使用Python從有道詞典網(wǎng)頁獲取單詞翻譯

更新時(shí)間：2016年07月03日 15:00:00 投稿：hebedich

這篇文章主要介紹了使用Python從有道詞典網(wǎng)頁獲取單詞翻譯的相關(guān)資料,需要的朋友可以參考下

從有道詞典網(wǎng)頁獲取某單詞的中文解釋。

import re
import urllib

word=raw_input('input a word\n')
 
url='http://dict.youdao.com/search?q=%s'%word
 
content=urllib.urlopen(url)
 
pattern=re.compile("</h2.*?</ul>",re.DOTALL)
 
result=pattern.search(content.read()).group()
pattern2=re.compile('<li>.*?</li>')
for i in pattern2.findall(result):
  print i.strip('<li>').strip('</li>').decode('utf-8')

再給大家分享一個(gè)命令行版的

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date  : 2014-04-03 21:12:16
# @Function: 有道翻譯命令行版
# @Author : BeginMan

import os
import sys
import urllib
import urllib2
reload(sys)
sys.setdefaultencoding("utf-8")
import simplejson as json
import platform
import datetime

API_KEY = '******'
KEYFORM = '******'
  
def GetTranslate(txt):
  url = 'http://fanyi.youdao.com/openapi.do'
  data = {
  'keyfrom': KEYFORM,
  'key': API_KEY,
  'type': 'data',
  'doctype': 'json',
  'version': 1.1,
  'q': txt
  }
  data = urllib.urlencode(data)
  url = url+'?'+data
  req = urllib2.Request(url)
  response = urllib2.urlopen(req)
  result = json.loads(response.read())
  return result
  
def Sjson(json_data):
  query = json_data.get('query','')        # 查詢的文本
  translation = json_data.get('translation','')  # 翻譯
  basic = json_data.get('basic','')        # basic 列表
  sequence = json_data.get('web',[])       # 短語列表
  phonetic,explains_txt,seq_txt,log_word_explains = '','','',''
  
  # 更多釋義
  if basic:
    phonetic = basic.get('phonetic','')     # 音標(biāo)
    explains = basic.get('explains',[])     # 更多釋義 列表
    for obj in explains:
      explains_txt += obj+'\n'
      log_word_explains += obj+','  
  # 句子解析
  if sequence:
    for obj in sequence:
      seq_txt += obj['key']+'\n'
      values = ''
      for i in obj['value']:
        values += i+','
      seq_txt += values+'\n'
    
  print_format = '*'*40+'\n'
  print_format += u'查詢對象: %s [%s]\n' %(query,phonetic)  
  print_format += explains_txt
  print_format += '-'*20+'\n'+seq_txt
  print_format += '*'*40+'\n'
  print print_format
  choices = raw_input(u'是否寫入單詞本,回復(fù)（y/n）:')
  if choices in ['y','Y']:
    filepath = r'/home/beginman/pyword/%s.xml' %datetime.date.today()
    if (platform.system()).lower() == 'windows':
      filepath = r'E:\pyword\%s.xml' %datetime.date.today()
    fp = open(filepath,'a+')
    file = fp.readlines()
    if not file:
      fp.write('<wordbook>\n')
      fp.write(u"""  <item>\n  <word>%s</word>\n  <trans><![CDATA[%s]]></trans>\n  <phonetic><![CDATA[[%s]]]></phonetic>\n  <tags>%s</tags>\n  <progress>1</progress>\n  </item>\n\n""" %(query,log_word_explains,phonetic,datetime.date.today()))
    fp.close()
    print u'寫入成功.'

def main():
  while True:
    txt = raw_input(u'請輸入要查詢的文本：\n')
    if txt:
      Sjson(GetTranslate(txt))

if __name__ == '__main__':
  main()

以上就是本文的所有內(nèi)容了，希望大家能夠喜歡

您可能感興趣的文章: