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

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_str,
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     int_or_none,
  15     parse_duration,
  16 )
  17
  18
  19 class PluralsightIE(InfoExtractor):
  20     IE_NAME = 'pluralsight'
  21     _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/training/player\?'
  22     _LOGIN_URL = 'https://www.pluralsight.com/id/'
  23     _NETRC_MACHINE = 'pluralsight'
  24
  25     _TESTS = [{
  26         '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',
  27         'md5': '4d458cf5cf4c593788672419a8dd4cf8',
  28         'info_dict': {
  29             'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
  30             'ext': 'mp4',
  31             'title': 'Management of SQL Server - Demo Monitoring',
  32             'duration': 338,
  33         },
  34         'skip': 'Requires pluralsight account credentials',
  35     }, {
  36         'url': 'https://app.pluralsight.com/training/player?course=angularjs-get-started&author=scott-allen&name=angularjs-get-started-m1-introduction&clip=0&mode=live',
  37         'only_matching': True,
  38     }]
  39
  40     def _real_initialize(self):
  41         self._login()
  42
  43     def _login(self):
  44         (username, password) = self._get_login_info()
  45         if username is None:
  46             self.raise_login_required('Pluralsight account is required')
  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         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  80
  81         author = qs.get('author', [None])[0]
  82         name = qs.get('name', [None])[0]
  83         clip_id = qs.get('clip', [None])[0]
  84         course = qs.get('course', [None])[0]
  85
  86         if any(not f for f in (author, name, clip_id, course,)):
  87             raise ExtractorError('Invalid URL', expected=True)
  88
  89         display_id = '%s-%s' % (name, clip_id)
  90
  91         webpage = self._download_webpage(url, display_id)
  92
  93         collection = self._parse_json(
  94             self._search_regex(
  95                 r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)',
  96                 webpage, 'modules'),
  97             display_id)
  98
  99         module, clip = None, None
 100
 101         for module_ in collection:
 102             if module_.get('moduleName') == name:
 103                 module = module_
 104                 for clip_ in module_.get('clips', []):
 105                     clip_index = clip_.get('clipIndex')
 106                     if clip_index is None:
 107                         continue
 108                     if compat_str(clip_index) == clip_id:
 109                         clip = clip_
 110                         break
 111
 112         if not clip:
 113             raise ExtractorError('Unable to resolve clip')
 114
 115         QUALITIES = {
 116             'low': {'width': 640, 'height': 480},
 117             'medium': {'width': 848, 'height': 640},
 118             'high': {'width': 1024, 'height': 768},
 119         }
 120
 121         ALLOWED_QUALITIES = (
 122             ('webm', ('high',)),
 123             ('mp4', ('low', 'medium', 'high',)),
 124         )
 125
 126         formats = []
 127         for ext, qualities in ALLOWED_QUALITIES:
 128             for quality in qualities:
 129                 f = QUALITIES[quality].copy()
 130                 clip_post = {
 131                     'a': author,
 132                     'cap': 'false',
 133                     'cn': clip_id,
 134                     'course': course,
 135                     'lc': 'en',
 136                     'm': name,
 137                     'mt': ext,
 138                     'q': '%dx%d' % (f['width'], f['height']),
 139                 }
 140                 request = compat_urllib_request.Request(
 141                     'http://app.pluralsight.com/training/Player/ViewClip',
 142                     json.dumps(clip_post).encode('utf-8'))
 143                 request.add_header('Content-Type', 'application/json;charset=utf-8')
 144                 format_id = '%s-%s' % (ext, quality)
 145                 clip_url = self._download_webpage(
 146                     request, display_id, 'Downloading %s URL' % format_id, fatal=False)
 147                 if not clip_url:
 148                     continue
 149                 f.update({
 150                     'url': clip_url,
 151                     'ext': ext,
 152                     'format_id': format_id,
 153                 })
 154                 formats.append(f)
 155         self._sort_formats(formats)
 156
 157         # TODO: captions
 158         # http://www.pluralsight.com/training/Player/ViewClip + cap = true
 159         # or
 160         # http://www.pluralsight.com/training/Player/Captions
 161         # { a = author, cn = clip_id, lc = end, m = name }
 162
 163         return {
 164             'id': clip['clipName'],
 165             'title': '%s - %s' % (module['title'], clip['title']),
 166             'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')),
 167             'creator': author,
 168             'formats': formats
 169         }
 170
 171
 172 class PluralsightCourseIE(InfoExtractor):
 173     IE_NAME = 'pluralsight:course'
 174     _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/courses/(?P<id>[^/]+)'
 175     _TEST = {
 176         # Free course from Pluralsight Starter Subscription for Microsoft TechNet
 177         # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz
 178         'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas',
 179         'info_dict': {
 180             'id': 'hosting-sql-server-windows-azure-iaas',
 181             'title': 'Hosting SQL Server in Microsoft Azure IaaS Fundamentals',
 182             'description': 'md5:61b37e60f21c4b2f91dc621a977d0986',
 183         },
 184         'playlist_count': 31,
 185     }
 186
 187     def _real_extract(self, url):
 188         course_id = self._match_id(url)
 189
 190         # TODO: PSM cookie
 191
 192         course = self._download_json(
 193             'http://www.pluralsight.com/data/course/%s' % course_id,
 194             course_id, 'Downloading course JSON')
 195
 196         title = course['title']
 197         description = course.get('description') or course.get('shortDescription')
 198
 199         course_data = self._download_json(
 200             'http://www.pluralsight.com/data/course/content/%s' % course_id,
 201             course_id, 'Downloading course data JSON')
 202
 203         entries = []
 204         for module in course_data:
 205             for clip in module.get('clips', []):
 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         return self.playlist_result(entries, course_id, title, description)