首页完成这段代码：import csv from pathlib import Path from bs4 import BeautifulSoup as BS def fun2(filename='test'): in_file = f'{path}/{filename}.html' out_file = f'{path}/{filename}.csv'将以下表格的所有数据用bs4提取出来，并保存为同名的csv文件：<!DOCTYPE html><html><head> <title>Test Table</title></head><body> <table border="1"> <tr> <td>1</td> <td>2</td> </tr> <tr> <td>3</td> <td>4</td> </tr> <tr> <td>5</td> <td>6</td> </tr> </table></body></html>

完成这段代码：import csv from pathlib import Path from bs4 import BeautifulSoup as BS def fun2(filename='test'): in_file = f'{path}/{filename}.html' out_file = f'{path}/{filename}.csv'将以下表格的所有数据用bs4提取出来，并保存为同名的csv文件：<!DOCTYPE html><html><head> <title>Test Table</title></head><body> <table border="1"> <tr> <td>1</td> <td>2</td> </tr> <tr> <td>3</td> <td>4</td> </tr> <tr> <td>5</td> <td>6</td> </tr> </table></body></html>

时间: 2023-06-02 11:02:40 浏览: 161

import reimport requestsfrom bs4 import BeautifulSoupimport t

import re import requests from bs4 import BeautifulSoup import time from xlwt import * poems = [] # 将故事变成了一个全局变量。 def getHtml(page): ''' 获取网页数据 :param page: 页数 :return: 网页html数据(文本格式) ''' headers = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36' } url = 'https://www.gushiwen.org/default_{}.aspx'.format(page) # 获取几页数据 respons = requests.get(url, headers=headers

import csv from pathlib import Path from bs4 import BeautifulSoup as BS path = Path.cwd() def fun2(filename='test'): in_file = f'{path}/{filename}.html' out_file = f'{path}/{filename}.csv' with open(in_file, 'r') as f: soup = BS(f, 'html.parser') table = soup.find('table') rows = table.find_all('tr') with open(out_file, 'w', newline='') as csvfile: writer = csv.writer(csvfile) for row in rows: cols = row.find_all('td') cols = [col.text.strip() for col in cols] writer.writerow(cols)

阅读全文