diff options
author | peugeot <peugeot@psa.fr> | 2014-08-30 18:37:45 +0200 |
---|---|---|
committer | peugeot <peugeot@psa.fr> | 2014-08-30 18:37:45 +0200 |
commit | 72c65d39ff4cfadba5eb5021c8dfd99e69c3e3a4 (patch) | |
tree | 87d9c605d188947dbe48f906b84dc647e0c66600 | |
parent | 08a36c35693d212405a50b490f7f1828830e60ee (diff) |
Add support for AnySex
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/anysex.py | 42 |
2 files changed, 43 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1479d998a..84f601cef 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -4,6 +4,7 @@ from .addanime import AddAnimeIE from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE from .anitube import AnitubeIE +from .anysex import AnySexIE from .aol import AolIE from .allocine import AllocineIE from .aparat import AparatIE diff --git a/youtube_dl/extractor/anysex.py b/youtube_dl/extractor/anysex.py new file mode 100644 index 000000000..ef74805dd --- /dev/null +++ b/youtube_dl/extractor/anysex.py @@ -0,0 +1,42 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +class AnySexIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?anysex\.com/(?P<id>\d+)/?' + _TEST = { + 'url': 'http://anysex.com/156592/', + 'md5': '023e9fbb7f7987f5529a394c34ad3d3d', + 'info_dict': { + 'id': '156592', + 'ext': 'mp4', + 'title': 'Busty and sexy blondie in her bikini strips for you', + 'duration': 270 + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') + video_url = self._html_search_regex(r'video_url: \'(.*?)\',', webpage, 'video_url') + thumbnail = self._html_search_regex(r'preview_url: \'(.*?)\',', webpage, 'thumbnail') + + mobj = re.search(r'<b>Duration:</b> (?P<minutes>\d+):(?P<seconds>\d+)<', webpage) + duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None + + view_count = self._html_search_regex(r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False) + + return { + 'id': video_id, + 'ext': 'mp4', + 'url': video_url, + 'title': title, + 'duration': duration, + 'view_count': view_count + } |