解码BSC交易Input Data触发OverflowError问题求助

调用BSCScan API获取指定BSC交易的Input Data后，使用eth_abi的decode方法解码address[]和uint256[]类型数据时，触发OverflowError: Python int too large to convert to C ssize_t错误。

原代码 #

import requests
from web3 import Web3
from eth_abi import decode

def get_transaction_input_data(tx_hash):
    apikey = "xxx"
    url = f"https://api.bscscan.com/api?module=proxy&action=eth_getTransactionByHash&txhash={txhash}&apikey={apikey}"
    response = requests.get(url)
    transaction = response.json().get('result', {})
    
    return transaction.get('input', '')

input_data = get_transaction_input_data("0xcbf70aa81c21cff3ae91fc95e0ec5b473fbb4d046e898b02cf93830e98fdeb7e")
print(f"Input Data: {input_data}")

w3 = Web3(Web3.HTTPProvider('https://bsc-dataseed1.binance.org/'))

types = ['address[]', 'uint256[]']
decoded_data = decode(types, bytes.fromhex(input_data[2:]))

recipients = decoded_data[0]
amounts = decoded_data[1]

print("Recipients: ", recipients)
print("Amounts: ", amounts)

报错信息 #

File "D:\python\bsc\query.py", line 23, in <module>
    decoded_data = decode(types, bytes.fromhex(input_data[2:]))
  File "D:\python\bsc\venv\lib\site-packages\eth_abi\codec.py", line 161, in decode
    return decoder(stream)
  File "D:\python\bsc\venv\lib\site-packages\eth_abi\decoding.py", line 129, in __call__
    return self.decode(stream)
  File "D:\python\bsc\venv\lib\site-packages\eth_utils\functional.py", line 47, in inner
    return callback(fn(*args, **kwargs))
  File "D:\python\bsc\venv\lib\site-packages\eth_abi\decoding.py", line 175, in decode
    yield decoder(stream)
  File "D:\python\bsc\venv\lib\site-packages\eth_abi\decoding.py", line 129, in __call__
    return self.decode(stream)
  File "D:\python\bsc\venv\lib\site-packages\eth_abi\decoding.py", line 146, in decode
    stream.push_frame(start_pos)
  File "D:\python\bsc\venv\lib\site-packages\eth_abi\decoding.py", line 95, in push_frame
    self.seek_in_frame(0)
  File "D:\python\bsc\venv\lib\site-packages\eth_abi\decoding.py", line 84, in seek_in_frame
    self.seek(self._total_offset + pos, *args, **kwargs)
OverflowError: Python int too large to convert to C ssize_t

问题原因 #

EVM交易的Input Data前4字节是函数签名哈希，用于标识调用的合约函数。原代码仅去掉了0x前缀（input_data[2:]），但保留了函数签名，导致eth_abi将前4字节错误解析为数组长度，得到一个极大的数值，后续计算偏移量时超出了C类型ssize_t的范围，触发溢出错误。

解决方案 #

方案一：修正解码数据范围 #

去掉0x前缀和前4字节的函数签名（共10个字符：2个0x字符 + 8个函数签名十六进制字符），仅解码实际参数部分：

import requests
from eth_abi import decode

def get_transaction_input_data(tx_hash):
    apikey = "xxx"
    url = f"https://api.bscscan.com/api?module=proxy&action=eth_getTransactionByHash&txhash={tx_hash}&apikey={apikey}"
    response = requests.get(url)
    transaction = response.json().get('result', {})
    
    return transaction.get('input', '')

input_data = get_transaction_input_data("0xcbf70aa81c21cff3ae91fc95e0ec5b473fbb4d046e898b02cf93830e98fdeb7e")
print(f"Input Data: {input_data}")

# 去掉0x前缀和前4字节函数签名，提取实际参数数据
pure_param_data = bytes.fromhex(input_data[10:])
types = ['address[]', 'uint256[]']
decoded_data = decode(types, pure_param_data)

recipients = decoded_data[0]
amounts = decoded_data[1]

print("Recipients: ", recipients)
print("Amounts: ", amounts)

方案二：使用Web3的函数解码（推荐） #

利用Web3的decode_function_input方法，自动处理函数签名和参数解码，更健壮且不易出错。需要提前获取对应合约的ABI（可从BSCScan的合约页面获取）：

import requests
from web3 import Web3

def get_transaction_input_data(tx_hash):
    apikey = "xxx"
    url = f"https://api.bscscan.com/api?module=proxy&action=eth_getTransactionByHash&txhash={tx_hash}&apikey={apikey}"
    response = requests.get(url)
    transaction = response.json().get('result', {})
    
    return transaction.get('input', '')

input_data = get_transaction_input_data("0xcbf70aa81c21cff3ae91fc95e0ec5b473fbb4d046e898b02cf93830e98fdeb7e")
print(f"Input Data: {input_data}")

w3 = Web3(Web3.HTTPProvider('https://bsc-dataseed1.binance.org/'))

# 替换为目标合约的实际ABI（这里以multisend函数为例）
contract_abi = [
    {
        "inputs": [
            {"internalType": "address[]", "name": "_recipients", "type": "address[]"},
            {"internalType": "uint256[]", "name": "_amounts", "type": "uint256[]"}
        ],
        "name": "multisend",
        "outputs": [],
        "stateMutability": "payable",
        "type": "function"
    }
]

contract = w3.eth.contract(abi=contract_abi)
# 自动解码函数签名和参数
function, decoded_params = contract.decode_function_input(input_data)

print("Recipients: ", decoded_params['_recipients'])
print("Amounts: ", decoded_params['_amounts'])

内容的提问来源于stack exchange，提问作者jdoe