X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsnotr.py;h=da3b05a8dc8ca89345e755225ed7885fa580c973;hb=5c2266df4b9aeb7881ed8c026a038e2a25e43734;hp=f89e81bf32035f689fa8adf520055729973ceb18;hpb=8adec2b9e05d356a6996ea6f85aa9b4bf0665ce2;p=youtube-dl diff --git a/youtube_dl/extractor/snotr.py b/youtube_dl/extractor/snotr.py index f89e81bf3..da3b05a8d 100644 --- a/youtube_dl/extractor/snotr.py +++ b/youtube_dl/extractor/snotr.py @@ -4,70 +4,65 @@ from __future__ import unicode_literals import re from .common import InfoExtractor - from ..utils import ( - + float_or_none, str_to_int, - parse_iso8601, - - - + parse_duration, ) + class SnotrIE(InfoExtractor): _VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P\d+)/([\w]+)' - _TESTS =[ { + _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 - } - }, - - - - { - + 'filesize_approx': 98566144, + 'description': 'A drone flying through Fourth of July Fireworks', + } + }, { '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 - } - }] - + 'filesize_approx': 8912896, + 'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!', + } + }] 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')) + view_count = str_to_int(self._html_search_regex( + r'

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

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

\nLength:\n(.*?)

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

\nLength:\n\s*([0-9:]+).*?

', + webpage, 'duration', fatal=False)) - file_size = self._html_search_regex(r'

\nFilesize:\n(.*?)

',webpage,'filesize') - file_size = str_to_int(re.match(r'\d+',file_size).group())*131072 + filesize_approx = float_or_none(self._html_search_regex( + r'

\nFilesize:\n\s*([0-9.]+)\s*megabyte

', + webpage, 'filesize', fatal=False), invscale=1024 * 1024) return { 'id': video_id, + 'description': description, 'title': title, - 'url':video_url, - 'view_count':view_count, - 'duration':duration, - 'filesize':file_size - - } \ No newline at end of file + 'url': video_url, + 'view_count': view_count, + 'duration': duration, + 'filesize_approx': filesize_approx, + }