urllib

urllib

from urllib.request import Request, urlopen

url = "http://www.baidu.com"
header = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
}

request = Request(url, headers=header)

response = urlopen(request)

info = response.read().decode()

print(info)

response方法

#响应状态码
response.getcode()

#返回数据的实际url，防止重定向
response.geturl()

#响应报头
response.info()

request方法

#获取请求头
request.get_header('User-Agent')

动态UA

from fake_useragent import UserAgent

ua = UserAgent()
print(ua.ie)   #随机打印ie浏览器任意版本
print(ua.firefox) #随机打印firefox浏览器任意版本
print(ua.chrome)  #随机打印chrome浏览器任意版本
print(ua.random)  #随机打印任意厂家的浏览器

post参数

from urllib.parse import urlencode
f_data = {
	pa = 123
}

f_data = urlencode(f_data)
request = Request(url, headers=header， data=data.encode())

https忽略CA认证的证书(不是CA认证的而是个人的)

import ssl
context = ssl._create_unverified_context()

response = urlopen(request,context=context)

代理

from urllib.request import Request, urlopen, build_opener, ProxyHandler

url = "http://www.baidu.com"
header = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
}

request = Request(url, headers=header)
handler = ProxyHandler({'http': 'zx:123@127.0.0.1:80'})
opener = build_opener(handler)
response = opener.open(request)

info = response.read().decode()

print(info)

cookie

from urllib.request import Request, urlopen
from fake_useragent import UserAgent
from urllib.parse import urlencode
from urllib.request import HTTPCookieProcessor,build_opener
# 登录
login_url = "http://www.sxt.cn/index/login/login"
headers = {
    "User-Agent": UserAgent().chrome,
}
form_data = {
    "user": "17703181473",
    "password": "123456"
}
f_data = urlencode(form_data).encode()
request = Request(login_url, headers=headers, data=f_data)

#保存cookies，用于下次访问
handler = HTTPCookieProcessor()
opener = build_opener(handler)
response = opener.open(request)

# 访问页面
info_url = "http://www.sxt.cn/index/user.html"
request = Request(info_url, headers=headers)

response = opener.open(request)
print(response.read().decode())

cookiejar

from urllib.request import Request, build_opener, HTTPCookieProcessor
from fake_useragent import UserAgent
from http.cookiejar import MozillaCookieJar
from urllib.parse import urlencode


# 登录
# 保存cookie到文件中
def get_cookie():
    login_url = "http://www.sxt.cn/index/login/login"
    headers = {
        "User-Agent": UserAgent().chrome
    }
    form_data = {
        "user": "17703181473",
        "password": "123456"
    }
    f_data = urlencode(form_data).encode()
    request = Request(login_url, headers=headers, data=f_data)
    
    cookie_jar = MozillaCookieJar()
    handler = HTTPCookieProcessor(cookie_jar)
    opener = build_opener(handler)
    response = opener.open(request)
    #保存cookies到本地文件，过期依然保存
    cookie_jar.save("cookie.txt", ignore_expires=True, ignore_discard=True)


def use_cookie():
    info_url = "http://www.sxt.cn/index/user.html"
    headers = {
        "User-Agent": UserAgent().chrome
    }
    request = Request(info_url, headers=headers)
    cookie_jar = MozillaCookieJar()
    #取本地cookies
    cookie_jar.load("cookie.txt", ignore_discard=True, ignore_expires=True)
    handler = HTTPCookieProcessor(cookie_jar)
    opener = build_opener(handler)
    response = opener.open(request)
    print(response.read().decode())


# 获取cookie从文件中
# 访问页面
if __name__ == '__main__':
    # get_cookie()
    use_cookie()

URLError

from urllib.request import Request, urlopen
from fake_useragent import UserAgent
from urllib.error import URLError

url = "http://www.sx123t.cn/index/login/login123"

headers = {
    "User-Agent": UserAgent().chrome
}
try:
    req = Request(url, headers=headers)
    resp = urlopen(req)
    print(resp.read().decode())s
except URLError as e:
	
    if e.args == ():
        print(e.code)
    else:
        print(e.args[0].errno)
print("访问完成")