aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/wat.py
blob: 8ef3e0906436b3a13e1bc368173e7f7c81ba6c22 (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
# coding: utf-8
from __future__ import unicode_literals

import re

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


class WatIE(InfoExtractor):
    _VALID_URL = r'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)'
    IE_NAME = 'wat.tv'
    _TESTS = [
        {
            'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
            'info_dict': {
                'id': '11713067',
                'ext': 'mp4',
                'title': 'Soupe de figues à l\'orange et aux épices',
                'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
                'upload_date': '20140819',
                'duration': 120,
            },
            'params': {
                # m3u8 download
                'skip_download': True,
            },
            'expected_warnings': ['HTTP Error 404'],
        },
        {
            'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
            'md5': 'b16574df2c3cd1a36ca0098f2a791925',
            'info_dict': {
                'id': '11713075',
                'ext': 'mp4',
                'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
                'upload_date': '20140816',
            },
            'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
        },
    ]

    _FORMATS = (
        (200, 416, 234),
        (400, 480, 270),
        (600, 640, 360),
        (1200, 640, 360),
        (1800, 960, 540),
        (2500, 1280, 720),
    )

    def _real_extract(self, url):
        video_id = self._match_id(url)
        video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36))

        # 'contentv4' is used in the website, but it also returns the related
        # videos, we don't need them
        video_data = self._download_json(
            'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
        video_info = video_data['media']

        error_desc = video_info.get('error_desc')
        if error_desc:
            self.report_warning(
                '%s returned error: %s' % (self.IE_NAME, error_desc))

        chapters = video_info['chapters']
        if chapters:
            first_chapter = chapters[0]

            def video_id_for_chapter(chapter):
                return chapter['tc_start'].split('-')[0]

            if video_id_for_chapter(first_chapter) != video_id:
                self.to_screen('Multipart video detected')
                entries = [self.url_result('wat:%s' % video_id_for_chapter(chapter)) for chapter in chapters]
                return self.playlist_result(entries, video_id, video_info['title'])
            # Otherwise we can continue and extract just one part, we have to use
            # the video id for getting the video url
        else:
            first_chapter = video_info

        title = first_chapter['title']

        def extract_url(path_template, url_type):
            req_url = 'http://www.wat.tv/get/%s' % (path_template % video_id)
            head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type, fatal=False)
            if head:
                red_url = head.geturl()
                if req_url != red_url:
                    return red_url
            return None

        def remove_bitrate_limit(manifest_url):
            return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url)

        formats = []
        try:
            alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')]
            manifest_urls = self._download_json(
                'http://www.wat.tv/get/webhtml/' + video_id, video_id)
            m3u8_url = manifest_urls.get('hls')
            if m3u8_url:
                m3u8_url = remove_bitrate_limit(m3u8_url)
                for m3u8_alt_url in alt_urls(m3u8_url):
                    formats.extend(self._extract_m3u8_formats(
                        m3u8_alt_url, video_id, 'mp4',
                        'm3u8_native', m3u8_id='hls', fatal=False))
                    formats.extend(self._extract_f4m_formats(
                        m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'),
                        video_id, f4m_id='hds', fatal=False))
            mpd_url = manifest_urls.get('mpd')
            if mpd_url:
                mpd_url = remove_bitrate_limit(mpd_url)
                for mpd_alt_url in alt_urls(mpd_url):
                    formats.extend(self._extract_mpd_formats(
                        mpd_alt_url, video_id, mpd_id='dash', fatal=False))
            self._sort_formats(formats)
        except ExtractorError:
            abr = 64
            for vbr, width, height in self._FORMATS:
                tbr = vbr + abr
                format_id = 'http-%s' % tbr
                fmt_url = 'http://dnl.adv.tf1.fr/2/USP-0x0/%s/%s/%s/ssm/%s-%s-64k.mp4' % (video_id[-4:-2], video_id[-2:], video_id, video_id, vbr)
                if self._is_valid_url(fmt_url, video_id, format_id):
                    formats.append({
                        'format_id': format_id,
                        'url': fmt_url,
                        'vbr': vbr,
                        'abr': abr,
                        'width': width,
                        'height': height,
                    })

        date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4')
        upload_date = unified_strdate(date_diffusion) if date_diffusion else None
        duration = None
        files = video_info['files']
        if files:
            duration = int_or_none(files[0].get('duration'))

        return {
            'id': video_id,
            'title': title,
            'thumbnail': first_chapter.get('preview'),
            'description': first_chapter.get('description'),
            'view_count': int_or_none(video_info.get('views')),
            'upload_date': upload_date,
            'duration': duration,
            'formats': formats,
        }