1

2

3

4

5

url = "目標網站的URL"

response = requests.get(url)

html = response.text

soup = BeautifulSoup(html, "html.parser")

1

2

3

4

5

6

7

# 示例：提取新聞標題和鏈接

news_list = soup.find_all("a", class_="news-title")? # 假設新聞標題使用CSS類名 "news-title"

for news in news_list:

????title = news.text

????link = news["href"]

????print(title, link)

1

2

3

4

5

6

7

# 示例：將數據存儲到文件

with open("news.txt", "w", encoding="utf-8") as f:

????for news in news_list:

????????title = news.text

????????link = news["href"]

????????f.write(f"{title}??? {link}

")

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

import time

# 示例：設置延時和爬取數量

interval = 2? # 延時2秒

count = 0? # 爬取數量計數器

for news in news_list:

????if count < 10:? # 爬取10條新聞

????????title = news.text

????????link = news["href"]

????????print(title, link)

????????count += 1

????????time.sleep(interval)? # 延時

????else:

????????break