爬虫页面源码中提取内容

先介绍整体思路

构造请求

# 导入库

import requests
from fake_useragent import UserAgent
import re
import pandas as pd


# 伪装浏览器
url = "https://www.qiushibaike.com/text/page/1/"
headers = {
    "User-Agent":UserAgent().random
}

# 构造请求 - 获取源码
response = requests.get(url,headers = headers)
info = response.text

利用正则提取内容

infos = re.findall(r'<div class="content">\s*<span>\s*(.+)\s*</span>',info)

print(infos[0])

使用DataFrame写入文件

import pandas as pd

# 将列表转成DataFrame，
data1 = {
    "小说":infos
}
df1 = pd.DataFrame(data1)

# 写入excel和txt文档


df1.to_excel("./笑话.xlsx",sheet_name="好笑话",encoding="utf-8")

df1.to_string("./笑txt话.txt",encoding="utf-8")

import os
os.listdir()
# os.getcwd()