Python学习笔记22（urllib模块）

Python3和Python2的urllib模块不太一样，本篇文章是以Python3为前提。

1.urlopen的使用

import urllib.request

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

#url：需要抓取的网页
#data：Post提交的数据。默认为空，使用的是get请求，若data有数据则是Post请求
#timeout：设置网站的访问超时时间

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8'))

#response.read() 获取的数据格式为bytes类型
#需要decode（），转换成str类型

#POST请求

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())

#超时设置
import urllib.request

response = urllib.request.urlopen('http://httpbin.org/get', timeout=0.1)
print(response.read())

2.Request的使用

#get请求
import urllib.request

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

#post请求
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'))

3.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().decode('utf-8'))

4.Cookie

#获取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)

#获取cookie并且保存在文件中
#有两种格式，记得哪种格式存的哪种格式读就好
#格式一
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)
#格式二
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)


#以格式二读cookie，并且访问url
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'))

5.异常处理

#urllib.error有两个错误类URLError和HTTPError，HTTPError是URLError的子类，所以一般先捕捉小的错误类，再捕捉大的错误类

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')