From db40364b8767839cc1abf5ece53511167d70f792 Mon Sep 17 00:00:00 2001 From: Mohammad Teimori Pabandi Date: Thu, 26 Mar 2015 18:17:21 +0430 Subject: [PATCH] [Varzesh3] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/varzesh3.py | 63 ++++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) create mode 100644 youtube_dl/extractor/varzesh3.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b0df52afdf..3011b784d2 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -548,6 +548,7 @@ from .ultimedia import UltimediaIE from .unistra import UnistraIE from .urort import UrortIE from .ustream import UstreamIE, UstreamChannelIE +from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veehd import VeeHDIE from .veoh import VeohIE diff --git a/youtube_dl/extractor/varzesh3.py b/youtube_dl/extractor/varzesh3.py new file mode 100644 index 0000000000..85dcd8734c --- /dev/null +++ b/youtube_dl/extractor/varzesh3.py @@ -0,0 +1,63 @@ +# coding: utf-8 +from __future__ import unicode_literals +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) +import re + + +class Varzesh3IE(InfoExtractor): + _VALID_URL = r'(?P(https?://(?:www\.)?video\.varzesh3\.com)/(?P.+))' + _TESTS = [ + { + 'url': 'http://video.varzesh3.com/video/%D8%AF%D8%A7%D9%86%D9%85%D8%A7%D8%B1%DA%A9-3-2-%D8%A2%D9%85%D8%B1%DB%8C%DA%A9%D8%A7/', + 'md5': 'c4b850780df9374b078463c5cf6b3318', + 'info_dict': { + 'url': 'http://dl1.video.varzesh3.com/video/clip94/1/international/friendly/usa_2_3_danmark.mp4', + 'id': '76464', + 'ext': 'mp4', + 'title': u'دانمارک ۳-۲ آمریکا (گلهای بازی)', + 'thumbnail': 'http://video.varzesh3.com/wp-content/uploads/250315_usa_danmark_site.jpg', + 'description': u'بازی دوستانه ۲۰۱۵', + + } + }, + { + 'url': 'http://video.varzesh3.com/germany/bundesliga/5-%D9%88%D8%A7%DA%A9%D9%86%D8%B4-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AF%D8%B1%D9%88%D8%A7%D8%B2%D9%87%E2%80%8C%D8%A8%D8%A7%D9%86%D8%A7%D9%86%D8%9B%D9%87%D9%81%D8%AA%D9%87-26-%D8%A8%D9%88%D9%86%D8%AF%D8%B3/', + 'md5': '2a933874cb7dce4366075281eb49e855', + 'info_dict': { + 'url': 'http://dl1.video.varzesh3.com/video/clip94/1/video/namayeshi/saves_week26.mp4', + 'id': '76337', + 'ext': 'mp4', + 'title': u'۵ واکنش برتر دروازه‌بانان؛هفته ۲۶ بوندسلیگا', + 'thumbnail': 'http://video.varzesh3.com/wp-content/uploads/230315_saves_week26.jpg', + 'description': u'فصل ۲۰۱۵-۲۰۱۴', + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + if not 'shortlink' in webpage: + raise ExtractorError('URL has no videos or there is a problem.') + + title = self._html_search_regex(r'meta[^>]+property="og:title"[^>]+content="([^"]+)"', webpage, 'title') + video_link = self._html_search_regex(r'source[^>]+src="([^"]+)"', webpage, 'video_link') + vid_id = self._html_search_regex(r"link[^>]+rel='canonical'[^>]+href='\/\?p=([^']+)'\/>", webpage, 'vid_id') + try: + description = self._html_search_regex(r'
(.*?)
', webpage, 'description', flags=re.DOTALL) + except: + description = title + thumbnail = self._html_search_regex(r'link[^>]+rel="image_src"[^>]+href="([^"]+)"', webpage, 'thumbnail') + + return { + 'url': video_link, + 'id': vid_id, + 'title': title, + 'ext': video_link.split(".")[-1], + 'description': description, + 'thumbnail': thumbnail, + }