Utilisateur:Probot/NoCat.py

# -*- coding: utf-8	 -*-

import wikipedia, pagegenerators
import sys
import re
import catlib
import codecs


def utf8(text):
	return unicode(text, 'utf-8')


class ExtractCats:
	def __init__(self, generator, acceptall = False):
		self.generator = generator
		self.acceptall = acceptall

	def run(self):
		file = codecs.open('fichier.html','w','utf-8')
		file.write("<table border=\"1\">\n")
		for page in self.generator:
			try:
				if (page.exists()):
					if (page.namespace()==0):
						c = page.categories()
						if (len(c)==0):
							file.write("<tr bgcolor=\"red\">")
						else:
							file.write("<tr>")
						file.write("<td>")
						file.write("[[%s]]" % page._title)
						file.write( "</td>")
						file.write("<td>")
						for i in c:
							file.write(i.aslink() + "<br />")
						file.write("</td>")
						file.write("</tr>\n")
			except wikipedia.NoPage:
				print "Page %s does not exist?!" % page.aslink()
			except wikipedia.IsRedirectPage:
				print "Page %s is a redirect; skipping." % page.aslink()
			except wikipedia.LockedPage:
				print "Page %s is locked?!" % page.aslink()
			print "%s OK" % page._title
		file.write("</table>")
		file.close()

def main():
	#page generator
	gen = None
	pageTitle = []
	for arg in wikipedia.handleArgs():
		if arg.startswith('-start:'):
			gen = pagegenerators.AllpagesPageGenerator(arg[7:])
		elif arg.startswith('-ref:'):
			referredPage = wikipedia.Page(wikipedia.getSite(), arg[5:])
			gen = pagegenerators.ReferringPageGenerator(referredPage)
		elif arg.startswith('-links:'):
			linkingPage = wikipedia.Page(wikipedia.getSite(), arg[7:])
			gen = pagegenerators.LinkedPageGenerator(linkingPage)
		elif arg.startswith('-file:'):
			gen = pagegenerators.TextfilePageGenerator(arg[6:])
		elif arg.startswith('-cat:'):
			cat = catlib.Category(wikipedia.getSite(), 'Category:%s' % arg[5:])
			gen = pagegenerators.CategorizedPageGenerator(cat)
		else:
			pageTitle.append(arg)

	if pageTitle:
		page = wikipedia.Page(wikipedia.getSite(), ' '.join(pageTitle))
		gen = iter([page])
	if not gen:
		wikipedia.showHelp()
	else:
		preloadingGen = pagegenerators.PreloadingGenerator(gen)
		bot = ExtractCats(preloadingGen)
		bot.run()

if __name__ == "__main__":
	try:
		main()
	finally:
		wikipedia.stopme()