抓取网页能源的,Python3中urllib详细使用办法

作者: 网络编程  发布:2019-09-03

python3 抓取网页能源的 N 种方法,python3抓取

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 图片 1

#! /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]' : '[email protected]',
          '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"))

图片 2
  4、发送数据和header 图片 3

#! /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]' : '[email protected]',
          '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"))

图片 4
  5、http 错误 图片 5

#! /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"))

图片 6   6、极度管理1 图片 7

#! /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"))

图片 8
  7、万分管理2 图片 9

#! /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"))

图片 10
  8、HTTP 认证 图片 11

#! /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)

图片 12
  9、使用代理 图片 13

#! /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)

图片 14
  10、超时 图片 15

#! /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)

图片 16  

抓取网页能源的 N 种方法,python3抓取 1、最简便易行 import urllib.request response = urllib.request.urlopen('') html = response.read() 2、使用...

 

python3 抓取网页能源的 N 种方法

1、最简单

import urllib.request
response = urllib.request.urlopen('')
html = response.read()

2、使用 Request

import urllib.request

req = urllib.request.Request('')
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 = ''
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', '')
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 = ''
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(' ')
try:
urllib.request.urlopen(req)
except urllib.error.HTTPError as e:
print(e.code)
print(e.read().decode("utf8"))

6、格外管理1

#! /usr/bin/env python3

from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
req = Request(" /")
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、格外管理2

#! /usr/bin/env python3

from urllib.request import Request, urlopen
from urllib.error import  URLError
req = Request(" /")
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://www.111cn.net /"
password_mgr.add_password(None, top_level_url, 'rekfan', 'xxxxxx')

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 = " /"
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(" ").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(' /')
a = urllib.request.urlopen(req).read()
print(a)

本文由王中王开奖结果发布于网络编程,转载请注明出处:抓取网页能源的,Python3中urllib详细使用办法

关键词: