youtube-dl

commit 9c2718898891678038dffcb683c3948722c6b47d
parent 84b91dd4e3cd45498fb6cd3c7aa611816f61a3d5
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Thu,  8 Sep 2016 00:31:06 +0800

Merge branch 'xyb-miaopai'

Diffstat:
M
ChangeLog
 | 
1
+
M
youtube_dl/extractor/extractors.py
 | 
1
+
A
youtube_dl/extractor/miaopai.py
 | 
40
++++++++++++++++++++++++++++++++++++++++

3 files changed, 42 insertions(+), 0 deletions(-)
diff --git 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)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -476,6 +476,7 @@ 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
@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class MiaoPaiIE(InfoExtractor):
+    _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',
+        '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 = '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)
+        webpage = self._download_webpage(
+            url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
+
+        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,
+        })
+        return info