1 from __future__ import unicode_literals
5 from .common import InfoExtractor
12 class InstagramIE(InfoExtractor):
13 _VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
15 'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
16 'md5': '0d2da106a9d2631273e192b372806516',
20 'uploader_id': 'naomipq',
21 'title': 'Video by naomipq',
22 'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
26 def _real_extract(self, url):
27 video_id = self._match_id(url)
29 webpage = self._download_webpage(url, video_id)
30 uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
31 webpage, 'uploader id', fatal=False)
32 desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',
37 'url': self._og_search_video_url(webpage, secure=False),
39 'title': 'Video by %s' % uploader_id,
40 'thumbnail': self._og_search_thumbnail(webpage),
41 'uploader_id': uploader_id,
46 class InstagramUserIE(InfoExtractor):
47 _VALID_URL = r'https://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
48 IE_DESC = 'Instagram user profile'
49 IE_NAME = 'instagram:user'
51 'url': 'https://instagram.com/porsche',
56 'playlist_mincount': 2,
59 'id': '614605558512799803_462752227',
61 'title': '#Porsche Intelligent Performance.',
62 'thumbnail': 're:^https?://.*\.jpg',
63 'uploader': 'Porsche',
64 'uploader_id': 'porsche',
65 'timestamp': 1387486713,
66 'upload_date': '20131219',
71 'skip_download': True,
75 def _real_extract(self, url):
76 mobj = re.match(self._VALID_URL, url)
77 uploader_id = mobj.group('username')
81 media_url = 'http://instagram.com/%s/media' % uploader_id
83 page = self._download_json(
84 media_url, uploader_id,
85 note='Downloading page %d ' % (page_count + 1),
89 for it in page['items']:
90 if it.get('type') != 'video':
92 like_count = int_or_none(it.get('likes', {}).get('count'))
93 user = it.get('user', {})
97 'height': v.get('height'),
98 'width': v.get('width'),
100 } for k, v in it['videos'].items()]
101 self._sort_formats(formats)
103 thumbnails_el = it.get('images', {})
104 thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
106 # In some cases caption is null, which corresponds to None
107 # in python. As a result, it.get('caption', {}) gives None
108 title = (it.get('caption') or {}).get('text', it['id'])
112 'title': limit_length(title, 80),
114 'thumbnail': thumbnail,
115 'webpage_url': it.get('link'),
116 'uploader': user.get('full_name'),
117 'uploader_id': user.get('username'),
118 'like_count': like_count,
119 'timestamp': int_or_none(it.get('created_time')),
122 if not page['items']:
124 max_id = page['items'][-1]['id']
126 'http://instagram.com/%s/media?max_id=%s' % (
127 uploader_id, max_id))
133 'title': uploader_id,