aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tvp.py
blob: 536b580fc5b13b80589ffc355dc0b72281c6cb47 (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    clean_html,
    get_element_by_attribute,
    ExtractorError,
)


class TVPIE(InfoExtractor):
    IE_NAME = 'tvp'
    IE_DESC = 'Telewizja Polska'
    _VALID_URL = r'https?://[^/]+\.tvp\.(?:pl|info)/(?:video/(?:[^,\s]*,)*|(?:(?!\d+/)[^/]+/)*)(?P<id>\d+)'

    _TESTS = [{
        'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536',
        'md5': 'a21eb0aa862f25414430f15fdfb9e76c',
        'info_dict': {
            'id': '194536',
            'ext': 'mp4',
            'title': 'Czas honoru, odc. 13 – Władek',
            'description': 'md5:437f48b93558370b031740546b696e24',
        },
    }, {
        'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
        'md5': 'b0005b542e5b4de643a9690326ab1257',
        'info_dict': {
            'id': '17916176',
            'ext': 'mp4',
            'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
            'description': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
        },
    }, {
        # page id is not the same as video id(#7799)
        'url': 'https://wiadomosci.tvp.pl/33908820/28092017-1930',
        'md5': '84cd3c8aec4840046e5ab712416b73d0',
        'info_dict': {
            'id': '33908820',
            'ext': 'mp4',
            'title': 'Wiadomości, 28.09.2017, 19:30',
            'description': 'Wydanie główne codziennego serwisu informacyjnego.'
        },
        'skip': 'HTTP Error 404: Not Found',
    }, {
        'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
        'only_matching': True,
    }, {
        'url': 'http://wiadomosci.tvp.pl/25169746/24052016-1200',
        'only_matching': True,
    }, {
        'url': 'http://krakow.tvp.pl/25511623/25lecie-mck-wyjatkowe-miejsce-na-mapie-krakowa',
        'only_matching': True,
    }, {
        'url': 'http://teleexpress.tvp.pl/25522307/wierni-wzieli-udzial-w-procesjach',
        'only_matching': True,
    }, {
        'url': 'http://sport.tvp.pl/25522165/krychowiak-uspokaja-w-sprawie-kontuzji-dwa-tygodnie-to-maksimum',
        'only_matching': True,
    }, {
        'url': 'http://www.tvp.info/25511919/trwa-rewolucja-wladza-zdecydowala-sie-na-pogwalcenie-konstytucji',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        page_id = self._match_id(url)
        webpage = self._download_webpage(url, page_id)
        video_id = self._search_regex([
            r'<iframe[^>]+src="[^"]*?object_id=(\d+)',
            r"object_id\s*:\s*'(\d+)'",
            r'data-video-id="(\d+)"'], webpage, 'video id', default=page_id)
        return {
            '_type': 'url_transparent',
            'url': 'tvp:' + video_id,
            'description': self._og_search_description(
                webpage, default=None) or self._html_search_meta(
                'description', webpage, default=None),
            'thumbnail': self._og_search_thumbnail(webpage, default=None),
            'ie_key': 'TVPEmbed',
        }


class TVPEmbedIE(InfoExtractor):
    IE_NAME = 'tvp:embed'
    IE_DESC = 'Telewizja Polska'
    _VALID_URL = r'(?:tvp:|https?://[^/]+\.tvp\.(?:pl|info)/sess/tvplayer\.php\?.*?object_id=)(?P<id>\d+)'

    _TESTS = [{
        'url': 'tvp:194536',
        'md5': 'a21eb0aa862f25414430f15fdfb9e76c',
        'info_dict': {
            'id': '194536',
            'ext': 'mp4',
            'title': 'Czas honoru, odc. 13 – Władek',
        },
    }, {
        # not available
        'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268',
        'md5': '8c9cd59d16edabf39331f93bf8a766c7',
        'info_dict': {
            'id': '22670268',
            'ext': 'mp4',
            'title': 'Panorama, 07.12.2015, 15:40',
        },
        'skip': 'Transmisja została zakończona lub materiał niedostępny',
    }, {
        'url': 'tvp:22670268',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(
            'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id)

        error = self._html_search_regex(
            r'(?s)<p[^>]+\bclass=["\']notAvailable__text["\'][^>]*>(.+?)</p>',
            webpage, 'error', default=None) or clean_html(
            get_element_by_attribute('class', 'msg error', webpage))
        if error:
            raise ExtractorError('%s said: %s' % (
                self.IE_NAME, clean_html(error)), expected=True)

        title = self._search_regex(
            r'name\s*:\s*([\'"])Title\1\s*,\s*value\s*:\s*\1(?P<title>.+?)\1',
            webpage, 'title', group='title')
        series_title = self._search_regex(
            r'name\s*:\s*([\'"])SeriesTitle\1\s*,\s*value\s*:\s*\1(?P<series>.+?)\1',
            webpage, 'series', group='series', default=None)
        if series_title:
            title = '%s, %s' % (series_title, title)

        thumbnail = self._search_regex(
            r"poster\s*:\s*'([^']+)'", webpage, 'thumbnail', default=None)

        video_url = self._search_regex(
            r'0:{src:([\'"])(?P<url>.*?)\1', webpage,
            'formats', group='url', default=None)
        if not video_url or 'material_niedostepny.mp4' in video_url:
            video_url = self._download_json(
                'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id,
                video_id)['video_url']

        formats = []
        video_url_base = self._search_regex(
            r'(https?://.+?/video)(?:\.(?:ism|f4m|m3u8)|-\d+\.mp4)',
            video_url, 'video base url', default=None)
        if video_url_base:
            # TODO: <Group> found instead of <AdaptationSet> in MPD manifest.
            # It's not mentioned in MPEG-DASH standard. Figure that out.
            # formats.extend(self._extract_mpd_formats(
            #     video_url_base + '.ism/video.mpd',
            #     video_id, mpd_id='dash', fatal=False))
            formats.extend(self._extract_ism_formats(
                video_url_base + '.ism/Manifest',
                video_id, 'mss', fatal=False))
            formats.extend(self._extract_f4m_formats(
                video_url_base + '.ism/video.f4m',
                video_id, f4m_id='hds', fatal=False))
            m3u8_formats = self._extract_m3u8_formats(
                video_url_base + '.ism/video.m3u8', video_id,
                'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
            self._sort_formats(m3u8_formats)
            m3u8_formats = list(filter(
                lambda f: f.get('vcodec') != 'none', m3u8_formats))
            formats.extend(m3u8_formats)
            for i, m3u8_format in enumerate(m3u8_formats, 2):
                http_url = '%s-%d.mp4' % (video_url_base, i)
                if self._is_valid_url(http_url, video_id):
                    f = m3u8_format.copy()
                    f.update({
                        'url': http_url,
                        'format_id': f['format_id'].replace('hls', 'http'),
                        'protocol': 'http',
                    })
                    formats.append(f)
        else:
            formats = [{
                'format_id': 'direct',
                'url': video_url,
                'ext': determine_ext(video_url, 'mp4'),
            }]

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'thumbnail': thumbnail,
            'formats': formats,
        }


class TVPSeriesIE(InfoExtractor):
    IE_NAME = 'tvp:series'
    _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$'

    _TESTS = [{
        'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem',
        'info_dict': {
            'title': 'Ogniem i mieczem',
            'id': '4278026',
        },
        'playlist_count': 4,
    }, {
        'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat',
        'info_dict': {
            'title': 'Boso przez świat',
            'id': '9329207',
        },
        'playlist_count': 86,
    }]

    def _real_extract(self, url):
        display_id = self._match_id(url)
        webpage = self._download_webpage(url, display_id, tries=5)

        title = self._html_search_regex(
            r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series')
        playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id')
        playlist = self._download_webpage(
            'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend'
            'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5,
            note='Downloading playlist')

        videos_paths = re.findall(
            '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist)
        entries = [
            self.url_result('http://vod.tvp.pl%s' % v_path, ie=TVPIE.ie_key())
            for v_path in videos_paths]

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