sk-1Qpxob9KYXq6b6oCypgyxjFwuiA817KfPAHo8XET7HjWQqUBase

{
  "apiKey": "your-api-key",
  "apiBase": "https://api.cursorai.art/v1",
  "model": "cursor-3-5-sonnet-20241022",
  "title": "Claude-3-5-sonnet-20241022",
  "systemMessage": "You are an expert software developer. You give helpful and concise responses.",
  "provider": "openai"
}

"tabAutocompleteModel": {
  "apiKey": "your-api-key",
  "apiBase": "https://api.cursorai.art/v1",
  "model": "gpt-4o-mini",
  "title": "gpt-4o-mini",
  "provider": "openai"
}

import requests
from bs4 import BeautifulSoup
import csv
from time import sleep
import random

def crawl_douban_top250(output_file, items_per_page=25):
    base_url = "https://movie.douban.com/top250"
    headers = {
      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
      'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
      'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
    }
    total_pages = 10
    movies_data = []

    try:
        for page in range(total_pages):
            start_index = page * items_per_page
            url = f"{base_url}?start={start_index}"
            print(f"Scraping page {page + 1}...")

            response = requests.get(url, headers=headers)
            response.raise_for_status()
            soup = BeautifulSoup(response.text, 'html.parser')
            movie_items = soup.find_all('div', class_='item')

            if not movie_items:
                print(f"Warning: No movie data found on page {page + 1}")
                continue

            for item in movie_items:
                try:
                    rank = item.find('em').text
                    title = item.find('span', class_='title').text
                    info = item.find('div', class_='bd').find('p').text.strip()
                    info_lines = [line.strip() for line in info.split('\n') if line.strip()]
                    year = info_lines[1].split('/')[0].strip()
                    director = info_lines[0].split('导演: ')[1].split('主演:')[0].strip()
                    rating = item.find('span', class_='rating_num').text
                    votes = item.find('div', class_='star').find_all('span')[-1].text
                    votes = ''.join(filter(str.isdigit, votes))
                    movies_data.append([rank, title, year, director, rating, votes])
                    print(f"Scraped: {title}")
                except Exception as e:
                    print(f"Error processing movie data: {e}")
                    continue

            delay = random.uniform(3, 7)
            print(f"Waiting for {delay:.2f} seconds before continuing...")
            sleep(delay)

        with open(output_file, 'w', newline='', encoding='utf-8-sig') as f:
            writer = csv.writer(f)
            writer.writerow(['Rank', 'Movie Title', 'Year', 'Director', 'Rating', 'Number of Votes'])
            writer.writerows(movies_data)

        print(f"Scraping completed! A total of {len(movies_data)} movies scraped.")
        print(f"Data saved to {output_file}")

    except requests.RequestException as e:
        print(f"Network request error: {e}")
    except Exception as e:
        print(f"Program execution error: {e}")

if __name__ == "__main__":
    output_file = "douban_top250.csv"
    crawl_douban_top250(output_file)