75接口采集学习网址信息，顺便清理一个存入csv的坑

对一个学习网址进行外页爬取

# coding=gbk
# -*- coding:uft-8 -*-
# @Time: 2023/2/13
# @Author: 十架bgm
# @FileName: ca213
import csv

import requests
import re
import os

os.environ['NO_PROXY'] = 'https://cc-api.sbaliyun.com/v1/completions'


def one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36'
    }
    res = requests.get(url, headers)
    return res.text if res.status_code == 200 else None


def parse_one_page(html):
    pattern = re.compile(r'<a.*?>(.*?)</a></p>')
    titles = re.findall(pattern, html)
    # print(titles)
    totals = re.findall(r'picture_list_detail_intro">(.*?)</p>', html)
    # print(totals)
    teacher = re.findall(r'picture_list_detail_teacher">(.*?)</p>', html)
    with open("学习平台.csv", 'a', encoding='ANSI', newline='') as f:
        headers = ['课程名', '学习人数', 'teacher']
        writer = csv.writer(f)
        writer.writerow(headers)
        for title, total, te in zip(titles, totals, teacher):
            print(f"{title}----{total}----{te}")
            f.write(f'{title.replace(",","")}, {total}, {te}\n')    # 这里存入csv时候，title里面的逗号默认被分割，要替换中文逗号或者空白
            # exit()


def mian(offset):
    url = f'https://www.youdongla.com/course/1_{str(offset)}'
    html = one_page(url)
    parse_one_page(html)


if __name__ == '__main__':
    for offset in range(1, 4):
        mian(offset)

存入到csv问题：title以","分割了

如图

解决方法：

替换一下，我换了空，完美解决