Question

我有一个早期工作但由于UnicodeEncodeError而停止的脚本。

我使用的是Python 3.4.3。

完整的错误消息如下：

Traceback (most recent call last):
  File "R:/A/APIDevelopment/ScivalPubsExternal/Combine/ScivalPubsExt.py", line 58, in <module>
    outputFD.writerow(row)
  File "C:\Python34\lib\encodings\cp1252.py", line 19, in encode
    return codecs.charmap_encode(input,self.errors,encoding_table)[0]
UnicodeEncodeError: 'charmap' codec can't encode character '\x8a' in position 413: character maps to <undefined>

如何解决此错误？

Python脚本如下：

import pdb
import csv,sys,os
import glob
import os
import codecs

os.chdir('R:/A/APIDevelopment/ScivalPubsExternal/Combine')
joinedFileOut='ScivalUpdate'
csvSourceDir="R:/A/APIDevelopment/ScivalPubsExternal/Combine/AustralianUniversities"

# create dictionary from Codes file (Institution names and codes)
codes = csv.reader(open('Codes.csv'))
#rows of the file are stored as lists/arrays
InstitutionCodesDict = {}
InstitutionYearsDict = {}
for row in codes:
   #keys: instnames, #values: instcodes
    InstitutionCodesDict[row[0]] = row[1]
    #define year dictionary with empty values field
    InstitutionYearsDict[row[0]] = []

#to create a fiel descriptor for the outputfile, wt means text mode (also rt opr r is the same)
with open(joinedFileOut,'wt') as csvWriteFD:
#write the file (it is still empty here)
   outputFD=csv.writer(csvWriteFD,delimiter=',')
#with closes the file at the end, if exception occurs then before that


   # open each scival file, create file descriptor (encoding needed) and then read it and print the name of the file
   if not glob.glob(csvSourceDir+"/*.csv"):
      print("CSV source files not found")
      sys.exit()

   for scivalFile in glob.glob(csvSourceDir+"/*.csv"):
       #with open(scivalFile,"rt", encoding="utf8") as csvInFD:
       with open(scivalFile,"rt", encoding="ISO-8859-1") as csvInFD:
          fileFD = csv.reader(csvInFD)
          print(scivalFile)

          #create condition for loop
          printon=False

          #reads all rows in file and creates lists/arrays of each row
          for row in fileFD:
              if len(row)>1:
                 #the next printon part is skipped when looping through the rows above the data because it is not set to true
                 if printon:
                    #inserts instcode and inst sequentially to each row where there is data and after the header row
                    row.insert(0, InstitutionCode)
                    row.insert(0, Institution)
                    if row[10].strip() == "-":
                       row[10] = " "
                    else:
                       p = row[10].zfill(8)
                       q = p[0:4] + '-' + p[4:]
                       row[10] = q
                    #writes output file
                    outputFD.writerow(row)
                 else:
                    if "Publications at" in row[1]:
                       #get institution name from cell B1
                       Institution=row[1].replace('Publications at the ', "").replace('Publications at ',"")
                       print(Institution)
                       #lookup institution code from dictionary
                       InstitutionCode=InstitutionCodesDict[Institution]
                    #printon gets set to TRUE after the header column
                    if "Title" in row[0]: printon=True
                    if "Publication years" in row[0]:
                       #get the year to print it later to see which years were pulled
                       year=row[1]
                       #add year to institution in dictionary
                       if not year in InstitutionYearsDict[Institution]:
                          InstitutionYearsDict[Institution].append(year)


# Write a report showing the institution name followed by the years for
# which we have that institution's data.
with open("Instyears.txt","w") as instReportFD:
   for inst in (InstitutionYearsDict):
      instReportFD.write(inst)
      for yr in InstitutionYearsDict[inst]:
         instReportFD.write(" "+yr)
      instReportFD.write("\n")

Answer 1

该错误是由尝试使用系统的默认cp1252编码写入包含U + 008A字符的字符串引起的。解决这个问题很简单，只需为输出文件声明一个latin1编码（或iso-8859-1）（因为它只输出原始字节而不进行转换）：

with open(joinedFileOut,'wt', encoding='latin1') as csvWriteFD:

但这只会隐藏真正的问题：这个0x8a角色来自哪里？我的建议是拦截异常并将其转移到发生的位置：

try:
    outputFD.writerow(row)
except UnicodeEncodeError:
    # print row, the name of the file being processed and the line number

这可能是因为其中一个输入文件不是is-8859-1编码但更可能是utf8编码......

Answer 2

确保使用源文件和目标文件的正确编码。您可以在三个位置打开文件：

codes = csv.reader(open('Codes.csv'))
  :    :    :
with open(joinedFileOut,'wt') as csvWriteFD:
    outputFD=csv.writer(csvWriteFD,delimiter=',')
  :    :    :
with open(scivalFile,"rt", encoding="ISO-8859-1") as csvInFD:
    fileFD = csv.reader(csvInFD)

这应该类似于：

# Use the correct encoding.  If you made this file on
# Windows it is likely Windows-1252 (also known as cp1252):
with open('Codes.csv', encoding='cp1252') as f:
    codes = csv.reader(f)
  :    :    :
# The output encoding can be anything you want.  UTF-8
# supports all Unicode characters.  Windows apps tend to like
# the files to start with a UTF-8 BOM if the file is UTF-8,
# so 'utf-8-sig' is an option.
with open(joinedFileOut,'w', encoding='utf-8-sig') as csvWriteFD:
    outputFD=csv.writer(csvWriteFD)
  :    :    :
# This file is probably the cause of your problem and is not ISO-8859-1.
# Maybe UTF-8 instead? 'utf-8-sig' will safely handle and remove a UTF-8 BOM
# if present.
with open(scivalFile,'r', encoding='utf-8-sig') as csvInFD:
    fileFD = csv.reader(csvInFD)

Python CSV操作脚本中的UnicodeEncodeError

2 个答案: