diff options
author | peugeot <peugeot@psa.fr> | 2014-09-01 20:12:51 +0200 |
---|---|---|
committer | peugeot <peugeot@psa.fr> | 2014-09-01 20:12:51 +0200 |
commit | d740f7e16f936262fec6b23bb8729374f1cf847d (patch) | |
tree | 1ecfb0b9c9d437e6b60d15a337447d1ea5e0adcc | |
parent | 07e7dc4bdcdf7a9393594ab88a42cb2dfed0208d (diff) |
Add support for drtuber.com
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/drtuber.py | 48 |
2 files changed, 49 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9f43bb8f4..00c9e7042 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -70,6 +70,7 @@ from .daum import DaumIE from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE +from .drtuber import DrTuberIE from .drtv import DRTVIE from .dump import DumpIE from .defense import DefenseGouvFrIE diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py new file mode 100644 index 000000000..7b4b19509 --- /dev/null +++ b/youtube_dl/extractor/drtuber.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DrTuberIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<title_dash>[\w-]+)' + _TEST = { + 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf', + 'md5': '93e680cf2536ad0dfb7e74d94a89facd', + 'info_dict': { + 'id': '1740434', + 'ext': 'mp4', + 'title': 'Hot Perky Blonde Naked Golf', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'<source src="([^"]+)"', webpage, 'video URL') + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*Free', webpage, 'title') + + thumbnail = self._html_search_regex( + r'poster="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + categories_str = self._html_search_regex( + r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) + categories = categories_str.split(' ') + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'categories': categories, + } |