From 66aa382eae9342506db64ce3328a009fd3f06d5c Mon Sep 17 00:00:00 2001 From: Naglis Jonaitis Date: Wed, 16 Jul 2014 02:07:20 +0300 Subject: [PATCH] [sockshare] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/sockshare.py | 77 +++++++++++++++++++++++++++++++ 2 files changed, 78 insertions(+) create mode 100644 youtube_dl/extractor/sockshare.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e49ac3e52..f3575b6c9 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -262,6 +262,7 @@ from .smotri import ( SmotriUserIE, SmotriBroadcastIE, ) +from .sockshare import SockshareIE from .sohu import SohuIE from .soundcloud import ( SoundcloudIE, diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py new file mode 100644 index 000000000..cbf2d7abe --- /dev/null +++ b/youtube_dl/extractor/sockshare.py @@ -0,0 +1,77 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, + determine_ext, +) +import re + +from .common import InfoExtractor + + +class SockshareIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P[0-9A-Za-z]+)' + _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.' + _TEST = { + 'url': 'http://www.sockshare.com/file/437BE28B89D799D7', + 'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd', + 'info_dict': { + 'id': '437BE28B89D799D7', + 'title': 'big_buck_bunny_720p_surround.avi', + 'ext': 'avi', + 'thumbnail': 're:^http://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://sockshare.com/file/%s' % video_id + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError(u'Video %s does not exist' % video_id, + expected=True) + + confirm_hash = self._html_search_regex(r'''(?x)(.+)', webpage, 'title') + thumbnail = self._html_search_regex(r'