Python:Updatelog.py

#!/usr/bin/python
# -*- coding: utf-8  -*-
"""
This is a little (always little, eh? ^__^) script that is used in wiktionary-it to pick up
the log written from import-it.py and add it in the page: Wikipedia:Proposte_di_trasferimento/transferlist.js
"""
#
# (C) Filnik, 2007
#
# Distributed under the terms of the MIT license.
#
# Version: 1.2
#
 
import wikipedia, config
import re
 
# Defing the most important function of the code.
def getstring(site, raw, title = list(), dizionario = {}):
    pos = 0
    parseList = list()
    while 1:
        # This is the regex used to load the strings
        regex = """\"(.*?)\", \"(.*?)\", \"(.*?)\", \"(.*?)\","""
        pl = re.compile(regex, re.UNICODE)
        m = pl.search(raw, pos)
        if m == None:
            if len(parseList) >= 1:
                wikipedia.output(u"Data taken...\n")
                break
            elif len(parseList) == 0:
                wikipedia.output(u"Find nothing! Wrong regex! Pls check!")
                break
                wikipedia.stopme()
        pos = m.end()
        # This is the page from we import
        pagefrom = m.group(1).encode(site.encoding())
        # The project in which we import
        project = m.group(2).encode(site.encoding())
        # The comment used to import
        comment = m.group(3).encode(site.encoding())
        # And the final page where we import
        pageto = m.group(4).encode(site.encoding())
        # That's a list that take all these parameters
        singlelist = [pagefrom, project, comment, pageto]
        # Adding the list to parseList (that is useless, but i use
        # it to understand if the regex is wrong or not)
        if singlelist not in parseList:
            parseList += singlelist
            # That's a list with only the first page
            title += [pagefrom]
            # And that's a dictionary where the keys are the first pages :-)
            dizionario[pagefrom] = singlelist
            continue
        else:
            continue
    return (title, dizionario)
 
texttoadd = """/* <pre> */
// SI PREGA DI INSERIRE LE PAGINE IN ***ORDINE ALFABETICO***. Grazie.
function setup_transferlist()
{
transferlist = Array("""
 
textend = \
"""
""
);}
/* </pre> */"""
 
# Main code :-)
try:
    # Defing the first site where we load the pages
    site = wikipedia.getSite('it', 'wikipedia')
    Loadpage = wikipedia.Page(site, 'Wikipedia:Proposte_di_trasferimento/transferlist.js')
    raw = Loadpage.get() # <-- The text loaded
    (title, dizionario) = getstring(site, raw) # <-- Using the function to parse the results
    # Here there is the second site
    wiktsite = wikipedia.getSite('it', 'wiktionary')
    wiktpage = wikipedia.Page(wiktsite, 'Utente:Filbot/Log')
    raw1 = wiktpage.get()
    (totaltitle, dizionario) = getstring(wiktsite, raw1, title, dizionario) #<-- Parsing..
    totaltitle.sort() #<-- Better if we sort the results ;-)
 
    # Rebilding the data into strings
    for a in totaltitle:
        #print dizionario
        lista = dizionario[a] # Understood why i need a list and a dictionary? ^_-
        nome1 = lista[0].decode(site.encoding())
        nome2 = lista[1].decode(site.encoding())
        nome3 = lista[2].decode(site.encoding())
        nome4 = lista[3].decode(site.encoding())
        wikipedia.output(u'Checking the existance of %s...' % nome1)
        if not wikipedia.Page(site, nome1).exists():
            string = '"%s", "%s", "%s", "%s",' % (nome1, nome2, nome3, nome4)
            texttoadd = texttoadd + '\n' + string
    # Final text! :-)
    totaltxt = texttoadd + textend
    # And at the end, we have to put the result! :-)
    Loadpage.put(totaltxt, 'Bot: Aggiungo voci caricate su wiktionary')
    wiktpage.put('This is a report page for the imported pages, please translate me. --[[User:Filbot|Filbot]]')
finally:
    wikipedia.output(u'Done.')
    wikipedia.stopme()