1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104

#!/usr/bin/python

##
#	Author: bont
#	Date: September 8, 2009
#
#	Takes a list of Spanish words or files with words in them and gets the definitions of those words.
##

import urllib2, htmllib, formatter

class SpanishDict(htmllib.HTMLParser):
	def __init__(self):
		htmllib.HTMLParser.__init__(self, formatter.NullFormatter())
		self.word = ''
		self.div = 0
	
	def translate(self, word):
		self.word = word
		self.data = ''

		url = 'http://www.spanishdict.com/translate/' + urllib2.quote(self.word)
		
		try:
			f = urllib2.urlopen(url)
			self.feed(f.read())
			self.close()
			f.close()
		except urllib2.URLError, err:
			if err.code == 8:
				print "Unable to connect to the internet. Check your connection and try again."
			else:
				print err

		data = re.sub(r'('+w+' \[.*?\])', r'\n\n\1', self.data) + "\n"
		data = re.sub(r'([0-9]+\.)', r"\n\1", data)
		data = re.sub(r'(adjective|adverb|verb)', r"\n\n\1", data)
		data = re.sub(r'([^or](masculine|feminine)*[^\]]noun)', r"\n\n\1", data)
		data = re.sub(r'(masculine or\n\n feminine noun)', r"\n\nmasculine or feminine noun", data)
		data = re.sub(r'(]noun)', r"]\n\nnoun", data)

		return data
		
	def start_div(self, attributes):
		if self.div >= 1:
			self.div += 1
			return
		
		for name, value in attributes:
			if name == 'id' and value.startswith('word_'):
				self.div = 1
				self.save_bgn()
				return
	
	def end_div(self):
		if self.div < 1:
			return
		elif self.div >= 1:
			self.div -= 1
			
			if self.div <= 0:
				self.data += self.save_end()

if __name__ == '__main__':
	from optparse import OptionParser
	import re

	parser = OptionParser("usage: %prog [options] file [file2, file3, ...]")
	parser.add_option('-o', help="where to send the output, file name or '-' to indicate stdout [default: %default]", default='{first file}.defs', dest='output')
	parser.add_option('--words', help='interpret the input as words, not file names [default: %default]', default=False, action='store_true')
	parser.add_option('--delimiter', help='delimiter between words in the files [default: %default]', default='\\n')

	(options, args) = parser.parse_args()

	if options.words == True:
		words = args
	else:
		delim = options.delimiter
		if delim == '\\n':
			delim = "\n"
		words = []
		for filename in args:
			f = open(filename)
			words.extend(f.read().split(delim))
			f.close()
	
	translator = SpanishDict()
	data = ''

	for w in words:
		if w is not '':
			text = translator.translate(w)
			data += "\n==== "+w+" ====\n\n"+text

	if options.output is '-':
		print data
	else:
		if options.output is '{first file}.defs':
			outfile = args[0] + '.defs'
		else:
			outfile = options.output
		f = open(outfile, 'w')
		f.write(data)
		f.close()