aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/iconosquare.py
blob: bb69c7a0fb9c53500236d229601a44066d848459 (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
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    int_or_none,
    get_element_by_id,
    remove_end,
)


class IconosquareIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
    _TEST = {
        'url': 'http://statigr.am/p/522207370455279102_24101272',
        'md5': '6eb93b882a3ded7c378ee1d6884b1814',
        'info_dict': {
            'id': '522207370455279102_24101272',
            'ext': 'mp4',
            'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
            'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
            'timestamp': 1376471991,
            'upload_date': '20130814',
            'uploader': 'aguynamedpatrick',
            'uploader_id': '24101272',
            'comment_count': int,
            'like_count': int,
        },
    }

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

        webpage = self._download_webpage(url, video_id)

        media = self._parse_json(
            get_element_by_id('mediaJson', webpage),
            video_id)

        formats = [{
            'url': f['url'],
            'format_id': format_id,
            'width': int_or_none(f.get('width')),
            'height': int_or_none(f.get('height'))
        } for format_id, f in media['videos'].items()]
        self._sort_formats(formats)

        title = remove_end(self._og_search_title(webpage), ' - via Iconosquare')

        timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))
        description = media.get('caption', {}).get('text')

        uploader = media.get('user', {}).get('username')
        uploader_id = media.get('user', {}).get('id')

        comment_count = int_or_none(media.get('comments', {}).get('count'))
        like_count = int_or_none(media.get('likes', {}).get('count'))

        thumbnails = [{
            'url': t['url'],
            'id': thumbnail_id,
            'width': int_or_none(t.get('width')),
            'height': int_or_none(t.get('height'))
        } for thumbnail_id, t in media.get('images', {}).items()]

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'thumbnails': thumbnails,
            'timestamp': timestamp,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'comment_count': comment_count,
            'like_count': like_count,
            'formats': formats,
        }