aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/polskieradio.py
blob: 5ff173774a410bf0eba85069f6f1ed33cd583e7b (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
# coding: utf-8
from __future__ import unicode_literals

import itertools
import re

from .common import InfoExtractor
from ..compat import (
    compat_str,
    compat_urllib_parse_unquote,
    compat_urlparse
)
from ..utils import (
    extract_attributes,
    int_or_none,
    strip_or_none,
    unified_timestamp,
)


class PolskieRadioIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+/\d+/Artykul/(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://www.polskieradio.pl/7/5102/Artykul/1587943,Prof-Andrzej-Nowak-o-historii-nie-da-sie-myslec-beznamietnie',
        'info_dict': {
            'id': '1587943',
            'title': 'Prof. Andrzej Nowak: o historii nie da się myśleć beznamiętnie',
            'description': 'md5:12f954edbf3120c5e7075e17bf9fc5c5',
        },
        'playlist': [{
            'md5': '2984ee6ce9046d91fc233bc1a864a09a',
            'info_dict': {
                'id': '1540576',
                'ext': 'mp3',
                'title': 'md5:d4623290d4ac983bf924061c75c23a0d',
                'timestamp': 1456594200,
                'upload_date': '20160227',
                'duration': 2364,
                'thumbnail': 're:^https?://static\.prsa\.pl/images/.*\.jpg$'
            },
        }],
    }, {
        'url': 'http://www.polskieradio.pl/265/5217/Artykul/1635803,Euro-2016-nie-ma-miejsca-na-blad-Polacy-graja-ze-Szwajcaria-o-cwiercfinal',
        'info_dict': {
            'id': '1635803',
            'title': 'Euro 2016: nie ma miejsca na błąd. Polacy grają ze Szwajcarią o ćwierćfinał',
            'description': 'md5:01cb7d0cad58664095d72b51a1ebada2',
        },
        'playlist_mincount': 12,
    }, {
        'url': 'http://polskieradio.pl/9/305/Artykul/1632955,Bardzo-popularne-slowo-remis',
        'only_matching': True,
    }, {
        'url': 'http://www.polskieradio.pl/7/5102/Artykul/1587943',
        'only_matching': True,
    }, {
        # with mp4 video
        'url': 'http://www.polskieradio.pl/9/299/Artykul/1634903,Brexit-Leszek-Miller-swiat-sie-nie-zawali-Europa-bedzie-trwac-dalej',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(url, playlist_id)

        content = self._search_regex(
            r'(?s)<div[^>]+class="audio atarticle"[^>]*>(.+?)<script>',
            webpage, 'content')

        timestamp = unified_timestamp(self._html_search_regex(
            r'(?s)<span[^>]+id="datetime2"[^>]*>(.+?)</span>',
            webpage, 'timestamp', fatal=False))

        thumbnail_url = self._og_search_thumbnail(webpage)

        entries = []

        media_urls = set()

        for data_media in re.findall(r'<[^>]+data-media=({[^>]+})', content):
            media = self._parse_json(data_media, playlist_id, fatal=False)
            if not media.get('file') or not media.get('desc'):
                continue
            media_url = self._proto_relative_url(media['file'], 'http:')
            if media_url in media_urls:
                continue
            media_urls.add(media_url)
            entries.append({
                'id': compat_str(media['id']),
                'url': media_url,
                'title': compat_urllib_parse_unquote(media['desc']),
                'duration': int_or_none(media.get('length')),
                'vcodec': 'none' if media.get('provider') == 'audio' else None,
                'timestamp': timestamp,
                'thumbnail': thumbnail_url
            })

        title = self._og_search_title(webpage).strip()
        description = strip_or_none(self._og_search_description(webpage))

        return self.playlist_result(entries, playlist_id, title, description)


class PolskieRadioCategoryIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+(?:,[^/]+)?/(?P<id>\d+)'
    _TESTS = [{
        'url': 'http://www.polskieradio.pl/7/5102,HISTORIA-ZYWA',
        'info_dict': {
            'id': '5102',
            'title': 'HISTORIA ŻYWA',
        },
        'playlist_mincount': 38,
    }, {
        'url': 'http://www.polskieradio.pl/7/4807',
        'info_dict': {
            'id': '4807',
            'title': 'Vademecum 1050. rocznicy Chrztu Polski'
        },
        'playlist_mincount': 5
    }, {
        'url': 'http://www.polskieradio.pl/7/129,Sygnaly-dnia?ref=source',
        'only_matching': True
    }, {
        'url': 'http://www.polskieradio.pl/37,RedakcjaKatolicka/4143,Kierunek-Krakow',
        'info_dict': {
            'id': '4143',
            'title': 'Kierunek Kraków',
        },
        'playlist_mincount': 61
    }, {
        'url': 'http://www.polskieradio.pl/10,czworka/214,muzyka',
        'info_dict': {
            'id': '214',
            'title': 'Muzyka',
        },
        'playlist_mincount': 61
    }, {
        'url': 'http://www.polskieradio.pl/7,Jedynka/5102,HISTORIA-ZYWA',
        'only_matching': True,
    }, {
        'url': 'http://www.polskieradio.pl/8,Dwojka/196,Publicystyka',
        'only_matching': True,
    }]

    @classmethod
    def suitable(cls, url):
        return False if PolskieRadioIE.suitable(url) else super(PolskieRadioCategoryIE, cls).suitable(url)

    def _entries(self, url, page, category_id):
        content = page
        for page_num in itertools.count(2):
            for a_entry, entry_id in re.findall(
                    r'(?s)<article[^>]+>.*?(<a[^>]+href=["\']/\d+/\d+/Artykul/(\d+)[^>]+>).*?</article>',
                    content):
                entry = extract_attributes(a_entry)
                href = entry.get('href')
                if not href:
                    continue
                yield self.url_result(
                    compat_urlparse.urljoin(url, href), PolskieRadioIE.ie_key(),
                    entry_id, entry.get('title'))
            mobj = re.search(
                r'<div[^>]+class=["\']next["\'][^>]*>\s*<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1',
                content)
            if not mobj:
                break
            next_url = compat_urlparse.urljoin(url, mobj.group('url'))
            content = self._download_webpage(
                next_url, category_id, 'Downloading page %s' % page_num)

    def _real_extract(self, url):
        category_id = self._match_id(url)
        webpage = self._download_webpage(url, category_id)
        title = self._html_search_regex(
            r'<title>([^<]+) - [^<]+ - [^<]+</title>',
            webpage, 'title', fatal=False)
        return self.playlist_result(
            self._entries(url, webpage, category_id),
            category_id, title)