commit 81650f95e2d28f4acc8a864c5221f1e95f75adda
parent 34dbcb8505897ffc91197e6db909bf38d390475e
Author: Sergey M․ <dstftw@gmail.com>
Date: Sun, 13 Jul 2014 04:03:22 +0700
[ruhd] Add extractor
Diffstat:
2 files changed, 47 insertions(+), 0 deletions(-)
diff --git 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
@@ -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<id>\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'<param name="src" value="([^"]+)"', webpage, 'video url')
+ title = self._html_search_regex(
+ r'<title>([^<]+) RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title')
+ description = self._html_search_regex(
+ r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False)
+ thumbnail = self._html_search_regex(
+ r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False)
+ if thumbnail:
+ thumbnail = 'http://www.ruhd.ru' + thumbnail
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ }