youtube-dl/youtube_dl/extractor/hellporno.py

72 lines
2.2 KiB
Python
Raw Normal View History

2014-12-26 14:49:12 +00:00
from __future__ import unicode_literals
import re
2014-12-26 14:49:12 +00:00
from .common import InfoExtractor
from ..utils import (
js_to_json,
remove_end,
)
2014-12-26 14:49:12 +00:00
2014-12-29 09:38:07 +00:00
2014-12-26 14:49:12 +00:00
class HellPornoIE(InfoExtractor):
2014-12-29 09:38:07 +00:00
_VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
2014-12-26 14:49:12 +00:00
_TEST = {
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
'md5': '1fee339c610d2049699ef2aa699439f1',
'info_dict': {
'id': '149116',
2014-12-29 09:38:07 +00:00
'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
2014-12-26 14:49:12 +00:00
'ext': 'mp4',
'title': 'Dixie is posing with naked ass very erotic',
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
}
}
def _real_extract(self, url):
2014-12-29 09:38:07 +00:00
display_id = self._match_id(url)
2014-12-26 14:49:12 +00:00
webpage = self._download_webpage(url, display_id)
2014-12-26 14:49:12 +00:00
title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
2014-12-26 14:49:12 +00:00
flashvars = self._parse_json(self._search_regex(
r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
display_id, transform_source=js_to_json)
2014-12-26 14:49:12 +00:00
video_id = flashvars.get('video_id')
thumbnail = flashvars.get('preview_url')
ext = flashvars.get('postfix', '.mp4')[1:]
2014-12-26 14:49:12 +00:00
formats = []
for video_url_key in ['video_url', 'video_alt_url']:
video_url = flashvars.get(video_url_key)
if not video_url:
continue
video_text = flashvars.get('%s_text' % video_url_key)
fmt = {
'url': video_url,
'ext': ext,
'format_id': video_text,
}
m = re.search(r'^(?P<height>\d+)[pP]', video_text)
if m:
fmt['height'] = int(m.group('height'))
formats.append(fmt)
self._sort_formats(formats)
2014-12-26 14:49:12 +00:00
2014-12-29 09:38:07 +00:00
categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
2014-12-26 14:49:12 +00:00
return {
'id': video_id,
2014-12-29 09:38:07 +00:00
'display_id': display_id,
2014-12-26 14:49:12 +00:00
'title': title,
'thumbnail': thumbnail,
'categories': categories,
'age_limit': 18,
'formats': formats,
2014-12-26 14:49:12 +00:00
}