import re
from .common import InfoExtractor
+from ..utils import (
+ js_to_json,
+ remove_end,
+)
+
class HellPornoIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<display_id>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
_TEST = {
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
'md5': '1fee339c610d2049699ef2aa699439f1',
'info_dict': {
'id': '149116',
+ 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
'ext': 'mp4',
'title': 'Dixie is posing with naked ass very erotic',
- 'description': 'md5:5ba02cbf31eff820147b3cc25306d89a',
- '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'video_id:\s*\'([^\']+)\'', webpage, 'id')
+ display_id = self._match_id(url)
- video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url')
+ webpage = self._download_webpage(url, display_id)
- ext = self._html_search_regex(r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:]
+ title = remove_end(self._html_search_regex(
+ r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
- title = self._html_search_regex(
- r'<title>([^<]+)\s*-\s*Hell Porno</title>', webpage, 'title')
+ flashvars = self._parse_json(self._search_regex(
+ r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
+ display_id, transform_source=js_to_json)
- description = self._html_search_meta('description', webpage, 'description', fatal=False)
+ video_id = flashvars.get('video_id')
+ thumbnail = flashvars.get('preview_url')
+ ext = flashvars.get('postfix', '.mp4')[1:]
- thumbnail = self._html_search_regex(
- r'preview_url:\s*\'([^\']+)\'',
- webpage, 'thumbnail', fatal=False)
+ 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)
- categories_str = self._html_search_regex(
- r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
- categories = (
- None if categories_str is None
- else categories_str.split(','))
+ categories = self._html_search_meta(
+ 'keywords', webpage, 'categories', default='').split(',')
return {
'id': video_id,
- 'url': video_url,
+ 'display_id': display_id,
'title': title,
- 'ext': ext,
- 'description': description,
'thumbnail': thumbnail,
'categories': categories,
'age_limit': 18,
+ 'formats': formats,
}