mirror of
https://gitlab.com/dstftw/youtube-dl.git
synced 2020-11-16 09:42:26 +00:00
[statigram] Simplify
This commit is contained in:
parent
5dc733f071
commit
9bc70948e1
|
@ -1,36 +1,38 @@
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
|
||||||
|
|
||||||
class StatigramIE(InfoExtractor):
|
class StatigramIE(InfoExtractor):
|
||||||
_VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
|
_VALID_URL = r'https?://(www\.)?statigr\.am/p/(?P<id>[^/]+)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
u'url': u'http://statigr.am/p/522207370455279102_24101272',
|
'url': 'http://statigr.am/p/522207370455279102_24101272',
|
||||||
u'file': u'522207370455279102_24101272.mp4',
|
'md5': '6eb93b882a3ded7c378ee1d6884b1814',
|
||||||
u'md5': u'6eb93b882a3ded7c378ee1d6884b1814',
|
'info_dict': {
|
||||||
u'info_dict': {
|
'id': '522207370455279102_24101272',
|
||||||
u'uploader_id': u'aguynamedpatrick',
|
'ext': 'mp4',
|
||||||
u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
|
'uploader_id': 'aguynamedpatrick',
|
||||||
|
'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, 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)
|
webpage = self._download_webpage(url, video_id)
|
||||||
html_title = self._html_search_regex(
|
html_title = self._html_search_regex(
|
||||||
r'<title>(.+?)</title>',
|
r'<title>(.+?)</title>',
|
||||||
webpage, u'title')
|
webpage, 'title')
|
||||||
title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
|
title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
|
||||||
uploader_id = self._html_search_regex(
|
uploader_id = self._html_search_regex(
|
||||||
r'@([^ ]+)', title, u'uploader name', fatal=False)
|
r'@([^ ]+)', title, 'uploader name', fatal=False)
|
||||||
ext = 'mp4'
|
|
||||||
|
|
||||||
return [{
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'url': self._og_search_video_url(webpage),
|
'url': self._og_search_video_url(webpage),
|
||||||
'ext': ext,
|
'title': title,
|
||||||
'title': title,
|
|
||||||
'thumbnail': self._og_search_thumbnail(webpage),
|
'thumbnail': self._og_search_thumbnail(webpage),
|
||||||
'uploader_id' : uploader_id
|
'uploader_id': uploader_id
|
||||||
}]
|
}
|
||||||
|
|
Loading…
Reference in a new issue