summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/tubetugraz.py
blob: d5dbf007b1fb31118570c5e2f0909f63b7360a00 (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
from .common import InfoExtractor
from ..utils import (
    float_or_none,
    parse_resolution,
    traverse_obj,
    urlencode_postdata,
    variadic,
)


class TubeTuGrazBaseIE(InfoExtractor):
    _NETRC_MACHINE = 'tubetugraz'

    _API_EPISODE = 'https://tube.tugraz.at/search/episode.json'
    _FORMAT_TYPES = ('presentation', 'presenter')

    def _perform_login(self, username, password):
        urlh = self._request_webpage(
            'https://tube.tugraz.at/Shibboleth.sso/Login?target=/paella/ui/index.html',
            None, fatal=False, note='downloading login page', errnote='unable to fetch login page')
        if not urlh:
            return

        response = self._download_webpage_handle(
            urlh.url, None, fatal=False, headers={'referer': urlh.url},
            note='logging in', errnote='unable to log in',
            data=urlencode_postdata({
                'lang': 'de',
                '_eventId_proceed': '',
                'j_username': username,
                'j_password': password,
            }))
        if not response:
            return

        content, urlh = response
        if urlh.url == 'https://tube.tugraz.at/paella/ui/index.html':
            return

        if not self._html_search_regex(
                r'<p\b[^>]*>(Bitte geben Sie einen OTP-Wert ein:)</p>',
                content, 'TFA prompt', default=None):
            self.report_warning('unable to login: incorrect password')
            return

        urlh = self._request_webpage(
            urlh.url, None, fatal=False, headers={'referer': urlh.url},
            note='logging in with TFA', errnote='unable to log in with TFA',
            data=urlencode_postdata({
                'lang': 'de',
                '_eventId_proceed': '',
                'j_tokenNumber': self._get_tfa_info(),
            }))
        if not urlh or urlh.url == 'https://tube.tugraz.at/paella/ui/index.html':
            return

        self.report_warning('unable to login: incorrect TFA code')

    def _extract_episode(self, episode_info):
        video_id = episode_info.get('id')
        formats = list(self._extract_formats(
            traverse_obj(episode_info, ('mediapackage', 'media', 'track')), video_id))

        title = traverse_obj(episode_info, ('mediapackage', 'title'), 'dcTitle')
        series_title = traverse_obj(episode_info, ('mediapackage', 'seriestitle'))
        creator = ', '.join(variadic(traverse_obj(
            episode_info, ('mediapackage', 'creators', 'creator'), 'dcCreator', default='')))
        return {
            'id': video_id,
            'title': title,
            'creator': creator or None,
            'duration': traverse_obj(episode_info, ('mediapackage', 'duration'), 'dcExtent'),
            'series': series_title,
            'series_id': traverse_obj(episode_info, ('mediapackage', 'series'), 'dcIsPartOf'),
            'episode': series_title and title,
            'formats': formats,
        }

    def _set_format_type(self, formats, fmt_type):
        for f in formats:
            f['format_note'] = fmt_type
            if not fmt_type.startswith(self._FORMAT_TYPES[0]):
                f['preference'] = -2
        return formats

    def _extract_formats(self, format_list, video_id):
        has_hls, has_dash = False, False

        for format_info in format_list or []:
            url = traverse_obj(format_info, ('tags', 'url'), 'url')
            if url is None:
                continue

            fmt_type = format_info.get('type') or 'unknown'
            transport = (format_info.get('transport') or 'https').lower()

            if transport == 'https':
                formats = [{
                    'url': url,
                    'abr': float_or_none(traverse_obj(format_info, ('audio', 'bitrate')), 1000),
                    'vbr': float_or_none(traverse_obj(format_info, ('video', 'bitrate')), 1000),
                    'fps': traverse_obj(format_info, ('video', 'framerate')),
                    **parse_resolution(traverse_obj(format_info, ('video', 'resolution'))),
                }]
            elif transport == 'hls':
                has_hls, formats = True, self._extract_m3u8_formats(
                    url, video_id, 'mp4', fatal=False, note=f'downloading {fmt_type} HLS manifest')
            elif transport == 'dash':
                has_dash, formats = True, self._extract_mpd_formats(
                    url, video_id, fatal=False, note=f'downloading {fmt_type} DASH manifest')
            else:
                # RTMP, HDS, SMOOTH, and unknown formats
                # - RTMP url fails on every tested entry until now
                # - HDS url 404's on every tested entry until now
                # - SMOOTH url 404's on every tested entry until now
                continue

            yield from self._set_format_type(formats, fmt_type)

        # TODO: Add test for these
        for fmt_type in self._FORMAT_TYPES:
            if not has_hls:
                hls_formats = self._extract_m3u8_formats(
                    f'https://wowza.tugraz.at/matterhorn_engage/smil:engage-player_{video_id}_{fmt_type}.smil/playlist.m3u8',
                    video_id, 'mp4', fatal=False, note=f'Downloading {fmt_type} HLS manifest', errnote=False) or []
                yield from self._set_format_type(hls_formats, fmt_type)

            if not has_dash:
                dash_formats = self._extract_mpd_formats(
                    f'https://wowza.tugraz.at/matterhorn_engage/smil:engage-player_{video_id}_{fmt_type}.smil/manifest_mpm4sav_mvlist.mpd',
                    video_id, fatal=False, note=f'Downloading {fmt_type} DASH manifest', errnote=False)
                yield from self._set_format_type(dash_formats, fmt_type)


class TubeTuGrazIE(TubeTuGrazBaseIE):
    IE_DESC = 'tube.tugraz.at'

    _VALID_URL = r'''(?x)
        https?://tube\.tugraz\.at/paella/ui/watch.html\?id=
        (?P<id>[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12})
    '''
    _TESTS = [
        {
            'url': 'https://tube.tugraz.at/paella/ui/watch.html?id=f2634392-e40e-4ac7-9ddc-47764aa23d40',
            'md5': 'a23a3d5c9aaca2b84932fdba66e17145',
            'info_dict': {
                'id': 'f2634392-e40e-4ac7-9ddc-47764aa23d40',
                'ext': 'mp4',
                'title': '#6 (23.11.2017)',
                'episode': '#6 (23.11.2017)',
                'series': '[INB03001UF] Einführung in die strukturierte Programmierung',
                'creator': 'Safran C',
                'duration': 3295818,
                'series_id': 'b1192fff-2aa7-4bf0-a5cf-7b15c3bd3b34',
            },
        }, {
            'url': 'https://tube.tugraz.at/paella/ui/watch.html?id=2df6d787-e56a-428d-8ef4-d57f07eef238',
            'md5': 'de0d854a56bf7318d2b693fe1adb89a5',
            'info_dict': {
                'id': '2df6d787-e56a-428d-8ef4-d57f07eef238',
                'title': 'TubeTuGraz video #2df6d787-e56a-428d-8ef4-d57f07eef238',
                'ext': 'mp4',
            },
            'expected_warnings': ['Extractor failed to obtain "title"'],
        },
    ]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        episode_data = self._download_json(
            self._API_EPISODE, video_id, query={'id': video_id, 'limit': 1}, note='Downloading episode metadata')

        episode_info = traverse_obj(episode_data, ('search-results', 'result'), default={'id': video_id})
        return self._extract_episode(episode_info)


class TubeTuGrazSeriesIE(TubeTuGrazBaseIE):
    _VALID_URL = r'''(?x)
        https?://tube\.tugraz\.at/paella/ui/browse\.html\?series=
        (?P<id>[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12})
    '''
    _TESTS = [{
        'url': 'https://tube.tugraz.at/paella/ui/browse.html?series=0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
        'id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
        'info_dict': {
            'id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
            'title': '[209351] Strassenwesen',
        },
        'playlist': [
            {
                'info_dict': {
                    'id': 'ee17ce5d-34e2-48b7-a76a-fed148614e11',
                    'series_id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
                    'ext': 'mp4',
                    'title': '#4 Detailprojekt',
                    'episode': '#4 Detailprojekt',
                    'series': '[209351] Strassenwesen',
                    'creator': 'Neuhold R',
                    'duration': 6127024,
                },
            },
            {
                'info_dict': {
                    'id': '87350498-799a-44d3-863f-d1518a98b114',
                    'series_id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
                    'ext': 'mp4',
                    'title': '#3 Generelles Projekt',
                    'episode': '#3 Generelles Projekt',
                    'series': '[209351] Strassenwesen',
                    'creator': 'Neuhold R',
                    'duration': 5374422,
                },
            },
            {
                'info_dict': {
                    'id': '778599ea-489e-4189-9e05-3b4888e19bcd',
                    'series_id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
                    'ext': 'mp4',
                    'title': '#2 Vorprojekt',
                    'episode': '#2 Vorprojekt',
                    'series': '[209351] Strassenwesen',
                    'creator': 'Neuhold R',
                    'duration': 5566404,
                },
            },
            {
                'info_dict': {
                    'id': '75e4c71c-d99d-4e56-b0e6-4f2bcdf11f29',
                    'series_id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
                    'ext': 'mp4',
                    'title': '#1 Variantenstudium',
                    'episode': '#1 Variantenstudium',
                    'series': '[209351] Strassenwesen',
                    'creator': 'Neuhold R',
                    'duration': 5420200,
                },
            },
        ],
        'min_playlist_count': 4,
    }]

    def _real_extract(self, url):
        playlist_id = self._match_id(url)
        episodes_data = self._download_json(
            self._API_EPISODE, playlist_id, query={'sid': playlist_id}, note='Downloading episode list')
        series_data = self._download_json(
            'https://tube.tugraz.at/series/series.json', playlist_id, fatal=False,
            note='downloading series metadata', errnote='failed to download series metadata',
            query={
                'seriesId': playlist_id,
                'count': 1,
                'sort': 'TITLE',
            })

        return self.playlist_result(
            map(self._extract_episode, episodes_data['search-results']['result']), playlist_id,
            traverse_obj(series_data, ('catalogs', 0, 'http://purl.org/dc/terms/', 'title', 0, 'value')))