爬虫登录online.ncu.edu.cn获取页面
先登录某教学平台，获取cookie，再将这cookie写入一文件cookie.txt(注意格式是7个字段)
# Netscape HTTP Cookie File
# http://curl.haxx.se/rfc/cookie_spec.html
# This is a generated file! Do not edit.
online.ncu.edu.cn FALSE /eol FALSE 8934789840 JSESSIONID A02A1B0C173C67BCD2DB31EC481BDE15.TEOL小爬虫登录(开启器姿势)：
# coding=utf-8
import urllib.error, urllib.request, urllib.parse
import http.cookiejar
ncu_url="http://online.ncu.edu.cn/eol/main.jsp"
para={"IPT_LOGINUSERNAME":"学号","IPT_LOGINPASSWORD":"密码"}
post_data=urllib.parse.urlencode(para).encode()
headers = {"User-Agent":"Mozilla/5.0 (iPhone; CPU iPhone OS 7_1_2 like Mac OS X) App leWebKit/537.51.2 (KHTML, like Gecko) Version/7.0 Mobile/11D257 Safari/9537.53",
"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
'Connection':'keep-alive'
}
filename="cookie.txt"
cookie_aff=http.cookiejar.MozillaCookieJar()
cookie_aff.load(filename, ignore_discard=True, ignore_expires=True)
handler=urllib.request.HTTPCookieProcessor(cookie_aff)
opener=urllib.request.build_opener(handler)
req=urllib.request.Request(ncu_url,post_data,headers)
try:
response=opener.open(req)
except urllib.error.URLError as e:
print(e.reason)
with open("main_page.jsp","w") as f:#登录后将网页保存为jsp页面
f.write(str(response.read(),'gbk'))
print()或直接将cookie写入头文件(session姿势：
# coding=utf-8
import requests
session = requests.Session()
headers = {"User-Agent":"Mozilla/5.0 (iPhone; CPU iPhone OS 7_1_2 like Mac OS X) App leWebKit/537.51.2 (KHTML, like Gecko) Version/7.0 Mobile/11D257 Safari/9537.53",
"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Cookie":"JSESSIONID=A02A1B0C173C67BCD2DB31EC481BDE15.TEOL",
}
para={"IPT_LOGINUSERNAME":"学号","IPT_LOGINPASSWORD":"密码"}
s=session.post("http://online.ncu.edu.cn/eol/main.jsp",data=para,headers=headers)
with open("main_page.jsp","w") as f:
f.write(s.content.decode("gbk"))
print()运行，结果为
"可以看到个人课程".equal("登录成功了")