diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/hellporno.py | 71 | 
2 files changed, 72 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c79e5b7d0..ea4faf2a6 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -169,6 +169,7 @@ from .grooveshark import GroovesharkIE  from .groupon import GrouponIE  from .hark import HarkIE  from .heise import HeiseIE +from .hellporno import HellPornoIE  from .helsinki import HelsinkiIE  from .hentaistigma import HentaiStigmaIE  from .hornbunny import HornBunnyIE diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py new file mode 100644 index 000000000..7a1c75b65 --- /dev/null +++ b/youtube_dl/extractor/hellporno.py @@ -0,0 +1,71 @@ +from __future__ import unicode_literals + +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<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', +            'thumbnail': 're:https?://.*\.jpg$', +            'age_limit': 18, +        } +    } + +    def _real_extract(self, url): +        display_id = self._match_id(url) + +        webpage = self._download_webpage(url, display_id) + +        title = remove_end(self._html_search_regex( +            r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno') + +        flashvars = self._parse_json(self._search_regex( +            r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), +            display_id, transform_source=js_to_json) + +        video_id = flashvars.get('video_id') +        thumbnail = flashvars.get('preview_url') +        ext = flashvars.get('postfix', '.mp4')[1:] + +        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 = self._html_search_meta( +            'keywords', webpage, 'categories', default='').split(',') + +        return { +            'id': video_id, +            'display_id': display_id, +            'title': title, +            'thumbnail': thumbnail, +            'categories': categories, +            'age_limit': 18, +            'formats': formats, +        }  | 
