yt-dlp/youtube_dl/extractor/eporner.py

76 lines
2.5 KiB
Python
Raw Normal View History

2014-08-30 14:28:53 -06:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-08-31 15:51:36 -06:00
from ..utils import (
parse_duration,
str_to_int,
)
2014-08-30 14:28:53 -06:00
class EpornerIE(InfoExtractor):
2014-09-02 08:39:22 -06:00
_VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)'
2014-08-30 14:28:53 -06:00
_TEST = {
'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
'md5': '39d486f046212d8e1b911c52ab4691f8',
2014-08-30 14:28:53 -06:00
'info_dict': {
'id': '95008',
2014-09-02 08:39:22 -06:00
'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
'ext': 'mp4',
2014-08-30 14:28:53 -06:00
'title': 'Infamous Tiffany Teen Strip Tease Video',
2014-08-31 15:51:36 -06:00
'duration': 194,
'view_count': int,
2014-09-01 15:07:48 -06:00
'age_limit': 18,
2014-08-30 14:28:53 -06:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-09-02 08:39:22 -06:00
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
2014-08-31 15:51:36 -06:00
title = self._html_search_regex(
r'<title>(.*?) - EPORNER', webpage, 'title')
2014-08-30 14:28:53 -06:00
2014-08-31 15:51:36 -06:00
redirect_code = self._html_search_regex(
r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
webpage, 'redirect_code')
redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
2014-09-01 15:07:48 -06:00
player_code = self._download_webpage(
2014-09-02 08:39:22 -06:00
redirect_url, display_id, note='Downloading player config')
sources = self._search_regex(
r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
formats = []
for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
fmt = {
'url': video_url,
'format_id': format_id,
}
m = re.search(r'^(\d+)', format_id)
if m:
fmt['height'] = int(m.group(1))
formats.append(fmt)
self._sort_formats(formats)
2014-08-30 14:28:53 -06:00
2014-08-31 15:51:36 -06:00
duration = parse_duration(self._search_regex(
r'class="mbtim">([0-9:]+)</div>', webpage, 'duration',
fatal=False))
view_count = str_to_int(self._search_regex(
r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
webpage, 'view count', fatal=False))
2014-08-30 14:28:53 -06:00
return {
'id': video_id,
2014-09-02 08:39:22 -06:00
'display_id': display_id,
2014-08-30 14:28:53 -06:00
'title': title,
2014-08-31 15:51:36 -06:00
'duration': duration,
'view_count': view_count,
2014-09-02 08:39:22 -06:00
'formats': formats,
2014-09-01 15:07:48 -06:00
'age_limit': self._rta_search(webpage),
2014-08-30 14:28:53 -06:00
}