-1 urlib Example

import urllib.request
import json
from html.parser import HTMLParser

class 

def main1():
    webUrl = urllib.request.urlopen("http://www.baidu.com")
    print(str(webUrl.getcode()))
    data = webUrl.read()
    print(data)

-2 Parser HTML Example

# 
# Example file for parsing and processing HTML
#

# import the HTMLParser module
# in Python 3 you need to import from html.parser
from html.parser import HTMLParser

metacount = 0;

# create a subclass of HTMLParser and override the handler methods
class MyHTMLParser(HTMLParser):
  # function to handle an opening tag in the doc
  # this will be called when the closing ">" of the tag is reached
  def handle_starttag(self, tag, attrs):
    global metacount
    if tag == "meta":
      metacount += 1

    print ("Encountered a start tag:", tag)
    pos = self.getpos() # returns a tuple indication line and character
    print ("\tAt line: ", pos[0], " position ", pos[1])

    if attrs.__len__() > 0:
      print ("\tAttributes:")
      for a in attrs:
        print ("\t", a[0],"=",a[1])
      
  # function to handle the ending tag
  def handle_endtag(self, tag):
    print ("Encountered an end tag:", tag)
    pos = self.getpos()
    print ("\tAt line: ", pos[0], " position ", pos[1])
    
  # function to handle character and text data (tag contents)
  def handle_data(self, data):
    if (data.isspace()):
      return
    print ("Encountered some text data:", data)
    pos = self.getpos()
    print ("\tAt line: ", pos[0], " position ", pos[1])
  
  # function to handle the processing of HTML comments
  def handle_comment(self, data):
    print ("Encountered comment:", data)
    pos = self.getpos()
    print ("\tAt line: ", pos[0], " position ", pos[1])

def main():
  # instantiate the parser and feed it some HTML
  parser = MyHTMLParser()
    
  # open the sample HTML file and read it
  f = open("samplehtml.html")
  if f.mode == "r":
    contents = f.read() # read the entire file
    parser.feed(contents)
  
  print ("%d meta tags encountered" % metacount)

if __name__ == "__main__":
  main();

-2 Parser XML Example

# 
# Example file for parsing and processing XML
#

import xml.dom.minidom

def main():
  # use the parse() function to load and parse an XML file
  doc = xml.dom.minidom.parse("samplexml.xml")
  
  # print out the document node and the name of the first child tag
  print (doc.nodeName)
  print (doc.firstChild.tagName)
  
  # get a list of XML tags from the document and print each one
  skills = doc.getElementsByTagName("skill")
  print ("%d skills:" % skills.length)
  for skill in skills:
    print (skill.getAttribute("name"))
    
  # create a new XML tag and add it into the document
  newSkill = doc.createElement("skill")
  newSkill.setAttribute("name", "jQuery")
  doc.firstChild.appendChild(newSkill)

  skills = doc.getElementsByTagName("skill")
  print ("%d skills:" % skills.length)
  for skill in skills:
    print (skill.getAttribute("name"))
        
if __name__ == "__main__":
  main();