pymultitran/pymultitran.py

   1 #!/usr/bin/env python3
   2
   3 """
   4 Copyright (c) 2010, Dmitry
   5 All rights reserved.
   6
   7 Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
   8
   9 1) Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
  10 2) Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
  11 3) Neither the name of the author nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
  12
  13 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  14 """
  15
  16 REMOTE_ENCODING = "cp1251"
  17
  18 DEFAULT_COLOUR = "\x1b[0;0m"
  19 GREY_COLOUR = "\x1b[0;37;m"
  20
  21 BAR_COLOUR = DEFAULT_COLOUR
  22 MEANING_COLOUR = "\x1b[3;32m"
  23 SYNONYM_COLOUR = "\x1b[0;0m"
  24 WORD_COLOUR = "\x1b[1m"
  25 PARTICLE_COLOUR = "\x1b[0;36m"
  26
  27 from sys import argv, exit
  28 from urllib.request import urlopen
  29 from urllib.parse import urlencode
  30
  31 class TruncationException(Exception):
  32     def __init__(self, value):
  33         self.value = value
  34     def __str__(self):
  35         return repr(self.value)
  36
  37 def ltrunc( page, sub ):
  38
  39     pos = page.find(sub)
  40     if pos < 0:
  41         raise TruncationException("Necessary html sequence is not found.")
  42
  43     return page[pos + len(sub):]
  44
  45 def remove_crap( page ):
  46
  47     page = ltrunc(page, """document.translation.s.select()\r\ndocument.translation.s.focus()""")
  48
  49     endsign = """|<span STYLE="color:black">&nbsp;<a href="#start"><FONT SIZE=2>в начало</FONT></a></td></tr></table>"""
  50     end = page.find(endsign)
  51
  52     page = page[:end]
  53
  54     return page
  55
  56 def read_meanings( page ):
  57
  58     first = True
  59
  60     while 1:
  61         try:
  62             page = ltrunc(page, "<td bgcolor=\"#DBDBDB\" colspan=\"2\"> <a href=\"")
  63             page = ltrunc(page, "\">")
  64
  65             word = page[:page.find("</a>")]
  66
  67             page = ltrunc(page, "<em>")
  68
  69             particle_type = page[:page.find("</em>")]
  70
  71             if first:
  72                 first = False
  73             else:
  74                 print("")
  75
  76             print("%s=== %s%s %s(%s%s%s) ===" % (BAR_COLOUR,
  77                                                  WORD_COLOUR, word,
  78                                                  BAR_COLOUR,
  79                                                  PARTICLE_COLOUR, particle_type,
  80                                                  BAR_COLOUR))
  81
  82         except TruncationException:
  83             pass
  84
  85         try:
  86             page = ltrunc(page, "<td >  <a title=\"")
  87         except TruncationException:
  88             break
  89
  90         page = ltrunc(page, "<i>")
  91
  92         closing_pos = page.find("</i>")
  93         meaning_type = page[:closing_pos]
  94
  95         synonym_words = []
  96
  97         page = ltrunc(page, "</i> </a>\r\n</td>")
  98
  99
 100         while 1:
 101             page = ltrunc(page, "<a href=\"m.exe?t=")
 102             page = ltrunc(page, "\">")
 103
 104             synonym_words.append(page[:page.find("<")])
 105
 106             page = ltrunc(page, "</a>")
 107
 108             if page[0] != ";":
 109                 break
 110
 111         print(" %s%8s  %s%s" % (MEANING_COLOUR, meaning_type,
 112                                 SYNONYM_COLOUR, ", ".join(synonym_words)))
 113
 114 if len(argv) < 2:
 115     print("Usage: %s word" % argv[0])
 116     exit(1)
 117
 118 word = argv[1]
 119
 120 args = urlencode([("l1", "1"), ("l2", "2"), ("s", word)],
 121                  encoding = REMOTE_ENCODING)
 122 fp = urlopen('http://www.multitran.ru/c/m.exe?%s' % args)
 123
 124 page = fp.read().decode(REMOTE_ENCODING)
 125
 126 page = remove_crap(page)
 127 page = page.replace("&nbsp;", " ")
 128 page = page.replace("<span STYLE=&#34;color:gray&#34;>", GREY_COLOUR)
 129 page = page.replace("<span STYLE=&#34;color:black&#34;>", DEFAULT_COLOUR)
 130 read_meanings(page)