From 95be19d436d1938d104310e194e85ea5a10c3353 Mon Sep 17 00:00:00 2001
From: Xie Yanbo <xieyanbo@gmail.com>
Date: Sun, 4 Sep 2016 23:23:40 +0800
Subject: [PATCH 1/4] [miaopai] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/miaopai.py    | 44 ++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)
 create mode 100644 youtube_dl/extractor/miaopai.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 8c6ee0503..d511b04bc 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -471,6 +471,7 @@ from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .mgtv import MGTVIE
+from .miaopai import MiaoPaiIE
 from .microsoftvirtualacademy import (
     MicrosoftVirtualAcademyIE,
     MicrosoftVirtualAcademyCourseIE,
diff --git a/youtube_dl/extractor/miaopai.py b/youtube_dl/extractor/miaopai.py
new file mode 100644
index 000000000..c36b441b8
--- /dev/null
+++ b/youtube_dl/extractor/miaopai.py
@@ -0,0 +1,44 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import sanitized_Request
+
+
+class MiaoPaiIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+).htm'
+    _TEST = {
+        'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
+        'md5': '095ed3f1cd96b821add957bdc29f845b',
+        'info_dict': {
+            'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
+            'ext': 'mp4',
+            'title': '西游记音乐会的秒拍视频',
+            'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
+        }
+    }
+
+    _USER_AGENT_IPAD = 'User-Agent:Mozilla/5.0 ' \
+                       '(iPad; CPU OS 9_1 like Mac OS X) ' \
+                       'AppleWebKit/601.1.46 (KHTML, like Gecko) ' \
+                       'Version/9.0 Mobile/13B143 Safari/601.1'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        request = sanitized_Request(url)
+        request.add_header('User-Agent', self._USER_AGENT_IPAD)
+        webpage = self._download_webpage(request, video_id)
+
+        title = self._html_search_regex(r'<title>([^<]*)</title>',
+                                        webpage,
+                                        'title')
+        regex = r"""<div *class=['"]video_img[^>]*data-url=['"]([^'"]*\.jpg)['"]"""
+        thumbnail = self._html_search_regex(regex, webpage, '')
+        regex = r"""<video *[^>]*src=['"]([^'"]*)['"]""",
+        video_url = self._html_search_regex(regex, webpage, '')
+
+        return {'id': video_id,
+                'title': title,
+                'url': video_url,
+                'thumbnail': thumbnail,
+                }

From a493f1020888e87a464ab8a948c797c18fc3aca3 Mon Sep 17 00:00:00 2001
From: Xie Yanbo <xieyanbo@gmail.com>
Date: Mon, 5 Sep 2016 23:08:33 +0800
Subject: [PATCH 2/4] using _parse_html5_media_entries to parse video tag

---
 youtube_dl/extractor/miaopai.py | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/youtube_dl/extractor/miaopai.py b/youtube_dl/extractor/miaopai.py
index c36b441b8..2477d1009 100644
--- a/youtube_dl/extractor/miaopai.py
+++ b/youtube_dl/extractor/miaopai.py
@@ -34,11 +34,11 @@ class MiaoPaiIE(InfoExtractor):
                                         'title')
         regex = r"""<div *class=['"]video_img[^>]*data-url=['"]([^'"]*\.jpg)['"]"""
         thumbnail = self._html_search_regex(regex, webpage, '')
-        regex = r"""<video *[^>]*src=['"]([^'"]*)['"]""",
-        video_url = self._html_search_regex(regex, webpage, '')
+        videos = self._parse_html5_media_entries(url, webpage, video_id)
+        info = videos[0]
 
-        return {'id': video_id,
-                'title': title,
-                'url': video_url,
-                'thumbnail': thumbnail,
-                }
+        info.update({'id': video_id,
+                     'title': title,
+                     'thumbnail': thumbnail,
+                     })
+        return info

From f87feb4b688f7b6e02714f8405c8343e27956400 Mon Sep 17 00:00:00 2001
From: Yen Chi Hsuan <yan12125@gmail.com>
Date: Thu, 8 Sep 2016 00:28:33 +0800
Subject: [PATCH 3/4] [miaopai] Coding style (#10556)

---
 youtube_dl/extractor/miaopai.py | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/youtube_dl/extractor/miaopai.py b/youtube_dl/extractor/miaopai.py
index 2477d1009..f9e35ac7f 100644
--- a/youtube_dl/extractor/miaopai.py
+++ b/youtube_dl/extractor/miaopai.py
@@ -2,11 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import sanitized_Request
 
 
 class MiaoPaiIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+).htm'
+    _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
     _TEST = {
         'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
         'md5': '095ed3f1cd96b821add957bdc29f845b',
@@ -18,27 +17,24 @@ class MiaoPaiIE(InfoExtractor):
         }
     }
 
-    _USER_AGENT_IPAD = 'User-Agent:Mozilla/5.0 ' \
-                       '(iPad; CPU OS 9_1 like Mac OS X) ' \
-                       'AppleWebKit/601.1.46 (KHTML, like Gecko) ' \
-                       'Version/9.0 Mobile/13B143 Safari/601.1'
+    _USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        request = sanitized_Request(url)
-        request.add_header('User-Agent', self._USER_AGENT_IPAD)
-        webpage = self._download_webpage(request, video_id)
+        webpage = self._download_webpage(
+            url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
 
-        title = self._html_search_regex(r'<title>([^<]*)</title>',
-                                        webpage,
-                                        'title')
-        regex = r"""<div *class=['"]video_img[^>]*data-url=['"]([^'"]*\.jpg)['"]"""
-        thumbnail = self._html_search_regex(regex, webpage, '')
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+        thumbnail = self._html_search_regex(
+            r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
+            webpage, 'thumbnail', fatal=False, group='url')
         videos = self._parse_html5_media_entries(url, webpage, video_id)
         info = videos[0]
 
-        info.update({'id': video_id,
-                     'title': title,
-                     'thumbnail': thumbnail,
-                     })
+        info.update({
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+        })
         return info

From b84d311d53a4cc023eb458072c09cf382f45c762 Mon Sep 17 00:00:00 2001
From: Yen Chi Hsuan <yan12125@gmail.com>
Date: Thu, 8 Sep 2016 00:29:55 +0800
Subject: [PATCH 4/4] [ChangeLog] Update for #10556

---
 ChangeLog | 1 +
 1 file changed, 1 insertion(+)

diff --git a/ChangeLog b/ChangeLog
index 8322af9d1..52c066c99 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,6 +1,7 @@
 version <unreleased>
 
 Extractors
++ [miaopai] New extractor (#10556)
 * [gamestar] Fix metadata extraction (#10479)
 + [bilibili] Support episodes (#10190)
 + [tvnoe] New extractor (#10524)