From 81650f95e2d28f4acc8a864c5221f1e95f75adda Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Sun, 13 Jul 2014 04:03:22 +0700 Subject: [PATCH] [ruhd] Add extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/ruhd.py | 46 ++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) create mode 100644 youtube_dl/extractor/ruhd.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c215811c3..e89a83e32 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -240,6 +240,7 @@ from .rtbf import RTBFIE from .rtlnow import RTLnowIE from .rts import RTSIE from .rtve import RTVEALaCartaIE +from .ruhd import RUHDIE from .rutube import ( RutubeIE, RutubeChannelIE, diff --git a/youtube_dl/extractor/ruhd.py b/youtube_dl/extractor/ruhd.py new file mode 100644 index 000000000..55b58e5e6 --- /dev/null +++ b/youtube_dl/extractor/ruhd.py @@ -0,0 +1,46 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class RUHDIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P\d+)' + _TEST = { + 'url': 'http://www.ruhd.ru/play.php?vid=207', + 'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83', + 'info_dict': { + 'id': '207', + 'ext': 'divx', + 'title': 'КОТ бааааам', + 'description': 'классный кот)', + 'thumbnail': 're:^http://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'([^<]+)   RUHD.ru - Видео Высокого качества №1 в России!', webpage, 'title') + description = self._html_search_regex( + r'(?s)
(.+?)', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'