diff options
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/hellporno.py | 56 |
2 files changed, 57 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index fd0ebffe3..de5206729 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -166,6 +166,7 @@ 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..06f85127f --- /dev/null +++ b/youtube_dl/extractor/hellporno.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +class HellPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<display_id>[^/]+)' + _TEST = { + 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', + 'md5': '1fee339c610d2049699ef2aa699439f1', + 'info_dict': { + 'id': '149116', + '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') + + video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') + + ext = self._html_search_regex(r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:] + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*Hell Porno</title>', webpage, 'title') + + description = self._html_search_meta('description', webpage, 'description', fatal=False) + + thumbnail = self._html_search_regex( + r'preview_url:\s*\'([^\']+)\'', + webpage, 'thumbnail', fatal=False) + + 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(',')) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': ext, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'age_limit': 18, + } |