批量获取title

import requests
from bs4 import BeautifulSoup
import pandas as pd
from openpyxl import Workbook
import concurrent.futures

# 读取 .txt 文件中的 URL
with open("urls.txt", "r") as file:
    urls = file.read().splitlines()

# 存储 URL 和 title
data = []

def fetch_title(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, "html.parser")
    title = soup.find("title").text
    return (url, title)

with concurrent.futures.ThreadPoolExecutor(max_workers=20) as executor:
    futures = [executor.submit(fetch_title, url) for url in urls]

    for future in concurrent.futures.as_completed(futures):
        result = future.result()
        data.append(result)

# 将 URL 和 title 写入 Excel 文件
df = pd.DataFrame(data, columns=["URL", "Title"])

book = Workbook()
writer = pd.ExcelWriter("titles.xlsx", engine="openpyxl")
writer.book = book

df.to_excel(writer, index=False)

writer.save()
　　由于是最后一起写入到excel，所以单次URL获取不宜过多