0
0
Fork 0
youtube-dl/youtube_dl/extractor/empflix.py

49 lines
1.3 KiB
Python
Raw Normal View History

2014-05-13 18:14:05 +10:00
from __future__ import unicode_literals
2014-05-12 21:10:29 +10:00
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
2014-05-13 18:14:05 +10:00
2014-05-12 21:10:29 +10:00
class EmpflixIE(InfoExtractor):
2014-05-13 18:14:05 +10:00
_VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
2014-05-12 21:10:29 +10:00
_TEST = {
2014-05-13 18:14:05 +10:00
'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
'md5': '5e5cc160f38ca9857f318eb97146e13e',
'info_dict': {
'id': '33051',
'ext': 'flv',
'title': 'Amateur Finger Fuck',
'age_limit': 18,
2014-05-12 21:10:29 +10:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-05-13 18:14:05 +10:00
video_id = mobj.group('id')
2014-05-12 21:10:29 +10:00
webpage = self._download_webpage(url, video_id)
age_limit = self._rta_search(webpage)
2014-05-13 18:14:05 +10:00
video_title = self._html_search_regex(
r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
2014-05-12 21:10:29 +10:00
2014-05-13 18:14:05 +10:00
cfg_url = self._html_search_regex(
r'flashvars\.config = escape\("([^"]+)"',
webpage, 'flashvars.config')
2014-05-12 21:10:29 +10:00
2014-05-13 18:14:05 +10:00
cfg_xml = self._download_xml(
cfg_url, video_id, note='Downloading metadata')
2014-05-12 21:10:29 +10:00
video_url = cfg_xml.find('videoLink').text
2014-05-13 18:14:05 +10:00
return {
'id': video_id,
'url': video_url,
'ext': 'flv',
'title': video_title,
'age_limit': age_limit,
}