urllib是Python自帶的標(biāo)準(zhǔn)庫(kù)氢烘，無(wú)需安裝说订，直接可以用愚屁。

提供了如下功能：

• 網(wǎng)頁(yè)請(qǐng)求
• 響應(yīng)獲取
• 代理和cookie設(shè)置
• 異常處理
• URL解析

用法

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

# request: POST
# http測(cè)試：http://httpbin.org/
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())

# 超時(shí)設(shè)置
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')

響應(yīng)

# 響應(yīng)類型
import urllib.open
response = urllib.request.urlopen('https:///www.python.org')
print(type(response))
# 狀態(tài)碼死宣， 響應(yīng)頭
import urllib.request
response = urllib.request.urlopen('https://www.python.org')
print(response.status)
print(response.getheaders())
print(response.getheader('Server'))

Request

# 簡(jiǎn)單例子
import urllib.request
request = urllib.request.Requests('https://python.org')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))

# 增加header
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/57.0.2987.133 Safari/537.36'
    'Host':'httpbin.org'
}
# 構(gòu)造POST表格
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')

Handler：處理更加復(fù)雜的頁(yè)面

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_openner(proxy_handler)
response = opener.open('http://www.baidu.com')
print(response.read())

Cookie:客戶端用于記錄用戶身份,維持登錄信息

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)

# 保存cooki為文本
import http.cookiejar, urllib.request
filename = "cookie.txt"
# 保存類型有很多種
## 類型1
cookie = http.cookiejar.MozillaCookieJar(filename)
## 類型2
cookie = http.cookiejar.LWPCookieJar(filename)

handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open("http://www.baidu.com")

# 使用相應(yīng)的方法讀取
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")

異常處理

# 訪問(wèn)不存在的頁(yè)面
from urllib import request, error
try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.URLError as e:
    print(e.reason)

# 先捕獲子類錯(cuò)誤
from urllib imort 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')
# 判斷原因
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')