python爬虫知识点总结（三）urllib库详解

一、什么是Urllib？

官方学习文档：https://docs.python.org/3/library/urllib.html

廖雪峰的网站：https://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000/001432002680493d1babda364904ca0a6e28374498d59a7000

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

二、相比Python2的变化

Pyhton2

import urllib2

response = urllib2.urlopen('http://www.baidu.com')

Python3

import urllib.request

response = urllib.request

response = urllib.request.urlopen('http://www.baidu.com')

三、用法讲解

urlopen

urllib.request.urlopen(url,data=None,[timeout,]*,cafile=None,capath=None,cadefault=False,context=None)

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')

print(response.read().decode('utf-8'))

import urllib.parse

import urllib.request

data = bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf8')

response = urllib.request.urlopen('http://httpbin.org/post',data=data)

print(response.read)

import urllib.request

response = urllib.request.urlopen('http://httpbin.org/get',timeout=1)

print(response.read)

import socket

import urllib.request

import urllib.error

try:

    response = 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')

响应

响应类型

import urllib.request

response = urllib.request.urlopen('http://www.python.org')

print(type(response))

状态码、响应头

import urllib.request

response = urllib.request.urlopen('https://www.python.org')

print(response.status)

print(response.getheaders())

print(response.getheader('Server'))

print(response.read().decode('utf-8'))

Request

import urllib.request

request = urllib.request.Request('https://python.org')

response = urllib.request.urlopen(request)

print(response.read().decode('utf-8'))

from urllib import request,parse

url = 'http://httpbin.org/post'

headers = {

    'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'

}

dict = {

    'name':'jack'

}

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'))

from urllib import request,parse

url = 'http://httpbin.org/post'

dict = {

    'name':'jack'

}

data = bytes(parse.urlencode(dict),encoding='utf8')

req = request.Request(url=url,data=data,method='POST')

user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'

req.add_header( 'User-Agent', user_agent)

response = request.urlopen(req)

print(response.read().decode('utf-8'))

handler

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://www.baidu.com')

print(response.read())

　　通过代理可以伪装一个ip，比如现在用一个科学上网工具，伪装的是日本ip，那这段代码会弹出浏览器显示如图信息：

Cookie

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)

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)

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)

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

from urllib import request,error

try:

    response = request.urlopen('http://culdjiadaqingcal.com/index.html')

except error.URLError as e:

    print(e.reason)

from urllib import request,error

try:

    response  =request.urlopen('http://www.baidu.com/index.html')

except error.HTTPError as e:

    print(e.reason,e.code,e.headers,sep = '\n')

except error.URLError as e:

    print(e.reason)

else:

    print('Request Successfully')

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")

URL解析

urlparse

urllib.parse.urlparse(urlstring,scheme='',allow_fragment=True)

from urllib.parse import urlparse

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

print(type(result),result)

from urllib.parse import urlparse

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

print(result)

from urllib.parse import urlparse

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

print(result)

from urllib.parse import urlparse

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

print(result)

urlunparse

from urllib.parse import urlunparse

data = {'http','www.baidu.com','index.html','user','id=6','comment'}

print(urlunparse(data))

urljoin

from urllib.parse import urljoin

print(urljoin('http://www.baidu.com','FAQ.html'))

print(urljoin('http://www.baidu.com','https://curere.com/FAQ.html'))

print(urljoin('http://www.baidu.com/about.html','https://curere.com/FAQ.html'))

print(urljoin('http://www.baidu.com/about.html','https://curere.com/FAQ.html?question=2'))

print(urljoin('http://www.baidu.com?wd=abc','https://curere.com/index.php'))

print(urljoin('http://www.baidu.com','?catefory=2#comment'))

print(urljoin('www.baidu.com','?category=2#comment'))

print(urljoin('www.baidu.com#comment','?category=2'))

urlencode

from urllib.parse import urlencode

params = {

     'name':'jack',

    'age':22

}

base_url = 'http://www.baidu.com?'

url = base_url+urlencode(params)

print(url)

robotparser

import urllib.robotparser

rp = urllib.robotparser.RobotFileParser()

rp.set_url("http://www.musi-cal.com/robots.txt")

rp.read()

rrate = rp.request_rate("*")

rrate.requests

rrate.seconds

rp.crawl_delay("*")

rp.can_fetch("*", "http://www.musi-cal.com/cgi-bin/search?city=San+Francisco")

rp.can_fetch("*", "http://www.musi-cal.com/")

巴特西