From 8adec2b9e05d356a6996ea6f85aa9b4bf0665ce2 Mon Sep 17 00:00:00 2001 From: hassaanaliw Date: Sat, 19 Jul 2014 22:49:25 +0500 Subject: [PATCH] [snotr] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/snotr.py | 73 ++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) create mode 100644 youtube_dl/extractor/snotr.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 78b95c2a5..faf473548 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -263,6 +263,7 @@ SmotriUserIE, SmotriBroadcastIE, ) +from .snotr import SnotrIE from .sohu import SohuIE from .soundcloud import ( SoundcloudIE, 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\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'

\nViews:\n([\d,\.]+)

',webpage,'view count')) + + duration = self._html_search_regex(r'

\nLength:\n(.*?)

',webpage,'duration') + duration = str_to_int(duration[:1])*60 + str_to_int(duration[2:4]) + + file_size = self._html_search_regex(r'

\nFilesize:\n(.*?)

',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