python—urllib库的使用

其他 2019-01-07 10:56:48 阅读次数: 0

Urllib库

"""
python 内置的HTTP请求库
urllib.request 请求模块
urllib.error 异常处理模块
urllib.parse url解析模块
urllib.robotparser  robots.txt 解析模块
"""

# python2
import urllib2
response = urllib2.urlopen('http://www.baidu.com')
# python3
import urllib.request
resp = urllib.request.urlopen('http://www.baidu.com')

urllib的请求

# get 请求
import urllib.request
resp = urllib.request.urlopen('http://www.baidu.com')
print(resp.read().decode("utf-8"))

# post请求
import urllib.parse
import urllib.request
#http://httpbin.org/get  测试http请求
data = bytes(urllib.parse.urlencode({"world":"hello"}),encoding="utf8")
response = urllib.request.urlopen("http://httpbin.org/get",data=data)
print(response.read())

# 设置超时等待时间
import urllib.request
resp = urllib.request.urlopen('http://httpbin.org/get',timeout=1)
print(resp.read().decode("utf-8"))

# 异常处理
import socket
import urllib.request
import urllib.error

try:
	resp = urllib.request.urlopen('http://httpbin.org/get',timeout=0.1)
except urllib.error.URLError as e:
    if isinstance(e.reason,socket.timeout):
        print("TIME OUT")

urllib 响应

# 状态码和响应头
import urllib.request
resp = urllib.request.urlopen('http://httpbin.org/get',timeout=1)
print(resp.status)
print(resp.getheaders())
# 一个列表，列表里面是一个一个的2位元祖[("server","nginx"),]
print(resp.getheader("server")) # nginx

# 响应体的内容
print(response.read()decode("utf8"))

更为复杂的请求

# 使用urllib.request 创造一个对象，传入urlopen
import urllib.request

request = urllib.request.Request('https://python.org')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))


# 增加请求头和数据
from urllib import request, parse

url = 'http://httpbin.org/post'
headers = {
    'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
    'Host': 'httpbin.org'
}
dict = {
    'name': 'Germey'
}
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, headers=headers, method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

# 另外增加请求头的方法
from urllib import request, parse

url = 'http://httpbin.org/post'
dict = {
    'name': 'Germey'
}
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, method='POST')
req.add_header('User-Agent', 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

设置代理

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    'http': 'http://127.0.0.1:9743',
    'https': 'https://127.0.0.1:9743'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://httpbin.org/get')
print(response.read())

cookie

# cookie获取
import http.cookiejar, urllib.request

cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
for item in cookie:
	print(item.name+"="+item.value)
    
# 存cookie，保存到本地txt,MozillaCookieJar格式
import http.cookiejar, urllib.request
filename = "cookie.txt"
cookie = http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True, ignore_expires=True)

# LWPCookieJar格式保存cookie
import http.cookiejar, urllib.request
filename = 'cookie.txt'
cookie = http.cookiejar.LWPCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True, ignore_expires=True)

# 读取刚刚保存下来的cookie
import http.cookiejar, urllib.request
cookie = http.cookiejar.LWPCookieJar()
cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
print(response.read().decode('utf-8'))

异常处理

# 打印异常信息
from urllib import request, error
try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.URLError as e:
    print(e.reason)
    
# 捕捉详细的异常信息
from urllib import request, error

try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.HTTPError as e: #httperror 有三个属性
    print(e.reason, e.code, e.headers, sep='\n')
except error.URLError as e: #URLErrot 有一个属性
    print(e.reason)
else:
    print('Request Successfully')

# 异常原因
import socket
import urllib.request
import urllib.error

try:
    response = urllib.request.urlopen('https://www.baidu.com', timeout=0.01)
except urllib.error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason, socket.timeout):
        print('TIME OUT')

urlparse

# 传入url,将url分割
urllib.parse.urlparse(urlstring, scheme='', allow_fragments=True)

# url 拆分为标准结构，我们可以去取自己想要的片段
from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result), result)
"""
<class 'urllib.parse.ParseResult'> 
ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5', fragment='comment')

协议类型  域名 地址  
params='user'这个不常用到, 
query='id=5'

fragment='comment'
#fragment: 片段ID
该部分与上面的?后面的表单信息本质的区别就是这部分内容不会被传递到服务器端。一般用于页面的锚。就是我们常见的网站右下脚一般有一个回到顶部的按钮，一般就是使用其实现的。
"""

# 指定协议类型
from urllib.parse import urlparse

result = urlparse('www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)

# 如果已经指定了，后面的https不会生效
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)

# allow_fragments=False,#comment会向前拼接
from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', allow_fragments=False)
print(result)

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html#comment', allow_fragments=False)
print(result)

urlunparse

"""
与 urlparse是反函数
urlparse是拆分，urlunparse则是拼接的
"""

from urllib.parse import urlunparse
data = ['http', 'www.baidu.com', 'index.html', 'user', 'a=6', 'comment']
print(urlunparse(data))
# http://www.baidu.com/index.html;user?a=6#comment

urljoin

# url拼合 拼接
from urllib.parse import urljoin

# 拼接
print(urljoin('http://www.baidu.com', 'FAQ.html'))
# 以后者为准，覆盖掉前面
print(urljoin('http://www.baidu.com', 'https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html?question=2'))
print(urljoin('http://www.baidu.com?wd=abc', 'https://cuiqingcai.com/index.php'))
print(urljoin('http://www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com#comment', '?category=2'))

"""
http://www.baidu.com/FAQ.html
https://cuiqingcai.com/FAQ.html
https://cuiqingcai.com/FAQ.html
https://cuiqingcai.com/FAQ.html?question=2
https://cuiqingcai.com/index.php
http://www.baidu.com?category=2#comment
www.baidu.com?category=2#comment
www.baidu.com?category=2
"""

urlencode

# 将字典转换成url参数
from urllib.parse import urlencode

params = {
    'name': 'germey',
    'age': 22
}
base_url = 'http://www.baidu.com?'
url = base_url + urlencode(params)
print(url)

# http://www.baidu.com?name=germey&age=22

猜你喜欢

转载自blog.csdn.net/sunt2018/article/details/85875339
今日推荐
火速冲上 GitHub 热榜 —— 开源编程语言、框架哪有这么可爱？
北京人形机器人创新中心发布全球首个纯电驱拟人奔跑的全尺寸人形机器人“天工”
LFOSSA 源来如此公开课 | 掌握云原生未来：CNCF 认证全面攻略与备考秘籍
国产云输入法——仅华为无云端数据上传安全问题
开源日报 | 工业开源项目OGG 1.0；姐姐，你要和我一起配置火狐吗；苹果AI遥遥落后？Fedora 40
开放签电子签章：停止新增，优化体验，前进更进（五一假期前工作）
开源日报 | 中学生开源前端动画引擎；全球首个Llama3 8B中文版开源模型；联想电脑恐出局；Linus讽刺AI炒作
周排行
浏览器对同一域名进行请求的最大并发连接数
React Hook之自定义Hook
【转】MyBatis缓存机制
-Java-泛型
自动化测试常用脚本-发送邮件
LeetCode#859: Buddy Strings
java、Python处理字符串
第二篇の博客
Hadoop伪分布式环境安装
SQL Server进阶（十一）临时表、表变量
每日归档
更多
2024-04-27(56)
2024-04-26(39)
2024-04-25(22)
2024-04-24(36)
2024-04-23(26)
2024-04-22(39)
2024-04-21(0)
2024-04-20(6)
2024-04-19(5)
2024-04-18(0)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022