_ 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 PluralsightBaseIE(InfoExtractor):
  20     _API_BASE = 'http://app.pluralsight.com'
  21
  22
  23 class PluralsightIE(PluralsightBaseIE):
  24     IE_NAME = 'pluralsight'
  25     _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/training/player\?'
  26     _LOGIN_URL = 'https://app.pluralsight.com/id/'
  27
  28     _NETRC_MACHINE = 'pluralsight'
  29
  30     _TESTS = [{
  31         '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',
  32         'md5': '4d458cf5cf4c593788672419a8dd4cf8',
  33         'info_dict': {
  34             'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
  35             'ext': 'mp4',
  36             'title': 'Management of SQL Server - Demo Monitoring',
  37             'duration': 338,
  38         },
  39         'skip': 'Requires pluralsight account credentials',
  40     }, {
  41         'url': 'https://app.pluralsight.com/training/player?course=angularjs-get-started&author=scott-allen&name=angularjs-get-started-m1-introduction&clip=0&mode=live',
  42         'only_matching': True,
  43     }, {
  44         # available without pluralsight account
  45         'url': 'http://app.pluralsight.com/training/player?author=scott-allen&name=angularjs-get-started-m1-introduction&mode=live&clip=0&course=angularjs-get-started',
  46         'only_matching': True,
  47     }]
  48
  49     def _real_initialize(self):
  50         self._login()
  51
  52     def _login(self):
  53         (username, password) = self._get_login_info()
  54         if username is None:
  55             return
  56
  57         login_page = self._download_webpage(
  58             self._LOGIN_URL, None, 'Downloading login page')
  59
  60         login_form = self._hidden_inputs(login_page)
  61
  62         login_form.update({
  63             'Username': username.encode('utf-8'),
  64             'Password': password.encode('utf-8'),
  65         })
  66
  67         post_url = self._search_regex(
  68             r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
  69             'post url', default=self._LOGIN_URL, group='url')
  70
  71         if not post_url.startswith('http'):
  72             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
  73
  74         request = compat_urllib_request.Request(
  75             post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
  76         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  77
  78         response = self._download_webpage(
  79             request, None, 'Logging in as %s' % username)
  80
  81         error = self._search_regex(
  82             r'<span[^>]+class="field-validation-error"[^>]*>([^<]+)</span>',
  83             response, 'error message', default=None)
  84         if error:
  85             raise ExtractorError('Unable to login: %s' % error, expected=True)
  86
  87         if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
  88             raise ExtractorError('Unable to log in')
  89
  90     def _real_extract(self, url):
  91         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  92
  93         author = qs.get('author', [None])[0]
  94         name = qs.get('name', [None])[0]
  95         clip_id = qs.get('clip', [None])[0]
  96         course = qs.get('course', [None])[0]
  97
  98         if any(not f for f in (author, name, clip_id, course,)):
  99             raise ExtractorError('Invalid URL', expected=True)
 100
 101         display_id = '%s-%s' % (name, clip_id)
 102
 103         webpage = self._download_webpage(url, display_id)
 104
 105         collection = self._parse_json(
 106             self._search_regex(
 107                 r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)',
 108                 webpage, 'modules'),
 109             display_id)
 110
 111         module, clip = None, None
 112
 113         for module_ in collection:
 114             if module_.get('moduleName') == name:
 115                 module = module_
 116                 for clip_ in module_.get('clips', []):
 117                     clip_index = clip_.get('clipIndex')
 118                     if clip_index is None:
 119                         continue
 120                     if compat_str(clip_index) == clip_id:
 121                         clip = clip_
 122                         break
 123
 124         if not clip:
 125             raise ExtractorError('Unable to resolve clip')
 126
 127         QUALITIES = {
 128             'low': {'width': 640, 'height': 480},
 129             'medium': {'width': 848, 'height': 640},
 130             'high': {'width': 1024, 'height': 768},
 131         }
 132
 133         ALLOWED_QUALITIES = (
 134             ('webm', ('high',)),
 135             ('mp4', ('low', 'medium', 'high',)),
 136         )
 137
 138         formats = []
 139         for ext, qualities in ALLOWED_QUALITIES:
 140             for quality in qualities:
 141                 f = QUALITIES[quality].copy()
 142                 clip_post = {
 143                     'a': author,
 144                     'cap': 'false',
 145                     'cn': clip_id,
 146                     'course': course,
 147                     'lc': 'en',
 148                     'm': name,
 149                     'mt': ext,
 150                     'q': '%dx%d' % (f['width'], f['height']),
 151                 }
 152                 request = compat_urllib_request.Request(
 153                     '%s/training/Player/ViewClip' % self._API_BASE,
 154                     json.dumps(clip_post).encode('utf-8'))
 155                 request.add_header('Content-Type', 'application/json;charset=utf-8')
 156                 format_id = '%s-%s' % (ext, quality)
 157                 clip_url = self._download_webpage(
 158                     request, display_id, 'Downloading %s URL' % format_id, fatal=False)
 159                 # #6989: sleep 3 seconds to avoid 429 errors.
 160                 # should help with #6842.
 161                 self._sleep(3, display_id)
 162                 if not clip_url:
 163                     continue
 164                 f.update({
 165                     'url': clip_url,
 166                     'ext': ext,
 167                     'format_id': format_id,
 168                 })
 169                 formats.append(f)
 170         self._sort_formats(formats)
 171
 172         # TODO: captions
 173         # http://www.pluralsight.com/training/Player/ViewClip + cap = true
 174         # or
 175         # http://www.pluralsight.com/training/Player/Captions
 176         # { a = author, cn = clip_id, lc = end, m = name }
 177
 178         return {
 179             'id': clip['clipName'],
 180             'title': '%s - %s' % (module['title'], clip['title']),
 181             'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')),
 182             'creator': author,
 183             'formats': formats
 184         }
 185
 186
 187 class PluralsightCourseIE(PluralsightBaseIE):
 188     IE_NAME = 'pluralsight:course'
 189     _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/(?:library/)?courses/(?P<id>[^/]+)'
 190     _TESTS = [{
 191         # Free course from Pluralsight Starter Subscription for Microsoft TechNet
 192         # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz
 193         'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas',
 194         'info_dict': {
 195             'id': 'hosting-sql-server-windows-azure-iaas',
 196             'title': 'Hosting SQL Server in Microsoft Azure IaaS Fundamentals',
 197             'description': 'md5:61b37e60f21c4b2f91dc621a977d0986',
 198         },
 199         'playlist_count': 31,
 200     }, {
 201         # available without pluralsight account
 202         'url': 'https://www.pluralsight.com/courses/angularjs-get-started',
 203         'only_matching': True,
 204     }, {
 205         'url': 'https://app.pluralsight.com/library/courses/understanding-microsoft-azure-amazon-aws/table-of-contents',
 206         'only_matching': True,
 207     }]
 208
 209     def _real_extract(self, url):
 210         course_id = self._match_id(url)
 211
 212         # TODO: PSM cookie
 213
 214         course = self._download_json(
 215             '%s/data/course/%s' % (self._API_BASE, course_id),
 216             course_id, 'Downloading course JSON')
 217
 218         title = course['title']
 219         description = course.get('description') or course.get('shortDescription')
 220
 221         course_data = self._download_json(
 222             '%s/data/course/content/%s' % (self._API_BASE, course_id),
 223             course_id, 'Downloading course data JSON')
 224
 225         entries = []
 226         for module in course_data:
 227             for clip in module.get('clips', []):
 228                 player_parameters = clip.get('playerParameters')
 229                 if not player_parameters:
 230                     continue
 231                 entries.append(self.url_result(
 232                     '%s/training/player?%s' % (self._API_BASE, player_parameters),
 233                     'Pluralsight'))
 234
 235         return self.playlist_result(entries, course_id, title, description)