爬取并提取Stripe博客页面的内容

import requests
import time
import json
from datetime import datetime

# 配置
API_URL = 'https://api.olostep.com/v1'
API_KEY = '<your_olostep_api_key>'
HEADERS = {
    'Content-Type': 'application/json',
    'Authorization': f'Bearer {API_KEY}'
}

# 记录开始时间以跟踪爬取持续时间
crawl_start_time = time.time()

print(f"[{datetime.now().strftime('%H:%M:%S')}] 开始爬取Stripe博客...")

# 开始一个专注于Stripe工程博客文章的爬取
# 你可以根据具体兴趣调整模式
payload = {
    "start_url": "https://stripe.com/blog",
    "include_urls": ["/blog/engineering/**"],  # 专注于工程文章
    "max_pages": 25  # 此示例限制为25页
}

# 开始爬取
print("开始爬取Stripe的工程博客文章...")
response = requests.post(f'{API_URL}/crawls', headers=HEADERS, json=payload)
data = response.json()
crawl_id = data['id']
print(f"爬取已开始，ID: {crawl_id}")

# 监控爬取进度
while True:
    status_response = requests.get(f'{API_URL}/crawls/{crawl_id}', headers=HEADERS)
    status_data = status_response.json()
    print(f"爬取状态: {status_data['status']} - 已爬取页面: {status_data.get('pages_count', 0)}")
    
    if status_data['status'] == 'completed' or status_data['status'] == 'failed':
        break
        
    # 等待5秒后再次检查
    time.sleep(5)

# 计算并显示爬取持续时间
crawl_duration = time.time() - crawl_start_time
print(f"[{datetime.now().strftime('%H:%M:%S')}] 爬取在 {crawl_duration:.2f} 秒内完成")

import requests
import time
import json
from datetime import datetime
import os
from concurrent.futures import ThreadPoolExecutor, as_completed

# 配置
API_URL = 'https://api.olostep.com/v1'
API_KEY = '<your_olostep_api_key>'
HEADERS = {
    'Content-Type': 'application/json',
    'Authorization': f'Bearer {API_KEY}'
}

# 函数以markdown格式检索内容
def retrieve_content(retrieve_id, formats):
    params = {
        "retrieve_id": retrieve_id,
        "formats": json.dumps(formats)
    }
    response = requests.get(f"{API_URL}/retrieve", headers=HEADERS, params=params)
    return response.json()

# 继续之前的爬取示例
if status_data['status'] == 'completed':
    print(f"\n爬取完成！已检索 {status_data['pages_count']} 页。")
    pages_response = requests.get(f'{API_URL}/crawls/{crawl_id}/pages', headers=HEADERS)
    pages_data = pages_response.json()
    
    # 如果输出目录不存在则创建
    os.makedirs("output", exist_ok=True)
    
    # 准备收集markdown内容
    markdown_pages = []
    total_pages = len(pages_data['pages'])
    
    # 并行处理页面以获取markdown内容
    with ThreadPoolExecutor(max_workers=10) as executor:
        # 创建内容检索的期物
        future_to_page = {
            executor.submit(retrieve_content, page['retrieve_id'], ["markdown"]): page
            for page in pages_data['pages']
        }
        
        # 处理完成的结果
        for i, future in enumerate(as_completed(future_to_page), 1):
            page = future_to_page[future]
            url = page['url']
            print(f"处理 {i}/{total_pages}: {url}")
            
            try:
                content_data = future.result()
                if content_data and "markdown_content" in content_data:
                    markdown_pages.append({
                        'url': url,
                        'title': page['title'],
                        'markdown_content': content_data['markdown_content']
                    })
                    print(f"✓ 已检索 {url} 的markdown内容")
                else:
                    print(f"⚠ {url} 没有markdown内容")
            except Exception as e:
                print(f"❌ 检索 {url} 内容时出错: {str(e)}")
    
    # 将所有markdown内容保存到一个文件中
    output_file = "output/stripe_blog_markdown.md"
    
    with open(output_file, "w", encoding="utf-8") as f:
        for page in markdown_pages:
            # 写入页面标题和URL
            f.write(f"URL: {page['url']}\n\n")
            
            # 写入markdown内容
            f.write(f"{page['markdown_content']}\n\n")
            
            # 在页面之间添加分隔符
            f.write("---\n\n")
            
            print(f"✓ 已添加 {page['url']} 的markdown内容")

    print(f"\n✅ 处理完成！所有markdown内容已保存到 '{output_file}'")
    print(f"处理的总页数: {len(markdown_pages)}")
else:
    print(f"爬取失败，状态: {status_data['status']}")