1.爬python官网，解析页面html信息，python3使用urllib库

import urllib.request

1. request type

req = urllib.request.Request("http://python.org/")
resp1 = urllib.request.urlopen(req)
print("*********req1*************")
print(resp1.read())
print("**********************")

2. request type

resp2 = urllib.request.urlopen("http://python.org/")
print("*********req2*************")
print(resp2.read())
print("**********************")

#########################################

url path get response

#########################################
def getPageHtml(url):
response = urllib.request.urlopen(url)
return response.read()

split page html data

def splitPageHtml(resouceData):
dataArr = [data for data in resouceData.split()]
print("dataArr len is :" + len(dataArr))
print("dataArr is start:")
print(dataArr[0:100])
print("dataArr is end:")

resource = getPageHtml("http://python.org")

print(splitPageHtml(resource))