Python - Very Simple Parser (See related posts)

   1  
   2  from sgmllib import SGMLParser
   3  
   4  import urllib
   5  
   6  class ParserHTML(SGMLParser):
   7  
   8  	def scrivi(self):
   9  		self.f = open('/tmp/fileOUT.html', 'w')
  10  
  11  	def unknown_starttag(self, tag, attrs):
  12  
  13  		value = 0
  14  		startTAG = '<' + tag
  15  		
  16  		for i in attrs:
  17  			if(i[0].lower() == i[1].lower() and not i[0] == i[1]):
  18  				startTAG = startTAG[:-1] + ' ' + str(i[1])
  19  				value = 1
  20  			else:
  21  				startTAG += ' ' + str(i[0]) + '="' + str(i[1]) + '"'
  22  				value = 0
  23  		
  24  		if(value == 1): startTAG += '"'
  25  
  26  		startTAG += '>'
  27  		self.f.write(startTAG + "\n")
  28  
  29  	def handle_data(self, data):
  30  
  31  		self.f.write(data + "\n")
  32  
  33  	def unknown_endtag(self, tag):
  34  
  35  		self.f.write('</' + tag + '>' + "\n")
  36  
  37  if __name__ == '__main__':
  38  
  39  	p = ParserHTML()
  40  	p.scrivi()
  41  	p.feed(open('/tmp/fileIN.html', 'r').read())