diff options
author | Sergey M․ <[email protected]> | 2014-07-24 21:12:45 +0700 |
---|---|---|
committer | Sergey M․ <[email protected]> | 2014-07-24 21:12:45 +0700 |
commit | 916c1452178c68bc7133b84f1538d19d5a7db17e (patch) | |
tree | ef977388b24db67fd12e427b4ae7b0f547224370 | |
parent | 4192b51c7c599d1fb1114dcee8abaa44bc48d03b (diff) | |
download | youtube-dl-916c1452178c68bc7133b84f1538d19d5a7db17e.tar.gz youtube-dl-916c1452178c68bc7133b84f1538d19d5a7db17e.zip |
[shared] Add extractor (Closes #3312)
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/shared.py | 57 |
2 files changed, 58 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 80aa2dfbb..2bb93d938 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -259,6 +259,7 @@ from .savefrom import SaveFromIE from .scivee import SciVeeIE from .screencast import ScreencastIE from .servingsys import ServingSysIE +from .shared import SharedIE from .sina import SinaIE from .slideshare import SlideshareIE from .slutload import SlutloadIE diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py new file mode 100644 index 000000000..8607482be --- /dev/null +++ b/youtube_dl/extractor/shared.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +import re +import base64 + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_request, + compat_urllib_parse, + int_or_none, +) + + +class SharedIE(InfoExtractor): + _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})' + + _TEST = { + 'url': 'http://shared.sx/0060718775', + 'md5': '53e1c58fc3e777ae1dfe9e57ba2f9c72', + 'info_dict': { + 'id': '0060718775', + 'ext': 'mp4', + 'title': 'Big Buck Bunny Trailer', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id) + + if re.search(r'>File does not exist<', page) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + + download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page)) + + request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + + video_page = self._download_webpage(request, video_id, 'Downloading video page') + + video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL') + title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8') + filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False)) + thumbnail = self._html_search_regex( + r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'filesize': filesize, + 'title': title, + 'thumbnail': thumbnail, + }
\ No newline at end of file |