youtube-dl/youtube_dl/extractor/tnaflix.py

85 lines
2.9 KiB
Python
Raw Normal View History

2014-09-03 14:10:06 +02:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
2014-09-03 16:07:18 +02:00
fix_xml_ampersands,
2014-09-03 14:10:06 +02:00
)
2014-09-03 16:07:18 +02:00
2014-09-03 14:10:06 +02:00
class TNAFlixIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[^/]+)/(?P<display_id>[^/]+)/video(?P<id>\d+)'
2014-09-03 16:07:18 +02:00
2014-12-31 19:11:56 +01:00
_TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
2014-09-03 16:07:18 +02:00
_DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
_CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
2014-09-03 14:10:06 +02:00
_TEST = {
'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
'md5': '6c431ea56756497e227fb3f01a687869',
2014-09-03 14:10:06 +02:00
'info_dict': {
'id': '358632',
'display_id': 'bunzHD-Ms.Donk',
2014-09-03 14:10:06 +02:00
'ext': 'mp4',
'title': 'bunzHD Ms.Donk',
'description': 'bubble booty ebony teen goddess Ms.Donk has a firm ass and acts like she is shy but really she is a freak in the sheets watch her 20 min XX rated vid at bunzHD.com click on the catalog link',
2014-09-03 14:10:06 +02:00
'thumbnail': 're:https?://.*\.jpg$',
'duration': 394,
2014-09-03 14:10:06 +02:00
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
2014-09-03 16:07:18 +02:00
title = self._html_search_regex(
self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
description = self._html_search_regex(
self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
age_limit = self._rta_search(webpage)
duration = self._html_search_meta('duration', webpage, 'duration', default=None)
if duration:
duration = parse_duration(duration[1:])
cfg_url = self._proto_relative_url(self._html_search_regex(
self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
2014-09-03 16:07:18 +02:00
cfg_xml = self._download_xml(
cfg_url, display_id, note='Downloading metadata',
transform_source=fix_xml_ampersands)
thumbnail = cfg_xml.find('./startThumb').text
2014-09-03 14:10:06 +02:00
formats = []
2014-09-03 16:07:18 +02:00
for item in cfg_xml.findall('./quality/item'):
video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
format_id = item.find('res').text
2014-09-03 14:10:06 +02:00
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)
2014-11-23 20:41:03 +01:00
2014-09-03 14:10:06 +02:00
return {
'id': video_id,
'display_id': display_id,
'title': title,
2014-09-03 16:07:18 +02:00
'description': description,
2014-09-03 14:10:06 +02:00
'thumbnail': thumbnail,
2014-09-03 16:07:18 +02:00
'duration': duration,
'age_limit': age_limit,
'formats': formats,
2014-09-03 14:10:06 +02:00
}