Une page de Wikipédia, l'encyclopédie libre.
# -*- coding: utf-8 -*-
# Extraction des images effacées par un admin
# Code : Dake - 2005
import wikipedia, pagegenerators, catlib
import config, replace, re, sys, urllib, codecs
username = raw_input("Nom de l'utilisateur (ex. Dake) : ")
maxdel = raw_input("Nombre de suppressions à récupérer (min. 100) : ")
outtxt = raw_input("Nom du fichier de sortie (ex. output.txt) : ")
refPics = []
f = codecs.open(outtxt, "w", "utf-8")
i = 0
while i < max(100,int(maxdel)):
print i, int(maxdel)
logUrl = "/w/index.php?title=Special:Log&type=delete&user=%s&page=&limit=250&offset=%s" % (username,str(i))
txt = wikipedia.getSite().getUrl(logUrl)
##print txt
findDeleted = re.compile(u'title=\"Image:.*?\"')
deletedPics = findDeleted.findall(txt)
###print deletedPics
findSingle = re.compile('title=\".*?\"')
for pic in deletedPics:
pic = findSingle.findall(pic)
pic = pic[0]
pic = pic.replace('title="', "")
pic = pic.replace('"', '')
if (pic not in refPics):
refPics.append(pic)
f.write(pic + "\n")
print pic
print "une page sauvée"
i+=100
f.close()
