使用python抓取有道词典的网页并返回结果信息

使用Python写了一个抓取有道词典首页的脚本，目前功能还不完善，只能抓取基本的Tag并使用BeautifulSoup显示出来，没有对Tag里的信息进行细分。另外，网页端是按utf-8编码的，放到Windows上的命令行里无法正常显示，目前还没有测试Linux终端里的情况。有时间再完善一下吧。

#! /usr/bin/python
# coding = utf-8

# youdao.py
# To-do: get meaning of a word from youdao.com
# Author: Steven
# Date: 2013/04/21

import urllib, urllib2
from bs4 import BeautifulSoup
import sys

inputDecode = sys.stdin.encoding
outputDecode = sys.stdout.encoding


def getHtml(word = 'bless'):
	#word = raw_input("Please input your word:")
	youdaoHtml = 'http://dict.youdao.com/search'
	youdaoData = {'le': 'eng', 'q': word, 'keyfrom': 'dict'}
	youdaoRequest = urllib2.Request(youdaoHtml, urllib.urlencode(youdaoData))
	youdaoRequest.add_header('User-Agent', 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)')
	wordHtml = urllib2.urlopen(youdaoRequest)
	return wordHtml.read().decode('utf-8')
	
def showMeaning(word = 'bless'):
	word = raw_input('Please input your word:')
	wordSoup = BeautifulSoup(getHtml(word))
	# show the word
	print "Word:\t", wordSoup.find('span', {'class', 'keyword'}).string
	# show the pronounce
	print "Prounaounciation:\t",
	for prons in wordSoup.find_all('span', {'class', 'phonetic'}):
		print prons.string.encode('utf-8'),
	# show meaning
	print 'Meaning:\n'
	for meaning in wordSoup.find_all('span', {'class', 'def'}):
		print '***\t', meaning.string.encode(outputDecode)
	
def sample(word = 'bless'):
	while 1:
		print "Input C to continue, input Q/q to quit.\n"
		selection = raw_input("Please input your command\n>>>")
		if selection in ['C', 'c']:
			showMeaning(word)
		elif selection in ['Q', 'q', 'quit', 'Quit']:
			break
		else:
			exit()
	
	
if __name__ == '__main__':
	sample()