[statigram] Simplify

This commit is contained in:
Jaime Marquínez Ferrándiz 2014-01-31 14:19:22 +01:00
parent 5dc733f071
commit 9bc70948e1

View file

@ -1,36 +1,38 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class StatigramIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
_VALID_URL = r'https?://(www\.)?statigr\.am/p/(?P<id>[^/]+)'
_TEST = {
u'url': u'http://statigr.am/p/522207370455279102_24101272',
u'file': u'522207370455279102_24101272.mp4',
u'md5': u'6eb93b882a3ded7c378ee1d6884b1814',
u'info_dict': {
u'uploader_id': u'aguynamedpatrick',
u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
'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)',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
html_title = self._html_search_regex(
r'<title>(.+?)</title>',
webpage, u'title')
webpage, 'title')
title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
uploader_id = self._html_search_regex(
r'@([^ ]+)', title, u'uploader name', fatal=False)
ext = 'mp4'
r'@([^ ]+)', title, 'uploader name', fatal=False)
return [{
'id': video_id,
'url': self._og_search_video_url(webpage),
'ext': ext,
'title': title,
return {
'id': video_id,
'url': self._og_search_video_url(webpage),
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'uploader_id' : uploader_id
}]
'uploader_id': uploader_id
}