爬虫04-cookie

1.cookie用法

1.cookie用法
from urllib import request

dapeng_url="http://www.renren.com/880151247/profile"
headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
    "Cookie":"anonymid=k7moestblfwn9n; depovince=GW; _r01_=1; JSESSIONID=abctZySjQA4fw9VKIuhdx; taihe_bi_sdk_uid=2953991007be972b7f10573a4b00556f; taihe_bi_sdk_session=7010938ea28567089ef82bd005ff5f88; ick_login=ee41edeb-6bf5-4a08-a2d3-1b4dd04be9ad; _de=DBED19DF5788B76E340E4CEC836F3769696BF75400CE19CC; p=37a48b8069a8222835e05b01a2b211182; first_login_flag=1; [email protected]; ln_hurl=http://hdn.xnimg.cn/photos/hdn421/20140822/1530/main_EZp3_74b800010d6a195a.jpg; t=632d1c65a531d7f64c812aabb68854132; societyguester=632d1c65a531d7f64c812aabb68854132; id=382801152; xnsid=38a3ee67; ver=7.0; loginfrom=null; jebe_key=4cd0ae48-b241-48a7-a029-1b6d9f412d1f%7C79960deff086b3597e7cca906ae5feaa%7C1583892666540%7C1%7C1583892665558; jebe_key=4cd0ae48-b241-48a7-a029-1b6d9f412d1f%7C79960deff086b3597e7cca906ae5feaa%7C1583892666540%7C1%7C1583892665559; wp_fold=0; jebecookies=7dc27970-341a-46da-a15f-09d125d1b9ca|||||"
}
req=request.Request(url=dapeng_url,headers=headers)
resp=request.urlopen(req)
with open("renren.html","w",encoding="utf-8") as fp:
    #write写入的是str格式
    fp.write(resp.read().decode("utf-8"))

2.利用cookieJar登录

from urllib import request
from http.cookiejar import CookieJar
from urllib import parse


dapeng_url="http://www.renren.com/880151247/profile"
login_url="http://www.renren.com/PLogin.do"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"}
data = {
    "email": "[email protected]",
    "password": "980885033..."
}
def get_opener():
    #1.登录
    #1.1创建一个cookiejar对象
    cookiejar=CookieJar()
    #1.2使用cookiejar创建一个HTTPCookieProcess对象
    handler=request.HTTPCookieProcessor(cookiejar)
    #1.3使用上一步创建的handler创建一个opener
    opener=request.build_opener(handler)
    return opener

def login_renren(opener):
    #1.4使用opener发送登陆的请求
    req=request.Request(login_url,data=parse.urlencode(data).encode("utf-8"),headers=headers)
    opener.open(req)

def visit_profile(opener):
    #2.访问个人主页
    #获取个人主页的页面的时候，不用新建opener，使用之前创建好的opener
    req=request.Request(dapeng_url,headers=headers)
    resp=opener.open(req)
    with open("renren2.html","w",encoding="utf-8") as fp:
        fp.write(resp.read().decode("utf-8"))

if __name__ == '__main__':
    opener=get_opener()
    login_renren(opener)
    visit_profile(opener)

3.存取cookie信息

from urllib import request
from http.cookiejar import MozillaCookieJar
#1.存储cookies文件
# cookiejar=MozillaCookieJar("other/cookie.txt")
# handler=request.HTTPCookieProcessor(cookiejar)
# opener=request.build_opener(handler)
#
# resp=opener.open("http://www.baidu.com")
# cookiejar.save(ignore_discard=True)#保存过期的cookies信息

#2.加载cookie
cookiejar=MozillaCookieJar("other/cookie.txt")
cookiejar.load(ignore_discard=True)#过期的cookie也加载
handler=request.HTTPCookieProcessor(cookiejar)
opener=request.build_opener(handler)

resp=opener.open("http://www.baidu.com")
for cookie in cookiejar:
    print(cookie)

猜你喜欢