From a745475808e125a590afb14df48c565309d3f75c Mon Sep 17 00:00:00 2001
From: Behrooz <behrooz.abbasy@gmail.com>
Date: Fri, 8 May 2015 02:50:46 +0200
Subject: [PATCH] Ir90Tv Add new extractor
---
youtube_dl/extractor/__init__.py | 1 +
youtube_dl/extractor/ir90tv.py | 41 ++++++++++++++++++++++++++++++++
2 files changed, 42 insertions(+)
create mode 100644 youtube_dl/extractor/ir90tv.py
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 5dfa781f8..ee05a6958 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -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
index 000000000..5aa9d6ff4
--- /dev/null
+++ b/youtube_dl/extractor/ir90tv.py
@@ -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