]> git.bitcoin.ninja Git - youtube-dl/commitdiff
Ir90Tv Add new extractor
authorBehrooz <behrooz.abbasy@gmail.com>
Fri, 8 May 2015 00:50:46 +0000 (02:50 +0200)
committerBehrooz <behrooz.abbasy@gmail.com>
Fri, 8 May 2015 00:50:46 +0000 (02:50 +0200)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/ir90tv.py [new file with mode: 0644]

index 5dfa781f88d6fd1d9c05a23363c3b58f447c9d87..ee05a69583309105cc8f459e096590014057be39 100644 (file)
@@ -229,6 +229,7 @@ from .infoq import InfoQIE
 from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
+from .ir90tv import Ir90TvIE
 from .ivi import (
     IviIE,
     IviCompilationIE
diff --git a/youtube_dl/extractor/ir90tv.py b/youtube_dl/extractor/ir90tv.py
new file mode 100644 (file)
index 0000000..5aa9d6f
--- /dev/null
@@ -0,0 +1,41 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class Ir90TvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?90tv\.ir/video/(?P<id>[0-9]+)/.*'
+    _TEST = {
+        'url': 'http://90tv.ir/video/95719/%D8%B4%D8%A7%DB%8C%D8%B9%D8%A7%D8%AA-%D9%86%D9%82%D9%84-%D9%88-%D8%A7%D9%86%D8%AA%D9%82%D8%A7%D9%84%D8%A7%D8%AA-%D9%85%D9%87%D9%85-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7-940218',
+        'md5': '411dbd94891381960cb9e13daa47a869',
+        'info_dict': {
+            'id': '95719',
+            'ext': 'mp4',
+            'title': 'شایعات نقل و انتقالات مهم فوتبال اروپا 94/02/18',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # TODO more code goes here, for example ...
+        title = self._html_search_regex(
+            r'<title>\n90tv.ir :: (.*?)</title>', webpage, 'title')
+
+        video_url = self._search_regex(
+            r'<source[^>]+src="([^"]+)"', webpage, 'video url')
+
+        thumbnail = self._search_regex(r'poster="([^"]+)"', webpage, 'thumbnail url')
+        print thumbnail
+
+
+        return {
+            'url': video_url,
+            'id': video_id,
+            'title': title,
+            'video_url' : video_url,
+            'thumbnail' : thumbnail,
+        }
\ No newline at end of file