1 from __future__ import unicode_literals
5 from .common import InfoExtractor
12 class InstagramIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+)'
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 'url': 'https://www.instagram.com/p/BA-pQFBG8HZ/?taken-by=britneyspears',
30 'uploader_id': 'britneyspears',
31 'title': 'Video by britneyspears',
34 'skip_download': True,
37 'url': 'https://instagram.com/p/-Cmh1cukG2/',
38 'only_matching': True,
41 def _real_extract(self, url):
42 video_id = self._match_id(url)
44 webpage = self._download_webpage(url, video_id)
45 uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
46 webpage, 'uploader id', fatal=False)
47 desc = self._search_regex(
48 r'"caption":"(.+?)"', webpage, 'description', default=None)
52 'url': self._og_search_video_url(webpage, secure=False),
54 'title': 'Video by %s' % uploader_id,
55 'thumbnail': self._og_search_thumbnail(webpage),
56 'uploader_id': uploader_id,
61 class InstagramUserIE(InfoExtractor):
62 _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
63 IE_DESC = 'Instagram user profile'
64 IE_NAME = 'instagram:user'
66 'url': 'https://instagram.com/porsche',
71 'playlist_mincount': 2,
74 'id': '614605558512799803_462752227',
76 'title': '#Porsche Intelligent Performance.',
77 'thumbnail': 're:^https?://.*\.jpg',
78 'uploader': 'Porsche',
79 'uploader_id': 'porsche',
80 'timestamp': 1387486713,
81 'upload_date': '20131219',
86 'skip_download': True,
90 def _real_extract(self, url):
91 mobj = re.match(self._VALID_URL, url)
92 uploader_id = mobj.group('username')
96 media_url = 'http://instagram.com/%s/media' % uploader_id
98 page = self._download_json(
99 media_url, uploader_id,
100 note='Downloading page %d ' % (page_count + 1),
104 for it in page['items']:
105 if it.get('type') != 'video':
107 like_count = int_or_none(it.get('likes', {}).get('count'))
108 user = it.get('user', {})
112 'height': v.get('height'),
113 'width': v.get('width'),
115 } for k, v in it['videos'].items()]
116 self._sort_formats(formats)
118 thumbnails_el = it.get('images', {})
119 thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
121 # In some cases caption is null, which corresponds to None
122 # in python. As a result, it.get('caption', {}) gives None
123 title = (it.get('caption') or {}).get('text', it['id'])
127 'title': limit_length(title, 80),
129 'thumbnail': thumbnail,
130 'webpage_url': it.get('link'),
131 'uploader': user.get('full_name'),
132 'uploader_id': user.get('username'),
133 'like_count': like_count,
134 'timestamp': int_or_none(it.get('created_time')),
137 if not page['items']:
139 max_id = page['items'][-1]['id']
141 'http://instagram.com/%s/media?max_id=%s' % (
142 uploader_id, max_id))
148 'title': uploader_id,