python3实现抓取网页资源的 N 种方法_网络技术_宿州市腾雀网络科技有限公司

这两天学习了python3实现抓取网页资源的方法，发现了很多种方法，所以，今天添加一点小笔记。

1、最简单

import urllib.request
response = urllib.request.urlopen('http://python.org/')
html = response.read()

2、使用 Request

import urllib.request
 
req = urllib.request.Request('http://python.org/')
response = urllib.request.urlopen(req)
the_page = response.read()

3、发送数据

#! /usr/bin/env python3
 
import urllib.parse
import urllib.request
 
url = 'http://localhost/login.php'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
     'act' : 'login',
     'login[email]' : 'yzhang@i9i8.com',
     'login[password]' : '123456'
     }
 
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data)
req.add_header('Referer', 'http://www.python.org/')
response = urllib.request.urlopen(req)
the_page = response.read()
 
print(the_page.decode("utf8"))

4、发送数据和header

#! /usr/bin/env python3
 
import urllib.parse
import urllib.request
 
url = 'http://localhost/login.php'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
     'act' : 'login',
     'login[email]' : 'yzhang@i9i8.com',
     'login[password]' : '123456'
     }
headers = { 'User-Agent' : user_agent }
 
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data, headers)
response = urllib.request.urlopen(req)
the_page = response.read()
 
print(the_page.decode("utf8"))

5、http 错误

#! /usr/bin/env python3
 
import urllib.request
 
req = urllib.request.Request('http://www.python.org/fish.html')
try:
  urllib.request.urlopen(req)
except urllib.error.HTTPError as e:
  print(e.code)
  print(e.read().decode("utf8"))

6、异常处理1

#! /usr/bin/env python3
 
from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
req = Request("http://twitter.com/")
try:
  response = urlopen(req)
except HTTPError as e:
  print('The server couldn\'t fulfill the request.')
  print('Error code: ', e.code)
except URLError as e:
  print('We failed to reach a server.')
  print('Reason: ', e.reason)
else:
  print("good!")
  print(response.read().decode("utf8"))

7、异常处理2

#! /usr/bin/env python3
 
from urllib.request import Request, urlopen
from urllib.error import URLError
req = Request("http://twitter.com/")
try:
  response = urlopen(req)
except URLError as e:
  if hasattr(e, 'reason'):
    print('We failed to reach a server.')
    print('Reason: ', e.reason)
  elif hasattr(e, 'code'):
    print('The server couldn\'t fulfill the request.')
    print('Error code: ', e.code)
else:
  print("good!")
  print(response.read().decode("utf8"))

8、HTTP 认证

#! /usr/bin/env python3
 
import urllib.request
 
# create a password manager
password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()
 
# Add the username and password.
# If we knew the realm, we could use it instead of None.
top_level_url = "https://cms.tetx.com/"
password_mgr.add_password(None, top_level_url, 'yzhang', 'cccddd')
 
handler = urllib.request.HTTPBasicAuthHandler(password_mgr)
 
# create "opener" (OpenerDirector instance)
opener = urllib.request.build_opener(handler)
 
# use the opener to fetch a URL
a_url = "https://cms.tetx.com/"
x = opener.open(a_url)
print(x.read())
 
# Install the opener.
# Now all calls to urllib.request.urlopen use our opener.
urllib.request.install_opener(opener)
 
a = urllib.request.urlopen(a_url).read().decode('utf8')
print(a)

9、使用代理

#! /usr/bin/env python3
 
import urllib.request
 
proxy_support = urllib.request.ProxyHandler({'sock5': 'localhost:1080'})
opener = urllib.request.build_opener(proxy_support)
urllib.request.install_opener(opener)

 
a = urllib.request.urlopen("http://g.cn").read().decode("utf8")
print(a)

10、超时

#! /usr/bin/env python3
 
import socket
import urllib.request
 
# timeout in seconds
timeout = 2
socket.setdefaulttimeout(timeout)
 
# this call to urllib.request.urlopen now uses the default timeout
# we have set in the socket module
req = urllib.request.Request('http://twitter.com/')
a = urllib.request.urlopen(req).read()
print(a)

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。

# python # 抓取网页 # python抓取网页内容 # python抓取网页数据 # 利用Python3分析sitemap.xml并抓取导出全站链接详解 # 详解python3百度指数抓取实例 # Python3使用requests包抓取并保存网页源码的方法 # 使用Python3编写抓取网页和只抓网页图片的脚本 # python3抓取中文网页的方法 # 在Python3中使用asyncio库进行快速数据抓取的教程 # Python使用lxml模块和Requests模块抓取HTML页面的教程 # 用Python程序抓取网页的HTML信息的一个小实例 # python抓取并保存html页面时乱码问题的解决方法 # Python使用urllib2模块抓取HTML页面资源的实例分享 # Python3实现抓取javascript动态生成的html网页功能示例 # 种方法 # 这两天 # 最简单 # 大家多多 # 发现了 # NT # Windows # email # act # values # MSIE # user_agent # php # login # compatible # Mozilla # yzhang # decode # print # www

相关栏目：【网站优化151355 】【网络推广146373 】【网络技术251813 】【 AI营销90571 】