1 from __future__ import unicode_literals
7 from .common import InfoExtractor
11 compat_urllib_request,
21 class PluralsightBaseIE(InfoExtractor):
22 _API_BASE = 'http://app.pluralsight.com'
25 class PluralsightIE(PluralsightBaseIE):
26 IE_NAME = 'pluralsight'
27 _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/training/player\?'
28 _LOGIN_URL = 'https://app.pluralsight.com/id/'
30 _NETRC_MACHINE = 'pluralsight'
33 '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',
34 'md5': '4d458cf5cf4c593788672419a8dd4cf8',
36 'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
38 'title': 'Management of SQL Server - Demo Monitoring',
41 'skip': 'Requires pluralsight account credentials',
43 'url': 'https://app.pluralsight.com/training/player?course=angularjs-get-started&author=scott-allen&name=angularjs-get-started-m1-introduction&clip=0&mode=live',
44 'only_matching': True,
46 # available without pluralsight account
47 'url': 'http://app.pluralsight.com/training/player?author=scott-allen&name=angularjs-get-started-m1-introduction&mode=live&clip=0&course=angularjs-get-started',
48 'only_matching': True,
51 def _real_initialize(self):
55 (username, password) = self._get_login_info()
59 login_page = self._download_webpage(
60 self._LOGIN_URL, None, 'Downloading login page')
62 login_form = self._hidden_inputs(login_page)
65 'Username': username.encode('utf-8'),
66 'Password': password.encode('utf-8'),
69 post_url = self._search_regex(
70 r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
71 'post url', default=self._LOGIN_URL, group='url')
73 if not post_url.startswith('http'):
74 post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
76 request = compat_urllib_request.Request(
77 post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
78 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
80 response = self._download_webpage(
81 request, None, 'Logging in as %s' % username)
83 error = self._search_regex(
84 r'<span[^>]+class="field-validation-error"[^>]*>([^<]+)</span>',
85 response, 'error message', default=None)
87 raise ExtractorError('Unable to login: %s' % error, expected=True)
89 if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
90 raise ExtractorError('Unable to log in')
92 def _real_extract(self, url):
93 qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
95 author = qs.get('author', [None])[0]
96 name = qs.get('name', [None])[0]
97 clip_id = qs.get('clip', [None])[0]
98 course = qs.get('course', [None])[0]
100 if any(not f for f in (author, name, clip_id, course,)):
101 raise ExtractorError('Invalid URL', expected=True)
103 display_id = '%s-%s' % (name, clip_id)
105 webpage = self._download_webpage(url, display_id)
107 collection = self._parse_json(
109 r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)',
113 module, clip = None, None
115 for module_ in collection:
116 if module_.get('moduleName') == name:
118 for clip_ in module_.get('clips', []):
119 clip_index = clip_.get('clipIndex')
120 if clip_index is None:
122 if compat_str(clip_index) == clip_id:
127 raise ExtractorError('Unable to resolve clip')
130 'low': {'width': 640, 'height': 480},
131 'medium': {'width': 848, 'height': 640},
132 'high': {'width': 1024, 'height': 768},
135 AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities'])
137 ALLOWED_QUALITIES = (
138 AllowedQuality('webm', ('high',)),
139 AllowedQuality('mp4', ('low', 'medium', 'high',)),
142 # In order to minimize the number of calls to ViewClip API and reduce
143 # the probability of being throttled or banned by Pluralsight we will request
144 # only single format until formats listing was explicitly requested.
145 if self._downloader.params.get('listformats', False):
146 allowed_qualities = ALLOWED_QUALITIES
148 def guess_allowed_qualities():
149 req_format = self._downloader.params.get('format') or 'best'
150 req_format_split = req_format.split('-')
151 if len(req_format_split) > 1:
152 req_ext, req_quality = req_format_split
153 for allowed_quality in ALLOWED_QUALITIES:
154 if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities:
155 return (AllowedQuality(req_ext, (req_quality, )), )
156 req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4'
157 return (AllowedQuality(req_ext, ('high', )), )
158 allowed_qualities = guess_allowed_qualities()
161 for ext, qualities in allowed_qualities:
162 for quality in qualities:
163 f = QUALITIES[quality].copy()
172 'q': '%dx%d' % (f['width'], f['height']),
174 request = compat_urllib_request.Request(
175 '%s/training/Player/ViewClip' % self._API_BASE,
176 json.dumps(clip_post).encode('utf-8'))
177 request.add_header('Content-Type', 'application/json;charset=utf-8')
178 format_id = '%s-%s' % (ext, quality)
179 clip_url = self._download_webpage(
180 request, display_id, 'Downloading %s URL' % format_id, fatal=False)
182 # Pluralsight tracks multiple sequential calls to ViewClip API and start
183 # to return 429 HTTP errors after some time (see
184 # https://github.com/rg3/youtube-dl/pull/6989). Moreover it may even lead
185 # to account ban (see https://github.com/rg3/youtube-dl/issues/6842).
186 # To somewhat reduce the probability of these consequences
187 # we will sleep random amount of time before each call to ViewClip.
189 random.randint(2, 5), display_id,
190 '%(video_id)s: Waiting for %(timeout)s seconds to avoid throttling')
197 'format_id': format_id,
200 self._sort_formats(formats)
203 # http://www.pluralsight.com/training/Player/ViewClip + cap = true
205 # http://www.pluralsight.com/training/Player/Captions
206 # { a = author, cn = clip_id, lc = end, m = name }
209 'id': clip['clipName'],
210 'title': '%s - %s' % (module['title'], clip['title']),
211 'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')),
217 class PluralsightCourseIE(PluralsightBaseIE):
218 IE_NAME = 'pluralsight:course'
219 _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/(?:library/)?courses/(?P<id>[^/]+)'
221 # Free course from Pluralsight Starter Subscription for Microsoft TechNet
222 # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz
223 'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas',
225 'id': 'hosting-sql-server-windows-azure-iaas',
226 'title': 'Hosting SQL Server in Microsoft Azure IaaS Fundamentals',
227 'description': 'md5:61b37e60f21c4b2f91dc621a977d0986',
229 'playlist_count': 31,
231 # available without pluralsight account
232 'url': 'https://www.pluralsight.com/courses/angularjs-get-started',
233 'only_matching': True,
235 'url': 'https://app.pluralsight.com/library/courses/understanding-microsoft-azure-amazon-aws/table-of-contents',
236 'only_matching': True,
239 def _real_extract(self, url):
240 course_id = self._match_id(url)
244 course = self._download_json(
245 '%s/data/course/%s' % (self._API_BASE, course_id),
246 course_id, 'Downloading course JSON')
248 title = course['title']
249 description = course.get('description') or course.get('shortDescription')
251 course_data = self._download_json(
252 '%s/data/course/content/%s' % (self._API_BASE, course_id),
253 course_id, 'Downloading course data JSON')
256 for module in course_data:
257 for clip in module.get('clips', []):
258 player_parameters = clip.get('playerParameters')
259 if not player_parameters:
261 entries.append(self.url_result(
262 '%s/training/player?%s' % (self._API_BASE, player_parameters),
265 return self.playlist_result(entries, course_id, title, description)