urllib库(2)

当前位置:

首页 > Python基础教程 >

urllib库(2)

from urllib import request,parse from http.cookiejar import CookieJar headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36' }

def get_opener(): cookiejar = CookieJar() handler = request.HTTPCookieProcessor(cookiejar) opener = request.build_opener(handler) return opener

def login_renren(opener): data = {"email": "970138074@qq.com", "password": "pythonspider"} data = parse.urlencode(data).encode('utf-8') login_url = "http://www.renren.com/PLogin.do" req = request.Request(login_url, headers=headers, data=data) opener.open(req)

def visit_profile(opener): url = 'http://www.renren.com/880151247/profile' req = request.Request(url,headers=headers) resp = opener.open(req) with open('renren.html','w') as fp: fp.write(resp.read().decode("utf-8"))

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

保存cookie到本地：

保存cookie到本地，可以使用cookiejar的save方法，并且需要指定一个文件名：

from urllib import request from http.cookiejar import MozillaCookieJar cookiejar = MozillaCookieJar("cookie.txt") handler = request.HTTPCookieProcessor(cookiejar) opener = request.build_opener(handler) headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36' } req = request.Request('http://httpbin.org/cookies',headers=headers)

resp = opener.open(req) print(resp.read()) cookiejar.save(ignore_discard=True,ignore_expires=True)

从本地加载cookie：

从本地加载cookie，需要使用cookiejar的load方法，并且也需要指定方法：

from urllib import request from http.cookiejar import MozillaCookieJar cookiejar = MozillaCookieJar("cookie.txt") cookiejar.load(ignore_expires=True,ignore_discard=True) handler = request.HTTPCookieProcessor(cookiejar) opener = request.build_opener(handler) headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36' } req = request.Request('http://httpbin.org/cookies',headers=headers)

resp = opener.open(req) print(resp.read())

__EOF__

本文作者：吊打闰土的猹

栏目列表