diff options
author | hassaanaliw <hassaanaliw@gmail.com> | 2014-07-19 22:49:25 +0500 |
---|---|---|
committer | hassaanaliw <hassaanaliw@gmail.com> | 2014-07-19 22:49:25 +0500 |
commit | 8adec2b9e05d356a6996ea6f85aa9b4bf0665ce2 (patch) | |
tree | 6da12e50f6ec4d9d9c83f9f62e4fc4f56ed2ef58 /youtube_dl/extractor/snotr.py | |
parent | 43f0537c06384b9b97235a93ea39649ee3de4d45 (diff) |
[snotr] Add new extractor
Diffstat (limited to 'youtube_dl/extractor/snotr.py')
-rw-r--r-- | youtube_dl/extractor/snotr.py | 73 |
1 files changed, 73 insertions, 0 deletions
diff --git a/youtube_dl/extractor/snotr.py b/youtube_dl/extractor/snotr.py new file mode 100644 index 000000000..f89e81bf3 --- /dev/null +++ b/youtube_dl/extractor/snotr.py @@ -0,0 +1,73 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +from ..utils import ( + + str_to_int, + parse_iso8601, + + + +) + +class SnotrIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)' + _TESTS =[ { + 'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks', + 'info_dict': { + 'id': '13708', + 'ext': 'flv', + 'title': 'Drone flying through fireworks!', + 'duration': 247, + 'filesize':12320768 + } + }, + + + + { + + 'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10', + 'info_dict': { + 'id': '530', + 'ext': 'flv', + 'title': 'David Letteman - George W. Bush Top 10', + 'duration': 126, + 'filesize': 1048576 + } + }] + + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + # TODO more code goes here, for example ... + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + + description = self._og_search_description(webpage) + + video_url = "http://cdn.videos.snotr.com/%s.flv" % video_id + + view_count = str_to_int(self._html_search_regex(r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>',webpage,'view count')) + + duration = self._html_search_regex(r'<p>\n<strong>Length:</strong>\n(.*?)</p>',webpage,'duration') + duration = str_to_int(duration[:1])*60 + str_to_int(duration[2:4]) + + file_size = self._html_search_regex(r'<p>\n<strong>Filesize:</strong>\n(.*?)</p>',webpage,'filesize') + file_size = str_to_int(re.match(r'\d+',file_size).group())*131072 + + return { + 'id': video_id, + 'title': title, + 'url':video_url, + 'view_count':view_count, + 'duration':duration, + 'filesize':file_size + + }
\ No newline at end of file |