aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/wdr.py
blob: 6174eb19fc70e775a1bf1efb2b2bebb76dc3d903 (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 ..utils import (
    determine_ext,
    js_to_json,
    strip_jsonp,
    unified_strdate,
    ExtractorError,
)


class WDRIE(InfoExtractor):
    _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
    _PAGE_REGEX = r'/mediathek/(?P<media_type>[^/]+)/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
    _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.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'
                }]},
            },
        },
        {
            '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': {}
            },
        },
        {
            'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
            'info_dict': {
                'id': 'mdb-103364',
                'ext': 'mp4',
                'display_id': 'index',
                'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
                'alt_title': 'WDR Fernsehen Live',
                'upload_date': None,
                'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
                'is_live': True,
                'subtitles': {}
            },
            'params': {
                'skip_download': True,  # m3u8 download
            },
        },
        {
            'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
            'playlist_mincount': 8,
            'info_dict': {
                'id': 'aktuelle-stunde/aktuelle-stunde-120',
            },
        },
        {
            'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
            'info_dict': {
                'id': 'mdb-1096487',
                'ext': 'flv',
                'upload_date': 're:^[0-9]{8}$',
                'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
                'description': '- Die Sendung mit der Maus -',
            },
            'skip': 'The id changes from week to week because of the new episode'
        },
        {
            'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5',
            # HDS download, MD5 is unstable
            'info_dict': {
                'id': 'mdb-186083',
                'ext': 'flv',
                'upload_date': '20130919',
                'title': 'Sachgeschichte - Achterbahn ',
                'description': '- Die Sendung mit der Maus -',
            },
        },
    ]

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

        # for wdr.de the data-extension is in a tag with the class "mediaLink"
        # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
        json_metadata = self._html_search_regex(
            r'class=(?:"mediaLink\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
            webpage, 'media link', default=None, flags=re.MULTILINE)

        if not json_metadata:
            entries = [
                self.url_result(page_url + href[0], 'WDR')
                for href in re.findall(
                    r'<a href="(%s)"[^>]+data-extension=' % self._PAGE_REGEX,
                    webpage)
            ]

            if entries:  # Playlist page
                return self.playlist_result(entries, playlist_id=display_id)

            raise ExtractorError('No downloadable streams found', expected=True)

        media_link_obj = self._parse_json(json_metadata, display_id,
                                          transform_source=js_to_json)
        jsonp_url = media_link_obj['mediaObj']['url']

        metadata = self._download_json(
            jsonp_url, 'metadata', transform_source=strip_jsonp)

        metadata_tracker_data = metadata['trackerData']
        metadata_media_resource = metadata['mediaResource']

        formats = []

        # check if the metadata contains a direct URL to a file
        metadata_media_alt = metadata_media_resource.get('alt')
        if metadata_media_alt:
            for tag_name in ['videoURL', 'audioURL']:
                if tag_name in metadata_media_alt:
                    alt_url = metadata_media_alt[tag_name]
                    if determine_ext(alt_url) == 'm3u8':
                        m3u_fmt = self._extract_m3u8_formats(
                            alt_url, display_id, 'mp4', 'm3u8_native',
                            m3u8_id='hls')
                        formats.extend(m3u_fmt)
                    else:
                        formats.append({
                            'url': alt_url
                        })

        # check if there are flash-streams for this video
        if 'dflt' in metadata_media_resource and 'videoURL' in metadata_media_resource['dflt']:
            video_url = metadata_media_resource['dflt']['videoURL']
            if video_url.endswith('.f4m'):
                full_video_url = video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
                formats.extend(self._extract_f4m_formats(full_video_url, display_id, f4m_id='hds', fatal=False))
            elif video_url.endswith('.smil'):
                formats.extend(self._extract_smil_formats(video_url, 'stream', fatal=False))

        subtitles = {}
        caption_url = metadata_media_resource.get('captionURL')
        if caption_url:
            subtitles['de'] = [{
                'url': caption_url
            }]

        title = metadata_tracker_data.get('trackerClipTitle')
        is_live = url_type == 'live'

        if is_live:
            title = self._live_title(title)
            upload_date = None
        elif 'trackerClipAirTime' in metadata_tracker_data:
            upload_date = metadata_tracker_data['trackerClipAirTime']
        else:
            upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')

        if upload_date:
            upload_date = unified_strdate(upload_date)

        self._sort_formats(formats)

        return {
            'id': metadata_tracker_data.get('trackerClipId', display_id),
            'display_id': display_id,
            'title': title,
            'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
            'formats': formats,
            'upload_date': upload_date,
            'description': self._html_search_meta('Description', webpage),
            'is_live': is_live,
            'subtitles': subtitles,
        }


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',
            },
        }