用ChatGPT爬取CNN新闻并总结

发表于 更新于 分类于 阅读次数： 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
import os
import datetime
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import openai
import time
 
# 在这里设置你的 OpenAI API 密钥
openai.api_key = 'sk-rCJsSuapC0JknFaaxxxxxxxxxxxxxxxxx'
 
# 获取当前日期
current_date = datetime.date.today()
 
# 创建文件夹路径
folder_path = os.path.join("C:/桌面/每日新闻", str(current_date))
 
# 创建文件夹
os.makedirs(folder_path, exist_ok=True)
 
# 创建文件路径
file_path = os.path.join(folder_path, "CNN新闻.txt")
 
url = "https://edition.cnn.com/"
 
response = requests.get(url)
html_content = response.content
 
soup = BeautifulSoup(html_content, "html.parser")
 
container = soup.find(class_="container__field-links container_ribbon__field-links")
 
if container:
    links = container.find_all("a")
 
    # 打开文件并写入内容
    with open(file_path, "w", encoding="utf-8") as file:
        # 遍历链接并访问每个链接
        for link in links:
            href = link.get("href")
            full_link = urljoin(url, href)
 
            try:
                response = requests.get(full_link)
                response.raise_for_status()  # 检查是否有异常状态码
                html = BeautifulSoup(response.content, "html.parser")
 
                articles = html.find_all(class_="article__content")
 
                if articles is None:
                    continue
 
                content = ' '.join([article.get_text() for article in articles])
 
                user_input = f"摘要以下文章内容：\n{content}\n摘要："
 
                # 控制请求频率
                time_between_requests = 60 / 30  # 3 RPM
                time.sleep(time_between_requests)
 
                summary_response = openai.ChatCompletion.create(
                    model="gpt-3.5-turbo",
                    messages=[
                        {"role": "system", "content": "You are a helpful assistant."},
                        {"role": "user", "content": user_input}
                    ],
                    temperature=1,
                    max_tokens=256,
                )
 
                summary = summary_response.choices[0].message['content'].strip()
 
                # 将摘要写入文件
                file.write(summary + "\n\n")
 
                # 打印摘要
                print(summary)
                print('---------------------------------------------------------------------------------')
 
            except requests.RequestException as e:
                print(f"请求出错：{str(e)}")
 
    print("文件写入完成！")