Qianmo Add New Extractor

youtube_dl/extractor/__init__.py

@@ -477,6 +477,7 @@ from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .puls4 import Puls4IE
 from .pyvideo import PyvideoIE
+from .qianmo import QianmoIE
 from .qqmusic import (
     QQMusicIE,
     QQMusicSingerIE,

youtube_dl/extractor/qianmo.py

@@ -0,0 +1,48 @@
+# http://qianmo.com/bazingayue/324
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from lxml import html
+import requests
+
+import re
+
+
+class QianmoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?qianmo\.com/(?P<user>[A-Za-z]+)/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://qianmo.com/kawaei/281',
+        'info_dict': {
+            'id': '281',
+            'ext': 'mp4',
+            'title': '[中字] Google新logo宣传片 「Google, 进化」 - 阡陌视频社区',
+            # TODO more properties, either as:
+            # * A value
+            # * MD5 checksum; start the string with md5:
+            # * A regular expression; start the string with re:
+            # * Any Python type (for example int or float)
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        print type(webpage)
+        # TODO more code goes here, for example ...
+        title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
+        print title
+        # postInfo = self._html_search_regex(r'postInfo =(.*?);', webpage, u'postInfo')
+        # regex = 
+        video_url = self._html_search_regex(r'"urls":\["(.*?)"\],', webpage, 'url')
+        print video_url
+        print "Hanh"
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'ext': 'mp4',
+            # TODO more properties (see youtube_dl/extractor/common.py)
+        }