因为一些网络环境的问题,以太坊的这个https://etherscan.io/网站并不能直接访问,所以需要配置一下。
此爬虫能将官网上的最新的500个智能合约爬取下来,健壮性还行。
代码直接Copy后,需要修改一下文件的路径filepath,即可执行。
运行环境建议使用Python3.6以上。
# -*- coding: utf8 -*- # SmartContactSpider.py import requests from bs4 import BeautifulSoup import traceback import os import time import datetime from sys import stdin def printtime(): print(time.strftime("%Y-%m-%d %H:%M:%S:", time.localtime()), end = \' \') return 0 def getsccodecore(eachLine): filename = eachLine[29:71] filepath = "C:\\Users\\15321\\Desktop\\SmartContract\\code\\" if (os.path.exists(filepath + filename + \'.sol\')): printtime() print(filename + \'已存在!\') return 0 # 伪装成浏览器 headers = { \'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.87 Safari/537.36\'} failedTimes = 100 while True: # 在制定次数内一直循环,直到访问站点成功 if (failedTimes <= 0): printtime() print("失败次数过多,请检查网络环境!") break failedTimes -= 1 try: # 以下except都是用来捕获当requests请求出现异常时, # 通过捕获然后等待网络情况的变化,以此来保护程序的不间断运行 printtime() print(\'正在连接的的网址链接是 \' + eachLine, end = \'\') response = requests.get(eachLine, headers=headers, timeout=5) break except requests.exceptions.ConnectionError: printtime() print(\'ConnectionError!请等待3秒!\') time.sleep(3) except requests.exceptions.ChunkedEncodingError: printtime() print(\'ChunkedEncodingError!请等待3秒!\') time.sleep(3) except: printtime() print(\'Unfortunitely,出现未知错误!请等待3秒!\') time.sleep(3) response.encoding = response.apparent_encoding soup = BeautifulSoup(response.text, "html.parser") targetPRE = soup.find_all(\'pre\', \'js-sourcecopyarea editor\') fo = open(filepath + filename + \'.sol\', "w+", encoding="utf-8"); fo.write(targetPRE[0].text) fo.close() printtime() print(filename + \'新建完成!\') return 0 def getsccode(): try: SCAddress = open("C:\\Users\\15321\\Desktop\\SmartContract\\address\\address.txt", "r") except: printtime() print(\'打开智能合约URL地址仓库错误!请检查文件目录是否正确!\') for eachLine in SCAddress: getsccodecore(eachLine) # 这个才是获取智能合约代码的核心函数 SCAddress.close() return 0 def getSCAddress(eachurl, filepath): # 伪装成某种浏览器,防止被服务器拒绝服务 headers = { \'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.87 Safari/537.36\'} # 设置访问网址失败的最高次数,达到制定次数后,报告错误,停止程序 failedTimes = 50 while True: # 一直循环,直到在制定的次数内访问站点成功 if (failedTimes <= 0): printtime() print("失败次数过多,请检查网络环境!") break failedTimes -= 1 # 每执行一次就要减1 try: # 以下except都是用来捕获当requests请求出现异常时, # 通过捕获然后等待网络情况的变化,以此来保护程序的不间断运行 print(\'正在连接的的网址链接是 \' + eachurl ) response = requests.get(url=eachurl, headers=headers, timeout=5) # 执行到这一句意味着成功访问,于是退出while循环 break except requests.exceptions.ConnectionError: printtime() print(\'ConnectionError!请等待3秒!\') time.sleep(3) except requests.exceptions.ChunkedEncodingError: printtime() print(\'ChunkedEncodingError!请等待3秒!\') time.sleep(3) except: printtime() print(\'出现未知错误!请等待3秒!\') time.sleep(3) # 转换成UTF-8编码 response.encoding = response.apparent_encoding # 煲汤 soup = BeautifulSoup(response.text, "html.parser") # 查找这个字段,这个字段下,包含智能合约代码的URL地址 targetDiv = soup.find_all(\'div\',\'table-responsive mb-2 mb-md-0\') try: targetTBody = targetDiv[0].table.tbody except: printtime() print("targetTBody未成功获取!") return 1 # 以追加的方式打开文件。 # 如果文件不存在,则新建;如果文件已存在,则在文件指针末尾追加 fo = open(filepath + "address.txt", "a") # 把每一个地址,都写到文件里面保存下来 for targetTR in targetTBody: if targetTR.name == \'tr\': fo.write("https://etherscan.io" + targetTR.td.find(\'a\', \'hash-tag text-truncate\').attrs[\'href\'] + "\n") fo.close() return 0 def updatescurl(): urlList = ["https://etherscan.io/contractsVerified/1?ps=100", "https://etherscan.io/contractsVerified/2?ps=100", "https://etherscan.io/contractsVerified/3?ps=100", "https://etherscan.io/contractsVerified/4?ps=100", "https://etherscan.io/contractsVerified/5?ps=100"] # filepath是保存要爬取的智能合约地址的文件的存放路径 # 请根据自己的需求改成自己想要的路径。 filepath = \'C:\\Users\\15321\\Desktop\\SmartContract\\address\\\' # 把旧的存放合约地址的文件清除干净 try: if (os.path.exists(filepath + "address.txt")): os.remove(filepath + "address.txt") printtime() print(\'已清除%s目录下的旧文件(仓库)!\' % filepath) except IOError: printtime() print("出现一个不能处理的错误,终止程序:IOError!") # 函数不正常执行,返回1 return 1 # 读取urlList里的每一个URL网页里的智能合约地址 for eachurl in urlList: time = 0 while( 1 == getSCAddress(eachurl, filepath)): time += 1 if(time == 10): break pass # 函数正常执行,返回0 return 0 def main(): # 更新要爬取的智能合约的地址 if(os.path.exists("C:\\Users\\15321\\Desktop\\SmartContract\\address\\address.txt") == True): print(\'是否更新智能合约地址库?输入Y或者y开头的字符串表示确定更新,其他字符表示不更新\') input_string = str(stdin.readline()) if((input_string[0] == \'Y\') | (input_string[0] == \'y\')): print(\'开始更新智能合约地址库:\') updatescurl() else: print(\'开始新建智能合约地址库:\') updatescurl() # 根据智能合约的地址去爬取智能合约的代码 getsccode() input() main()