报错1:
UnicodeDecodeError: 'mbcs' codec can't decode byte 0xfc in position 3094: No mapping for the Unicode character exists in the target code page.
# 原因:
# 编码不对
1.需求场景
\capture_info文件夹下有这么多文件,需要所有文本中提取出ip字段
2.代码示例
def test_data2():
# 1.从文件中读取数据
# 2.从文件中去提取ip
path = file_path # 文件夹目录 将路径设置为变量参数
files = os.listdir(path) # 得到文件夹下的所有文件名称
txt_list = [] # 定义空列表来存储
for file in files: # 遍历文件夹
position = path + '\\' + file # 构造绝对路径,"\\",其中一个'\'为转义符
print(position)
with open(position, mode='r', encoding='utf-8') as f: # 打开文件 #注意编码格式
date = f.read() # 读取文件
txt_list.append(date) # 添加到数组中
txt_list = ','.join(txt_list) # 转化为非数组类型
# print(type(txt_list))
# print(txt_list)
# 提取ip
ips = re.findall(r"@ijiami_ip:(.+?)@jvm_stack_start", txt_list)
print(ips) # 返回一个数组
# 统计ip出现次数
ip_num = Counter(ips)
print(ip_num)
# 将结果输出到一个txt中
mylog = open('E:\\mycode\\result_num1.txt', mode='a', encoding='utf-8')
print(ip_num, file=mylog)
print(domain_num, file=mylog)
print('\n')
mylog.close()
# 运行结果:
Counter({
'113.96.232.29:80': 31, '39.103.130.125:443': 2, '110.185.186.35:443': 2, '203.209.230.17:443': 1, '42.120.158.121:80': 1........