ydict-py

#!/usr/bin/env python
# coding=UTF-8
# Chen Wen <chenpc@cs.nctu.edu.tw>
# Web Site http://code.google.com/p/ydict/
# Blog : http://chenpc.csie.in
import httplib, urllib,string,sys
from HTMLParser import HTMLParser
from optparse import OptionParser
import locale
from codecs import EncodedFile
import shelve,os
import random

version="ydict 1.0.9"
red="\33[31;1m"
lindigo="\33[36;1m"
indigo="\33[36m"
green="\33[32m"
yellow="\33[33;1m"
blue="\33[34;1m"
org="\33[0m"
light="\33[0;1m"
learn=0
if os.access(os.getenv("HOME")+"/.ydict.db", os.F_OK):
	db=shelve.open(os.getenv("HOME")+"/.ydict.db","c")
	learn=1

def importfile(file):
	fp = open(file)
	db=shelve.open(os.getenv("HOME")+"/.ydict.db","c")
	for line in fp:
		newword=line.split(" ")[0]
		if db.has_key(newword) == 0:
			db[newword]=0
	print "File imported!"
def result(count, total):
	if total == 0:
		print ""
		exit()
	print "\nScore: ",int(count),"/",int(total),"(",count/total,")"
	exit()

def seckey(x):
        return x[1]

def wordlearn():
	wordlist = list(db.iteritems())
	wordlist.sort(key=seckey)
	size=len(wordlist)
	totalcount = 0.0
	right = 0.0
	if size <= 1:
		print "There must be at least two words needed in the list."
		exit()
	while True:
			
		k=wordlist[int(random.triangular(0, size-1, 0))][0]
		k=k.lower()
		print dict(k,1).replace(k, "####").replace(k.upper(), "####").replace(k[0].swapcase()+k[1:].lower(),"####")
		try:
			word=raw_input("Input :")
		except KeyboardInterrupt:
			result(right,totalcount)
		if word == k.lower():
			print "Bingo!"
			right+=1
			db[k]+=1
			if db[k] >= 100:
				db[k]=100
		else:
			db[k]-=3
			if db[k] < 0:
				db[k]=0
			print "WRONG! Correct answer is : ",k
			try:
				raw_input("Press Enter to contiune......")
			except KeyboardInterrupt:
				result(right,totalcount)
		db.sync()
		totalcount+=1
		if totalcount % (int(size/4)+1) == 0:
			wordlist=list(db.iteritems())
			wordlist.sort(key=seckey)
def wordlist():
	db=shelve.open(os.getenv("HOME")+"/.ydict.db","c")
	wordlist = list(db.iteritems())
	wordlist.sort(key=seckey)
	for k,v in wordlist:
		print k,v
class MyHTMLParser(HTMLParser):
	redirect=0
	pron=True
	def __init__(self):
		self.show=0
		self.prefix=""
		self.postfix=org
		self.entry=1
		self.desc=0
		self.result=[]
		self.learn=learn
		self.learnword=0
		self.chinese=0

	def handle_starttag(self, tag, attrs):
		if self.redirect == 1 and tag == "strong":
			self.show=1
			self.prefix="Spell Check: ["+yellow
			self.postfix=org+"]"
		
		elif tag == "span" and len(attrs)==0:
			if self.pron == True:
				self.show=1
				self.prefix=""
		elif tag == "div" and len(attrs)==0:
			if self.pron == True:
				self.show=1
				self.prefix=""
		elif tag == "div" and len(attrs)!=0:
			if attrs[0][1]=="pronunciation" and self.pron==True:
				self.result.append(blue)
			elif attrs[0][1]=="caption":
				self.show=1
				self.prefix=red
			elif attrs[0][1]=="theme clr":
				self.show=1
				if self.chinese == 0:
					self.learnword=1
					self.prefix="["+light
					self.postfix=org+"]"
			elif attrs[0][1]=="description":
				if self.desc != 0:
					self.show=1
					self.prefix="  "+org
				self.desc+=1
		elif tag == "p" and len(attrs)!=0:
			if attrs[0][1] == "example":
				self.show=1
				self.prefix="	"+indigo
			elif attrs[0][1] == "interpret":
				self.show=1
				self.prefix="  "+org+str(self.entry)+"."
				self.entry+=1

	def handle_data(self,data):
		if self.show == 1:
			self.result.append(self.prefix+data+self.postfix+"\n")
			self.show=0
			self.prefix=""
			self.postfix=""
		if(self.learn == 1 and self.learnword == 1):
			if(db.has_key(data.lower()) == 0 and data.lower().isalpha() ):
				db[data.lower()]=0
			self.learnword=0

	def handle_endtag(self, tag):
		if tag == "div":
			self.result.append(org)

def htmlspcahrs(content):
	content=content.replace("&amp;","&")
	content=content.replace("&#39;","\'")
	content=content.replace("&quot;","\"")
	content=content.replace("&gt",">")
	content=content.replace("&lt","<")
	content=content.replace("<span>","")
	content=content.replace("</span>","")
	content=content.replace("<b>",lindigo)
	content=content.replace("</b>",org+indigo)
	content=content.replace("\n","\n	"+green)
	return content


def http_postconn(word):
	yahoourl="tw.dictionary.yahoo.com"
	params = urllib.urlencode({'p': word ,'ei' : 'UTF-8'})
	return urllib.urlopen("http://%s/search" % yahoourl, params)

def dict(word,pron):
	output=""
	word=word.strip()
	if len(word) <= 0:
		return output
	r1=http_postconn(word)
	data1 = r1.read()
	p=MyHTMLParser()
	p.redirect=0
	p.chinese=0
	p.pron=pron
	try:
		#data1=data1[:16+string.index(data1,"Online Resources")]
		data1=data1[:16+string.index(data1,'<div id="adbn_BE" class="ad">')]
	except ValueError:
		return output

	
	try:
		index1=string.index(data1,"您是不是要查")
		p.redirect=1
	except ValueError:
		try:
			index1=string.index(data1,"很抱歉，字典找不到您要的資料喔！")
			return yellow+"Not Found!"+org+"\n"
		except ValueError:
			index1=string.index(data1,"字典搜尋")
	
	try:
		index3=string.index(data1,"以下為 <strong>")
		index4=string.index(data1,"</strong> 在字典中的結果")
		print yellow+"以下為 "+light+data1[index3+18:index4]+yellow+" 在字典中的結果"+org
	except ValueError:
		pass
	try:
		string.index(data1,"拼音")
		string.index(data1,"注音")
		p.chinese=1
	except ValueError:
		pass

		
	data=data1[index1:]
	p.reset()
	data=htmlspcahrs(data)
	p.feed(data)
	for s in p.result:
		output+=s
	return output
			
if __name__ == '__main__':
	parser = OptionParser()
	parser.add_option("-s", "--step", dest="step", help="one step mode.",default=False,action="store_true")
	parser.add_option("-p", "--pron", dest="pron", help="disable pronounce.",default=True,action="store_false")
	parser.add_option("-u", "--utf8", dest="utf8", help="force utf-8 encoding.",default=False,action="store_true")
	parser.add_option("-b", "--big5", dest="big5", help="force big5 encoding.",default=False,action="store_true")
	parser.add_option("-w", "--word", dest="oneword", type="string" , help="only one word.",action="store")
	parser.add_option("-v", "--version", dest="version", help="show version.",default=False,action="store_true")
	parser.add_option("-d", "--database", dest="database", help="initial database.",default=False,action="store_true")
	parser.add_option("-l", "--learn", dest="learnmode", help="start learning mode.",default=False,action="store_true")
	parser.add_option("-a", "--list", dest="listall", help="list all word in list.",default=False,action="store_true")
	parser.add_option("-i", "--import", dest="importfile", type="string", help="import a word list",default=False,action="store")

	(options, args) = parser.parse_args()
	m_pron=options.pron
	(lang , enc)=locale.getdefaultlocale()

	if options.importfile:
		importfile(options.importfile)
		exit()
		
	if options.version == True:
		print version
		exit()
	if options.utf8 == True:
		enc="utf8"
	elif options.big5 == True:
		enc="big5"
	if options.database == True:
		db=shelve.open(os.getenv("HOME")+"/.ydict.db","c")
		db.close()
		exit()

	if options.utf8 == options.big5 ==True:
		print "Can not select utf-8 and big5 at the same time"
		exit()
	if enc == 'big5':
		m_pron=False
	
	if True:
		result=dict(sys.argv[1],m_pron)
		result=unicode(result,'utf8')
		result=result.encode(enc)
		print result
		exit()
	if options.learnmode:
		wordlearn()
	elif options.listall:
		wordlist()
		exit()

	while(1):
		try:
			word=raw_input("<PyDict> ")
		except KeyboardInterrupt:
			print ""
			exit()
		except EOFError:
			print ""
			exit()

		result=dict(word,m_pron)
		result=unicode(result,'utf8')
		result=result.encode(enc)
		print result

		if options.step == True:
			exit()