aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/wdr.py
blob: d6ba254f5d8eb04de9775f6dbbbada7735c8d49e (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_str,
    compat_urlparse,
)
from ..utils import (
    determine_ext,
    ExtractorError,
    js_to_json,
    strip_jsonp,
    try_get,
    unified_strdate,
    update_url_query,
    urlhandle_detect_ext,
)


class WDRIE(InfoExtractor):
    _VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P<id>\d+)\.js'
    _GEO_COUNTRIES = ['DE']
    _TEST = {
        'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js',
        'info_dict': {
            'id': 'mdb-1140188',
            'display_id': 'dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100',
            'ext': 'mp4',
            'title': 'DFB-Team geht gut gelaunt ins Spiel gegen Polen',
            'description': 'Vor dem zweiten Gruppenspiel gegen Polen herrscht gute Stimmung im deutschen Team. Insbesondere Bastian Schweinsteiger strotzt vor Optimismus nach seinem Tor gegen die Ukraine.',
            'upload_date': '20160615',
        },
        'skip': 'Geo-restricted to Germany',
    }

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

        metadata = self._download_json(
            url, video_id, transform_source=strip_jsonp)

        is_live = metadata.get('mediaType') == 'live'

        tracker_data = metadata['trackerData']
        media_resource = metadata['mediaResource']

        formats = []

        # check if the metadata contains a direct URL to a file
        for kind, media_resource in media_resource.items():
            if kind not in ('dflt', 'alt'):
                continue

            for tag_name, medium_url in media_resource.items():
                if tag_name not in ('videoURL', 'audioURL'):
                    continue

                ext = determine_ext(medium_url)
                if ext == 'm3u8':
                    formats.extend(self._extract_m3u8_formats(
                        medium_url, video_id, 'mp4', 'm3u8_native',
                        m3u8_id='hls'))
                elif ext == 'f4m':
                    manifest_url = update_url_query(
                        medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
                    formats.extend(self._extract_f4m_formats(
                        manifest_url, video_id, f4m_id='hds', fatal=False))
                elif ext == 'smil':
                    formats.extend(self._extract_smil_formats(
                        medium_url, 'stream', fatal=False))
                else:
                    a_format = {
                        'url': medium_url
                    }
                    if ext == 'unknown_video':
                        urlh = self._request_webpage(
                            medium_url, video_id, note='Determining extension')
                        ext = urlhandle_detect_ext(urlh)
                        a_format['ext'] = ext
                    formats.append(a_format)

        self._sort_formats(formats)

        subtitles = {}
        caption_url = media_resource.get('captionURL')
        if caption_url:
            subtitles['de'] = [{
                'url': caption_url,
                'ext': 'ttml',
            }]

        title = tracker_data['trackerClipTitle']

        return {
            'id': tracker_data.get('trackerClipId', video_id),
            'title': self._live_title(title) if is_live else title,
            'alt_title': tracker_data.get('trackerClipSubcategory'),
            'formats': formats,
            'subtitles': subtitles,
            'upload_date': unified_strdate(tracker_data.get('trackerClipAirTime')),
            'is_live': is_live,
        }


class WDRPageIE(InfoExtractor):
    _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
    _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
    _VALID_URL = r'https?://(?:www\d?\.)?(?:wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL

    _TESTS = [
        {
            'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html',
            # HDS download, MD5 is unstable
            'info_dict': {
                'id': 'mdb-1058683',
                'ext': 'flv',
                'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100',
                'title': 'Geheimnis Aachener Dom',
                'alt_title': 'Doku am Freitag',
                'upload_date': '20160304',
                'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
                'is_live': False,
                'subtitles': {'de': [{
                    'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml',
                    'ext': 'ttml',
                }]},
            },
            'skip': 'HTTP Error 404: Not Found',
        },
        {
            'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
            'md5': 'f4c1f96d01cf285240f53ea4309663d8',
            'info_dict': {
                'id': 'mdb-1072000',
                'ext': 'mp3',
                'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100',
                'title': 'Schriftstellerin Juli Zeh',
                'alt_title': 'WDR 3 Gespräch am Samstag',
                'upload_date': '20160312',
                'description': 'md5:e127d320bc2b1f149be697ce044a3dd7',
                'is_live': False,
                'subtitles': {}
            },
            'skip': 'HTTP Error 404: Not Found',
        },
        {
            'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
            'info_dict': {
                'id': 'mdb-1406149',
                'ext': 'mp4',
                'title': r're:^WDR Fernsehen im Livestream \(nur in Deutschland erreichbar\) [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
                'alt_title': 'WDR Fernsehen Live',
                'upload_date': '20150101',
                'is_live': True,
            },
            'params': {
                'skip_download': True,  # m3u8 download
            },
        },
        {
            'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
            'playlist_mincount': 7,
            'info_dict': {
                'id': 'aktuelle-stunde-120',
            },
        },
        {
            'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
            'info_dict': {
                'id': 'mdb-1552552',
                'ext': 'mp4',
                'upload_date': 're:^[0-9]{8}$',
                'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
            },
            'skip': 'The id changes from week to week because of the new episode'
        },
        {
            'url': 'http://www.wdrmaus.de/filme/sachgeschichten/achterbahn.php5',
            'md5': '803138901f6368ee497b4d195bb164f2',
            'info_dict': {
                'id': 'mdb-186083',
                'ext': 'mp4',
                'upload_date': '20130919',
                'title': 'Sachgeschichte - Achterbahn ',
            },
        },
        {
            'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
            # Live stream, MD5 unstable
            'info_dict': {
                'id': 'mdb-869971',
                'ext': 'mp4',
                'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
                'upload_date': '20160101',
            },
            'params': {
                'skip_download': True,  # m3u8 download
            }
        },
        {
            'url': 'http://www.sportschau.de/handballem2018/handball-nationalmannschaft-em-stolperstein-vorrunde-100.html',
            'info_dict': {
                'id': 'mdb-1556012',
                'ext': 'mp4',
                'title': 'DHB-Vizepräsident Bob Hanning - "Die Weltspitze ist extrem breit"',
                'upload_date': '20180111',
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
            'only_matching': True,
        }
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        display_id = mobj.group('display_id')
        webpage = self._download_webpage(url, display_id)

        entries = []

        # Article with several videos

        # for wdr.de the data-extension is in a tag with the class "mediaLink"
        # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
        # for wdrmaus, in a tag with the class "videoButton" (previously a link
        # to the page in a multiline "videoLink"-tag)
        for mobj in re.finditer(
            r'''(?sx)class=
                    (?:
                        (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+|
                        (["\'])videoLink\b.*?\2[\s]*>\n[^\n]*
                    )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3
                    ''', webpage):
            media_link_obj = self._parse_json(
                mobj.group('data'), display_id, transform_source=js_to_json,
                fatal=False)
            if not media_link_obj:
                continue
            jsonp_url = try_get(
                media_link_obj, lambda x: x['mediaObj']['url'], compat_str)
            if jsonp_url:
                entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key()))

        # Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html)
        if not entries:
            entries = [
                self.url_result(
                    compat_urlparse.urljoin(url, mobj.group('href')),
                    ie=WDRPageIE.ie_key())
                for mobj in re.finditer(
                    r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension=',
                    webpage) if re.match(self._PAGE_REGEX, mobj.group('href'))
            ]

        return self.playlist_result(entries, playlist_id=display_id)


class WDRElefantIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)'
    _TEST = {
        'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015',
        'info_dict': {
            'title': 'Folge Oster-Spezial 2015',
            'id': 'mdb-1088195',
            'ext': 'mp4',
            'age_limit': None,
            'upload_date': '20150406'
        },
        'params': {
            'skip_download': True,
        },
    }

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

        # Table of Contents seems to always be at this address, so fetch it directly.
        # The website fetches configurationJS.php5, which links to tableOfContentsJS.php5.
        table_of_contents = self._download_json(
            'https://www.wdrmaus.de/elefantenseite/data/tableOfContentsJS.php5',
            display_id)
        if display_id not in table_of_contents:
            raise ExtractorError(
                'No entry in site\'s table of contents for this URL. '
                'Is the fragment part of the URL (after the #) correct?',
                expected=True)
        xml_metadata_path = table_of_contents[display_id]['xmlPath']
        xml_metadata = self._download_xml(
            'https://www.wdrmaus.de/elefantenseite/' + xml_metadata_path,
            display_id)
        zmdb_url_element = xml_metadata.find('./movie/zmdb_url')
        if zmdb_url_element is None:
            raise ExtractorError(
                '%s is not a video' % display_id, expected=True)
        return self.url_result(zmdb_url_element.text, ie=WDRIE.ie_key())


class WDRMobileIE(InfoExtractor):
    _VALID_URL = r'''(?x)
        https?://mobile-ondemand\.wdr\.de/
        .*?/fsk(?P<age_limit>[0-9]+)
        /[0-9]+/[0-9]+/
        (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
    IE_NAME = 'wdr:mobile'
    _TEST = {
        'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
        'info_dict': {
            'title': '4283021',
            'id': '421735',
            'ext': 'mp4',
            'age_limit': 0,
        },
        'skip': 'Problems with loading data.'
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        return {
            'id': mobj.group('id'),
            'title': mobj.group('title'),
            'age_limit': int(mobj.group('age_limit')),
            'url': url,
            'http_headers': {
                'User-Agent': 'mobile',
            },
        }