Church infobox URL length report generator

churchchecker.py

#!/usr/bin/python
# -*- coding: utf-8  -*-
"""
An incomplete sample script.

This is not a complete bot; rather, it is a template from which simple
bots can be made. You can rename it to mybot.py, then edit it in
whatever way you want.

The following parameters are supported:

&params;

"""
#
# (C) Pywikibot team, 2006-2014
#
# Distributed under the terms of the MIT license.
#
__version__ = '$Id: 33d6319ef50b20b70e4eaccc851ab4ddb43053a8 $'
#

import pywikibot
from pywikibot import pagegenerators
from pywikibot import i18n
import mwparserfromhell

# This is required for the text that is shown when you run this script
# with the parameter -help.
docuReplacements = {
    '&params;': pagegenerators.parameterHelp
}


class BasicBot:

    """An incomplete sample bot."""

    # Edit summary message that should be used is placed on /i18n subdirectory.
    # The file containing these messages should have the same name as the caller
    # script (i.e. basic.py in this case)

    def __init__(self, generator):
        """
        Constructor.

        Parameters:
            @param generator: The page generator that determines on which pages
                              to work.
            @type generator: generator.
        """
        self.generator = generator
        site = pywikibot.Site()

    def run(self):
        """Process each page from the generator."""
        for page in self.generator:
            self.treat(page)

    def treat(self, page):
        """Load the given page, does some changes, and saves it."""
        text = self.load(page)
        if not text:
            return

        wtext = mwparserfromhell.parse(text)
        for tmpl in wtext.filter_templates():
            if tmpl.name != u"Kirke":
                continue
            if not tmpl.has(u"Websted"):
                continue
            www = tmpl.get(u"Websted")
            pywikibot.output(u"{}:{}:{}".format(page.title(), len(www.value.strip()),
                www.value.strip()), toStdout=True)

    def load(self, page):
        """Load the text of the given page."""
        try:
            # Load the page
            text = page.get()
        except pywikibot.NoPage:
            pywikibot.output(u"Page %s does not exist; skipping."
                             % page.title(asLink=True))
        except pywikibot.IsRedirectPage:
            pywikibot.output(u"Page %s is a redirect; skipping."
                             % page.title(asLink=True))
        else:
            return text
        return None


def main(*args):
    """
    Process command line arguments and invoke bot.

    If args is an empty list, sys.argv is used.

    @param args: command line arguments
    @type args: list of unicode
    """
    # Process global arguments to determine desired site
    local_args = pywikibot.handle_args(args)

    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()
    # The generator gives the pages that should be worked upon.
    gen = None
    # If dry is True, doesn't do any real changes, but only show
    # what would have been changed.
    dry = False

    # Parse command line arguments
    for arg in local_args:
        if arg.startswith("-dry"):
            dry = True
        else:
            genFactory.handleArg(arg)

    if not gen:
        gen = genFactory.getCombinedGenerator()
    if gen:
        # The preloading generator is responsible for downloading multiple
        # pages from the wiki simultaneously.
        gen = pagegenerators.PreloadingGenerator(gen)
        bot = BasicBot(gen)
        bot.run()
    else:
        pywikibot.showHelp()

if __name__ == "__main__":
    main()