Live Demo and reset function added

README.md

@@ -7,4 +7,5 @@ Progress
 ===
 ### Text Extractor
 * 正文提取，参考 [基于行块分布函数的通用网页正文抽取算法](https://cx-extractor.googlecode.com/files/%E5%9F%BA%E4%BA%8E%E8%A1%8C%E5%9D%97%E5%88%86%E5%B8%83%E5%87%BD%E6%95%B0%E7%9A%84%E9%80%9A%E7%94%A8%E7%BD%91%E9%A1%B5%E6%AD%A3%E6%96%87%E6%8A%BD%E5%8F%96%E7%AE%97%E6%B3%95.pdf) 实现 Python 版本做粗略文本提取。
-	* Example: ```python extractor.py http://hb.qq.com/a/20130324/000235.htm```
+	* Example: ```python extractor.py http://hb.qq.com/a/20130324/000235.htm```
+	* Live Demo: [https://py-newt0n.rhcloud.com/](https://py-newt0n.rhcloud.com/)

extractor.py

@@ -11,14 +11,7 @@
 
 class Extractor(object):
 
-    rawPage = ''
-    text = ''
-    isGB = True
-    textLines = []
-    blocksLen = []
-    isCharsetGB = True
-
-    def __init__(self, url, blockSize=3):
+    def __init__(self, url='', blockSize=3):
         self.url = url
         self.blockSize = blockSize
 
@@ -41,6 +34,14 @@ def __init__(self, url, blockSize=3):
         # Reduce redundancy
         self.reRedun = re.compile('\n{%s,}' % (self.blockSize+1))
 
+    def reset(self):
+        self.rawPage = ''
+        self.text = ''
+        self.isGB = True
+        self.textLines = []
+        self.blocksLen = []
+        self.isCharsetGB = True
+
     def getRawPage(self):
         self.rawPage = urllib2.urlopen(self.url).read()
 
@@ -89,10 +90,15 @@ def calcBlockLens(self):
             self.blocksLen.append(blockLen)
 
     # Merge the most possibile blocks as the final plaintext
-    def getPlainText(self):
+    def getPlainText(self, url=''):
+        self.reset()
+        if url:
+            self.url = url
         self.getRawPage()
         self.handleEncoding()
         preProcDoc = self.preProcess(self.rawPage)
+        # f = open('dump')
+        # preProcDoc = f.read()
         self.getTextLines(preProcDoc)
         self.calcBlockLens()