aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/orf.py
blob: 4fed83bd615172140f7e163534cee58924b8bc0d (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
# coding: utf-8
from __future__ import unicode_literals

import json
import re
import calendar
import datetime

from .common import InfoExtractor
from ..utils import (
    HEADRequest,
    unified_strdate,
    ExtractorError,
)


class ORFTVthekIE(InfoExtractor):
    IE_NAME = 'orf:tvthek'
    IE_DESC = 'ORF TVthek'
    _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics?/.+?|program/[^/]+)/(?P<id>\d+)'

    _TESTS = [{
        'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
        'playlist': [{
            'md5': '2942210346ed779588f428a92db88712',
            'info_dict': {
                'id': '8896777',
                'ext': 'mp4',
                'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
                'description': 'md5:c1272f0245537812d4e36419c207b67d',
                'duration': 2668,
                'upload_date': '20141208',
            },
        }],
        'skip': 'Blocked outside of Austria / Germany',
    }, {
        'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
        'playlist': [{
            'md5': '68f543909aea49d621dfc7703a11cfaf',
            'info_dict': {
                'id': '7982259',
                'ext': 'mp4',
                'title': 'Best of Ingrid Thurnher',
                'upload_date': '20140527',
                'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
            }
        }],
        '_skip': 'Blocked outside of Austria / Germany',
    }]

    def _real_extract(self, url):
        playlist_id = self._match_id(url)
        webpage = self._download_webpage(url, playlist_id)

        data_json = self._search_regex(
            r'initializeAdworx\((.+?)\);\n', webpage, 'video info')
        all_data = json.loads(data_json)

        def get_segments(all_data):
            for data in all_data:
                if data['name'] in (
                        'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM',
                        'Tracker::EPISODE_DETAIL_PAGE_OVER_TOPIC'):
                    return data['values']['segments']

        sdata = get_segments(all_data)
        if not sdata:
            raise ExtractorError('Unable to extract segments')

        def quality_to_int(s):
            m = re.search('([0-9]+)', s)
            if m is None:
                return -1
            return int(m.group(1))

        entries = []
        for sd in sdata:
            video_id = sd['id']
            formats = [{
                'preference': -10 if fd['delivery'] == 'hls' else None,
                'format_id': '%s-%s-%s' % (
                    fd['delivery'], fd['quality'], fd['quality_string']),
                'url': fd['src'],
                'protocol': fd['protocol'],
                'quality': quality_to_int(fd['quality']),
            } for fd in sd['playlist_item_array']['sources']]

            # Check for geoblocking.
            # There is a property is_geoprotection, but that's always false
            geo_str = sd.get('geoprotection_string')
            if geo_str:
                try:
                    http_url = next(
                        f['url']
                        for f in formats
                        if re.match(r'^https?://.*\.mp4$', f['url']))
                except StopIteration:
                    pass
                else:
                    req = HEADRequest(http_url)
                    self._request_webpage(
                        req, video_id,
                        note='Testing for geoblocking',
                        errnote=((
                            'This video seems to be blocked outside of %s. '
                            'You may want to try the streaming-* formats.')
                            % geo_str),
                        fatal=False)

            self._sort_formats(formats)

            upload_date = unified_strdate(sd['created_date'])
            entries.append({
                '_type': 'video',
                'id': video_id,
                'title': sd['header'],
                'formats': formats,
                'description': sd.get('description'),
                'duration': int(sd['duration_in_seconds']),
                'upload_date': upload_date,
                'thumbnail': sd.get('image_full_url'),
            })

        return {
            '_type': 'playlist',
            'entries': entries,
            'id': playlist_id,
        }


# Audios on ORF radio are only available for 7 days, so we can't add tests.


class ORFOE1IE(InfoExtractor):
    IE_NAME = 'orf:oe1'
    IE_DESC = 'Radio Österreich 1'
    _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'

    def _real_extract(self, url):
        show_id = self._match_id(url)
        data = self._download_json(
            'http://oe1.orf.at/programm/%s/konsole' % show_id,
            show_id
        )

        timestamp = datetime.datetime.strptime('%s %s' % (
            data['item']['day_label'],
            data['item']['time']
        ), '%d.%m.%Y %H:%M')
        unix_timestamp = calendar.timegm(timestamp.utctimetuple())

        return {
            'id': show_id,
            'title': data['item']['title'],
            'url': data['item']['url_stream'],
            'ext': 'mp3',
            'description': data['item'].get('info'),
            'timestamp': unix_timestamp
        }


class ORFFM4IE(InfoExtractor):
    IE_DESC = 'orf:fm4'
    IE_DESC = 'radio FM4'
    _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)'

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        show_date = mobj.group('date')
        show_id = mobj.group('show')

        data = self._download_json(
            'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id),
            show_id
        )

        def extract_entry_dict(info, title, subtitle):
            return {
                'id': info['loopStreamId'].replace('.mp3', ''),
                'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'],
                'title': title,
                'description': subtitle,
                'duration': (info['end'] - info['start']) / 1000,
                'timestamp': info['start'] / 1000,
                'ext': 'mp3'
            }

        entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]

        return {
            '_type': 'playlist',
            'id': show_id,
            'title': data['title'],
            'description': data['subtitle'],
            'entries': entries
        }