使用python进行翻译

# -*- coding: utf-8 -*-# import scrapyfrommathimportceilimportreimportjsonimportrequests### def get_opencalais_results(text, api_key):#     # 设置API URL和请求头#     url = 'https://api.thomsonreuters.com/permid/calais'#     headers = {'X-AG-Access-Token': api_key, 'Content-Type': 'text/raw', 'outputformat': 'application/json'}##     # 发送请求并获取响应#     response = requests.post(url, data=text.encode('utf-8'), headers=headers)#     response_dict = json.loads(response.text)##     # 从响应中提取实体#     entities = {}#     for key, value in response_dict.items():#         if '_typeGroup' in value and value['_typeGroup'] == 'entities':#             if 'name' in value and 'score' in value:#                 entities.setdefault(value['_type'], []).append((value['name'], value['score']))##     return entities### # 调用OpenCalais API并处理结果# text = "Facebook is investing $5.7 billion in Reliance Jio, a move that will give the social media giant a 9.99% stake in the Indian telecom company."# api_key = "your_api_key"## entities = get_opencalais_results(text, api_key)## # 输出结果# for entity_type, values in entities.items():#     print(entity_type.upper())#     print('-' * 20)#     for value in values:#         print(value[0], value[1])#     print('\n')# import spacy## nlp = spacy.load("en_core_web_sm")# doc = nlp("Apple is looking at buying U.K. startup for $1 billion")## for token in doc:#     print(token.text, token.lemma_, token.pos_, token.tag_, token.dep_,#             token.shape_, token.is_alpha, token.is_stop)importjsonimportrequestsfromurllibimportrequestimporturllibimportreimportpandasaspdfromopenpyxlimportWorkbookfromopenpyxlimportload_workbookclassYouDaoTranslator(object):
deffanyi(self,key):
print('--key-', key)
# -----伪装浏览器进行爬虫# header = {#     "User-Agent": " Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54"}# url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule"header= {
# 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36','Accept': 'application/json, text/javascript, */*; q=0.01',
# 'Accept-Encoding': 'gzip, deflate','Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
'Connection': 'keep-alive',
# 'Content-Length': '223','Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Cookie': 'OUTFOX_SEARCH_USER_ID=-493176930@10.168.8.63; OUTFOX_SEARCH_USER_ID_NCOO=38624120.26076847; SESSION_FROM_COOKIE=unknown; JSESSIONID=aaabYcV4ZOU-JbQUha2uw; ___rl__test__cookies=1534210912076',
'Host': 'fanyi.youdao.com',
'Origin': 'http://fanyi.youdao.com',
'Referer': 'http://fanyi.youdao.com/',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
'X-Requested-With': 'XMLHttpRequest',
        }
url='http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'salt=int(time.time() *1000+random.randint(0, 10))
salt_str=str(salt)
D="ebSeFb%=XZ%T[KZ)c(sy!"S="fanyideskweb"sign_str=S+key+salt_str+D# 调用加密的方法sign_md5_str=md5_jiami(sign_str)
# -----增加参数formdata= {}
formdata['i'] =keyformdata['from'] ='AUTO'formdata['to'] ='AUTO'formdata['smartresult'] ='dict'formdata['client'] ='fanyideskweb'# formdata['salt'] = '15821157689747'# formdata['sign'] = 'd5a392995c28c285198043f7111d1d00'formdata['salt'] =salt_str,
formdata['sign'] =sign_md5_str,
formdata['ts'] ='1582115768974'formdata['bv'] ='ec579abcd509567b8d56407a80835950'formdata['doctype'] ='json'formdata['version'] ='2.1'formdata['keyfrom'] ='fanyi.web'formdata['action'] ='FY_BY_CLICKBUTTION'data=urllib.parse.urlencode(formdata).encode('utf-8')
# -----爬虫req=request.Request(url, data=data, headers=header)
# -----解析resp=request.urlopen(req).read().decode()
pat=r'"tgt":"(.*?)"}]]'result1=re.findall(pat, resp)
print('--result1-',result1)
returnresult1[0]
deftranslator(self,str):
"""        input : str 需要翻译的字符串        output：translation 翻译后的字符串        """# APIurl='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ifresponse.status_code==200:
# 通过 json.loads 把返回的结果加载成 json 格式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']
returntranslationelse:
print("有道词典调用失败")
# 相应失败就返回空returnNonedeftranslatorAll(self,chineseList=None):
ifchineseListisNone:
chineseList= {}
forchineseinchineseList:
print(chinese.strip())
translation=self.translator(chinese.strip())
chineseList[chinese] =translation.lower().replace(' ', '_').replace('\"', '').replace('.', '').strip("_")
print(translation.lower().replace(' ', '_').replace('\"', '').replace('.', '').strip("_"))
importjson,time,randomimporthashlibdefmd5_jiami(str_data):
md5_obj=hashlib.md5()
sign_bytes_data=str_data.encode('utf-8')
# 调用update()函数，来更新md5_obj值md5_obj.update(sign_bytes_data)
# 返回加密后的strsign_str=md5_obj.hexdigest()
returnsign_strimportenchantdefis_spelled_correctly(word, lang='en_US'):
ifword=='nan':return""if' 'inword: returnworddictionary=enchant.Dict(lang)
foriinrange(1, len(word)):
first_word=word[:i]
second_word=word[i:]
ifdictionary.check(first_word) anddictionary.check(second_word):
print(word,first_word,second_word)
returnfirst_word+" "+second_wordreturnworddefremove_common_prefix(row):
# print('row[company]:',row['company'])# 将两个字符串拆分为字符序列seq1_list=str(row['company']).lower().split('|')
seq2_list=str(row['brand1']).lower().split('|')
# 比较每一个字符，找到最长公共前缀new_seq2_list= []
forseq1inseq1_list:
forseq2inseq2_list:
i=0j=0p=0whilei<len(seq1) andj<len(seq2):
if (seq1[i] ==seq2[j]):
i+=1j+=1if (i==len(seq1)-1):
new_seq2_list.append(seq2[j+1:].strip())
breakelse:
if (p==len(seq1)-1):
new_seq2_list.append(seq2.strip())
breakp+=1i=pj=0return'|'.join(set(new_seq2_list))
if__name__=='__main__':
#分词# is_spelled_correctly('controlmicrosystems')#剔除公司前缀# row={}# row['company']=''# row['brand1']='apache spamassassin'# result=remove_common_prefix(row)# print(result)#同一个remark合并属性# import pandas as pd## # 创建DataFrame# df = pd.DataFrame({#     'cev': ['cev1', 'cev2', 'cev3', 'cev4'],#     'remark': ['remarK1', 'remark1', 'remark2', 'remark2'],#     'company': ['com1', 'com2', 'com3', 'com4'],#     'brand': ['brand1', 'brand2', 'brand3', 'brand4'],#     'system': ['sys1', 'sys2', 'sys3', 'sys4']# })### # 定义一个聚合函数，用于对其他列进行拼接# def join_cols(s):#     return '|'.join(s)### # 对 df 按照 remark 列分组，对其他列进行拼接# df['remark'] = df['remark'].map(str.lower)# grouped = df.groupby('remark').agg(join_cols)# grouped=grouped.reset_index()# print(grouped)################################################################有道翻译# pattern = r'(\d+)\.([a-zA-Z]+)'# text = '** DISPUTED **  Directory traversal vulnerability in check_vote.php in Weekly Drawing Contest 0.0.1 allows remote attackers to read arbitrary files via a .. (dot dot) in the order parameter.  NOTE: another researcher disputes this vulnerability, noting that the order variable is not used in any context that allows opening files.'# # 将数字和字母之间的 '.' 替换为 '_'# text = re.sub(pattern, r'\1_\2', text)# print(text)## mytranslator=YouDaoTranslator()# # result = mytranslator.translator(text)# result = mytranslator.fanyi(text)# print(result)###############################################################有道再翻译# pattern = r'(\d+)\.([a-zA-Z]+)'# mytranslator = YouDaoTranslator()## # #使用翻译接口对爬虫数据转中文# exist_data = pd.read_excel("all_spyder(中文).xlsx")# exist_cves=list(exist_data['cveid'])## data_output = pd.read_excel("all_spyder.xlsx")# ##去重# print(data_output.columns)# print(data_output.head())## filename = "all_spyder(中文new).xlsx"## # 遍历 dataframe 的每一行# for index, row in data_output.iterrows():#     if index<0: continue     #20472#     # print(f"row: {row}")##     print(f"index: {index}  {row['cveid']}")  # 打印当前行的索引##     if row['cveid'] in exist_cves:#         print(f"{row['cveid']}已存在，跳过！！")#         continue##     if (len(str(row['describe']))<200)|(len(str(row['describe']))>400):#         print('长度不合规：{0}'.format(len(str(row['describe']))))#         print(row['describe'])#         continue#     try:#         workbook = load_workbook(filename)#         worksheet = workbook.active#     except FileNotFoundError:#         workbook = Workbook()#         worksheet = workbook.active#         header = ['cveid', 'describe_zh','describe', 'score', 'vulntype', 'producttype', 'vendor', 'product', 'version']#         worksheet.append(header)#     try :#         # row['describe_zh']=en2zh(row['describe'])#         text = re.sub(pattern, r'\1_\2', row['describe'])#         result= mytranslator.fanyi(text)#         if "},{" in result:#             row['describe_zh'] = '英文句号翻译错误！！'#             print('英文句号翻译错误！！')#         else:#             row['describe_zh'] = result#             print('翻译：',row['describe_zh'])#     except Exception as e:#         row['describe_zh']='接口调用报错！！'#         print('接口调用报错！！',str(e))#     finally:#         values = [row['cveid'], row['describe_zh'],row['describe'], row['score'], row['vulntype'], row['producttype'], row['vendor'],#           row['product'], row['version']]#         worksheet.append(values)##         workbook.save(filename)###########################################################  谷歌翻译接口# from pygtrans import Translate## client = Translate()# text = client.translate('Google Translate')# print(text.translatedText)  # 谷歌翻译########################################################## 获取时间戳1# start = time.perf_counter()# time.sleep(1)# # 获取结束时间# end = time.perf_counter()# # 计算运行时间# runTime = end - start# runTime_ms = runTime * 1000# # 输出运行时间# print("运行时间：", runTime, "秒")# print("运行时间：", runTime_ms, "毫秒")## exit()frompygtransimportTranslateimporttimeclient=Translate()
end=0# #使用翻译接口对爬虫数据转中文exist_data=pd.read_excel("all_spyder(中文).xlsx")
exist_cves=list(exist_data['cve'])
# data_output = pd.read_excel("all_spyder.xlsx")data_output=pd.read_excel("output(2015).xlsx")
data_output=data_output.rename(
columns={'cveid': 'cve', 'describe_zh': 'remark', 'vulntype': 'system', 'vendor': 'company',
'product': 'brand'})
##去重print(data_output.columns)
print(data_output.head())
print_index=0result=[]
# 遍历 dataframe 的每一行forindex, rowindata_output.iterrows():
ifindex<0: continue#20472# print(f"row: {row}")print(f"index: {index}{row['cve']}")  # 打印当前行的索引ifrow['cve'] inexist_cves:
print(f"{row['cve']}已存在，跳过！！")
continueif (len(str(row['describe']))<100)|(len(str(row['describe']))>200):
print('长度不合规！！')
# print('长度不合规：{0}'.format(len(str(row['describe']))))# print(row['describe'])continuetry :
start=time.perf_counter()
while ((end-start)<0.05)&(end!=0):
# print('等待....')end=time.perf_counter()
text=client.translate(row['describe'])
end=time.perf_counter()
# print(text.translatedText)  # 谷歌翻译row['remark'] =text.translatedTextprint('翻译：',row['remark'])
print_index+=1exceptExceptionase:
row['remark']='接口调用报错！！'print('接口调用报错！！',str(e))
finally:
values= [row['cve'], row['remark'],row['describe'], row['score'], row['system'], row['producttype'], row['company'],
row['brand'], row['version']]
result.append(values)
ifprint_index%20==0:
filename="all_spyder(中文new)_{0}.xlsx".format(print_index//1000)
print('写入...',filename)
try:
workbook=load_workbook(filename)
worksheet=workbook.activeexceptFileNotFoundError:
workbook=Workbook()
worksheet=workbook.activeheader= ['cve', 'remark', 'describe', 'score', 'system', 'producttype', 'company', 'brand', 'version']
worksheet.append(header)
finally:
forrinresult:
worksheet.append(r)
workbook.save(filename)
result=[]
workbook.close()