使用python爬取BSC链上交易（玩具版）

土狗你冲不冲，土狗你千万莫冲！

前言：

最近想要学习一点python，又找不到感兴趣的突破口，干脆就从爬虫开始吧。 那咱们干点啥，废话不多说，爬取BSC链上的交易吧。

目标

目标"土狗"：

1. 最新区块
2. 创建时间<7天的token
3. 买入金额大于100美金 满足目标： 写入txt文档

开始

装包

# requirements.txt
web3==5.31.3
requests==2.28.2
python-dotenv==0.19.2

初始化一个监控类

在init方法里去初始化一些常量，包括bsc节点，apikey和监控条件

class BSCMonitor:
    def __init__(self):
        # 多个BSC节点备用（提高稳定性）
        self.base_urls = [
            "https://bsc-dataseed.binance.org/",
            "https://bsc-dataseed1.defibit.io/",
            "https://bsc-dataseed1.ninicoin.io/",
            "https://bsc-dataseed2.defibit.io/",
        ]
        self.current_url_index = 0
        
        # 需要取bscan网站里去申请一个APIkey，每天都有免费调用额度
        self.api_key = "myAPIKey"
        
        # 监控条件
        self.min_usd_value = 100
        self.max_token_age_days = 7

开启监控

def start_monitoring(self):
        """开始监控"""
        print("🚀 启动BSC链监控...")
        print(f"监控条件: 买入金额 > ${self.min_usd_value}, token年龄 < {self.max_token_age_days}天")
        print("使用多个备用节点提高稳定性")
        
        # 初始化文件（确保使用正确编码）
        try:
            with open('monitored_txs.txt', 'w', encoding='utf-8') as f:
                f.write(f"BSC链监控记录 - 开始时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n")
                f.write(f"监控条件: 买入金额 > ${self.min_usd_value}, token年龄 < {self.max_token_age_days}天\n")
                f.write("="*80 + "\n")
            print("✅ 初始化监控文件成功")
        except Exception as e:
            print(f"初始化文件失败: {e}")
        
        # 检查连接
        if not self.is_connected():
            print("❌ 无法连接到任何BSC节点，请检查网络连接")
            return
        
        try:
            
           # 监控代码具体实现看下面具体分析
           
        except KeyboardInterrupt:
            print("\n🛑 监控停止")
        except Exception as e:

获取当前最新区块

注：

1. eth_blockNumber 是以太坊JSON-RPC API的一个方法，用于获取当前最新的区块号。BSC虽然不是以太坊，但是完全兼容以太坊的API标准。
2. JSON-RPC是一种轻量级的远程过程调用协议，使用JSON格式进行数据交换。
3. 返回数据样例：

    block = {
       "number": "0x12a45f",
       "hash": "0x9a71c...", 
       "timestamp": "0x642a5a3d",
       "transactions": [  # ← 这个就是我们要获取的
           {交易1数据},
           {交易2数据},
       ...
       ],
       "miner": "0x...",
       "gasUsed": "0x5208"
   }

while True:
    self.current_block = self.get_latest_block_number()
    block = self.bsc_request("eth_getBlockByNumber", [hex(self.current_block), True])
    if block:
         transactions = block.get('transactions', [])
         if transactions:
              print(f"区块 {block_num} 有 {len(transactions)} 笔交易")
                                   
              for tx in transactions:
                     self.analyze_transaction(tx, block_num)
                               
                     self.processed_blocks.add(block_num)



def get_latest_block_number:
    """获取最新区块号"""
       result = self.bsc_request("eth_blockNumber")
       if result and 'result' in result:
           block_number = int(result['result'], 16)
           return block_number
       return 0

def bsc_request(self, method, params=[]):
   # 增加重试机制
     max_retries = 3
       for attempt in range(max_retries):
           try:
               payload = {
                   "jsonrpc": "2.0",
                   "method": method,
                   "params": params,
                   "id": 1
               }
               response = requests.post(self.get_current_url(), json=payload, timeout=15)
               return response.json()
           except requests.exceptions.RequestException as e:
               print(f"请求失败 (尝试 {attempt + 1}/{max_retries}): {e}")
               if attempt < max_retries - 1:
                   self.switch_to_next_url()
                   time.sleep(2)
               else:
                   return None
           except Exception as e:
               print(f"未知错误: {e}")
               return None
       return None

交易前置校验

1. 为什么检查是否是DEX交易，过滤噪音（普通转账，NFT交易，合约部署，合约调用，授权操作）
2. 获取交易收据，检查交易是否成功，0x1 = 交易成功 0x0 = 交易失败

    def analyze_transaction(self, tx, block_number):
        """分析交易"""
        try:
            # 是否是DEX交易
            if not self.is_dex_transaction(tx):
                return
          
            tx_hash = tx['hash']
            print(f"🔍 分析DEX交易: {tx_hash[:10]}...")

            # 获取交易收据
            receipt = self.get_transaction_receipt(tx_hash)
            if not receipt or receipt.get('status') != '0x1':
                return

            # 分析日志
            logs = receipt.get('logs', [])
            for log in logs:
                if len(log.get('topics', [])) == 3:
                    self.process_transfer_log(log, tx, receipt, block_number)
                    
        except Exception as e:
            print(f"分析交易失败: {e}")

获取token信息

获取token信息的JSON-RPC的返回示例

{
    'symbol': 'USDT',           # 交易符号
    'decimals': 18,             # 小数位数
    'name': 'Tether USD'        # token全名
}

def process_transfer_log(self, log, tx, receipt, block_number):
            token_address = log['address']
            # 获取token信息
            token_info = self.get_token_info(token_address)
            token_symbol = token_info['symbol']
            token_name = token_info['name']
            decimals = token_info['decimals']
def get_token_Info(token_address):
     # 1. 先检查缓存
    if token_address in self.token_cache:
        return self.token_cache[token_address]
    
    # 2. 通过JSON-RPC调用合约方法
    symbol_data = {"to": token_address, "data": "0x95d89b41"}  # symbol()
    decimals_data = {"to": token_address, "data": "0x313ce567"} # decimals()  
    name_data = {"to": token_address, "data": "0x06fdde03"}     # name()
    
    # 3. 发送请求获取数据
    symbol_result = self.bsc_request("eth_call", [symbol_data, "latest"])
    decimals_result = self.bsc_request("eth_call", [decimals_data, "latest"])
    name_result = self.bsc_request("eth_call", [name_data, "latest"])
    
    # 4. 解析返回的16进制数据
    symbol = self.parse_string_result(symbol_result)
    decimals = self.parse_number_result(decimals_result)
    name = self.parse_string_result(name_result)
    return tokenInfo

是否是新TOKEN

1.提取合约创建交易的时间戳使用DexScreener的流动性池创建时间。 2.但是某些token不是第一笔交易创建的，所以增加一个else路线，使用DexScreener的流动性池创建时间。

                url = f"https://api.bscscan.com/api?module=account&action=txlist&address={token_address}&startblock=0&endblock=99999999&sort=asc&apikey={self.api_key}"
                
                response = requests.get(url, timeout=10)
                data = response.json()
                
                if data.get('status') == '1' and data.get('result'):
                    first_tx = data['result'][0]
                    timestamp = int(first_tx['timeStamp'])
                    creation_time = datetime.fromtimestamp(timestamp)
                    return creation_time
                else:
                    url = f"https://api.dexscreener.com/latest/dex/tokens/{token_address}"
                    response = requests.get(url, timeout=5)
                    data = response.json()
            
                    if 'pairs' in data and data['pairs']:
                        pair = data['pairs'][0]
                        if 'pairCreatedAt' in pair:
                            created_timestamp = pair['pairCreatedAt'] / 1000  # 转换为秒
                            creation_time = datetime.fromtimestamp(created_timestamp)
                            print(f"使用DexScreener的流动性池创建时间: {creation_time}")
                            return creation_time

获取价格,计算价值

 def get_token_price(token_address):
         url = f"https://api.dexscreener.com/latest/dex/tokens/{token_address}"
         response = requests.get(url, timeout=8)
         data = response.json()
                
         if 'pairs' in data and data['pairs']:
                price = float(data['pairs'][0]['priceUsd'])
                return price
         
 

发现token，告警

             print(f"🎯 发现符合条件的交易!")
             print(f"   token: {token_symbol} ({token_name})")
             print(f"   地址: {token_address[:8]}...")
             print(f"   金额: {token_amount:.4f} {token_symbol} ≈ ${usd_value:.2f}")
             print(f"   年龄: {token_age}天")

最后

愿我们在顶峰相遇～～手动狗头🐶🐶