2025 RationalWiki 'Oregon Plan' Fundraiser

There is no RationalWiki without you. We are a small non-profit with no staff—we are hundreds of volunteers who document pseudoscience and crankery around the world every day. We will never allow ads because we must remain independent. We cannot rely on big donors with corresponding big agendas. We are not the largest website around, but we believe we play an important role in defending truth and objectivity.

Fighting pseudoscience isn't free.
We are 100% user-supported! Help and donate $5, $10, $20 or whatever you can today with PayPal Logo.png!
Donations so far: $9223.37Goal: $10000

User:WigoBot/Source

From RationalWiki
Jump to navigation Jump to search
RedOpenSource.png
#!/usr/bin/env python3
# encoding: utf8
#
# Copyright © 2016 Martin Tournoij <martin@arp242.net>
# See below for full copyright

import re, sys, json, collections

import pywikibot
_site = pywikibot.Site()

# Pages to archive
_wigos = [
	'RationalWiki:What_is_going_on_in_the_world?',
	'RationalWiki:What is going on in the blogosphere?',
	'RationalWiki:What is going on in the clogosphere?',
	#'RationalWiki:What is going on with the elections?',
]

# Find an entry
_start_entry = r'^\s*(?:<vote poll=.*?|<!--)'
_end_entry = r'(?:<\/vote>|-->)\s*$'
_entry = _start_entry + r'.*?' + _end_entry

# Find current section
_section = r'==(.*?)=='

# Find instructions
_config = r'<!-- wigobot: (\d+) -->'


def pp(*ds):
	for d in ds:
		json.dump(d, sys.stdout, sort_keys=True, indent=4)
		print()


def main():
	for wigo in _wigos:
		#text = open('test.txt', 'r').read()
		page = pywikibot.Page(_site, wigo)
		text = page.text

		# Extract the number of archives to keep
		m = re.search(_config, text)
		if m is None:
			keep_num = 100
		else:
			keep_num = int(m.groups()[0])
			if keep_num == 0:
				print('Archiving has been disabled for {}'.format(wigo))
				continue

		# Store everything before the first section
		m = re.search(_section, text, re.MULTILINE)
		head = text[:m.start()]
		text = text[m.start():]

		# ... and the same for everything after the last entry
		m = re.search(r'.*' + _end_entry, text, re.MULTILINE + re.DOTALL)
		foot = text[m.end():]
		text = text[:m.end()].strip()

		# Split by sections and entries
		sections_tmp = []
		c = re.compile(_section)
		off = 0
		while True:
			m = c.search(text, off)
			if m is None: break
			off = m.end()
			sections_tmp.append(m)
		
		sections = []
		for i, s in enumerate(sections_tmp):
			if i + 2 > len(sections_tmp):
				end = len(text)
			else:
				end = sections_tmp[i + 1].start()

			section_text = text[s.end():end].strip()
			sections.append([s.groups()[0].strip(),
				re.findall(_entry, section_text, re.MULTILINE + re.DOTALL)])


		# Split in what we want to keep and archive
		keep = collections.OrderedDict()
		archives = collections.OrderedDict()
		n_archiving = 0
		n = 0
		for section, entries in sections:
			for entry in entries:
				n += 1
				if n > keep_num:
					if archives.get(section) is None: archives[section] = []
					archives[section].append(entry)
					n_archiving += 1
				else:
					if keep.get(section) is None: keep[section] = []
					keep[section].append(entry)

		def p(s):
			print('+-')
			for l in s.split('\n'): print('|', l[:120])
			print('+-\n')

		page.text = '{}\n{}\n\n{}'.format(
			head.strip(),
			'\n'.join(['\n=={}==\n{}'.format(k, '\n'.join(v)) for k, v in keep.items()]),
			foot.strip())

		#print('==> Updating the current page to this:'); p(page.text)
		page.save(summary='Bot: archiving {} entries'.format(n_archiving))

		archives = list(archives.items())
		archives.reverse()
		for k, v in archives:
			title = '{}/{}'.format(wigo, k)
			page = pywikibot.Page(_site, title, 4)

			if page.text == '':
				page.text = '=={}==\n'.format(k)
			else:
				page.text = page.text.strip() + '\n'
			page.text += '\n'.join(v)
			#print('==> Updating {} to this:'.format(k)); p(page.text)
			page.save(summary='Bot: archiving {} entries'.format(len(v)))

		# Purge cache for the archives
		pywikibot.Page(_site, '{}/Archive_list'.format(wigo), 4).purge()

if __name__ == '__main__':
	main()


# The MIT License (MIT)
#
# Copyright © 2016 Martin Tournoij
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to
# deal in the Software without restriction, including without limitation the
# rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
# sell copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# The software is provided "as is", without warranty of any kind, express or
# implied, including but not limited to the warranties of merchantability,
# fitness for a particular purpose and noninfringement. In no event shall the
# authors or copyright holders be liable for any claim, damages or other
# liability, whether in an action of contract, tort or otherwise, arising
# from, out of or in connection with the software or the use or other dealings
# in the software.