Source Code for Module SmootLight.inputs.HTMLInput

 1  from operationscore.Input import * 
 2  import urllib, re 
 3   
 4  """ 
 5  HTML Input, which takes 2 arguments: 
 6  - 'Src': a URL to a web page, and 
 7  - 'Regex': a Regex to parse data out of the web page. 
 8  The input parses the source code of the web page according to the regex, and processes the parsed regex groups. 
 9  """ 
10 -class HTMLInput(Input): 
11 -    def inputInit(self): 
12          self.src = self.argDict['Src'] 
13          self.regex = self.argDict['Regex'] 
14           
15 -    def getHTML(self): 
16          self.sock = urllib.urlopen(self.src); 
17          self.html = self.sock.read() 
18          self.sock.close() 
19   
20 -    def sensingLoop(self): 
21          self.getHTML() 
22          self.dataList = [] 
23           
24          pattern = re.compile(self.regex) 
25          matchObj = pattern.search(self.html)         
26          self.dataList = matchObj.groups() 
27   
28          self.respond(self.dataList) 
29