From 94b817edebb63c3d8485e1ae27cc394dd9e21f9d Mon Sep 17 00:00:00 2001
From: troywith77 <ruitang307@gmail.com>
Date: Tue, 9 May 2017 13:10:18 +0800
Subject: [PATCH] [pearvideo] Add extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/pear.py       | 34 ++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)
 create mode 100644 youtube_dl/extractor/pear.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 9d34447a9..75c1a3d0e 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -762,6 +762,7 @@ from .pandoratv import PandoraTVIE
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
+from .pear import PearIE
 from .people import PeopleIE
 from .periscope import (
     PeriscopeIE,
diff --git a/youtube_dl/extractor/pear.py b/youtube_dl/extractor/pear.py
new file mode 100644
index 000000000..77fd46852
--- /dev/null
+++ b/youtube_dl/extractor/pear.py
@@ -0,0 +1,34 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class PearIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pearvideo\.com/video_(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.pearvideo.com/video_1076290',
+        'info_dict': {
+            'id': '1076290',
+            'ext': 'mp4',
+            'title': '小浣熊在主人家玻璃上滚石头：没砸',
+            'description': '小浣熊找到一个小石头，仿佛发现了一个宝贝。它不停地用石头按在玻璃上，滚来滚去，吸引主人注意。',
+            'url': 'http://video.pearvideo.com/mp4/short/20170508/cont-1076290-10438018-hd.mp4'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<h1[^>]+class="video-tt">(.+)</h1>', webpage, 'title', fatal=False)
+        description = self._html_search_regex(r'<div[^>]+class="summary"[^>]*>([^<]+)<', webpage, 'description', fatal=False)
+        url = self._html_search_regex(r'hdUrl="(.*?)"', webpage, 'url', fatal=False)
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+            'url': url
+        }