Question

我只想在Excel中保存数据，我发现这个代码并且它运行良好：

import xlsxwriter

# Create a workbook and add a worksheet.
workbook = xlsxwriter.Workbook('zzzzz.xlsx')
worksheet = workbook.add_worksheet()

date = "17/08/2015"
bill = 001
item = "something"
customer = "Luis"
price = 100

# Start from the first cell. Rows and columns are zero indexed.
row = 0
col = 0

# Iterate over the data and write it out row by row.

worksheet.write(row, col, date )
worksheet.write(row, col + 1, bill)
worksheet.write(row, col + 2, item )
worksheet.write(row, col + 3, customer )
worksheet.write(row, col + 4,price)

workbook.close()

我遇到的问题是当我尝试使用空格保存信息时，如果：

customer = "JOSE LUIS FEBRERO LOPEZ"

错误：

    >>> 

Traceback (most recent call last):
  File "C:\Python27\crearexcel.py", line 28, in <module>
    workbook.close()
  File "C:\Python27\lib\site-packages\xlsxwriter\workbook.py", line 296, in close
    self._store_workbook()
  File "C:\Python27\lib\site-packages\xlsxwriter\workbook.py", line 520, in _store_workbook
    xml_files = packager._create_package()
  File "C:\Python27\lib\site-packages\xlsxwriter\packager.py", line 140, in _create_package
    self._write_shared_strings_file()
  File "C:\Python27\lib\site-packages\xlsxwriter\packager.py", line 280, in _write_shared_strings_file
    sst._assemble_xml_file()
  File "C:\Python27\lib\site-packages\xlsxwriter\sharedstrings.py", line 53, in _assemble_xml_file
    self._write_sst_strings()
  File "C:\Python27\lib\site-packages\xlsxwriter\sharedstrings.py", line 83, in _write_sst_strings
    self._write_si(string)
  File "C:\Python27\lib\site-packages\xlsxwriter\sharedstrings.py", line 110, in _write_si
    self._xml_si_element(string, attributes)
  File "C:\Python27\lib\site-packages\xlsxwriter\xmlwriter.py", line 122, in _xml_si_element
    self.fh.write("""<si><t%s>%s</t></si>""" % (attr, string))
  File "C:\Python27\lib\codecs.py", line 694, in write
    return self.writer.write(data)
  File "C:\Python27\lib\codecs.py", line 357, in write
    data, consumed = self.encode(object, self.errors)
UnicodeDecodeError: 'ascii' codec can't decode byte 0xa0 in position 11: ordinal not in range(128)

我尝试转换为字符串str(customer)，但这并不起作用。我发现的唯一解决方案是更换空间＆＃34; ＆＃34;为＆＃34; _＆＃34;

知道如何在Excel中用空格保存数据吗？

这是我的所有代码，我从文件夹中获取所有文件，稍后我转换为文本，在提取一些数据后，我尝试创建一个excel文件。

我尝试编码utf-8但不工作

# -*- coding: cp1252 -*-
# -*- coding: UTF-8 -*-
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
import os
import xlsxwriter

# Create a workbook and add a worksheet.
workbook = xlsxwriter.Workbook('zzzzz.xlsx')
worksheet = workbook.add_worksheet()

files = [f for f in os.listdir('.') if os.path.isfile(f)]
for f in files:

    z = 0

e = (len(files) - 1)



def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos=set()
    fstr = ''
    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages,    password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)

        str = retstr.getvalue()
        fstr += str

    fp.close()
    device.close()
    retstr.close()
    return fstr

row = 0
col = 0

while z<e:    

    factura = files[z]
    #ejemplo 1

    string = convert_pdf_to_txt(factura)
    lines = list(filter(bool,string.split('\n')))
    custData = {}
    for i in range(len(lines)):
        if 'EMAIL:' in lines[i]:
            custData['Name'] = lines[i+1]
        elif 'FACTURA' in lines[i]:
            custData['BillNumber'] = lines[i+1]
        elif 'Vencimientos:' in lines[i]:
            custData['price'] = lines[i+2]
        elif 'Banco:' in lines[i]:
            custData['paymentType'] = lines[i+1]



    #ejemplo 2
    txtList = convert_pdf_to_txt(factura).splitlines()
    nameIdx, billNumIdx, priceIdx, expirDateIdx, paymentIdx = -1, -1, -1, -1, -1

    for idx, line in enumerate(txtList):
        if line == "EMAIL: buendialogistica@gmail.com":
            nameIdx = idx +2 # in your example it should be +2...

        if line == "FACTURA":
            billNumIdx = idx + 1

        if "Vencimientos:" in line:
            priceIdx = idx + 2
            expirDateIdx = idx + 1

        if "Banco:" in line:
            paymentIdx = idx + 1

    name = txtList[nameIdx] if nameIdx != -1 else ''
    billNum = txtList[billNumIdx] if billNumIdx != -1 else ''
    price = txtList[priceIdx] if priceIdx != -1 else ''
    expirDate = txtList[expirDateIdx] if expirDateIdx != -1 else ''
    payment = txtList[paymentIdx] if paymentIdx != -1 else ''


    print expirDate

    billNum = billNum.replace("Â Â ", "")


    print billNum


    custData['Name'] = custData['Name'].replace("Â", "")

    print custData['Name']


    custData['paymentType'] = custData['paymentType'].replace("Â", "")

    print custData['paymentType']

    print price
    nombre = str(custData['Name'])


    formadepago = custData['paymentType']

    z+=1
    columna2 = str(billNum) + ", " + nombre + ", " + formadepago



    worksheet.write(row, col, expirDate)
    worksheet.write(row, col + 1, columna2) 
    worksheet.write(row, col + 2, price)
    row+=1

workbook.close()

您好，我在所有导入后添加了这段代码....现在我能够保存不间断的空间。

import sys
reload(sys)  
sys.setdefaultencoding('Cp1252')

Answer 1

sys.setdefaultencoding('Cp1252') - 这是一个令人讨厌的修复 - 所有黑客攻击。它掩盖了其他问题，并使您的代码变得脆弱和特定于平台。

"JOSE LUIS FEBRERO LOPEZ"包含Windows-1252编码的非中断空格（0xA0）。

xlsxwriter要求您在使用非ASCII字符时传递Unicode对象。事实上，将Unicode对象用于所有字符串是一种很好的做法。

通过将u附加到字符串的前面来创建Unicode对象：

u"JOSE LUIS FEBRERO LOPEZ"

由于您的Python源代码编码为Windows-1252，您需要将以下内容添加到源文件的顶部：

# coding=cp1252

这将告诉Python如何将源文件中的字符串解码为Unicode对象。

Answer 2

您可以尝试通过包含

将脚本的编码设置为utf-8

# coding=utf-8

作为第一行。然后你可以通过在它前面添加一个小写字母u来将字符串编码设置为utf-8：

customer = u"JOSE LUIS FEBRERO LOPEZ"

然后甚至可以在文本中使用非ascii字母，如Ñ。

或 - 如前所述 - 在文本中使用普通空格而不是不间断空格（0xa0）。

在Excel

2 个答案: