[empflix] Rewrite in terms of tnaflix

This commit is contained in:
Sergey M․ 2014-09-03 21:08:36 +07:00
parent eb833b7f5a
commit a232bb9551
2 changed files with 11 additions and 44 deletions

View File

@ -86,7 +86,7 @@
EllenTVClipsIE, EllenTVClipsIE,
) )
from .elpais import ElPaisIE from .elpais import ElPaisIE
from .empflix import EmpflixIE from .empflix import EMPFlixIE
from .engadget import EngadgetIE from .engadget import EngadgetIE
from .eporner import EpornerIE from .eporner import EpornerIE
from .escapist import EscapistIE from .escapist import EscapistIE

View File

@ -1,58 +1,25 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re from .tnaflix import TNAFlixIE
from .common import InfoExtractor
from ..utils import fix_xml_ampersands
class EmpflixIE(InfoExtractor): class EMPFlixIE(TNAFlixIE):
_VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html' _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html'
_TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
_DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
_CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
_TEST = { _TEST = {
'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
'md5': 'b1bc15b6412d33902d6e5952035fcabc', 'md5': 'b1bc15b6412d33902d6e5952035fcabc',
'info_dict': { 'info_dict': {
'id': '33051', 'id': '33051',
'display_id': 'Amateur-Finger-Fuck',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Amateur Finger Fuck', 'title': 'Amateur Finger Fuck',
'description': 'Amateur solo finger fucking.', 'description': 'Amateur solo finger fucking.',
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18, 'age_limit': 18,
} }
} }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
age_limit = self._rta_search(webpage)
video_title = self._html_search_regex(
r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
video_description = self._html_search_regex(
r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
cfg_url = self._html_search_regex(
r'flashvars\.config = escape\("([^"]+)"',
webpage, 'flashvars.config')
cfg_xml = self._download_xml(
cfg_url, video_id, note='Downloading metadata',
transform_source=fix_xml_ampersands)
formats = [
{
'url': item.find('videoLink').text,
'format_id': item.find('res').text,
} for item in cfg_xml.findall('./quality/item')
]
thumbnail = cfg_xml.find('./startThumb').text
return {
'id': video_id,
'title': video_title,
'description': video_description,
'thumbnail': thumbnail,
'formats': formats,
'age_limit': age_limit,
}