【Python爬虫】urllib库的使用

Python版本：3.6
urllib官方文档

urllib由几个和url相关的模块组成：

• urllib.request
  for opening and reading URLs
• urllib.error
  containing the exceptions raised by urllib.request
• urllib.parse
  for parsing URLs
• urllib.robotparser
  for parsing robots.txt files

urlopen

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

import urllib  # 使用urlopen进行get请求 response = urllib.request.urlopen('http://www.baidu.com') print(response.read().decode('utf-8'))   # 带请求参数的get请求 import urllib.parse data = bytes(urllib.parse.urlencode({'word': 'hello'}), encoding='utf8') response = urllib.request.urlopen('http://httpbin.org/post', data=data) print(response.read().decode('utf-8'))   # 指定超时时间 如果访问超时会报错 response = urllib.request.urlopen('http://httpbin.org/get', timeout=0.1) print(response.read())  # 异常处理 import socket 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')

import urllib.request response = urllib.request.urlopen('https://www.python.org') print(type(response)) #<class 'http.client.HTTPResponse'>   #状态码和响应头 response = urllib.request.urlopen('https://ww.python.org') print(response.status) print(response.getheaders()) #返回一个list print(response.getheader('Server'))

除了直接使用urlopen来进行请求，还可以使用Request对象进行请求

import urllib.request  request = urllib.request.Request('https://python.org') response = urllib.request.urlopen(request) print(response.read().decode('utf-8'))   #设置请求头参数的post请求 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(urllib.parse.urlencode(dict), encoding='utf8') req = urllib.request.Request(url=url,data=data,headers=headers,method='POST') response = urllib.request.urlopen(req) print(response.read().decode('utf-8'))

Handler

• 代理

import urllib.request  #设置代理handler proxy_handler = urllib.request.ProxyHandler({     'http': 'http://127.0.0.1:9743',     'https': 'https://127.0.0.1:9743' }) opener = urllib.request.build_opener(handler) response = opener.open('http://www.baidu.com') print(response.read().decode('utf-8'))

• Cookie

在一些涉及到登陆的爬虫中，可能会用到cookie

import http.cookie,urllib.request cookie = http.cookiejar.CookieJar() handler = urllib.request.HTTPCookieProcessor(cookie) opener = urllib.request.build_opener(handler) response = opener.open('http://www.baidu.com') #cookie本质上就是一个存储在客户端的k-v对小文件 for item in cookie:     print(item.name+"="+item.value)

#指定cookie的保存路径 import http.cookiejar, urllib.request filename = "cookie.txt" cookie = http.cookiejar.MozillaCookieJar(filename) #cookie = http.cookiejar.LWPCookieJar(filename) 这是另一种cookie的保存格式 handler = urllib.request.HTTPCookieProcessor(cookie) opener = urllib.request.build_opener(handler) response = opener.open('http://www.baidu.com') #保存cookie cookie.save(ignore_discard=True, ignore_expires=True)

import http.cookiejar, urllib.request cookie = http.cookiejar.LWPCookieJar() #加载本地cookie 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'))

urllib.error模块

from urllib import request, error  try:     response = request.urlopen('http://cuiqingcai.com/index.htm') 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')

urllib.parse模块

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 urlunparse  data = ['http', 'www.baidu.com', 'index.html', 'user', 'a=6', 'comment'] print(urlunparse(data)  from urllib.parse import urljoin  print(urljoin('http://www.baidu.com', 'FAQ.html')) 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'))   from urllib.parse import urlencode  params = {     'name': 'germey',     'age': 22 } base_url = 'http://www.baidu.com?' url = base_url + urlencode(params) print(url)

文章来源: 【Python爬虫】urllib库的使用