1 import requests

 2 from bs4 import BeautifulSoup

 3 import pandas as pd

 4 from openpyxl import Workbook

 5 import concurrent.futures

 6

 7 # 读取 .txt 文件中的 URL

 8 with open("urls.txt", "r") as file:

 9     urls = file.read().splitlines()

10

11 # 存储 URL 和 title

12 data = []

13

14 def fetch_title(url):

15     response = requests.get(url)

16     soup = BeautifulSoup(response.text, "html.parser")

17     title = soup.find("title").text

18     return (url, title)

19

20 with concurrent.futures.ThreadPoolExecutor(max_workers=20) as executor:

21     futures = [executor.submit(fetch_title, url) for url in urls]

22

23     for future in concurrent.futures.as_completed(futures):

24         result = future.result()

25         data.append(result)

26

27 # 将 URL 和 title 写入 Excel 文件

28 df = pd.DataFrame(data, columns=["URL", "Title"])

29

30 book = Workbook()

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

32 writer.book = book

33

34 df.to_excel(writer, index=False)

35

36 writer.save()

37 　　由于是最后一起写入到excel，所以单次URL获取不宜过多