#!/usr/bin/python
# -*- coding: utf-8 -*-
# =============================================================================
# Version: 1.1 (Mar 31, 2009)
# Author: Antonio Fuschetto (fuschett@di.unipi.it), University of Pisa
# =============================================================================
# =============================================================================
# This program is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License, version 3,
# as published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see .
# =============================================================================
"""Wikipedia Extractor:
Extracts and cleans text from Wikipedia database dump and stores each
article in file named as article title in AURORA code. Taken out from
Tanl software package.
Usage:
WikiExtractor.py [options]
Options:
-o ..., --output=... : place output files in specified directory (current
directory by default)
--help : display this help and exit
--usage : display script usage
"""
import sys
import getopt
import re
import os.path
### SUPPORT CLASSES ###########################################################
class WikiDocument:
def __init__(self):
self.id = None
self.url = None
self.text = None
self.title = None
def __str__(self):
return '%s\n' % (self.text)
#------------------------------------------------------------------------------
class WikiExtractor:
__garbage_tags = ('ref', 'gallery', 'timeline', 'noinclude', 'pre', 'table', 'tr', 'td',
'ul', 'li', 'ol', 'dl', 'dt', 'dd', 'menu', 'dir')
__wrapper_tags = ('nowiki', 'cite', 'source', 'hiero', 'div', 'font', 'span', 'strong',
'strike', 'blockquote', 'tt', 'var', 'sup', 'sub', 'big', 'small',
'center', 'h1', 'h2', 'h3', 'em', 'b', 'i', 'u', 'a', 's', 'p')
__single_tags = ('references', 'ref', 'img', 'br', 'hr', 'li', 'dt', 'dd')
__placeholder_tags = {'math':'Formula', 'code':'Codice'}
__project_namespaces = ('wikipedia', 'mediawiki', 'wikiquote', 'wikibooks', 'wikisource',
'wiktionary', 'wikispecies', 'wikinews', 'wikiversita', 'commons')
__garbage_namespaces = ('immagine', 'image', 'categoria', 'category')
__char_entities = {' ' :u'\u00A0', '¡' :u'\u00A1', '¢' :u'\u00A2',
'£' :u'\u00A3', '¤':u'\u00A4', '¥' :u'\u00A5',
'¦' :u'\u00A6', '§' :u'\u00A7', '¨' :u'\u00A8',
'©' :u'\u00A9', 'ª' :u'\u00AA', '«' :u'\u00AB',
'¬' :u'\u00AC', '' :u'\u00AD', '®' :u'\u00AE',
'¯' :u'\u00AF', '°' :u'\u00B0', '±' :u'\u00B1',
'²' :u'\u00B2', '³' :u'\u00B3', '´' :u'\u00B4',
'µ' :u'\u00B5', '¶' :u'\u00B6', '·' :u'\u00B7',
'¸' :u'\u00B8', '¹' :u'\u00B9', 'º' :u'\u00BA',
'»' :u'\u00BB', '¼':u'\u00BC', '½' :u'\u00BD',
'¾' :u'\u00BE', '¿':u'\u00BF', 'À' :u'\u00C0',
'Á' :u'\u00C1', 'Â' :u'\u00C2', 'Ã' :u'\u00C3',
'Ä' :u'\u00C4', 'Å' :u'\u00C5', 'Æ' :u'\u00C6',
'Ç' :u'\u00C7', 'È':u'\u00C8', 'É' :u'\u00C9',
'Ê' :u'\u00CA', 'Ë' :u'\u00CB', 'Ì' :u'\u00CC',
'Í' :u'\u00CD', 'Î' :u'\u00CE', 'Ï' :u'\u00CF',
'Ð' :u'\u00D0', 'Ñ':u'\u00D1', 'Ò' :u'\u00D2',
'Ó' :u'\u00D3', 'Ô' :u'\u00D4', 'Õ' :u'\u00D5',
'Ö' :u'\u00D6', '×' :u'\u00D7', 'Ø' :u'\u00D8',
'Ù' :u'\u00D9', 'Ú':u'\u00DA', 'Û' :u'\u00DB',
'Ü' :u'\u00DC', 'Ý':u'\u00DD', 'Þ' :u'\u00DE',
'ß' :u'\u00DF', 'à':u'\u00E0', 'á' :u'\u00E1',
'â' :u'\u00E2', 'ã':u'\u00E3', 'ä' :u'\u00E4',
'å' :u'\u00E5', 'æ' :u'\u00E6', 'ç' :u'\u00E7',
'è' :u'\u00E8', 'é':u'\u00E9', 'ê' :u'\u00EA',
'ë' :u'\u00EB', 'ì':u'\u00EC', 'í' :u'\u00ED',
'î' :u'\u00EE', 'ï' :u'\u00EF', 'ð' :u'\u00F0',
'ñ' :u'\u00F1', 'ò':u'\u00F2', 'ó' :u'\u00F3',
'ô' :u'\u00F4', 'õ':u'\u00F5', 'ö' :u'\u00F6',
'÷' :u'\u00F7', 'ø':u'\u00F8', 'ù' :u'\u00F9',
'ú' :u'\u00FA', 'û' :u'\u00FB', 'ü' :u'\u00FC',
'ý' :u'\u00FD', 'þ' :u'\u00FE', 'ÿ' :u'\u00FF',
'ƒ' :u'\u0192', 'Α' :u'\u0391', 'Β' :u'\u0392',
'Γ' :u'\u0393', 'Δ' :u'\u0394', 'Ε' :u'\u0395',
'Ζ' :u'\u0396', 'Η' :u'\u0397', 'Θ' :u'\u0398',
'Ι' :u'\u0399', 'Κ' :u'\u039A', 'Λ' :u'\u039B',
'Μ' :u'\u039C', 'Ν' :u'\u039D', 'Ξ' :u'\u039E',
'Ο':u'\u039F', 'Π' :u'\u03A0', 'Ρ' :u'\u03A1',
'Σ' :u'\u03A3', 'Τ' :u'\u03A4', 'Υ' :u'\u03A5',
'Φ' :u'\u03A6', 'Χ' :u'\u03A7', 'Ψ' :u'\u03A8',
'Ω' :u'\u03A9', 'α' :u'\u03B1', 'β' :u'\u03B2',
'γ' :u'\u03B3', 'δ' :u'\u03B4', 'ε' :u'\u03B5',
'ζ' :u'\u03B6', 'η' :u'\u03B7', 'θ' :u'\u03B8',
'ι' :u'\u03B9', 'κ' :u'\u03BA', 'λ' :u'\u03BB',
'μ' :u'\u03BC', 'ν' :u'\u03BD', 'ξ' :u'\u03BE',
'ο':u'\u03BF', 'π' :u'\u03C0', 'ρ' :u'\u03C1',
'ς' :u'\u03C2', 'σ' :u'\u03C3', 'τ' :u'\u03C4',
'υ':u'\u03C5', 'φ' :u'\u03C6', 'χ' :u'\u03C7',
'ψ' :u'\u03C8', 'ω' :u'\u03C9', 'ϑ':u'\u03D1',
'ϒ' :u'\u03D2', 'ϖ' :u'\u03D6', '•' :u'\u2022',
'…' :u'\u2026', '′' :u'\u2032', '″' :u'\u2033',
'‾' :u'\u203E', '⁄' :u'\u2044', '℘' :u'\u2118',
'ℑ' :u'\u2111', 'ℜ' :u'\u211C', '™' :u'\u2122',
'ℵ':u'\u2135', '←' :u'\u2190', '↑' :u'\u2191',
'→' :u'\u2192', '↓' :u'\u2193', '↔' :u'\u2194',
'↵' :u'\u21B5', '⇐' :u'\u21D0', '⇑' :u'\u21D1',
'⇒' :u'\u21D2', '⇓' :u'\u21D3', '⇔' :u'\u21D4',
'∀' :u'\u2200', '∂' :u'\u2202', '∃' :u'\u2203',
'∅' :u'\u2205', '∇' :u'\u2207', '∈' :u'\u2208',
'∉' :u'\u2209', '∋' :u'\u220B', '∏' :u'\u220F',
'∑' :u'\u2211', '−' :u'\u2212', '∗' :u'\u2217',
'√' :u'\u221A', '∝' :u'\u221D', '∞' :u'\u221E',
'∠' :u'\u2220', '∧' :u'\u2227', '∨' :u'\u2228',
'∩' :u'\u2229', '∪' :u'\u222A', '∫' :u'\u222B',
'∴' :u'\u2234', '∼' :u'\u223C', '≅' :u'\u2245',
'≈' :u'\u2248', '≠' :u'\u2260', '≡' :u'\u2261',
'≤' :u'\u2264', '≥' :u'\u2265', '⊂' :u'\u2282',
'⊃' :u'\u2283', '⊄' :u'\u2284', '⊆' :u'\u2286',
'⊇' :u'\u2287', '⊕' :u'\u2295', '⊗' :u'\u2297',
'⊥' :u'\u22A5', '⋅' :u'\u22C5', '⌈' :u'\u2308',
'⌉' :u'\u2309', '⌊':u'\u230A', '⌋' :u'\u230B',
'⟨' :u'\u2329', '⟩' :u'\u232A', '◊' :u'\u25CA',
'♠' :u'\u2660', '♣' :u'\u2663', '♥' :u'\u2665',
'♦' :u'\u2666', '"' :u'\u0022', '<' :u'\u003C',
'>' :u'\u003E', 'Œ' :u'\u0152', 'œ' :u'\u0153',
'Š' :u'\u0160', 'š':u'\u0161', 'Ÿ' :u'\u0178',
'ˆ' :u'\u02C6', '˜' :u'\u02DC', ' ' :u'\u2002',
' ' :u'\u2003', ' ':u'\u2009', '' :u'\u200C',
'' :u'\u200D', '' :u'\u200E', '' :u'\u200F',
'–' :u'\u2013', '—' :u'\u2014', '‘' :u'\u2018',
'’' :u'\u2019', '‚' :u'\u201A', '“' :u'\u201C',
'”' :u'\u201D', '„' :u'\u201E', '†' :u'\u2020',
'‡' :u'\u2021', '‰':u'\u2030', '‹' :u'\u2039',
'›' :u'\u203A', '€' :u'\u20AC'}
def __init__(self):
# Riconosce i commenti HTML
self.__comment_pattern = re.compile(r'', re.DOTALL)
# Riconosce i tag HTML spazzatura
self.__garbage_tag_patterns = list()
for tag in self.__class__.__garbage_tags:
pattern = re.compile(r'<\s*%s(\s*| [^/]+?)>.*?<\s*/\s*%s\s*>' % (tag, tag), re.DOTALL | re.IGNORECASE)
self.__garbage_tag_patterns.append(pattern)
# Riconosce i tag HTML contenitori
self.__wrapper_tag_patterns = list()
for tag in self.__class__.__wrapper_tags:
left_pattern = re.compile(r'<\s*%s(\s*| [^/]+?)>' % tag, re.DOTALL | re.IGNORECASE)
right_pattern = re.compile(r'<\s*/\s*%s\s*>' % tag, re.DOTALL | re.IGNORECASE)
self.__wrapper_tag_patterns.append((left_pattern, right_pattern))
# Riconosce i tag HTML singoli
self.__single_tag_patterns = list()
for tag in self.__class__.__single_tags:
good_pattern = re.compile(r'<\s*%s(\s*| .+?)/\s*>' % tag, re.DOTALL | re.IGNORECASE)
bad_pattern = re.compile(r'<\s*(/|\\)?\s*%s(\s*| [^/]+?)\\?\s*>' % tag, re.DOTALL | re.IGNORECASE)
self.__single_tag_patterns.append((good_pattern, bad_pattern))
# Riconosce i tag HTML segnaposto
self.__placeholder_tag_patterns = list()
for tag in self.__class__.__placeholder_tags.iterkeys():
pattern = re.compile(r'<\s*%s(\s*| [^/]+?)>.*?<\s*/\s*%s\s*>' % (tag, tag), re.DOTALL | re.IGNORECASE)
self.__placeholder_tag_patterns.append((pattern, self.__class__.__placeholder_tags[tag]))
# Riconosce le tabelle e i template
self.__table_pattern = re.compile(r'\{[^{]*?\}', re.DOTALL)
# Riconosce i wikilink
good_wikilink_pattern = re.compile(r'\[\[[^[]*?\]\]', re.DOTALL)
bad_left_wikilink_pattern = re.compile(r'\[[^[]*?\]\]', re.DOTALL)
bad_right_wikilink_pattern = re.compile(r'\[\[[^[]*?\]', re.DOTALL)
self.__wikilink_pattern = (good_wikilink_pattern, bad_left_wikilink_pattern, bad_right_wikilink_pattern)
# Riconosce i link HTTP
self.__http_link_pattern = re.compile(r'\[http.*?\]', re.DOTALL | re.IGNORECASE)
# Riconosce gli apostrofi che precedono grassetto e corsivo
apostrophe_bold_pattern = re.compile(r"\w'('''.*?''')", re.DOTALL)
apostrophe_italic_pattern = re.compile(r"\w'(''.*?'')", re.DOTALL)
self.__apostrophe_pattern = (apostrophe_bold_pattern, apostrophe_italic_pattern)
# Riconosce le entita' numeriche
self.__numeric_entity_pattern = re.compile(r'&#\d+?;')
# Riconosce gli spazi multipli
self.__multi_space_pattern = re.compile(r' {2,}')
# Riconosce i punti multipli
self.__multi_dot_pattern = re.compile(r'\.{4,}')
def extract(self, wiki_document):
wiki_document = self.__clean(wiki_document)
if not wiki_document: return None
wiki_document = self.__compact(wiki_document)
return wiki_document
def __clean(self, wiki_document):
# Rende maggiormente riconoscibili i tag
wiki_document.text = wiki_document.text.replace('<', '<').replace('>', '>')
wiki_document.text = wiki_document.text.replace('<<', u'«').replace('>>', u'»')
# Elimina i commenti HTML
wiki_document.text = self.__comment_pattern.sub('', wiki_document.text)
# Elimina i tag HTML spazzatura
for pattern in self.__garbage_tag_patterns:
wiki_document.text = pattern.sub('', wiki_document.text)
# Elimina i tag HTML contenitori
for left_pattern, right_pattern in self.__wrapper_tag_patterns:
wiki_document.text = left_pattern.sub('', wiki_document.text)
wiki_document.text = right_pattern.sub('', wiki_document.text)
# Elimina i tag HTML singoli
for good_pattern, bad_pattern in self.__single_tag_patterns:
wiki_document.text = good_pattern.sub('', wiki_document.text)
wiki_document.text = bad_pattern.sub('', wiki_document.text)
# Elimina i tag HTML segnaposto
for pattern, placeholder in self.__placeholder_tag_patterns:
index = 1
for match in pattern.finditer(wiki_document.text):
wiki_document.text = wiki_document.text.replace(match.group(), '[%s %d]' % (placeholder, index))
index += 1
# Elimina le tabelle e i template
wiki_document.text = wiki_document.text.replace('{{end box}}', '}')
wiki_document.text = wiki_document.text.replace('{{', '{').replace('}}', '}')
wiki_document.text = wiki_document.text.replace('{|', '{').replace('|}', '}')
wiki_document.text = self.__table_pattern.sub('', wiki_document.text)
wiki_document.text = self.__table_pattern.sub('', wiki_document.text)
wiki_document.text = self.__table_pattern.sub('', wiki_document.text)
# Gestisce i wikilink (ben formattati)
good_wikilink_pattern = self.__wikilink_pattern[0]
for match in good_wikilink_pattern.finditer(wiki_document.text):
wikilink = match.group()
wiki_document.text = wiki_document.text.replace(wikilink, self.__handle_wikilink(wikilink[2:-2]))
for match in good_wikilink_pattern.finditer(wiki_document.text):
wikilink = match.group()
wiki_document.text = wiki_document.text.replace(wikilink, self.__handle_wikilink(wikilink[2:-2]))
# Gestisce i wikilink (mal formattatia)
bad_left_wikilink_pattern = self.__wikilink_pattern[1]
for match in bad_left_wikilink_pattern.finditer(wiki_document.text):
wikilink = match.group()
wiki_document.text = wiki_document.text.replace(wikilink, self.__handle_wikilink(wikilink[1:-2]))
bad_right_wikilink_pattern = self.__wikilink_pattern[2]
for match in bad_right_wikilink_pattern.finditer(wiki_document.text):
wikilink = match.group()
wiki_document.text = wiki_document.text.replace(wikilink, self.__handle_wikilink(wikilink[2:-1]))
wiki_document.text = wiki_document.text.replace('[[', '').replace(']]', '')
# Elimina i link HTTP
wiki_document.text = self.__http_link_pattern.sub('', wiki_document.text).replace('[]', '')
# Gestisce i grassetti e i corsivi
apostrophe_bold_pattern = self.__apostrophe_pattern[0]
for match in apostrophe_bold_pattern.finditer(wiki_document.text):
bold_text = match.group(1)
wiki_document.text = wiki_document.text.replace(bold_text, bold_text[3:-3])
apostrophe_italic_pattern = self.__apostrophe_pattern[1]
for match in apostrophe_italic_pattern.finditer(wiki_document.text):
italic_text = match.group(1)
wiki_document.text = wiki_document.text.replace(italic_text, '"%s"' % italic_text[2:-2])
wiki_document.text = wiki_document.text.replace("'''", '').replace("''", '"')
# Gestisce i caratteri speciali
wiki_document.text = wiki_document.text.replace('&', '&').replace('""', '"')
for entity in self.__class__.__char_entities.iterkeys():
wiki_document.text = wiki_document.text.replace(entity, self.__class__.__char_entities[entity])
# Gestisce i caratteri speciali
for match in self.__numeric_entity_pattern.finditer(wiki_document.text):
entity = match.group()
wiki_document.text = wiki_document.text.replace(entity, self.__handle_unicode(entity))
# Gestisce alcune imperfezioni del testo
wiki_document.text = wiki_document.text.replace('\t', ' ')
wiki_document.text = self.__multi_space_pattern.sub(' ', wiki_document.text)
wiki_document.text = self.__multi_dot_pattern.sub('...', wiki_document.text)
wiki_document.text = wiki_document.text.replace(' ,', ',').replace(' .', '.')
wiki_document.text = wiki_document.text.replace(' :', ':').replace(' ;', ';')
wiki_document.text = wiki_document.text.replace(',,', ',').replace(',.', '.')
wiki_document.text = wiki_document.text.replace('( ', '(').replace(' )', ')')
wiki_document.text = wiki_document.text.replace('[ ', '[').replace(' ]', ']')
wiki_document.text = wiki_document.text.replace(u'« ', u'«').replace(u' »', u'»')
return wiki_document
def __compact(self, wiki_document):
page = list()
paragraph = list()
for line in wiki_document.text.split('\n'):
line = line.strip()
if not line: continue
# Gestisce il titolo della pagina
if line.startswith('++'):
title = line[2:-2]
if title and title[-1] not in '!?':
title = '%s.' % title
page = [title]
# Gestisce i titoli dei paragrafi
elif line.startswith('=='):
if len(paragraph) > 1:
page.extend(paragraph)
title = line[2:-2]
if title and title[-1] not in '!?':
title = '%s.' % title
paragraph = [title]
# Elimina gli elenchi puntati e numerati
elif line[0] in '*#:;':
continue
# Elimina i resti delle tabelle
elif line[0] in '{|' or line[-1] in '}':
continue
# Elimina le righe non significative
elif (line[0] == '(' and line[-1] == ')') or line.strip('.-') == '':
continue
# Elimina le righe con un basso numero di token
elif len(line.split()) < 6:
continue
# Gestisce il testo della pagina
elif len(paragraph) == 0:
page.append(line)
# Gestisce il testo dei paragrafi
else:
paragraph.append(line)
if len(paragraph) > 1:
page.extend(paragraph)
elif len(page) == 1: return None
wiki_document.text = '\n'.join(page)
return wiki_document
def __handle_wikilink(self, wikilink):
tokens = wikilink.split(':')
while not tokens[0]:
if len(tokens) < 2: return ''
tokens = tokens[1:]
if len(tokens) == 1 or tokens[0].strip().lower() in self.__class__.__project_namespaces:
tokens = tokens[-1].split('|')
while not tokens[-1]:
if len(tokens) < 2: return ''
tokens = tokens[:-1]
return tokens[-1].split('#')[-1].split('/')[-1].strip()
if tokens[0].strip().lower() in self.__class__.__garbage_namespaces: return ''
tokens = tokens[-1].split('|')
while not tokens[-1]:
if len(tokens) < 2: return ''
tokens = tokens[:-1]
if len(tokens) == 1: return ''
return tokens[-1].split('#')[-1].split('/')[-1].strip()
def __handle_unicode(self, entity):
numeric_code = int(entity[2:-1])
if numeric_code >= 0x10000: return ''
return unichr(numeric_code)
### CORE ######################################################################
def process_data(input_file, wiki_extractor, output_dir_name):
page = []
for line in input_file:
line = line.decode('utf-8').strip()
if line == '':
page = []
elif line == '':
process_page(page, wiki_extractor, output_dir_name)
else:
page.append(line)
#------------------------------------------------------------------------------
# Unicode --> AURORA
__trans = {u'а':'a', u'б':'b', u'в':'v', u'г':'g', u'д':'d',
u'ђ':'dx', u'е':'e', u'ж':'zx', u'з':'z', u'и':'i',
u'ј':'j', u'к':'k', u'л':'l', u'љ':'lx', u'м':'m',
u'н':'n', u'њ':'nx', u'о':'o', u'п':'p', u'р':'r',
u'с':'s', u'т':'t', u'ћ':'cx', u'ч':'cy', u'ф':'f',
u'х':'h', u'ц':'c', u'у':'u', u'џ':'dy', u'ш':'sx',
u'А':'A', u'Б':'B', u'В':'V', u'Г':'G', u'Д':'D',
u'Ђ':'Dx', u'Е':'E', u'Ж':'Zx', u'З':'Z', u'И':'I',
u'Ј':'J', u'К':'K', u'Л':'L', u'Љ':'Lx', u'М':'M',
u'Н':'N', u'Њ':'Nx', u'О':'O', u'П':'P', u'Р':'R',
u'С':'S', u'Т':'T', u'Ћ':'Cx', u'Ч':'Cy', u'Ф':'F',
u'Х':'H', u'Ц':'C', u'У':'U', u'Џ':'Dy', u'Ш':'Sx'};
def translate_article_name(name):
newname = ''
name = name.replace(' ','_')
for n in name:
if n in __trans:
newname += __trans[n]
elif n.isalnum():
newname += n
else:
newname += '_'
return newname
num_of_unknown = 0
def process_page(page, wiki_extractor, output_dir_name):
wiki_document = extract_document(page)
if not wiki_document: return
wiki_document = wiki_extractor.extract(wiki_document)
if not wiki_document: return
title = translate_article_name(wiki_document.title)
if not title:
title = "%d_Unknown" % num_of_unknown
num_of_unknown += 1
f = open(os.path.join(output_dir_name, "%s.txt" % title), 'w+')
f.write(wiki_document.__str__().encode('utf-8'))
f.close()
#------------------------------------------------------------------------------
def extract_document(page):
wiki_document = WikiDocument()
for line in page:
if not line: continue
# Identificatore della pagina (nodo XML)
if not wiki_document.id and line.startswith('') and line.endswith(''):
wiki_document.id = int(line[4:-5])
continue
# Titolo della pagina (nodo XML)
elif not wiki_document.url and line.startswith('') and line.endswith(''):
title = line[7:-8].replace('&', '&')
if ':' in title: return None
wiki_document.text = '++%s++' % title
wiki_document.title = title
continue
# Inizio del testo della pagina (nodo XML)
elif line.startswith(''): return None
line = line[27:]
if not line: continue
# Fine del testo della pagina (nodo XML)
elif line.endswith(''):
line = line[:-7]
if not line: continue
# Informazione superflua (nodo XML)
elif line[0] == '<':
continue
# Titolo di paragafo (testo della pagina)
elif line[0] == '=':
line = '==%s==' % line.strip('= ')
wiki_document.text += '\n%s' % line
return wiki_document
### USER INTERFACE ############################################################
def show_help():
print >> sys.stdout, __doc__,
def show_usage(output_file, script_name):
print >> output_file, 'Usage: %s [options]' % script_name
def show_suggestion(output_file, script_name):
print >> output_file, 'Try \'%s --help\' for more information.' % script_name
def show_file_error(script_name, file_name):
print >> sys.stderr, '%s: %s: No such file or directory' % (script_name, file_name)
def main():
script_name = os.path.basename(sys.argv[0])
try:
long_opts = ['help', 'usage', 'compress', 'bytes=', 'output=']
opts, args = getopt.gnu_getopt(sys.argv[1:], 'cb:o:', long_opts)
except getopt.GetoptError:
show_usage(sys.stderr, script_name)
show_suggestion(sys.stderr, script_name)
sys.exit(1)
output_dir_name = '.'
for opt, arg in opts:
if opt == '--help':
show_help()
sys.exit()
elif opt == '--usage':
show_usage(sys.stdout, script_name)
sys.exit()
elif opt in ('-o', '--output'):
if os.path.isdir(arg):
output_dir_name = arg
else:
show_file_error(script_name, arg)
sys.exit(3)
if len(args) > 0:
show_usage(sys.stderr, script_name)
show_suggestion(sys.stderr, script_name)
sys.exit(4)
wiki_extractor = WikiExtractor()
process_data(sys.stdin, wiki_extractor, output_dir_name)
if __name__ == '__main__':
main()