diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-12-04 08:20:01 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-12-04 08:20:01 +0100 |
commit | 7f142293dff64096a34446ce1e7d674a9f2f1bc9 (patch) | |
tree | f633992a92aee3cb8ef0497bb794a5122ccaa7fb | |
parent | d4e06d4a83b223e82814cd160bdf62e3a82f33e4 (diff) | |
parent | b92c54869345b60a29882297ac1832429f964d03 (diff) |
Merge remote-tracking branch 'zackfern/foxgay'
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/foxgay.py | 48 |
2 files changed, 49 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 8b513ffd1..b2c7fd586 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -121,6 +121,7 @@ from .fktv import ( from .flickr import FlickrIE from .folketinget import FolketingetIE from .fourtube import FourTubeIE +from .foxgay import FoxgayIE from .franceculture import FranceCultureIE from .franceinter import FranceInterIE from .francetv import ( diff --git a/youtube_dl/extractor/foxgay.py b/youtube_dl/extractor/foxgay.py new file mode 100644 index 000000000..a146a9180 --- /dev/null +++ b/youtube_dl/extractor/foxgay.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class FoxgayIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml' + _TEST = { + 'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml', + 'md5': '80d72beab5d04e1655a56ad37afe6841', + 'info_dict': { + 'id': '2582', + 'ext': 'mp4', + 'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a', + 'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf', + 'age_limit': 18, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + # Download the initial webpage and extract all available data. + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'<title>(?P<title>.*?)</title>', + webpage, 'title', fatal=False) + description = self._html_search_regex( + r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>', + webpage, 'description', fatal=False) + + # Find the URL for the iFrame which contains the actual video. + iframe = self._download_webpage( + self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'), + video_id) + video_url = self._html_search_regex( + r"v_path = '(?P<vid>http://.*?)'", iframe, 'url') + thumb_url = self._html_search_regex( + r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'description': description, + 'thumbnail': thumb_url, + 'age_limit': 18, + } |