API 文档

import requests
import json
import time
import os
from datetime import datetime

# 配置
API_KEY = "YOUR_API_KEY"
API_URL = "https://searchcans.youxikuang.cn/api/search"
KEYWORDS_FILE = "keywords.txt"  # 每行一个关键词
OUTPUT_DIR = "serp_results"
SEARCH_ENGINE = "bing"  # 中文站仅支持bing
MAX_RETRIES = 3

def load_keywords(filepath):
    """从文件加载关键词"""
    if not os.path.exists(filepath):
        print(f"❌ 错误：找不到 {filepath}")
        return []
    
    keywords = []
    with open(filepath, 'r', encoding='utf-8') as f:
        for line in f:
            keyword = line.strip()
            if keyword and not keyword.startswith('#'):
                keywords.append(keyword)
    return keywords

def search_keyword(keyword, page=1):
    """使用SERP API搜索单个关键词"""
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    
    payload = {
        "s": keyword,
        "t": SEARCH_ENGINE,
        "d": 10000,  # 10秒超时
        "p": page
    }
    
    try:
        response = requests.post(API_URL, headers=headers, json=payload, timeout=15)
        result = response.json()
        
        if result.get("code") == 0:
            print(f"✅ 成功：{len(result.get('data', []))} 条结果")
            return result
        else:
            print(f"❌ 失败：{result.get('msg')}")
            return None
            
    except Exception as e:
        print(f"❌ 错误：{e}")
        return None

def search_with_retry(keyword):
    """带自动重试的搜索"""
    for attempt in range(MAX_RETRIES):
        if attempt > 0:
            print(f"  🔄 重试 {attempt}/{MAX_RETRIES-1}...")
            time.sleep(2)
        
        result = search_keyword(keyword)
        if result:
            return result
    
    print(f"  ❌ {MAX_RETRIES} 次尝试后仍然失败")
    return None

def save_result(keyword, result, output_dir):
    """保存搜索结果"""
    # 创建安全的文件名
    safe_name = "".join(c if c.isalnum() or c in (' ', '-', '_') else '_' for c in keyword)
    safe_name = safe_name[:50]
    
    # 保存为单独的JSON文件
    json_file = os.path.join(output_dir, f"{safe_name}.json")
    with open(json_file, 'w', encoding='utf-8') as f:
        json.dump(result, f, ensure_ascii=False, indent=2)
    
    # 同时保存到汇总JSONL文件
    jsonl_file = os.path.join(output_dir, "all_results.jsonl")
    with open(jsonl_file, 'a', encoding='utf-8') as f:
        record = {
            "keyword": keyword,
            "timestamp": datetime.now().isoformat(),
            "result": result
        }
        f.write(json.dumps(record, ensure_ascii=False) + "\n")
    
    print(f"  💾 已保存：{safe_name}.json")

def main():
    """主执行函数"""
    print("🚀 SearchCans SERP API 批量搜索工具")
    print("=" * 60)
    
    # 加载关键词
    keywords = load_keywords(KEYWORDS_FILE)
    if not keywords:
        return
    
    total = len(keywords)
    print(f"📄 已加载 {total} 个关键词\n")
    
    # 创建输出目录
    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    output_dir = f"{OUTPUT_DIR}_{timestamp}"
    os.makedirs(output_dir, exist_ok=True)
    print(f"📂 输出目录：{output_dir}/\n")
    
    # 处理每个关键词
    completed = 0
    for index, keyword in enumerate(keywords, 1):
        print(f"[{index}/{total}] 关键词：{keyword}")
        
        result = search_with_retry(keyword)
        
        if result:
            save_result(keyword, result, output_dir)
            
            # 提取并显示URL
            urls = [item.get("url", "") for item in result.get("data", [])]
            if urls:
                print(f"  🔗 找到 {len(urls)} 个链接")
                for i, url in enumerate(urls[:3], 1):
                    print(f"     {i}. {url[:70]}...")
            
            completed += 1
        
        # 速率限制
        if index < total:
            time.sleep(1)
    
    # 统计摘要
    print("\n" + "=" * 60)
    print(f"📊 摘要：{completed}/{total} 个成功")
    print(f"📁 结果已保存到：{output_dir}/")

if __name__ == "__main__":
    main()
              

import requests
import json
import time

def extract_content(url, retry=3):
    """
    使用最佳设置和错误处理提取内容
    """
    api_url = "https://searchcans.youxikuang.cn/api/url"
    headers = {
        "Authorization": f"Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    }
    
    payload = {
        "s": url,
        "t": "url",
        "w": 3000,    # 等待3秒以完成JS渲染
        "d": 20000,   # 最大超时20秒
        "b": True     # 启用浏览器模式
    }
    
    for attempt in range(retry):
        try:
            # 设置超时略高于'd'参数
            response = requests.post(
                api_url, 
                headers=headers, 
                json=payload, 
                timeout=25
            )
            result = response.json()
            
            if result["code"] == 0:
                # 解析数据（可能是字符串或对象）
                data = result["data"]
                if isinstance(data, str):
                    data = json.loads(data)
                
                return {
                    "title": data.get("title", ""),
                    "markdown": data.get("markdown", ""),
                    "html": data.get("html", ""),
                    "description": data.get("description", "")
                }
            else:
                print(f"API错误：{result.get('msg')}")
                if attempt < retry - 1:
                    time.sleep(2)  # 重试前等待
                    continue
                return None
                
        except requests.exceptions.Timeout:
            print(f"第{attempt + 1}/{retry}次尝试超时")
            if attempt < retry - 1:
                time.sleep(2)
                continue
            return None
        except Exception as e:
            print(f"错误：{str(e)}")
            return None
    
    return None

# 使用示例
if __name__ == "__main__":
    url = "https://example.com/article"
    content = extract_content(url)
    
    if content:
        print(f"✅ 标题：{content['title']}")
        print(f"📄 内容长度：{len(content['markdown'])} 字符")
        
        # 保存到文件
        with open("output.md", "w", encoding="utf-8") as f:
            f.write(f"# {content['title']}\n\n")
            f.write(content['markdown'])
        print("✅ 已保存到 output.md")
    else:
        print("❌ 提取失败")