aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/twitter.py
blob: 1dd43ff3cbcdaa370aab4016105671e0e8f70cc9 (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
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
    float_or_none,
    unescapeHTML,
)


class TwitterCardIE(InfoExtractor):
    _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': 'a74f50b310c83170319ba16de6955192',
            '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,
            },
        }
    ]

    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)

            config = self._parse_json(
                unescapeHTML(self._search_regex(
                    r'data-player-config="([^"]+)"', webpage, 'data player config')),
                video_id)
            if 'playlist' not in config:
                if 'vmapUrl' in config:
                    webpage = self._download_webpage(config['vmapUrl'], video_id + ' (xml)')
                    video_url = self._search_regex(
                        r'<MediaFile>\s*<!\[CDATA\[(https?://.+?)\]\]>', webpage, 'data player config (xml)')
                    f = {
                        'url': video_url,
                    }
                    ext = re.search(r'\.([a-z0-9]{2,4})(\?.+)?$', video_url)
                    if ext:
                        f['ext'] = ext.group(1)
                    formats.append(f)
                    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(TwitterCardIE):
    _VALID_URL = r'https?://(?:www|m|mobile)?\.?twitter\.com/(?P<id>[^/]+/status/\d+)'

    _TESTS = [{
        'url': 'https://m.twitter.com/thereaIbanksy/status/614301758345490432',
        'md5': '8bbccb487bd7a31349b775915fcd412f',
        'info_dict': {
            'id': '614301758345490432',
            'ext': 'mp4',
            'title': 'thereaIbanksy - This time lapse is so pretty \U0001f60d\U0001f60d',
            'thumbnail': 're:^https?://.*\.jpg',
            'duration': 29.5,
            'description': 'banksy on Twitter: "This time lapse is so pretty \U0001f60d\U0001f60d http://t.co/QB8DDbqiR1"',
            'uploader': 'banksy',
            'uploader_id': 'thereaIbanksy',
        },
    }]

    def _real_extract(self, url):
        id = self._match_id(url)
        username, twid = re.match(r'([^/]+)/status/(\d+)', id).groups()
        name = username
        url = re.sub(r'https?://(m|mobile)\.', 'https://', url)
        webpage = self._download_webpage(url, 'tweet: ' + url)
        description = unescapeHTML(self._search_regex('<title>\s*(.+?)\s*</title>', webpage, 'title'))
        title = description.replace('\n', ' ')
        splitdesc = re.match(r'^(.+?)\s*on Twitter:\s* "(.+?)"$', title)
        if splitdesc:
            name, title = splitdesc.groups()
        title = re.sub(r'\s*https?://[^ ]+', '', title)  # strip  'https -_t.co_BJYgOjSeGA' junk from filenames
        card_id = self._search_regex(r'["\']/i/cards/tfw/v1/(\d+)', webpage, '/i/card/...')
        card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
        return {
            '_type': 'url_transparent',
            'ie_key': 'TwitterCard',
            'uploader_id': username,
            'uploader': name,
            'url': card_url,
            'webpage_url': url,
            'description': description,
            'title': username + ' - ' + title,
        }