CQU毕设爬虫

import requests
import time
import re

class Spyder:
    def __init__(self, user_name, pass_word):
        spyder = requests.session()
        self.spyder = spyder
        self.user_name = user_name
        self.pass_word = pass_word


    def login(self):
        url = "http://bysj.cqu.edu.cn/bysj/index.jsp"

        data={
            "id": self.user_name,
            "pwd": self.pass_word,
            "type": "student",
            "btlogin": "登陆"

        }
        response = self.spyder.post(url,data=data)
        html = response.text

    def get_paper(self):

        url = "http://bysj.cqu.edu.cn/bysj/thesiswork/student/manageThesisMaterials.htm"
        response = self.spyder.get(url)
        text = response.text
        url0 = "http://bysj.cqu.edu.cn"
        name = re.findall(r'<td class="title" colspan="7" height="30">(.*?)</td>',text)
        if(len(name)==0):
            print("获取失败")
            return 0
        else:
            stu_name=name[0][3:-2]
            print("正在获取"+stu_name)

        # 开题报告
        report = re.findall(r'href="(.*?)">查看开题报告</a></td>',text)
        if(len(report)==0):
            print("获取开题报告失败")
        else:
            print("开始下载开题报告")
            url = url0 + report[0]
            response = self.spyder.get(url)
            content = response.content
            with open(stu_name+"开题报告.doc","wb") as f:
                f.write(content)
        translate=re.findall(r'href="(.*?)">查看译文</a></td>',text)
        if (len(translate) == 0):
            print("获取论文翻译失败")
        else:
            print("开始下载文献翻译")
            url = url0 + translate[0]
            response = self.spyder.get(url)
            content = response.content
            with open(stu_name + "文献翻译.doc", "wb") as f:
                f.write(content)

        paper = re.findall(r'href="(.*?)">查看论文</a></td>', text)
        if (len(paper) == 0):
            print("获取论文失败")
        else:
            print("开始下载论文")
            url = url0 + paper[0]
            response = self.spyder.get(url)
            content = response.content
            with open(stu_name + "论文.doc", "wb") as f:
                f.write(content)


if __name__ == '__main__':
    for i in range(6300,6500):
        user_name = "2014" + str(i)
        pass_word = "000000"
        spyder = Spyder(user_name, pass_word)
        spyder.login()
        spyder.get_paper()
        time.sleep(1)