User:Ritchie333/afcbios.py

#!/usr/bin/python

import sys
import re
import pywikibot
from pywikibot import pagegenerators

name = 'Category:AfC submissions declined as a non-notable biography'
reText = re.compile( '(She is|She was|Her work|Her book)' )
reMarker = re.compile( '<ref.*\/ref>|{{.*}}|<!--.*-->|\'\'\'|----' )
reTitle = re.compile( '\(.*\)' )

site = pywikibot.Site()
cat = pywikibot.Category(site,name)
gen = pagegenerators.CategorizedPageGenerator(cat)
count = 0
for page in gen:
  ns = page.namespace()
  if( 118 == ns):
    text = page.text
    match = reText.search( text )
    if( match is not None ):
      if 0 == ( count % 50 ):
        print '== ' + str( count + 1 ) + ' - ' + str( count + 50 ) + ' =='
      title = page.title( False, False )
      print '* [[Draft:' + title.encode( 'utf-8' ) + ']]'
      shortText = reMarker.sub( '', text )
      shortTitle = reTitle.sub( '', title )
      sentences = re.search( shortTitle + '.*\.', shortText )
      if not sentences is None:
        components = sentences.group().partition( '.' )
        lead = components[ 0 ].replace( '<ref', 'ref' )
        print '::<small>' + lead.encode( 'utf-8' ) + '.</small>'
      count += 1