Un article de Wikipédia, l'encyclopédie libre.
#!/usr/bin/python
# -*- coding: utf-8 -*-
"""
This bot goes over multiple pages of the home wiki, and edits them without
changing. This is for example used to get category links in templates
working.
This script understands various command-line arguments:
-start: used as -start:page_name, specifies that the robot should
go alphabetically through all pages on the home wiki,
starting at the named page.
-file: used as -file:file_name, read a list of pages to treat
from the named textfile. Page titles should be enclosed
in [[double-squared brackets]].
-ref: used as -start:page_name, specifies that the robot should
touch all pages referring to the named page.
-cat: used as -cat:category_name, specifies that the robot should
touch all pages in the named category.
All other parameters will be regarded as a page title; in this case, the bot
will only touch a single page.
"""
import wikipedia, pagegenerators, catlib
import sys
import re
site = wikipedia.getSite()
#todo reutiliser le contenu de wikipedia
class TouchBot:
def __init__(self, generator):
self.generator = generator
def run(self):
for page in self.generator:
try:
if True:
next = False
for p in page.get().split("\n"):
if p[:3] == "*[[":
annee = p[3:7]
reste = p[11:]
#print annee,repr(reste)
import re
nb = len(re.findall("[Uu]tilisateur",reste))
if nb>0:
print annee, nb
if next:
next = False
nb = p[2:].strip()
if nb !="":
print annee,nb
if p[:4] == "| [[":
next = True
annee = p[4:8]
#utiliser page.title()
except wikipedia.NoPage:
print "Page %s does not exist?!" % page.aslink()
except wikipedia.IsRedirectPage:
print "Page %s is a redirect?!" % page.aslink()
except wikipedia.LockedPage:
print "Page %s is locked?!" % page.aslink()
def main():
#page generator
gen = None
pageTitle = []
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'touch')
if arg:
pageTitle.append(arg)
if pageTitle:
page = wikipedia.Page(wikipedia.getSite(), ' '.join(pageTitle))
gen = iter([page])
if not gen:
wikipedia.showHelp('touch')
else:
preloadingGen = pagegenerators.PreloadingGenerator(gen)
bot = TouchBot(preloadingGen)
bot.run()
if __name__ == "__main__":
try:
main()
finally:
wikipedia.stopme()
