1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

import csv 
def read_csv(filename):
    #预设编码列表
    encodings = ['gbk','utf-8','utf-8-sig','GB2312','gb18030','iso-8859-1']
    #循环编码列表，直到正确解析返回解析后的数组data,否则返回false
    for e in encodings:
        data = []
        try:
            with open(filename, encoding=e) as f:
                reader = csv.reader(f)
                header = next(reader)
                # print(header)
                for row in reader:
                    data.append(row)
            print(filename,e)
            return data
        except: 
            print(filename,e)
    return False

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

import csv
import chardet

def read_csv(filename):
    # 使用chardet检测文件编码
    with open(filename, 'rb') as f:
        result = chardet.detect(f.read())
        encoding = result['encoding']
    # 使用检测到的编码读取CSV文件
    with open(filename, encoding=encoding) as f:
        reader = csv.reader(f)
        header = next(reader)
        data = [row for row in reader]
    print(filename, encoding)
    return data

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65

import chardet
import pandas as pd

def read_csv_pd(filename, sep=','): 
    # 1. 使用 'rb' 模式打开文件并读取前几行/字节进行编码检测
    # chardet 有时可能不可靠，但常用于猜测编码
    try:
        with open(filename, 'rb') as f:
            # 读取部分文件内容以提高检测速度
            raw_data = f.read(4096) 
            encode = chardet.detect(raw_data)['encoding']
            
            # 确保检测到的编码名称是小写字符串
            if encode:
                encode = encode.lower()
            else:
                print(f"未能检测到文件编码: {filename}")
                return False
    except Exception as e:
        print(f"文件读取或编码检测失败: {e}")
        return False

    # 2. 尝试使用检测到的编码读取文件
    try:
        # **修复点 1：变量和编码名称统一使用字符串**
        if encode in ['utf-8', 'ascii']: # chardet 有时可能返回 ascii
            # 尝试最常见的 UTF-8
            data = pd.read_csv(filename, encoding='utf-8', sep=sep)
        
        elif 'gb' in encode:
            # **修复点 2：简化中文编码处理逻辑**
            # GB2312, GBK, GB18030 兼容性：从兼容性最好的 GB18030 开始尝试
            try:
                data = pd.read_csv(filename, encoding='gb18030', sep=sep)
            except UnicodeDecodeError:
                # 如果 GB18030 失败，尝试其他检测到的编码，例如原始的 'gbk'
                data = pd.read_csv(filename, encoding='gbk', sep=sep)
        
        elif encode == 'utf-8-sig':
            data = pd.read_csv(filename, encoding='utf-8-sig', sep=sep)
        
        elif encode == 'iso-8859-1':
            # **修复点 3：修正编码名称和参数拼写**
            data = pd.read_csv(filename, encoding='iso-8859-1', sep=sep)
            
        else:
            # 对于其他未知编码，直接用检测到的编码尝试读取
            print(f"尝试使用检测到的未知编码: {encode}")
            data = pd.read_csv(filename, encoding=encode, sep=sep)
            
    except UnicodeDecodeError as e:
        # **修复点 4：通用错误处理**
        print(f"读取文件 {filename} 时发生编码错误: {e}")
        # **解决方案：忽略错误**
        try:
             data = pd.read_csv(filename, encoding=encode, sep=sep, errors='ignore') 
        except Exception as final_e:
             print(f"无法使用任何方式读取文件: {final_e}")
             return False

    except Exception as e:
        print(f"读取文件时发生未知错误: {e}")
        return False
        
    return data