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