1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-22 22:47:55 +01:00

[eroprofile] new extractor

This commit is contained in:
peugeot 2014-12-26 17:15:34 +01:00
parent a542405200
commit 461b00f34a
2 changed files with 54 additions and 0 deletions

View File

@ -108,6 +108,7 @@ from .elpais import ElPaisIE
from .empflix import EMPFlixIE
from .engadget import EngadgetIE
from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .escapist import EscapistIE
from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE

View File

@ -0,0 +1,53 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class EroProfileIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<display_id>[^/]+)'
_TEST = {
'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
'info_dict': {
'id': '3733775',
'ext': 'm4v',
'title': 'HD MOVIES - sexy babe softcore',
'description': 'md5:831ee50526c333eb4f6c1e58d382c295',
'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg',
'age_limit': 18,
}
}
def _real_extract(self, url):
webpage = self._download_webpage(url, 'main')
video_id = self._html_search_regex(r'glbUpdViews\s*\(\'\d*\',\'(\d+)\'', webpage, 'id')
video_url = self._html_search_regex(r'<source src="([^"]+)', webpage, 'video_url')
title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*EroProfile</title>', webpage, 'title')
description = self._html_search_meta('description', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'onclick="showVideoPlayer\(\)"><img src="([^"]+)', webpage, 'thumbnail', fatal=False)
categories_str = self._html_search_meta(
'keywords', webpage, 'categories', fatal=False)
categories = (
None if categories_str is None
else categories_str.split(','))
return {
'id': video_id,
'url': video_url,
'title': title,
'ext': 'm4v',
'description': description,
'thumbnail': thumbnail,
'categories': categories,
'age_limit': 18,
}