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