分享十种py3爬取网页资源的方法

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(&＃39;http://python.org/&＃39;)
html = response.read()

2、使用 Request

import urllib.request
 
req = urllib.request.Request(&＃39;http://python.org/&＃39;)
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 = &＃39;http://localhost/login.php&＃39;
user_agent = &＃39;Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)&＃39;
values = {
     &＃39;act&＃39; : &＃39;login&＃39;,
     &＃39;login[email]&＃39; : &＃39;yzhang@i9i8.com&＃39;,
     &＃39;login[password]&＃39; : &＃39;123456&＃39;
     }
 
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data)
req.add_header(&＃39;Referer&＃39;, &＃39;http://www.python.org/&＃39;)
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 = &＃39;http://localhost/login.php&＃39;
user_agent = &＃39;Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)&＃39;
values = {
     &＃39;act&＃39; : &＃39;login&＃39;,
     &＃39;login[email]&＃39; : &＃39;yzhang@i9i8.com&＃39;,
     &＃39;login[password]&＃39; : &＃39;123456&＃39;
     }
headers = { &＃39;User-Agent&＃39; : 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(&＃39;http://www.python.org/fish.html&＃39;)
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(&＃39;The server couldn\&＃39;t fulfill the request.&＃39;)
  print(&＃39;Error code: &＃39;, e.code)
except URLError as e:
  print(&＃39;We failed to reach a server.&＃39;)
  print(&＃39;Reason: &＃39;, 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, &＃39;reason&＃39;):
    print(&＃39;We failed to reach a server.&＃39;)
    print(&＃39;Reason: &＃39;, e.reason)
  elif hasattr(e, &＃39;code&＃39;):
    print(&＃39;The server couldn\&＃39;t fulfill the request.&＃39;)
    print(&＃39;Error code: &＃39;, 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, &＃39;yzhang&＃39;, &＃39;cccddd&＃39;)
 
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(&＃39;utf8&＃39;)
print(a)

9、使用代理

#! /usr/bin/env python3
 
import urllib.request
 
proxy_support = urllib.request.ProxyHandler({&＃39;sock5&＃39;: &＃39;localhost:1080&＃39;})
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(&＃39;http://twitter.com/&＃39;)
a = urllib.request.urlopen(req).read()
print(a)