_ 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     def _real_extract(self, url):
  88         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  89
  90         author = qs.get('author', [None])[0]
  91         name = qs.get('name', [None])[0]
  92         clip_id = qs.get('clip', [None])[0]
  93         course = qs.get('course', [None])[0]
  94
  95         if any(not f for f in (author, name, clip_id, course,)):
  96             raise ExtractorError('Invalid URL', expected=True)
  97
  98         display_id = '%s-%s' % (name, clip_id)
  99
 100         webpage = self._download_webpage(url, display_id)
 101
 102         collection = self._parse_json(
 103             self._search_regex(
 104                 r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)',
 105                 webpage, 'modules'),
 106             display_id)
 107
 108         module, clip = None, None
 109
 110         for module_ in collection:
 111             if module_.get('moduleName') == name:
 112                 module = module_
 113                 for clip_ in module_.get('clips', []):
 114                     clip_index = clip_.get('clipIndex')
 115                     if clip_index is None:
 116                         continue
 117                     if compat_str(clip_index) == clip_id:
 118                         clip = clip_
 119                         break
 120
 121         if not clip:
 122             raise ExtractorError('Unable to resolve clip')
 123
 124         QUALITIES = {
 125             'low': {'width': 640, 'height': 480},
 126             'medium': {'width': 848, 'height': 640},
 127             'high': {'width': 1024, 'height': 768},
 128         }
 129
 130         ALLOWED_QUALITIES = (
 131             ('webm', ('high',)),
 132             ('mp4', ('low', 'medium', 'high',)),
 133         )
 134
 135         formats = []
 136         for ext, qualities in ALLOWED_QUALITIES:
 137             for quality in qualities:
 138                 f = QUALITIES[quality].copy()
 139                 clip_post = {
 140                     'a': author,
 141                     'cap': 'false',
 142                     'cn': clip_id,
 143                     'course': course,
 144                     'lc': 'en',
 145                     'm': name,
 146                     'mt': ext,
 147                     'q': '%dx%d' % (f['width'], f['height']),
 148                 }
 149                 request = compat_urllib_request.Request(
 150                     '%s/training/Player/ViewClip' % self._API_BASE,
 151                     json.dumps(clip_post).encode('utf-8'))
 152                 request.add_header('Content-Type', 'application/json;charset=utf-8')
 153                 format_id = '%s-%s' % (ext, quality)
 154                 clip_url = self._download_webpage(
 155                     request, display_id, 'Downloading %s URL' % format_id, fatal=False)
 156                 if not clip_url:
 157                     continue
 158                 f.update({
 159                     'url': clip_url,
 160                     'ext': ext,
 161                     'format_id': format_id,
 162                 })
 163                 formats.append(f)
 164         self._sort_formats(formats)
 165
 166         # TODO: captions
 167         # http://www.pluralsight.com/training/Player/ViewClip + cap = true
 168         # or
 169         # http://www.pluralsight.com/training/Player/Captions
 170         # { a = author, cn = clip_id, lc = end, m = name }
 171
 172         return {
 173             'id': clip['clipName'],
 174             'title': '%s - %s' % (module['title'], clip['title']),
 175             'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')),
 176             'creator': author,
 177             'formats': formats
 178         }
 179
 180
 181 class PluralsightCourseIE(PluralsightBaseIE):
 182     IE_NAME = 'pluralsight:course'
 183     _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/(?:library/)?courses/(?P<id>[^/]+)'
 184     _TESTS = [{
 185         # Free course from Pluralsight Starter Subscription for Microsoft TechNet
 186         # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz
 187         'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas',
 188         'info_dict': {
 189             'id': 'hosting-sql-server-windows-azure-iaas',
 190             'title': 'Hosting SQL Server in Microsoft Azure IaaS Fundamentals',
 191             'description': 'md5:61b37e60f21c4b2f91dc621a977d0986',
 192         },
 193         'playlist_count': 31,
 194     }, {
 195         # available without pluralsight account
 196         'url': 'https://www.pluralsight.com/courses/angularjs-get-started',
 197         'only_matching': True,
 198     }, {
 199         'url': 'https://app.pluralsight.com/library/courses/understanding-microsoft-azure-amazon-aws/table-of-contents',
 200         'only_matching': True,
 201     }]
 202
 203     def _real_extract(self, url):
 204         course_id = self._match_id(url)
 205
 206         # TODO: PSM cookie
 207
 208         course = self._download_json(
 209             '%s/data/course/%s' % (self._API_BASE, course_id),
 210             course_id, 'Downloading course JSON')
 211
 212         title = course['title']
 213         description = course.get('description') or course.get('shortDescription')
 214
 215         course_data = self._download_json(
 216             '%s/data/course/content/%s' % (self._API_BASE, course_id),
 217             course_id, 'Downloading course data JSON')
 218
 219         entries = []
 220         for module in course_data:
 221             for clip in module.get('clips', []):
 222                 player_parameters = clip.get('playerParameters')
 223                 if not player_parameters:
 224                     continue
 225                 entries.append(self.url_result(
 226                     '%s/training/player?%s' % (self._API_BASE, player_parameters),
 227                     'Pluralsight'))
 228
 229         return self.playlist_result(entries, course_id, title, description)