[Python知识库]从入门到入土：基于Python爬取四川大学所有官方网站|狗头保命|

此博客仅用于记录个人学习进度，学识浅薄，若有错误观点欢迎评论区指出。欢迎各位前来交流。（部分材料来源网络，若有侵权，立即删除）
本人博客所有文章纯属学习之用，不涉及商业利益。不合适引用，自当删除！
若被用于非法行为，与我本人无关

代码

from bs4 import BeautifulSoup
import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
    ,'Cookie':'FSSBBIl1UgzbN7N80S=pBl4cwL0BeYX7BPlMyu8rsdbp9lbioYMJaCy1tcn0qYZmGlqCZ41NqycE3AgE8WF; FSSBBIl1UgzbN7N80T=4nVkJRj8lDbIG2U8bykrp6XGWOzeYxavtdqV1340ExDzvNRE3c_j5vi.4dRnL0zOyWGRxZTriiaH69dIW7Dj6XvhptebZ2pmlNI6IZbBxDSRxjusk.MGvxkEEsHcvQt1lDovyurQAdHeF62SyyFz7_BCl73XGMLMFT7eZrXPZ0t4CKONrOscekARY4.Qg.lM7gHMqAA8uHLO0y675xXTqUsfpHObImX3D1vZwKlvkRip6wUu9TOnVXfWnHTw8I3CrC2AoXe_BwPPt6pxtbG2L0XIuv7T9aT.IUoGriJYlscW5rCRoWCyqVFNwojdxN8ogLNl; JSESSIONID=E8C04D8C5697FC67AF480BB7E5FDCE70'
}
def get_the_place():
    print("=" * 100)
    print("1. 查看学院设置官网")
    print("2. 查看机关部处官网")
    print("3. 查看业务单位官网")
    print("4. 查看科研平台官网")
    print("=" * 100)
    id=input("请输入命令：")

    if (id=='1'):
        str='xysz'
    elif(id=='2'):
        str='jgbc'
    elif(id=='3'):
        str='ywdw'
    elif(id=='4'):
        str='kypt'
    else:
        return 0
    for i in range(1):


        url = 'https://www.scu.edu.cn/zzjg/{}.htm'.format(str)
        #print(url)
        #https: // www.scu.edu.cn / zzjg / xysz.htm
        #https: // www.scu.edu.cn / zzjg / ywdw.htm
        #https: // www.scu.edu.cn / zzjg / jgbc.htm
        rs = requests.session()
        r = rs.get(url, headers=headers)
        #print(r.text)
        # random_sleep(1.5, 0.4)
        soup = BeautifulSoup(r.content, 'lxml')
        if(id!='4'):

            SET = soup.find('ul', {'class': 'settingList clearfix jgbcbox'})
            Li = SET.find_all('li')
            for li in Li:
                data=[]
                A=li.find_all('a')
                for a in A:

                    data.append(a.text)
                    data.append(a['href'])

                    print(data)
        else:
            block=soup.find('div',{'style':'display: block;'})
            SET1 = block.find('ul', {'class': 'settingList clearfix jgbcbox'})
            Li = SET1.find_all('li')
            for li in Li:
                data = []
                name = li.find('a').text
                net = li.find('a')['href']
                data.append(name)
                data.append(net)
                print(data)
            SET2 =block.find_all('ul', {'class': 'settingList clearfix'})
            for set2 in SET2:
                Li = set2.find_all('li')
                for li in Li:
                    data = []
                    name = li.find('a').text
                    net = li.find('a')['href']
                    data.append(name)
                    data.append(net)
                    print(data)
            none = soup.find('div', {'style': 'display: none;'})
            SET3 = none.find_all('ul', {'class': 'settingList clearfix'})
            for set3 in SET3:
                Li = set3.find_all('li')
                for li in Li:
                    data = []
                    name = li.find('a').text
                    net = li.find('a')['href']
                    data.append(name)
                    data.append(net)
                    print(data)






while 1:
    get_the_place()

实现截图