Question

目前，我正在尝试通过Spyder IDE / GUI获取Python 3程序，使用充满信息的文本文件进行一些操作。但是，在尝试读取文件时，我收到以下错误：

  File "<ipython-input-13-d81e1333b8cd>", line 77, in <module>
    parser(f)

  File "<ipython-input-13-d81e1333b8cd>", line 18, in parser
    data = infile.read()

  File "C:\ProgramData\Anaconda3\lib\encodings\cp1252.py", line 23, in decode
    return codecs.charmap_decode(input,self.errors,decoding_table)[0]

UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 29815: character maps to <undefined>

该计划的代码如下：

import os

os.getcwd()

import glob
import re
import sqlite3
import csv

def parser(file):

    # Open a TXT file. Store all articles in a list. Each article is an item
    # of the list. Split articles based on the location of such string as
    # 'Document PRN0000020080617e46h00461'

    articles = []
    with open(file, 'r') as infile:
        data = infile.read()
    start = re.search(r'\n HD\n', data).start()
    for m in re.finditer(r'Document [a-zA-Z0-9]{25}\n', data):
        end = m.end()
        a = data[start:end].strip()
        a = '\n   ' + a
        articles.append(a)
        start = end

    # In each article, find all used Intelligence Indexing field codes. Extract
    # content of each used field code, and write to a CSV file.

    # All field codes (order matters)
    fields = ['HD', 'CR', 'WC', 'PD', 'ET', 'SN', 'SC', 'ED', 'PG', 'LA', 'CY', 'LP',
              'TD', 'CT', 'RF', 'CO', 'IN', 'NS', 'RE', 'IPC', 'IPD', 'PUB', 'AN']

    for a in articles:
        used = [f for f in fields if re.search(r'\n   ' + f + r'\n', a)]
        unused = [[i, f] for i, f in enumerate(fields) if not re.search(r'\n   ' + f + r'\n', a)]
        fields_pos = []
        for f in used:
            f_m = re.search(r'\n   ' + f + r'\n', a)
            f_pos = [f, f_m.start(), f_m.end()]
            fields_pos.append(f_pos)
        obs = []
        n = len(used)
        for i in range(0, n):
            used_f = fields_pos[i][0]
            start = fields_pos[i][2]
            if i < n - 1:
                end = fields_pos[i + 1][1]
            else:
                end = len(a)
            content = a[start:end].strip()
            obs.append(content)
        for f in unused:
            obs.insert(f[0], '')
        obs.insert(0, file.split('/')[-1].split('.')[0])  # insert Company ID, e.g., GVKEY
        # print(obs)
        cur.execute('''INSERT INTO articles
                       (id, hd, cr, wc, pd, et, sn, sc, ed, pg, la, cy, lp, td, ct, rf,
                       co, ina, ns, re, ipc, ipd, pub, an)
                       VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?,
                       ?, ?, ?, ?, ?, ?, ?, ?)''', obs)

# Write to SQLITE
conn = sqlite3.connect('factiva.db')
with conn:
    cur = conn.cursor()
    cur.execute('DROP TABLE IF EXISTS articles')
    # Mirror all field codes except changing 'IN' to 'INC' because it is an invalid name
    cur.execute('''CREATE TABLE articles
                   (nid integer primary key, id text, hd text, cr text, wc text, pd text,
                   et text, sn text, sc text, ed text, pg text, la text, cy text, lp text,
                   td text, ct text, rf text, co text, ina text, ns text, re text, ipc text,
                   ipd text, pub text, an text)''')
    for f in glob.glob('*.txt'):
        print(f)
        parser(f)

# Write to CSV to feed Stata
with open('factiva.csv', 'w', newline='') as csvfile:
    writer = csv.writer(csvfile)
    with conn:
        cur = conn.cursor()
        cur.execute('SELECT * FROM articles WHERE hd IS NOT NULL')
        colname = [desc[0] for desc in cur.description]
        writer.writerow(colname)
        for obs in cur.fetchall():
            writer.writerow(obs)

Answer 1

在open语句中添加编码例如：

f=open("filename.txt","r",encoding='utf-8')

Answer 2

从https://en.wikipedia.org/wiki/Windows-1252看，代码0x9D未在CP1252中定义。

＆＃34;错误＆＃34;是例如在你的open函数中：你没有指定编码，所以python（仅在windows中）将使用一些系统编码。通常，如果您读取的文件可能不是在同一台机器上创建的，那么最好指定编码。

我建议您在open上编写csv编码。最好是明确的。

我不知道原始文件格式，但添加到open , encoding='utf-8'通常是件好事（它是Linux和MacO中的默认格式）。

Answer 3

如果不需要解码，也可以尝试file = open(filename, 'rb')'rb'转换为读取二进制。假设您只想上传到网站

Answer 4

以上内容不适用于我，请尝试以下操作：, errors='ignore' 成就奇迹！

Answer 5

我通过将文件格式从.csv更改为.xlsx来解决此问题。

Answer 6

errors ='ignore'解决了我的头痛问题：

import os
rootdir=('K:\\0\\000.THU.EEG.nedc_tuh_eeg\\000edf.01_tcp_ar\\01_tcp_ar\\')
for folder, dirs, files in os.walk(rootdir):
    for file in files:
        if file.endswith('.txt'):
            fullpath = os.path.join(folder, file)
            with open(fullpath, 'r', errors='ignore') as f:
                for line in f:
                    if "coma" in line:
                        print(fullpath)
                        break

如何修复''UnicodeDecodeError：'charmap'编解码器无法解码位置29815中的字节0x9d：字符映射到<undefined>''？

6 个答案: