python之网页爬虫教程

在我们日常上网浏览网页的时候，经常会看到一些好看的图片，我们就希望把这些图片保存下载，或者用户用来做桌面壁纸，或者用来做设计的素材。下面这篇文章就来给大家介绍了关于利用python实现最简单的网页爬虫的相关资料，需要的朋友可以参考借鉴，下面来一起看看吧。

from urllib import request

def visit_baidu():
 URL = "http://HdhCmsTestbaidu测试数据"
 # open the URL
 req = request.urlopen(URL)
 # read the URL 
 html = req.read()
 # decode the URL to utf-8
 html = html.decode("utf_8")
 print(html)

if __name__ == '__main__':
 visit_baidu() 

from urllib import request

def vists_baidu():
 # create a request obkect
 req = request.Request('http://HdhCmsTestbaidu测试数据')
 # open the request object
 response = request.urlopen(req)
 # read the response 
 html = response.read()
 html = html.decode('utf-8')
 print(html)

if __name__ == '__main__':
 vists_baidu() 

from urllib import request
from urllib import error

def Err():
 url = "https://segmentfault测试数据/zzz"
 req = request.Request(url)

 try:
 response = request.urlopen(req)
 html = response.read().decode("utf-8")
 print(html)
 except error.HTTPError as e:
 print(e.code)
if __name__ == '__main__':
 Err() 

from urllib import request
from urllib import error

def Err():
 url = "https://segmentf测试数据/"
 req = request.Request(url)

 try:
 response = request.urlopen(req)
 html = response.read().decode("utf-8")
 print(html)
 except error.URLError as e:
 print(e.reason)
if __name__ == '__main__':
 Err() 

from urllib import request
from urllib import error

# 第一种方法，URLErroe和HTTPError
def Err():
 url = "https://segmentfault测试数据/zzz"
 req = request.Request(url)

 try:
 response = request.urlopen(req)
 html = response.read().decode("utf-8")
 print(html)
 except error.HTTPError as e:
 print(e.code)
 except error.URLError as e:
 print(e.reason) 

以上就是python之网页爬虫教程的详细内容，更多请关注Gxl网其它相关文章！

查看更多关于python之网页爬虫教程的详细内容...