从excel（python）创建具有非ascii字符的pdf文件

Question

# -*- coding: utf-8 -*-

from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from reportlab.lib.pagesizes import landscape
from reportlab.graphics.barcode import code128
from reportlab.lib.units import mm
from reportlab.platypus import Image
import csv
data_file="variteks.csv"
attendee_data=csv.reader(open(data_file,"rb"))
def pdf_creater(data_file):
    attendee_data=csv.reader(open(data_file,"rb"))

    for row in attendee_data:
        barcode_name = row[0]
        barcode_number=row[1]
        barcode_stf=row[2]
        pdf_file_name= barcode_number+ ".pdf"
generate_certificate(barcode_name,barcode_number,barcode_stf,pdf_file_name)

def generate_certificate (barcode_name,barcode_number,barcode_stf,pdf_file_name):
    c= canvas.Canvas(pdf_file_name)#, pagesize=letter)
    c.setPageSize((400,600))
    c.setViewerPreference("FitWindow", "true")

    # first_image
    variteks = "variteks_first.png"
    c.drawImage(variteks, 40,400, width=None, height=None)

    variteks_ce = "variteks_ce.png"
    c.drawImage(variteks_ce, 40, 260, width=None, height=None)

    barcode = code128.Code128(barcode_number,barHeight=30,barWidth = 2)
    barcode.drawOn(c, 10 * mm, 20 * mm)

    #info
    c.drawCentredString(150,100,barcode_name)

    #info
    c.drawCentredString(150,150, barcode_stf)

    #barkod numarasi
    c.drawCentredString(100,40,barcode_number)
    #down info
    c.drawCentredString(150,15,"1 adet ürün içerir. Contains 1 Piece. LOT:",)

    c.showPage()
    c.save()
    print ("writing")
pdf_creater(data_file)

我有上面的代码来为产品创建贴纸。除非我将土耳其语字符放入 csv 文件，否则它工作正常。如果我输入土耳其字符，我会收到以下错误。你能帮我处理土耳其字符吗？ (ş,ı,ç,ğ,ü,ö) 我的代码有 2 张图片、3 个 str、1 个条形码。

C:\Python27\python.exe C:/Users/muhammedcan/PycharmProjects/mp1/variteks.py
Traceback (most recent call last):
  File "C:/Users/muhammedcan/PycharmProjects/mp1/variteks.py", line 57, in <module>
pdf_creater(data_file)
  File "C:/Users/muhammedcan/PycharmProjects/mp1/variteks.py", line 23, in pdf_creater
generate_certificate(barcode_name,barcode_number,barcode_stf,pdf_file_name)
  File "C:/Users/muhammedcan/PycharmProjects/mp1/variteks.py", line 47, in generate_certificate
c.drawCentredString(150,150, barcode_stf)
  File "C:\Users\muhammedcan\AppData\Roaming\Python\Python27\site-packages\reportlab\pdfgen\canvas.py", line 1575, in drawCentredString
width = self.stringWidth(text, self._fontname, self._fontsize)
  File "C:\Users\muhammedcan\AppData\Roaming\Python\Python27\site-packages\reportlab\pdfgen\canvas.py", line 1675, in stringWidth
(fontSize,self._fontsize)[fontSize is None])
  File "C:\Users\muhammedcan\AppData\Roaming\Python\Python27\site-packages\reportlab\pdfbase\pdfmetrics.py", line 747, in stringWidth
return getFont(fontName).stringWidth(text, fontSize, encoding=encoding)
  File "C:\Users\muhammedcan\AppData\Roaming\Python\Python27\site-packages\reportlab\pdfbase\pdfmetrics.py", line 360, in stringWidth
return instanceStringWidthT1(self, text, size, encoding=encoding)
  File "src\rl_addons\rl_accel\_rl_accel.c", line 748, in instanceStringWidthT1
  File "C:\Python27\lib\encodings\utf_8.py", line 16, in decode
return codecs.utf_8_decode(input, errors, True)
UnicodeDecodeError: 'utf8' codec can't decode byte 0xfe in position 0: invalid start byte

编辑：这是完整的错误。

Answer 1

从错误消息中我可以猜到您在 Windows 系统上使用 Python2.7。 Windows 是 unicode 友好的，但不是真正的 utf-8 友好。因此，您的源 csv 文件不太可能是 utf-8 编码的。另外错误信息还是提示：

'utf8' 编解码器无法解码位置 0

中的字节 0xfe

字节 0xfe 永远不能存在于 utf-8 编码文件中，既不能作为起始字节（低于 0xf8）也不能作为连续字节（低于 0xc0）。但它是 'ş' 的 windows-1254 代码页编码。所以我假设您的输入 csv 文件使用 windows-1254 字符集（Python 中的'cp1254'）

另一方面，reportlab 只接受 utf8 编码的字符串或真正的 unicode 字符串。 可以做什么：

• 在输入 reportlab 之前解码所有字符串（并传递 unicode 字符串）：

  ...
  coding = 'cp1254'
  ...
      #info
      c.drawCentredString(150,100,barcode_name.decode(coding))
  
      #info
      c.drawCentredString(150,150, barcode_stf.decode(coding))
  
      #barkod numarasi
      c.drawCentredString(100,40,barcode_number.decode(coding))
      #down info (this one should already be utf8 encoded thanks to # -*- coding: utf-8 -*-
      c.drawCentredString(150,15,"1 adet ürün içerir. Contains 1 Piece. LOT:",)
  

• 使用编解码器模块在读取时重新编码文件（并传递 utf8 编码的字符串）

  ...
  import csv
  import codecs
  
  coding = 'cp1254'                   # or change if current encoding is different
  
  data_file="variteks.csv"
  #attendee_data=csv.reader(open(data_file,"rb"))
  def pdf_creater(data_file):
      attendee_data=csv.reader(codecs.EncodedFile(open(data_file,"rb"), coding, 'utf8'))
      ...