aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/twitter.py
blob: 0db7a4440186a5fd2c5af9f51a469236499afdf9 (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
    float_or_none,
    xpath_text,
    remove_end,
    int_or_none,
    ExtractorError,
)


class TwitterCardIE(InfoExtractor):
    IE_NAME = 'twitter:card'
    _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
    _TESTS = [
        {
            'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
            'md5': '4fa26a35f9d1bf4b646590ba8e84be19',
            'info_dict': {
                'id': '560070183650213889',
                'ext': 'mp4',
                'title': 'TwitterCard',
                'thumbnail': 're:^https?://.*\.jpg$',
                'duration': 30.033,
            }
        },
        {
            'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
            'md5': '7ee2a553b63d1bccba97fbed97d9e1c8',
            'info_dict': {
                'id': '623160978427936768',
                'ext': 'mp4',
                'title': 'TwitterCard',
                'thumbnail': 're:^https?://.*\.jpg',
                'duration': 80.155,
            },
        },
        {
            'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
            'md5': 'b6f35e8b08a0bec6c8af77a2f4b3a814',
            'info_dict': {
                'id': 'dq4Oj5quskI',
                'ext': 'mp4',
                'title': 'Ubuntu 11.10 Overview',
                'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10-things-to-do-after-installing-ubuntu-11-10/',
                'upload_date': '20111013',
                'uploader': 'OMG! Ubuntu!',
                'uploader_id': 'omgubuntu',
            },
        }
    ]

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

        # Different formats served for different User-Agents
        USER_AGENTS = [
            'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)',  # mp4
            'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0',  # webm
        ]

        config = None
        formats = []
        for user_agent in USER_AGENTS:
            request = compat_urllib_request.Request(url)
            request.add_header('User-Agent', user_agent)
            webpage = self._download_webpage(request, video_id)

            youtube_url = self._html_search_regex(
                r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
                webpage, 'youtube iframe', default=None)
            if youtube_url:
                return self.url_result(youtube_url, 'Youtube')

            config = self._parse_json(self._html_search_regex(
                r'data-player-config="([^"]+)"', webpage, 'data player config'),
                video_id)
            if 'playlist' not in config:
                if 'vmapUrl' in config:
                    vmap_data = self._download_xml(config['vmapUrl'], video_id)
                    video_url = xpath_text(vmap_data, './/MediaFile').strip()
                    formats.append({
                        'url': video_url,
                    })
                    break   # same video regardless of UA
                continue

            video_url = config['playlist'][0]['source']

            f = {
                'url': video_url,
            }

            m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
            if m:
                f.update({
                    'width': int(m.group('width')),
                    'height': int(m.group('height')),
                })
            formats.append(f)
        self._sort_formats(formats)

        thumbnail = config.get('posterImageUrl')
        duration = float_or_none(config.get('duration'))

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


class TwitterIE(InfoExtractor):
    IE_NAME = 'twitter'
    _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
    _TEMPLATE_URL = 'https://twitter.com/%s/status/%s'

    _TESTS = [{
        'url': 'https://twitter.com/freethenipple/status/643211948184596480',
        'md5': 'db6612ec5d03355953c3ca9250c97e5e',
        'info_dict': {
            'id': '643211948184596480',
            'ext': 'mp4',
            'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!',
            'thumbnail': 're:^https?://.*\.jpg',
            'duration': 12.922,
            'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
            'uploader': 'FREE THE NIPPLE',
            'uploader_id': 'freethenipple',
        },
    }, {
        'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1',
        'md5': 'f36dcd5fb92bf7057f155e7d927eeb42',
        'info_dict': {
            'id': '657991469417025536',
            'ext': 'mp4',
            'title': 'Gifs - tu vai cai tu vai cai tu nao eh capaz disso tu vai cai',
            'description': 'Gifs on Twitter: "tu vai cai tu vai cai tu nao eh capaz disso tu vai cai https://t.co/tM46VHFlO5"',
            'thumbnail': 're:^https?://.*\.png',
            'uploader': 'Gifs',
            'uploader_id': 'giphz',
        },
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        user_id = mobj.group('user_id')
        twid = mobj.group('id')

        webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid)

        username = remove_end(self._og_search_title(webpage), ' on Twitter')

        title = self._og_search_description(webpage).strip('').replace('\n', ' ')

        # strip  'https -_t.co_BJYgOjSeGA' junk from filenames
        mobj = re.match(r'“(.*)\s+(https?://[^ ]+)”', title)
        title, short_url = mobj.groups()

        info = {
            'uploader_id': user_id,
            'uploader': username,
            'webpage_url': url,
            'description': '%s on Twitter: "%s %s"' % (username, title, short_url),
            'title': username + ' - ' + title,
        }

        card_id = self._search_regex(
            r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url', default=None)
        if card_id:
            card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
            info.update({
                '_type': 'url_transparent',
                'ie_key': 'TwitterCard',
                'url': card_url,
            })
            return info

        mobj = re.search(r'''(?x)
            <video[^>]+class="animated-gif"[^>]+
                (?:data-height="(?P<height>\d+)")?[^>]+
                (?:data-width="(?P<width>\d+)")?[^>]+
                (?:poster="(?P<poster>[^"]+)")?[^>]*>\s*
                <source[^>]+video-src="(?P<url>[^"]+)"
        ''', webpage)

        if mobj:
            info.update({
                'id': twid,
                'url': mobj.group('url'),
                'height': int_or_none(mobj.group('height')),
                'width': int_or_none(mobj.group('width')),
                'thumbnail': mobj.group('poster'),
            })
            return info

        raise ExtractorError('There\'s not video in this tweet.')