From deed48b472b3cfe2f496b0c4ff3fe40a391e6725 Mon Sep 17 00:00:00 2001 From: Sainyam Kapoor Date: Sat, 5 Apr 2014 10:40:03 +0530 Subject: [PATCH] [Videoweed] Added support for videoweed. --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/videoweed.py | 69 +++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) create mode 100644 youtube_dl/extractor/videoweed.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 66f71edf6..6a98bc42d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -284,6 +284,7 @@ from .vimeo import ( VimeoGroupsIE, VimeoReviewIE, ) +from .videoweed import VideoweedIE from .vine import VineIE from .viki import VikiIE from .vk import VKIE diff --git a/youtube_dl/extractor/videoweed.py b/youtube_dl/extractor/videoweed.py new file mode 100644 index 000000000..7110ecaa2 --- /dev/null +++ b/youtube_dl/extractor/videoweed.py @@ -0,0 +1,69 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urlparse +) + + +class VideoweedIE(InfoExtractor): + IE_NAME = 'videoweed' + IE_DESC = 'VideoWEED' + + #_VALID_URL = r'http://(?:(?:www\.)?%(host)s/file/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P[a-z\d]{13})' % {'host': 'videoweed\.com'} + _VALID_URL =r'http://(?:www\.)videoweed\.es/file/(?P[^"]+)' + _HOST = 'www.videoweed.es' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.[^"]+)";' + _TITLE_REGEX = r'

([^<]+)

' + _DESCRIPTION_REGEX = r'(?s)
\s*

[^<]+

([^<]+)

' + + _TEST = { + 'url': 'http://www.videoweed.es/file/89868b4aa3bdf', + 'md5': '7205f346a52bbeba427603ba10d4b935', + 'info_dict': { + 'id': '89868b4aa3bdf', + 'ext': 'flv', + 'title': 'law and order svu 103 dvdrip', + 'description': '' + }, + 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)' + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + print "itworks" + page = self._download_webpage( + 'http://%s/file/%s' % (self._HOST, video_id), video_id, 'Downloading video page') + + if re.search(self._FILE_DELETED_REGEX, page) is not None: + raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) + + filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey') + + title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False) + + description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False) + + api_response = self._download_webpage( + 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id, + 'Downloading video api response') + + response = compat_urlparse.parse_qs(api_response) + + if 'error_msg' in response: + raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True) + + video_url = response['url'][0] + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description + } \ No newline at end of file -- 2.22.2