Question

我制作脚本从pdf文件中提取一些数据，然后保存在excel文件中。

当我将pdf文件转换为文本时，我没有非ASCII字符的问题但是当我保存到excel文件时效果不好。

这是我的代码：

# -*- coding: cp1252 -*-
# -*- coding: UTF-8 -*-
# -*- 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

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


# 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]
            if custData['paymentType'] == "Vencimientos:":
                custData['paymentType'] = lines[i-2]



    #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()

这是我现在的错误：

FRECH ESPAÑA S.A.U. = FRECH ESPAÃ‘A S.A.U.

MONTSERRAT CARRIÓ KÖTZ - LA FUSTERIA = MONTSERRAT CARRIÃ“ KÃ–TZ - LA FUSTERIA.

我尝试使用非ASCII字符的许多代码，但我无法做任何工作。

我的代码中唯一可以包含非ASCII字符的变量是“nombre”

感谢您的帮助

保存非AscII字符python 2.7

0 个答案: