import requests from bs4 import BeautifulSoup def get_html(url): headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'} try: response = requests.get(url, headers=headers) response.raise_for_status() response.encoding = response.apparent_encoding return response.text except: return "" def parse_html(html): soup = BeautifulSoup(html, 'html.parser') book_list = soup.find_all('li', class_='subject-item') for book in book_list: title = book.find('div', class_='info').find('a')['title'] author_info = book.find('div', class_='pub').get_text().split('/') author = author_info[0].strip() publisher = author_info[-3].strip() print('书名：', title) print('作者：', author) print('出版社：', publisher) print('--------------------------') if __name__ == '__main__': for i in range(0,1000,20): url = 'https://book.douban.com/tag/%E5%8E%86%E5%8F%B2?start='+str(i)+'&type=T' html = get_html(url) parse_html(html)输出结果转为excle表格

好的，你可以使用pandas库将输出的结果转换成Excel表格。以下是修改后的代码：

import requests
from bs4 import BeautifulSoup
import pandas as pd

def get_html(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
    }
    try:
        response = requests.get(url, headers=headers)
        response.raise_for_status()
        response.encoding = response.apparent_encoding
        return response.text
    except:
        return ""

def parse_html(html):
    soup = BeautifulSoup(html, 'html.parser')
    book_list = soup.find_all('li', class_='subject-item')
    data = []
    for book in book_list:
        title = book.find('div', class_='info').find('a')['title']
        author_info = book.find('div', class_='pub').get_text().split('/')
        author = author_info[0].strip()
        publisher = author_info[-3].strip()
        data.append([title, author, publisher])
    return data

if __name__ == '__main__':
    data = []
    for i in range(0, 1000, 20):
        url = 'https://book.douban.com/tag/%E5%8E%86%E5%8F%B2?start=' + str(i) + '&type=T'
        html = get_html(url)
        data += parse_html(html)
    
    # 将数据转换成DataFrame，并输出到Excel表格
    df = pd.DataFrame(data, columns=['书名', '作者', '出版社'])
    df.to_excel('history_books.xlsx', index=False)

在这段代码中，我们在`parse_html`函数中将每本书的信息存储在一个列表中，然后在主函数中将所有列表合并成一个大列表。最后，使用pandas库将这个大列表转换成DataFrame，并输出到Excel表格中。输出的Excel表格文件名为`history_books.xlsx`，不包含行索引。