aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/lecturio.py
blob: 24f78d928449b999f09acec8337297fa62da8f55 (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    determine_ext,
    extract_attributes,
    ExtractorError,
    float_or_none,
    int_or_none,
    str_or_none,
    url_or_none,
    urlencode_postdata,
    urljoin,
)


class LecturioBaseIE(InfoExtractor):
    _LOGIN_URL = 'https://app.lecturio.com/en/login'
    _NETRC_MACHINE = 'lecturio'

    def _real_initialize(self):
        self._login()

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

        # Sets some cookies
        _, urlh = self._download_webpage_handle(
            self._LOGIN_URL, None, 'Downloading login popup')

        def is_logged(url_handle):
            return self._LOGIN_URL not in compat_str(url_handle.geturl())

        # Already logged in
        if is_logged(urlh):
            return

        login_form = {
            'signin[email]': username,
            'signin[password]': password,
            'signin[remember]': 'on',
        }

        response, urlh = self._download_webpage_handle(
            self._LOGIN_URL, None, 'Logging in',
            data=urlencode_postdata(login_form))

        # Logged in successfully
        if is_logged(urlh):
            return

        errors = self._html_search_regex(
            r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
            'errors', default=None)
        if errors:
            raise ExtractorError('Unable to login: %s' % errors, expected=True)
        raise ExtractorError('Unable to log in')


class LecturioIE(LecturioBaseIE):
    _VALID_URL = r'''(?x)
                    https://
                        (?:
                            app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture|
                            (?:www\.)?lecturio\.de/[^/]+/(?P<id_de>[^/?#&]+)\.vortrag
                        )
                    '''
    _TESTS = [{
        'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
        'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
        'info_dict': {
            'id': '39634',
            'ext': 'mp4',
            'title': 'Important Concepts and Terms – Introduction to Microbiology',
        },
        'skip': 'Requires lecturio account credentials',
    }, {
        'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
        'only_matching': True,
    }]

    _CC_LANGS = {
        'German': 'de',
        'English': 'en',
        'Spanish': 'es',
        'French': 'fr',
        'Polish': 'pl',
        'Russian': 'ru',
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        display_id = mobj.group('id') or mobj.group('id_de')

        webpage = self._download_webpage(
            'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
            display_id)

        lecture_id = self._search_regex(
            r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id')

        api_url = self._search_regex(
            r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
            'api url', group='url')

        video = self._download_json(api_url, display_id)

        title = video['title'].strip()

        formats = []
        for format_ in video['content']['media']:
            if not isinstance(format_, dict):
                continue
            file_ = format_.get('file')
            if not file_:
                continue
            ext = determine_ext(file_)
            if ext == 'smil':
                # smil contains only broken RTMP formats anyway
                continue
            file_url = url_or_none(file_)
            if not file_url:
                continue
            label = str_or_none(format_.get('label'))
            filesize = int_or_none(format_.get('fileSize'))
            formats.append({
                'url': file_url,
                'format_id': label,
                'filesize': float_or_none(filesize, invscale=1000)
            })
        self._sort_formats(formats)

        subtitles = {}
        automatic_captions = {}
        cc = self._parse_json(
            self._search_regex(
                r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles',
                default='{}'), display_id, fatal=False)
        for cc_label, cc_url in cc.items():
            cc_url = url_or_none(cc_url)
            if not cc_url:
                continue
            lang = self._search_regex(
                r'/([a-z]{2})_', cc_url, 'lang',
                default=cc_label.split()[0] if cc_label else 'en')
            original_lang = self._search_regex(
                r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang',
                default=None)
            sub_dict = (automatic_captions
                        if 'auto-translated' in cc_label or original_lang
                        else subtitles)
            sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
                'url': cc_url,
            })

        return {
            'id': lecture_id,
            'title': title,
            'formats': formats,
            'subtitles': subtitles,
            'automatic_captions': automatic_captions,
        }


class LecturioCourseIE(LecturioBaseIE):
    _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course'
    _TEST = {
        'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
        'info_dict': {
            'id': 'microbiology-introduction',
            'title': 'Microbiology: Introduction',
        },
        'playlist_count': 45,
        'skip': 'Requires lecturio account credentials',
    }

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

        webpage = self._download_webpage(url, display_id)

        entries = []
        for mobj in re.finditer(
                r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>',
                webpage):
            params = extract_attributes(mobj.group(0))
            lecture_url = urljoin(url, params.get('data-url'))
            lecture_id = params.get('data-id')
            entries.append(self.url_result(
                lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))

        title = self._search_regex(
            r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage,
            'title', default=None)

        return self.playlist_result(entries, display_id, title)


class LecturioDeCourseIE(LecturioBaseIE):
    _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
    _TEST = {
        'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
        'only_matching': True,
    }

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

        webpage = self._download_webpage(url, display_id)

        entries = []
        for mobj in re.finditer(
                r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
                webpage):
            lecture_url = urljoin(url, mobj.group('url'))
            lecture_id = mobj.group('id')
            entries.append(self.url_result(
                lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))

        title = self._search_regex(
            r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)

        return self.playlist_result(entries, display_id, title)