【技巧】如何生成科目四题库，并去重复的题目

一、生成题库并处理图片地址

import requests
from DrissionPage._pages.chromium_page import ChromiumPage
page = ChromiumPage()
import json
import re
import pandas as pd

list = []

for i in range(1):
    page.listen.start('kaoshiti/')
    page.get('https://www.jsyks.com/kms-fzks')
    resp = page.listen.wait()
    info = resp.response.body
    kaoshitiku = re.findall('var ExamCnts = (.*?);',info)[0]
    json_data = json.loads(kaoshitiku)
    for t in json_data:
        dic = {}
        tm= t['tm']
        dic['tm'] = tm
        dic['dalist'] = t['da']
        url = t['tv']
        tm1=tm[:10]
        print(tm1)
        if url == '/tkimg_files/source/':
            dic['newurl'] = '无'
        else:
            url_split = url.split('/')[-1]
            if url_split.endswith('.jpg'):
                newurl = 'https://tkimg.mnks.cn/i/' + url_split.replace('jpg', 'webp/jsyks')
                res = requests.get(newurl)

                open(f'./img/{tm1}.jpg',"wb").write(res.content)
                dic['filepath'] = f'file:///D:\PycharmProjects\pythonProject2024\PYTHON基础知识\DAY 15 自动答题系统\img\{tm1}.jpg'
                dic['newurl'] = newurl
            elif url_split.endswith('.gif'):
                newurl = 'https://tkimg.mnks.cn/i/' + url_split.replace('gif', 'webp/jsyks')
                dic['newurl'] = newurl
                res = requests.get(newurl)
                open(f'./img/{tm1}.jpg', "wb").write(res.content)
                dic['filepath'] = f'file:///D:\PycharmProjects\pythonProject2024\PYTHON基础知识\DAY 15 自动答题系统\img\{tm1}.jpg'

        list.append(dic)

    # print(list)


df=pd.DataFrame(list)
df.to_excel("科目四考试题库03.xlsx")

二、数据处理相同的题目保留第一个

import pandas as pd

# 读取Excel文件
df = pd.read_excel("科目四考试题库03.xlsx")

# 找出重复的行（不包括第一列）
# df.drop_duplicates(df.columns[1:])
duplicates = df.duplicated(df.columns[1:])

# 删除重复行，保留第一个出现的行
df = df.loc[~duplicates]

# 将结果写回Excel文件
df.to_excel('科目四考试题库04.xlsx', index=False)