在Ubuntu下，想在终端查询不认识的单词，所以就利用了Python语言，通过正则表达式等知识，对有道单词的网页进行爬取，提取出翻译结果。
#---------------------------------------------------------------- # -*- coding: utf-8 -*- #!/usr/bin/env python #---------------------------------------------------------------- # Author : Scharfsinnig # # E-Mail : [email protected] # # File : WebDict.py # # Introduction: # 脚本主要是对有道网的单词查询网页，进行简单的信息提取任务，找到 # 单词的翻译结果。方便自己在终端下对不认识的单词进行查询。 #---------------------------------------------------------------- import re import time import thread import urllib import urllib2 from urllib import quote class Spider_Youdao: #初始化 def __init__(self): #有道网页翻译段 self.Trans_Youdao_Tag = re.compile(r’s?<li>.*?</li>s?’) #21世纪大词典段 self.Trans_Shiji_Tag = re.compile(r’s?<span.*?class="def">.*?</span>’) #退出标志 self.run = True #获得查询的单词 def SearchWord(self): S_Word = raw_input(" #[输入单词] >") return S_Word #得到URL def GetUrl(self): SWord = self.SearchWord() #加上查询的单词以后 if quote(SWord) == SWord: MyUrl = "http://dict.youdao.com/search?len=eng&q="+quote(SWord)+"&keyfrom=dict.top" return MyUrl #获得页面 def GetPage(self): #获取URL Youdao_Url = self.GetUrl() #伪装成浏览器请求 user_agent = ’Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:32.0) Gecko/20100101 Firefox/32.0’ headers = { ’User-Agent’ : user_agent } req = urllib2.Request(Youdao_Url, headers = headers) Res = urllib2.urlopen(req) #将其他编码的字符串转换成unicode编码 ResultPage = Res.read().decode("utf-8") #ResultPage = Res.read() return ResultPage #开始提取网页中的信息 def ExtractPage(self): #获得页面 MyPage = self.GetPage() #提取有道的基本翻译 YoudaoTrans = self.Trans_Youdao_Tag #提取21世纪词典的翻译 ShijiTrans = self.Trans_Shiji_Tag print "--------------------------------------------" YouDaoTrans = self.Trans_Youdao_Tag TransYdIterator = YouDaoTrans.finditer(MyPage) print "#(翻译来自有道词典):" myItems = re.findall(’<div.*?class="trans-container">(.*?)<div id="webTrans" class="trans-wrapper trans-tab">’,MyPage,re.S) for item in myItems: YDTmp = item TransYdIterator = YouDaoTrans.finditer(YDTmp) for iterator in TransYdIterator: YouDao = iterator.group() YDTag = re.compile(’s?<.*?>’) print YDTag.sub(’’,YouDao) print "--------------------------------------------" TransSjIterator = ShijiTrans.finditer(MyPage) print "#(翻译来自21世纪大词典):" for iterator in TransSjIterator: ShiJi = iterator.group() SJTag = re.compile(’s?<.*?>’) print SJTag.sub(’’,ShiJi) print "--------------------------------------------" #启动爬虫 def Start(self): while self.run: S_Word = raw_input(" #["!"号退出.回车继续.] >") if S_Word != "!": self.ExtractPage() #thread.start_new_thread(self.ExtractPage,()) #time.sleep(5) else: self.run = False if __name__ == ’__main__’: mydict = Spider_Youdao() mydict.Start()
