#使用urllib库爬取百度html代码 import urllib.request url1='http://www.baidu.com/' req=urllib.request.Request(url1) with urllib.request.urlopen(req) as response: data=response.read() htmlstr=data.decode() #这里的read方法获取了response的内容,并转换格式 print(htmlstr)
#获取标题和页面资源 from selenium import webdriver from time import sleep import re, requests a=webdriver.Chrome() a.get('http://www.baidu.com/') a.find_element_by_xpath("//*[@id='kw']").send_keys("宫崎骏") a.maximize_window() a.find_element_by_id("su").click() sleep(5) print(a.title) print(a.page_source) a.quit()