对于程序员来说经常遇到英文手册，本文就是作者在工作过程中遇到英文的.chm格式的英文手册界面如图1所示，为了方便查询手册，利用python编程，网络在线翻译文档。具体的实现如下：
图1.原英文手册截图
1.利用windows系统自带的hh.exe文件还原.chm文件
进入cmd 使用语句 hh -decompile 目标文件夹 源CHM文件名
我使用的实例如图2所示
图2.还原.chm文件
还原后的文件如图3所示
图3.还原后的图片
2.还原后的文件包括各种文件类型，而我们需要翻译的是.htm文件类型。所以我们需要获取还原后的文件夹中的所有.html文件，这里就会用到编程语言中的递归，具体代码如下：
#获取所有的html 文件
def getHtmlFiles(dir):
global htmlFiles
fileNames = os.listdir(dir)
for i in range(len(fileNames)):
if fileNames[i].__contains__(".htm"):
htmlFiles.append(dir+"\\"+fileNames[i])
print(dir+"\\"+fileNames[i])
for i in range(len(fileNames)):
if os.path.isdir(dir + "\\" + fileNames[i]):
getHtmlFiles(dir + "\\" + fileNames[i])
打印出的文件路径如图4所示
图4.打印的所有.htm文件路径
3.以上获取到htm文件路径后，我们就可以根据路径读取htm的文件内容，实际操作过程中，我将翻译的结果替代htm的英文后，用浏览器打开会出现乱码，因此先要删除htm文件中关于语言的设置头文件。具体代码如下：
#删除头文件解决中文乱码
def deleteHtmlHead(index,path):
print('==1_删除头文件中的属性解决中文乱码Start==')
print('****'+str(index)+'****'+str(path))
filedata = ""
with open(path, "r") as html:
encoding = 'UTF-8'
# print("hhhhhhhhhhhhhhhhhhhhhhhh")
for line in html:
# print(line)
if line.__contains__(''):
line = ''
if line.__contains__(''):
line = ''
if line.__contains__('charset=windows-1252'):
line = ''
if line.__contains__('doctype HTML'):
line = ''
filedata += line
with open(path, "w") as html:
html.write(filedata)
print('==1_删除头文件中的属性解决中文乱码END==')
4.原始的.htm文件打开后如图5所示。
图5.原始的htm内容
提取内容的文本可使用BeautifulSoup或者htmlparser 使用过程中没有得到理想的效果，因此我使用代码获取'>'与'<'之间的值来获取。其实翻译的准确性与否就在于能否准确的提取出.htm文件中的英文文本。在实际的编程过程中有许多特殊字符串情况需要处理，而本人做的不够完美。
5.将获取到的英文文本调用有道的翻译接口进行翻译
6.用翻译的中文结果替换原文件中的英文完成翻译
4-6过程的具体代码如下：
#获取翻译结果
def translator(str):
"""
input : str 需要翻译的字符串
output：translation 翻译后的字符串
"""
# API
url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null'
# 传输的参数， i为要翻译的内容
key = {
'type': "AUTO",
'i': str,
"doctype": "json",
"version": "2.1",
"keyfrom": "fanyi.web",
"ue": "UTF-8",
"action": "FY_BY_CLICKBUTTON",
"typoResult": "true"
}
# key 这个字典为发送给有道词典服务器的内容
response = requests.post(url, data=key)
# 判断服务器是否相应成功
if response.status_code == 200:
# 通过 json.loads 把返回的结果加载成 json 格式
if response.text==None:
print("有道词典None")
return None
else:
if (response.text.__contains__('非常抱歉，来自您ip的请求异常频繁，为了保护其他用户的正常访问，只能暂时禁止您目前的访问。')):
print("非常抱歉，来自您ip的请求异常频繁")
return None
else:
result = json.loads(response.text)
# print ("输入的词为：%s" % result['translateResult'][0][0]['src'])
# print ("翻译结果为：%s" % result['translateResult'][0][0]['tgt'])
# translation = result['translateResult'][0][0]['tgt']
translation = result['translateResult']
return translation
else:
print("有道词典调用失败")
# 相应失败就返回空
return None
def getEnContentAndTrans(index,path):
print('==2_处理文本分割Start==')
print('****'+str(index)+'****'+str(path))
html = open(path,"r")
orgContent = html.read()
list=[]
if orgContent.__contains__('Example (C)'):
list = orgContent.split('Example (C)')
elif orgContent.__contains__('Example (C)'):
list = orgContent.split('Example (C)')
else:
list = orgContent.split('Example (C)')
html.close()
print('==2_处理文本分割 END==')
print('==3_截取英文字段并翻译Start==')
print('****'+str(index)+'****'+str(path))
dealText = list[0]
chTransText = dealText
totalSize = len(dealText)
beginPosition = 0
findLeft = True
leftPosition = 0
rightPosition = 0
enTextList=[]
for i in range(beginPosition,totalSize):
if dealText[i]==">" and findLeft:
beginPosition=i
leftPosition = i;
findLeft = False
if dealText[i]=="<" and not findLeft:
beginPosition = i
rightPosition = i
findLeft = True
enText = dealText[leftPosition+1:rightPosition]
checkText = re.sub("\s", "", enText)
#屏蔽
checkNbspText = checkText
checkNbspText = checkNbspText.replace(' ', '')
checkNbspText = checkNbspText.replace('\n', '')
checkNbspText = checkNbspText.replace(' ', '')
checkNbspText = checkNbspText.replace('\t', '')
#屏蔽大写字母和数字
checkNum = checkNbspText
checkNum = checkNum.replace('.','')
isDigit = checkNum.isdigit()
isUpcase = checkNum.isupper()
if (len(checkText))>0 and len(checkNbspText)>0 and isDigit==False and isUpcase==False:
transResult = translator(enText)
# if enText.__contains__('With J1939, the Rx buffer is reserved for this CAN channel'):
# print('ssssssssssssssssssss')
ch=""
if transResult==None:
print("NONENONENONENONENONENONE")
sys.exit(0)
else:
for i in range(len(transResult)):
for j in range(len(transResult[i])):
item = transResult[i][j]
chx = item['tgt']
ch+=chx
print(enText+'___'+ch)
#dealText = dealText.replace(enText,ch,1)
if enText.__contains__('CAN') or enText.__contains__('Can') or enText.__contains__('can'):
chTransText = chTransText.replace(enText, 'CAN'+ch, 1)
elif ch.__contains__('手动RC系列30'):
ch=ch.replace('手动RC系列30','RC30系列手册',1)
chTransText = chTransText.replace(enText, ch, 1)
else:
chTransText = chTransText.replace(enText, ch, 1)
else:
if len(checkText)>0:
print('%%%%%%'+enText)
#enTextList.append(enText)
print('==3_截取英文字段并翻译 END==')
print('==4_将翻译后的文件保存Start==')
print('****'+str(index)+'****'+str(path))
with open(path,"w") as html:
chTransText=chTransText.replace('。','.')
html.write(chTransText)
if len(list)>1:
# html.write('Example')
# if orgContent.__contains__('Example (C)'):
# html.write('Example (C)')
# elif orgContent.__contains__('Example (C)'):
# html.write('Example (C)')
for i in range(1,len(list)):
if orgContent.__contains__('Example (C)'):
html.write('Example (C)')
elif orgContent.__contains__('Example (C)'):
html.write('Example (C)')
html.write(list[i])
print('==4_将翻译后的文件保存 END==')
翻译后的结果如图6所示
图6.翻译结果
7.利用.chm生成器将所有翻译后的文件打包成.chm文件
8.一些问题。有道接口一小时只能调用1000次，我的解决方案是电脑连接手机热点，当ip被有道封锁后，插拔sim卡，ip地址就不同了。整体的代码（包括调试过程中的所有有用或无用的方法）如下：
import json
import requests
import os
from bs4 import BeautifulSoup
import re
import sys
isFirst = True
htmlFiles=[]
#获取所有的html 文件
def getHtmlFiles(dir):
global htmlFiles
fileNames = os.listdir(dir)
for i in range(len(fileNames)):
if fileNames[i].__contains__(".htm"):
htmlFiles.append(dir+"\\"+fileNames[i])
print(dir+"\\"+fileNames[i])
for i in range(len(fileNames)):
if os.path.isdir(dir + "\\" + fileNames[i]):
getHtmlFiles(dir + "\\" + fileNames[i])
#删除头文件解决中文乱码
def deleteHtmlHead(index,path):
print('==1_删除头文件中的属性解决中文乱码Start==')
print('****'+str(index)+'****'+str(path))
filedata = ""
with open(path, "r") as html:
encoding = 'UTF-8'
# print("hhhhhhhhhhhhhhhhhhhhhhhh")
for line in html:
# print(line)
if line.__contains__(''):
line = ''
if line.__contains__(''):
line = ''
if line.__contains__('charset=windows-1252'):
line = ''
if line.__contains__('doctype HTML'):
line = ''
filedata += line
with open(path, "w") as html:
html.write(filedata)
print('==1_删除头文件中的属性解决中文乱码END==')
#处理html中的文本
def handHtmlContent(index,path):
print('========================')
print('==2_处理HTML中的文本Start==')
print('========================')
print(str(index)+'___'+str(path))
org=''
with open(path,"r") as html:
content = html.read()
soup = BeautifulSoup(content, "lxml")
org = str(soup.text)
# org = org.replace("\t", "\n")
# org = re.sub("\s\n", "\n", org)
# org=re.sub("\n\s\n","",org)
# org = re.sub("\n\s\s\n", "", org)
# org = re.sub("\s\s\s", "", org)
# org = re.sub("\s\s\s\s", "", org)
# org = re.sub("\s\s\s\s\s", "", org)
# org = re.sub("\s\s\s\s\s\s", "", org)
# org = re.sub("\s\s\s\s\s\s\s", "", org)
# org = re.sub("\s\s\s\s\s\s\s\s", "", org)
# org = re.sub("\s\s\s\s\s\s\s\s\s", "", org)
# org = re.sub("\s\s\s\s\s\s\s\s\s\s", "", org)
#
# while org.__contains__("\n\n"):
# org = org.replace("\n\n","\n")
print('========================')
print('==2_处理HTML中的文本 End==')
print('========================')
return org
#获取翻译结果
def translator(str):
"""
input : str 需要翻译的字符串
output：translation 翻译后的字符串
"""
# API
url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null'
# 传输的参数， i为要翻译的内容
key = {
'type': "AUTO",
'i': str,
"doctype": "json",
"version": "2.1",
"keyfrom": "fanyi.web",
"ue": "UTF-8",
"action": "FY_BY_CLICKBUTTON",
"typoResult": "true"
}
# key 这个字典为发送给有道词典服务器的内容
response = requests.post(url, data=key)
# 判断服务器是否相应成功
if response.status_code == 200:
# 通过 json.loads 把返回的结果加载成 json 格式
if response.text==None:
print("有道词典None")
return None
else:
if (response.text.__contains__('非常抱歉，来自您ip的请求异常频繁，为了保护其他用户的正常访问，只能暂时禁止您目前的访问。')):
print("非常抱歉，来自您ip的请求异常频繁")
return None
else:
result = json.loads(response.text)
# print ("输入的词为：%s" % result['translateResult'][0][0]['src'])
# print ("翻译结果为：%s" % result['translateResult'][0][0]['tgt'])
# translation = result['translateResult'][0][0]['tgt']
translation = result['translateResult']
return translation
else:
print("有道词典调用失败")
# 相应失败就返回空
return None
"""有道翻译函数 DONE!"""
#将翻译的文本结果替换到源文件
def updateHtmlContent(index,path,transResult):
print('=========================')
print('==4_将中文替换文本内容Start==')
print('=========================')
print(str(index) + '___' + str(path))
html = open(path, "r")
#lines = html.readlines()
maxContent = html.read()
updateContent = maxContent
for i in range(len(transResult)):
item = transResult[i][0]
en = item['src']
ch = item['tgt']
if ch==None or len(en)<=0 or en.__contains__('\xa0'):
continue
if updateContent.__contains__(en):
#print('==============='+ch)
updateContent = updateContent.replace(en,ch,1)
html.close()
with open(path, "w") as html:
html.write(updateContent)
print('=========================')
print('==4_将中文替换文本内容 END==')
print('=========================')
#def checkOnlyNBSP(text):
def getEnContentAndTrans(index,path):
print('==2_处理文本分割Start==')
print('****'+str(index)+'****'+str(path))
html = open(path,"r")
orgContent = html.read()
list=[]
if orgContent.__contains__('Example (C)'):
list = orgContent.split('Example (C)')
elif orgContent.__contains__('Example (C)'):
list = orgContent.split('Example (C)')
else:
list = orgContent.split('Example (C)')
html.close()
print('==2_处理文本分割 END==')
print('==3_截取英文字段并翻译Start==')
print('****'+str(index)+'****'+str(path))
dealText = list[0]
chTransText = dealText
totalSize = len(dealText)
beginPosition = 0
findLeft = True
leftPosition = 0
rightPosition = 0
enTextList=[]
for i in range(beginPosition,totalSize):
if dealText[i]==">" and findLeft:
beginPosition=i
leftPosition = i;
findLeft = False
if dealText[i]=="<" and not findLeft:
beginPosition = i
rightPosition = i
findLeft = True
enText = dealText[leftPosition+1:rightPosition]
checkText = re.sub("\s", "", enText)
#屏蔽
checkNbspText = checkText
checkNbspText = checkNbspText.replace(' ', '')
checkNbspText = checkNbspText.replace('\n', '')
checkNbspText = checkNbspText.replace(' ', '')
checkNbspText = checkNbspText.replace('\t', '')
#屏蔽大写字母和数字
checkNum = checkNbspText
checkNum = checkNum.replace('.','')
isDigit = checkNum.isdigit()
isUpcase = checkNum.isupper()
if (len(checkText))>0 and len(checkNbspText)>0 and isDigit==False and isUpcase==False:
transResult = translator(enText)
# if enText.__contains__('With J1939, the Rx buffer is reserved for this CAN channel'):
# print('ssssssssssssssssssss')
ch=""
if transResult==None:
print("NONENONENONENONENONENONE")
sys.exit(0)
else:
for i in range(len(transResult)):
for j in range(len(transResult[i])):
item = transResult[i][j]
chx = item['tgt']
ch+=chx
print(enText+'___'+ch)
#dealText = dealText.replace(enText,ch,1)
if enText.__contains__('CAN') or enText.__contains__('Can') or enText.__contains__('can'):
chTransText = chTransText.replace(enText, 'CAN'+ch, 1)
elif ch.__contains__('手动RC系列30'):
ch=ch.replace('手动RC系列30','RC30系列手册',1)
chTransText = chTransText.replace(enText, ch, 1)
else:
chTransText = chTransText.replace(enText, ch, 1)
else:
if len(checkText)>0:
print('%%%%%%'+enText)
#enTextList.append(enText)
print('==3_截取英文字段并翻译 END==')
print('==4_将翻译后的文件保存Start==')
print('****'+str(index)+'****'+str(path))
with open(path,"w") as html:
chTransText=chTransText.replace('。','.')
html.write(chTransText)
if len(list)>1:
# html.write('Example')
# if orgContent.__contains__('Example (C)'):
# html.write('Example (C)')
# elif orgContent.__contains__('Example (C)'):
# html.write('Example (C)')
for i in range(1,len(list)):
if orgContent.__contains__('Example (C)'):
html.write('Example (C)')
elif orgContent.__contains__('Example (C)'):
html.write('Example (C)')
html.write(list[i])
print('==4_将翻译后的文件保存 END==')
def main():
# rootDir = 'D:\用户手册\RC30_Manual'+'\\'+'3_controllers'+'\\'+'HWID00D3'+'\\'+'functions'
rootDir = 'D:\用户手册\RC30_Manual'
print('==0_获取所有的Html文件Start==')
global isFirst
if isFirst:
getHtmlFiles(rootDir)
isFirst=False
print('==0_获取所有的Html文件 END===')
# ** ** 118 ** ** D:\用户手册\RC30_Manual\5
# _API\CAN\can_sendDatabox.htm
'''
for i in range(len(htmlFiles)):
print(str(i)+'******'+htmlFiles[i])
if (str(htmlFiles[i])).__contains__('can_sendDatabox.htm'):
print('=============='+str(i))
'''
''''''
for i in range(207,len(htmlFiles)):
# for i in range(175, 176):
#print(str(i+1)+'__'+str(htmlFiles[i]))
# if i==0:
deleteHtmlHead(i,str(htmlFiles[i]))
getEnContentAndTrans(i,str(htmlFiles[i]))
'''
content = handHtmlContent(i,htmlFiles[i])
#print(content)
print('================================')
print('========3_调用有道翻译Start========')
print('================================')
transResult = translator(content)
print(transResult)
# print(transResult[0])
# print(transResult[0][0])
# print(transResult[1][0])
#
# print(len(transResult))
print('===============================')
print('========3_调用有道翻译 End========')
print('===============================')
updateHtmlContent(i,htmlFiles[i],transResult)
'''
if __name__=='__main__':
main()