我一直在尝试用Python编写一个程序，从Excel文件中读取单元格值，并将单元格的内容从爱沙尼亚语翻译成英语或俄语，并将它们组合成一个单独的字符串。结果将打印到文本文件中。爱沙尼亚语 - ＆gt;英语似乎工作正常，但俄语错误开始出现：
Traceback (most recent call last):
File "erid.py", line 140, in <module>
f.write(aNimed(row_index, 1, 'ru')+ '\n')
File "erid.py", line 120, in aNimed
nimi += komponendid[i].strip()
UnicodeDecodeError: 'ascii' codec can't decode byte 0xd0 in position 8: ordinal not in range(128)
Traceback (most recent call last):
File "erid.py", line 140, in <module>
f.write(aNimed(row_index, 1, 'ru')+ '\n') File "erid.py", line 120, in aNimed
nimi = nimi + komponendid[i][1:].strip()
UnicodeDecodeError: 'ascii' codec can't decode byte 0xd1 in position 9: ordinal not in
range(128)
第一个由“antiakteriaalne”一词触发，第二个由“+hoobkäepide”触发。我怀疑“+”符号是导致第二种情况出现问题的原因，而不是“ä”。一些俄罗斯人物似乎是一个问题，而有些则没有。我有点想法。
Python代码：
# -*- coding: utf-8 -*-
from xlrd import open_workbook, cellname, XL_CELL_TEXT
from xlwt import Workbook
from xlutils.copy import copy
import sonaraamatud #dictionary
# open file with data
book = open_workbook('Datafile.xls')
# Safe write unicode to ignore unicode errors
# http://developer.plone.org/troubleshooting/unicode.html
def safe_write(failName, word):
if type(word) == str:
failName.write(word + '\n')
else:
failName.write(word.decode("utf-8") + '\n')
def safeDecode(word):
if type(word) == str:
word = unicode(word, 'utf-8', errors='ignore')
return word
else:
word = unicode(word)
return word
# Translate surface coating name
def translatePind(langa, langb, word):
answ = ""
if (sonaraamatud.kasOlemas3(langa, sonaraamatud.pinnaKatted) == True):
answ = langa
return answ
#if langa is Estonian
if (langa == 'et'):
# if langb is english
if (langb == 'en'):
try:
answ = sonaraamatud.pinnakattedEstEng[word]
except KeyError:
answ = word
# If lang b is russian
elif (langb == "ru"):
try:
answ = sonaraamatud.pinnakattedEngRus[sonaraamatud.pinnakattedEstEng[word]]
except KeyError:
answ = word
# if langa is english
elif (langa == "en"):
# if langb is Estonian
if (langb == "et"):
try:
answ = sonaraamatud.pinnakattedEngEst[word]
except KeyError:
answ = word
# if langb is Russian
elif (langb == "ru"):
try:
answ = sonaraamatud.pinnakattedEngRus[word]
except KeyError:
answ = "KeyError"
return answ
def aNimed(row, sheetNr, lang):
# Function combines name
# name: aNimed
# @param: rida, lehe number
# @return: Product name
#vali leht (worksheet)
sheet = book.sheet_by_index(sheetNr) #sheetNr
komponendid = []
nimi = ""
if (lang == 'et'):
komponendid.append(str(sheet.cell(row, 5).value)) # Model
komponendid.append('(' + sheet.cell(row, 6).value + ')')#surface
komponendid.append(sheet.cell(row, 7).value) #extras
elif (lang == 'en'):
komponendid.append(str(sheet.cell(row, 5).value)) # Mudel
komponendid.append('(' + translatePind('et', 'en', sheet.cell(row, 6).value) + ')')
komponendid.append(sheet.cell(row, 7).value) #lisad
elif (lang == 'ru'):
"""
Alternativ method trying to use safeDecode, NOT working!
komponendid.append(str(safeDecode(sheet.cell(row, 5).value))) # Mudel
surface= safeDecode(sheet.cell(row, 6).value)
komponendid.append('(' + translatePind('et', 'ru', str(surface)) + ')')
komponendid.append(safeDecode(sheet.cell(row, 7).value)) #lisad
"""
komponendid.append(str(sheet.cell(row, 5).value)) # Mudel
komponendid.append('(' + translatePind('et', 'ru',sheet.cell(row, 6).value) + ')')
komponendid.append(sheet.cell(row, 7).value) #lisad
pikkus = len(komponendid)
print(komponendid)
for i in range(0, pikkus):
if (komponendid[i] == "" or komponendid[i] == "()" or komponendid[i] == " "):
i+=1
continue
elif (i == pikkus-1 and komponendid[i][0] != " "):
print("1"+ komponendid[i])
nimi += komponendid[i].strip()
i+=1
elif (komponendid[i][0] == " " and komponendid[i][1]== "+"):
#print("2"+ komponendid[i])
nimi = nimi + komponendid[i][1:].strip()
i+=1
else :
#print("4"+ komponendid[i])
nimi = nimi + komponendid[i].strip() + " "
i+=1
return nimi
# Use: aNimed(row, sheetNr, lang)
sheet = book.sheet_by_index(7)
f= open('data.txt', 'w')
for row_index in range (1, sheet.nrows):
#print(aNimed(row_index, 5, 'en'))
f.write(aNimed(row_index, 1, 'ru')+ '\n')
#safe_write(f, aNimed(row_index, 1, 'ru'))
f.close()
答案 0 :(得分：0)
它不是特别优雅，但我想我有一个解决方法。而不是从excel文件中读取，而是从csv文件中读取。例如，
`import csv
data = []
opened_file = open(csv_filename, 'rb')
reader = csv.reader(opened_file)
for row in reader:
data.append(row)
opened_file.close()`
现在您将数据保存为列表。你翻译并将其保存为不同的列表，比如translated_data。现在，这是关键，你可以用
打开一个新的工作簿`from xlwt import Workbook
book = Workbook(encoding="utf8")
foo = book.add_sheet("foo")
for row_num in range(len(translated_data)):
for col_num in range(len(translated_data[row_num]):
foo.write(row_num, col_num, translated_data[row_num][col_num]
book.save("filename.xls")`
关键是如果你使用Workbook（）就可以指定编码，但是如果使用open_workbook（），你似乎仍然坚持使用ascii。