[Varzesh3] Add new extractor
[youtube-dl] / youtube_dl / extractor / varzesh3.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3 from .common import InfoExtractor
4 from ..utils import (
5     ExtractorError,
6 )
7 import re
8
9
10 class Varzesh3IE(InfoExtractor):
11     _VALID_URL = r'(?P<url>(https?://(?:www\.)?video\.varzesh3\.com)/(?P<id>.+))'
12     _TESTS = [
13     {
14         '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/',
15         'md5': 'c4b850780df9374b078463c5cf6b3318',
16         'info_dict': {
17             'url': 'http://dl1.video.varzesh3.com/video/clip94/1/international/friendly/usa_2_3_danmark.mp4',
18             'id': '76464',
19             'ext': 'mp4',
20             'title': u'دانمارک   ۳-۲   آمریکا (گلهای بازی)',
21             'thumbnail': 'http://video.varzesh3.com/wp-content/uploads/250315_usa_danmark_site.jpg',
22             'description': u'بازی دوستانه ۲۰۱۵',
23
24         }
25     },
26     {
27         '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/',
28         'md5': '2a933874cb7dce4366075281eb49e855',
29         'info_dict': {
30             'url': 'http://dl1.video.varzesh3.com/video/clip94/1/video/namayeshi/saves_week26.mp4',
31             'id': '76337',
32             'ext': 'mp4',
33             'title': u'۵ واکنش برتر دروازه‌بانان؛هفته ۲۶ بوندسلیگا',
34             'thumbnail': 'http://video.varzesh3.com/wp-content/uploads/230315_saves_week26.jpg',
35             'description': u'فصل ۲۰۱۵-۲۰۱۴',
36         }
37     },
38     ]
39
40     def _real_extract(self, url):
41         video_id = self._match_id(url)
42         webpage = self._download_webpage(url, video_id)
43
44         if not 'shortlink' in webpage:
45             raise ExtractorError('URL has no videos or there is a problem.')
46
47         title = self._html_search_regex(r'meta[^>]+property="og:title"[^>]+content="([^"]+)"', webpage, 'title')
48         video_link = self._html_search_regex(r'source[^>]+src="([^"]+)"', webpage, 'video_link')
49         vid_id = self._html_search_regex(r"link[^>]+rel='canonical'[^>]+href='\/\?p=([^']+)'\/>", webpage, 'vid_id')
50         try:
51             description = self._html_search_regex(r'<div class="matn">(.*?)</div>', webpage, 'description', flags=re.DOTALL)
52         except:
53             description = title
54         thumbnail = self._html_search_regex(r'link[^>]+rel="image_src"[^>]+href="([^"]+)"', webpage, 'thumbnail')
55
56         return {
57             'url': video_link,
58             'id': vid_id,
59             'title': title,
60             'ext': video_link.split(".")[-1],
61             'description': description,
62             'thumbnail': thumbnail,
63         }