ytdl-nightly/youtube_dl/extractor/statigram.py

39 lines
1.2 KiB
Python
Raw Normal View History

2014-01-31 14:19:22 +01:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-01-31 14:19:22 +01:00
class StatigramIE(InfoExtractor):
2014-01-31 14:19:22 +01:00
_VALID_URL = r'https?://(www\.)?statigr\.am/p/(?P<id>[^/]+)'
2013-06-27 20:46:46 +02:00
_TEST = {
2014-01-31 14:19:22 +01:00
'url': 'http://statigr.am/p/522207370455279102_24101272',
'md5': '6eb93b882a3ded7c378ee1d6884b1814',
'info_dict': {
'id': '522207370455279102_24101272',
'ext': 'mp4',
'uploader_id': 'aguynamedpatrick',
'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
},
2013-06-27 20:46:46 +02:00
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-01-31 14:19:22 +01:00
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
html_title = self._html_search_regex(
r'<title>(.+?)</title>',
2014-01-31 14:19:22 +01:00
webpage, 'title')
2013-06-30 14:07:32 +02:00
title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
uploader_id = self._html_search_regex(
2014-01-31 14:19:22 +01:00
r'@([^ ]+)', title, 'uploader name', fatal=False)
2014-01-31 14:19:22 +01:00
return {
'id': video_id,
'url': self._og_search_video_url(webpage),
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
2014-01-31 14:19:22 +01:00
'uploader_id': uploader_id
}