Python3中urllib详细使用方法(header,代理,超时,认证,异常处理)
2016-03-12 08:31
761 查看
Python爬虫视频教程零基础小白到scrapy爬虫高手-轻松入门
https://item.taobao.com/item.htm?spm=a1z38n.10677092.0.0.482434a6EmUbbW&id=564564604865
urllib是python的一个获取url(Uniform Resource Locators,统一资源定址器)了,我们可以利用它来抓取远程的数据进行保存哦,下面整理了一些关于urllib使用中的一些关于header,代理,超时,认证,异常处理处理方法,下面一起来看看。
python3 抓取网页资源的 N 种方法
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.111cn.net ')
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://www.111cn.net /")
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://www.111cn.net /")
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 = "https://www.111cn.net /"
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://www.111cn.net ").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://www.111cn.net /')
a = urllib.request.urlopen(req).read()
print(a)
https://item.taobao.com/item.htm?spm=a1z38n.10677092.0.0.482434a6EmUbbW&id=564564604865
urllib是python的一个获取url(Uniform Resource Locators,统一资源定址器)了,我们可以利用它来抓取远程的数据进行保存哦,下面整理了一些关于urllib使用中的一些关于header,代理,超时,认证,异常处理处理方法,下面一起来看看。
python3 抓取网页资源的 N 种方法
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.111cn.net ')
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://www.111cn.net /")
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://www.111cn.net /")
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 = "https://www.111cn.net /"
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://www.111cn.net ").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://www.111cn.net /')
a = urllib.request.urlopen(req).read()
print(a)
相关文章推荐
- python代码风格-PEP8
- python之路--Django
- Sublime Text 2下搭建Python环境常见错误
- Python中使用with语句同时打开多个文件
- 利用Python实现朴素贝叶斯文本分类
- “笨办法学python”学习笔记-一些附加题
- Python回顾与整理1:Python基础
- 用Python实现多核心并行计算
- Python语言的面相对象编程方式初步学习
- 使用Python内置的模块与函数进行不同进制的数的转换
- 编写Python小程序来统计测试脚本的关键字
- 如何部署Python Web应用:记录一次Heroku部署完整过程
- python 字符串
- python的第一天
- win7,python安装pip的问题
- 用 eric6 与 PyQt5 实现python的极速GUI编程(系列01)--Hello world!
- python 作用域
- python 钩子函数详解
- Python3 mysql数据库操作
- python使用过程中遇到的各种奇怪的问题