143                     request, display_id, 'Downloading %s URL' % format_id, fatal=False)
 144                 if not clip_url:
 145                     continue
 146                 f.update({
 147                     'url': clip_url,
 148                     'ext': ext,
 149                     'format_id': format_id,
 150                 })
 151                 formats.append(f)
 152         self._sort_formats(formats)
 153
 154         # TODO: captions
 155         # http://www.pluralsight.com/training/Player/ViewClip + cap = true
 156         # or
 157         # http://www.pluralsight.com/training/Player/Captions
 158         # { a = author, cn = clip_id, lc = end, m = name }
 159
 160         return {
 161             'id': clip['clipName'],
 162             'title': '%s - %s' % (module['title'], clip['title']),
 163             'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')),
 164             'creator': author,
 165             'formats': formats
 166         }
 167
 168
 169 class PluralsightCourseIE(InfoExtractor):
 170     IE_NAME = 'pluralsight:course'
 171     _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/courses/(?P<id>[^/]+)'
 172     _TEST = {
 173         # Free course from Pluralsight Starter Subscription for Microsoft TechNet
 174         # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz
 175         'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas',
 176         'info_dict': {
 177             'id': 'hosting-sql-server-windows-azure-iaas',
 178             'title': 'Hosting SQL Server in Microsoft Azure IaaS Fundamentals',
 179             'description': 'md5:61b37e60f21c4b2f91dc621a977d0986',
 180         },
 181         'playlist_count': 31,
 182     }
 183
 184     def _real_extract(self, url):
 185         course_id = self._match_id(url)
 186
 187         course = self._download_json(
 188             'http://www.pluralsight.com/data/course/%s' % course_id,
 189             course_id, 'Downloading course JSON')
 190
 191         title = course['title']
 192         description = course.get('description') or course.get('shortDescription')
 193
 194         course_data = self._download_json(
 195             'http://www.pluralsight.com/data/course/content/%s' % course_id,
 196             course_id, 'Downloading course data JSON')
 197
 198         may_not_view = 0
 199
 200         entries = []
 201         for module in course_data:
 202             for clip in module.get('clips', []):
 203                 if clip.get('userMayViewClip') is False:
 204                     may_not_view += 1
 205                     continue
 206                 player_parameters = clip.get('playerParameters')
 207                 if not player_parameters:
 208                     continue
 209                 entries.append(self.url_result(
 210                     'http://www.pluralsight.com/training/player?%s' % player_parameters,
 211                     'Pluralsight'))
 212
 213         if may_not_view > 0:
 214             self._downloader.report_warning(
 215                 'There are %d videos in this course that are not available for you. '
 216                 'Upgrade your account to get access to these videos.' % may_not_view)
 217
 218         return self.playlist_result(entries, course_id, title, description)