Version:Python3.5 Os:win10
#伪装浏览器抓取网页信息：
import urllib.request
url = 'http://www.baidu.com/'
header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
req=urllib.request.Request(url=url,headers=header)
webPage=urllib.request.urlopen(req)
data = webPage.read()
data = data.decode('UTF-8')
print(data)
print('---------')
print(type(webPage))
print('---------')
print(webPage.geturl())
print('---------')
print(webPage.info())
print('---------')
print(webPage.getcode())
#保存爬取回来的信息：
def saveFile(data):
save_path = 'D:\temp.out'
f_obj = open(save_path, 'wb') # wb 表示打开方式
f_obj.write(data)
f_obj.close()
saveFile(data)
转载请注明原文地址: https://ju.6miu.com/read-1311201.html
