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
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import int_or_none
class InstagramIE(InfoExtractor):
_VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
_TEST = {
'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
'md5': '0d2da106a9d2631273e192b372806516',
'info_dict': {
'id': 'aye83DjauH',
'ext': 'mp4',
'uploader_id': 'naomipq',
'title': 'Video by naomipq',
'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
webpage, 'uploader id', fatal=False)
desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',
fatal=False)
return {
'id': video_id,
'url': self._og_search_video_url(webpage, secure=False),
'ext': 'mp4',
'title': 'Video by %s' % uploader_id,
'thumbnail': self._og_search_thumbnail(webpage),
'uploader_id': uploader_id,
'description': desc,
}
class InstagramUserIE(InfoExtractor):
_VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
IE_DESC = 'Instagram user profile'
IE_NAME = 'instagram:user'
_TEST = {
'url': 'http://instagram.com/porsche',
'info_dict': {
'id': 'porsche',
'title': 'porsche',
},
'playlist_mincount': 2,
'playlist': [{
'info_dict': {
'id': '614605558512799803_462752227',
'ext': 'mp4',
'title': '#Porsche Intelligent Performance.',
'thumbnail': 're:^https?://.*\.jpg',
'uploader': 'Porsche',
'uploader_id': 'porsche',
'timestamp': 1387486713,
'upload_date': '20131219',
},
}],
'params': {
'extract_flat': True,
'skip_download': True,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
uploader_id = mobj.group('username')
entries = []
page_count = 0
media_url = 'http://instagram.com/%s/media' % uploader_id
while True:
page = self._download_json(
media_url, uploader_id,
note='Downloading page %d ' % (page_count + 1),
)
page_count += 1
for it in page['items']:
if it.get('type') != 'video':
continue
like_count = int_or_none(it.get('likes', {}).get('count'))
user = it.get('user', {})
formats = [{
'format_id': k,
'height': v.get('height'),
'width': v.get('width'),
'url': v['url'],
} for k, v in it['videos'].items()]
self._sort_formats(formats)
thumbnails_el = it.get('images', {})
thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
title = it.get('caption', {}).get('text', it['id'])
entries.append({
'id': it['id'],
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'webpage_url': it.get('link'),
'uploader': user.get('full_name'),
'uploader_id': user.get('username'),
'like_count': like_count,
'timestamp': int_or_none(it.get('created_time')),
})
if not page['items']:
break
max_id = page['items'][-1]['id']
media_url = (
'http://instagram.com/%s/media?max_id=%s' % (
uploader_id, max_id))
return {
'_type': 'playlist',
'entries': entries,
'id': uploader_id,
'title': uploader_id,
}
|
