aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/pluralsight.py
blob: 597b11218394b6c034ef60608ddbb2ab60c0d656 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
from __future__ import unicode_literals

import collections
import json
import os
import random

from .common import InfoExtractor
from ..compat import (
    compat_str,
    compat_urlparse,
)
from ..utils import (
    dict_get,
    ExtractorError,
    float_or_none,
    int_or_none,
    parse_duration,
    qualities,
    srt_subtitles_timecode,
    try_get,
    update_url_query,
    urlencode_postdata,
)


class PluralsightBaseIE(InfoExtractor):
    _API_BASE = 'https://app.pluralsight.com'

    def _download_course(self, course_id, url, display_id):
        try:
            return self._download_course_rpc(course_id, url, display_id)
        except ExtractorError:
            # Old API fallback
            return self._download_json(
                'https://app.pluralsight.com/player/user/api/v1/player/payload',
                display_id, data=urlencode_postdata({'courseId': course_id}),
                headers={'Referer': url})

    def _download_course_rpc(self, course_id, url, display_id):
        response = self._download_json(
            '%s/player/functions/rpc' % self._API_BASE, display_id,
            'Downloading course JSON',
            data=json.dumps({
                'fn': 'bootstrapPlayer',
                'payload': {
                    'courseId': course_id,
                },
            }).encode('utf-8'),
            headers={
                'Content-Type': 'application/json;charset=utf-8',
                'Referer': url,
            })

        course = try_get(response, lambda x: x['payload']['course'], dict)
        if course:
            return course

        raise ExtractorError(
            '%s said: %s' % (self.IE_NAME, response['error']['message']),
            expected=True)


class PluralsightIE(PluralsightBaseIE):
    IE_NAME = 'pluralsight'
    _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/(?:training/)?player\?'
    _LOGIN_URL = 'https://app.pluralsight.com/id/'

    _NETRC_MACHINE = 'pluralsight'

    _TESTS = [{
        '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',
        'md5': '4d458cf5cf4c593788672419a8dd4cf8',
        'info_dict': {
            'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
            'ext': 'mp4',
            'title': 'Demo Monitoring',
            'duration': 338,
        },
        'skip': 'Requires pluralsight account credentials',
    }, {
        'url': 'https://app.pluralsight.com/training/player?course=angularjs-get-started&author=scott-allen&name=angularjs-get-started-m1-introduction&clip=0&mode=live',
        'only_matching': True,
    }, {
        # available without pluralsight account
        'url': 'http://app.pluralsight.com/training/player?author=scott-allen&name=angularjs-get-started-m1-introduction&mode=live&clip=0&course=angularjs-get-started',
        'only_matching': True,
    }, {
        'url': 'https://app.pluralsight.com/player?course=ccna-intro-networking&author=ross-bagurdes&name=ccna-intro-networking-m06&clip=0',
        'only_matching': True,
    }]

    def _real_initialize(self):
        self._login()

    def _login(self):
        (username, password) = self._get_login_info()
        if username is None:
            return

        login_page = self._download_webpage(
            self._LOGIN_URL, None, 'Downloading login page')

        login_form = self._hidden_inputs(login_page)

        login_form.update({
            'Username': username,
            'Password': password,
        })

        post_url = self._search_regex(
            r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
            'post url', default=self._LOGIN_URL, group='url')

        if not post_url.startswith('http'):
            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)

        response = self._download_webpage(
            post_url, None, 'Logging in',
            data=urlencode_postdata(login_form),
            headers={'Content-Type': 'application/x-www-form-urlencoded'})

        error = self._search_regex(
            r'<span[^>]+class="field-validation-error"[^>]*>([^<]+)</span>',
            response, 'error message', default=None)
        if error:
            raise ExtractorError('Unable to login: %s' % error, expected=True)

        if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
            BLOCKED = 'Your account has been blocked due to suspicious activity'
            if BLOCKED in response:
                raise ExtractorError(
                    'Unable to login: %s' % BLOCKED, expected=True)
            MUST_AGREE = 'To continue using Pluralsight, you must agree to'
            if any(p in response for p in (MUST_AGREE, '>Disagree<', '>Agree<')):
                raise ExtractorError(
                    'Unable to login: %s some documents. Go to pluralsight.com, '
                    'log in and agree with what Pluralsight requires.'
                    % MUST_AGREE, expected=True)

            raise ExtractorError('Unable to log in')

    def _get_subtitles(self, author, clip_id, lang, name, duration, video_id):
        captions_post = {
            'a': author,
            'cn': clip_id,
            'lc': lang,
            'm': name,
        }
        captions = self._download_json(
            '%s/player/retrieve-captions' % self._API_BASE, video_id,
            'Downloading captions JSON', 'Unable to download captions JSON',
            fatal=False, data=json.dumps(captions_post).encode('utf-8'),
            headers={'Content-Type': 'application/json;charset=utf-8'})
        if captions:
            return {
                lang: [{
                    'ext': 'json',
                    'data': json.dumps(captions),
                }, {
                    'ext': 'srt',
                    'data': self._convert_subtitles(duration, captions),
                }]
            }

    @staticmethod
    def _convert_subtitles(duration, subs):
        srt = ''
        TIME_OFFSET_KEYS = ('displayTimeOffset', 'DisplayTimeOffset')
        TEXT_KEYS = ('text', 'Text')
        for num, current in enumerate(subs):
            current = subs[num]
            start, text = (
                float_or_none(dict_get(current, TIME_OFFSET_KEYS)),
                dict_get(current, TEXT_KEYS))
            if start is None or text is None:
                continue
            end = duration if num == len(subs) - 1 else float_or_none(
                dict_get(subs[num + 1], TIME_OFFSET_KEYS))
            if end is None:
                continue
            srt += os.linesep.join(
                (
                    '%d' % num,
                    '%s --> %s' % (
                        srt_subtitles_timecode(start),
                        srt_subtitles_timecode(end)),
                    text,
                    os.linesep,
                ))
        return srt

    def _real_extract(self, url):
        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)

        author = qs.get('author', [None])[0]
        name = qs.get('name', [None])[0]
        clip_id = qs.get('clip', [None])[0]
        course_name = qs.get('course', [None])[0]

        if any(not f for f in (author, name, clip_id, course_name,)):
            raise ExtractorError('Invalid URL', expected=True)

        display_id = '%s-%s' % (name, clip_id)

        course = self._download_course(course_name, url, display_id)

        collection = course['modules']

        clip = None

        for module_ in collection:
            if name in (module_.get('moduleName'), module_.get('name')):
                for clip_ in module_.get('clips', []):
                    clip_index = clip_.get('clipIndex')
                    if clip_index is None:
                        clip_index = clip_.get('index')
                    if clip_index is None:
                        continue
                    if compat_str(clip_index) == clip_id:
                        clip = clip_
                        break

        if not clip:
            raise ExtractorError('Unable to resolve clip')

        title = clip['title']

        QUALITIES = {
            'low': {'width': 640, 'height': 480},
            'medium': {'width': 848, 'height': 640},
            'high': {'width': 1024, 'height': 768},
            'high-widescreen': {'width': 1280, 'height': 720},
        }

        QUALITIES_PREFERENCE = ('low', 'medium', 'high', 'high-widescreen',)
        quality_key = qualities(QUALITIES_PREFERENCE)

        AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities'])

        ALLOWED_QUALITIES = (
            AllowedQuality('webm', ['high', ]),
            AllowedQuality('mp4', ['low', 'medium', 'high', ]),
        )

        # Some courses also offer widescreen resolution for high quality (see
        # https://github.com/rg3/youtube-dl/issues/7766)
        widescreen = course.get('supportsWideScreenVideoFormats') is True
        best_quality = 'high-widescreen' if widescreen else 'high'
        if widescreen:
            for allowed_quality in ALLOWED_QUALITIES:
                allowed_quality.qualities.append(best_quality)

        # In order to minimize the number of calls to ViewClip API and reduce
        # the probability of being throttled or banned by Pluralsight we will request
        # only single format until formats listing was explicitly requested.
        if self._downloader.params.get('listformats', False):
            allowed_qualities = ALLOWED_QUALITIES
        else:
            def guess_allowed_qualities():
                req_format = self._downloader.params.get('format') or 'best'
                req_format_split = req_format.split('-', 1)
                if len(req_format_split) > 1:
                    req_ext, req_quality = req_format_split
                    req_quality = '-'.join(req_quality.split('-')[:2])
                    for allowed_quality in ALLOWED_QUALITIES:
                        if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities:
                            return (AllowedQuality(req_ext, (req_quality, )), )
                req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4'
                return (AllowedQuality(req_ext, (best_quality, )), )
            allowed_qualities = guess_allowed_qualities()

        formats = []
        for ext, qualities_ in allowed_qualities:
            for quality in qualities_:
                f = QUALITIES[quality].copy()
                clip_post = {
                    'author': author,
                    'includeCaptions': False,
                    'clipIndex': int(clip_id),
                    'courseName': course_name,
                    'locale': 'en',
                    'moduleName': name,
                    'mediaType': ext,
                    'quality': '%dx%d' % (f['width'], f['height']),
                }
                format_id = '%s-%s' % (ext, quality)
                viewclip = self._download_json(
                    '%s/video/clips/viewclip' % self._API_BASE, display_id,
                    'Downloading %s viewclip JSON' % format_id, fatal=False,
                    data=json.dumps(clip_post).encode('utf-8'),
                    headers={'Content-Type': 'application/json;charset=utf-8'})

                # Pluralsight tracks multiple sequential calls to ViewClip API and start
                # to return 429 HTTP errors after some time (see
                # https://github.com/rg3/youtube-dl/pull/6989). Moreover it may even lead
                # to account ban (see https://github.com/rg3/youtube-dl/issues/6842).
                # To somewhat reduce the probability of these consequences
                # we will sleep random amount of time before each call to ViewClip.
                self._sleep(
                    random.randint(2, 5), display_id,
                    '%(video_id)s: Waiting for %(timeout)s seconds to avoid throttling')

                if not viewclip:
                    continue

                clip_urls = viewclip.get('urls')
                if not isinstance(clip_urls, list):
                    continue

                for clip_url_data in clip_urls:
                    clip_url = clip_url_data.get('url')
                    if not clip_url:
                        continue
                    cdn = clip_url_data.get('cdn')
                    clip_f = f.copy()
                    clip_f.update({
                        'url': clip_url,
                        'ext': ext,
                        'format_id': '%s-%s' % (format_id, cdn) if cdn else format_id,
                        'quality': quality_key(quality),
                        'source_preference': int_or_none(clip_url_data.get('rank')),
                    })
                    formats.append(clip_f)

        self._sort_formats(formats)

        duration = int_or_none(
            clip.get('duration')) or parse_duration(clip.get('formattedDuration'))

        # TODO: other languages?
        subtitles = self.extract_subtitles(
            author, clip_id, 'en', name, duration, display_id)

        return {
            'id': clip.get('clipName') or clip['name'],
            'title': title,
            'duration': duration,
            'creator': author,
            'formats': formats,
            'subtitles': subtitles,
        }


class PluralsightCourseIE(PluralsightBaseIE):
    IE_NAME = 'pluralsight:course'
    _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/(?:library/)?courses/(?P<id>[^/]+)'
    _TESTS = [{
        # Free course from Pluralsight Starter Subscription for Microsoft TechNet
        # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz
        'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas',
        'info_dict': {
            'id': 'hosting-sql-server-windows-azure-iaas',
            'title': 'Hosting SQL Server in Microsoft Azure IaaS Fundamentals',
            'description': 'md5:61b37e60f21c4b2f91dc621a977d0986',
        },
        'playlist_count': 31,
    }, {
        # available without pluralsight account
        'url': 'https://www.pluralsight.com/courses/angularjs-get-started',
        'only_matching': True,
    }, {
        'url': 'https://app.pluralsight.com/library/courses/understanding-microsoft-azure-amazon-aws/table-of-contents',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        course_id = self._match_id(url)

        # TODO: PSM cookie

        course = self._download_course(course_id, url, course_id)

        title = course['title']
        course_name = course['name']
        course_data = course['modules']
        description = course.get('description') or course.get('shortDescription')

        entries = []
        for num, module in enumerate(course_data, 1):
            author = module.get('author')
            module_name = module.get('name')
            if not author or not module_name:
                continue
            for clip in module.get('clips', []):
                clip_index = int_or_none(clip.get('index'))
                if clip_index is None:
                    continue
                clip_url = update_url_query(
                    '%s/player' % self._API_BASE, query={
                        'mode': 'live',
                        'course': course_name,
                        'author': author,
                        'name': module_name,
                        'clip': clip_index,
                    })
                entries.append({
                    '_type': 'url_transparent',
                    'url': clip_url,
                    'ie_key': PluralsightIE.ie_key(),
                    'chapter': module.get('title'),
                    'chapter_number': num,
                    'chapter_id': module.get('moduleRef'),
                })

        return self.playlist_result(entries, course_id, title, description)