JargonWiki:BulkPageCreator.php

From JargonWiki

GNU General Public License

This article is subject to the GNU General Public License version 3.0.
No user contributions are accepted to pages licensed under the GNU GPL.
For more information see the standard editing privileges.

Note: SVN access, most recent versions, documentation, version history, and more are available at the Google Code site for this project:

http://code.google.com/p/jargonwiki/

<?php
#  PHP MediaWiki Bulk Page Creator
#  Version: 1.1
#  Author: Jonathan Cutrer
#  Website: http://jon.cutrer.org/
#
#  Modifications: Charlie File
#  Website: http://charlesfile.com/
#  Modified for: http://jargonwiki.com
#  
#  
#  This program must have the Snoopy Class Library to run.
#  http://sourceforge.net/projects/snoopy/
#
#
#  Syntax:
#  
#  Invoked via a Command Line Interface (CLI):
#  > php BulkPageCreator.php inputfile.txt
#  
#  - or -
#  
#  Invoked via a Uniform Resource Identifier (URI):
#  http://jargonwiki.com/wiki/BulkPageCreator.php?file=inputfile.txt
#  
#  
#
#

# This is basically a requirement for anything more than a handful of articles.
# Batch submits of thousands of articles to a remote host can take hours.
set_time_limit(0); //0 = no time limit.

include "./w/includes/Snoopy.class.php";
$snoopy = new Snoopy;
$wikiroot = "http://jargonwiki.com/wiki";
$login_url = $wikiroot . "/index.php?title=Special:Userlogin&action=submitlogin";
$submit_url = $wikiroot . "/index.php?title=Special:Userlogin&action=submitlogin";

# Set the username and password below:
$login_vars['wpName'] = 'JargonBot';
$login_vars['wpPassword'] = '';
$login_vars['wpRemember'] = '1';

# Login to Wiki
$snoopy->submit($login_url,$login_vars);

# Open Source File and Read into $contents
if (count($_GET) > 0) {
# Via URI:
	$fp = fopen($_GET['file'], 'r');
	$contents = fread($fp, filesize($_GET['file']));
	} else {
# Via CLI:
	$fp = fopen($argv[1], "r");
	$contents = fread($fp, filesize($argv[1]));
	}
fclose($fp);

# Split $contents in $pages array
$pages = split("--ENDPAGE--", $contents);

# Loop for each item in pages array
# During loop we will get edit page for token then submit form to create page
foreach ($pages as $key => $value) {
        list($title, $body) = split("--ENDTITLE--", $value);
        echo $title;
		
        # Get rid of newlines in title
        $title = str_replace("\n", "", $title);
		
        # Make Safetitle for URL
        $safetitle = rawurlencode(str_replace(" ", "_", $title));
		
        # Lets make sure $title contains something other than null
        if ($title) {
                # Submit to edit page for $title and get contents into $editpage
                if($snoopy->submit($wikiroot . "/index.php?title=" . $safetitle . "&action=edit",$login_vars)) {
                        $editpage = $snoopy->results;
                }
				
                # Pick out Edit Token into $token
				#echo "$editpage"; //DEBUG
                $ans = preg_match('/.*value="(.*?)".*name="wpEditToken"/',$editpage, $matches);
                $token = $matches[1];
                echo $token;
				
                # Set Post Variables before submitting
                $submit_vars['wpTextbox1'] = $body;
                $submit_vars['wpSummary'] = "";
                $submit_vars['wpSection'] = "";
                $submit_vars['wpEdittime'] = "";
                $submit_vars['wpMinoredit'] = "1";
                $submit_vars['wpSave'] = "Save page";
                $submit_vars['wpEditToken'] = $token;
				
                # Submit  or Post to create the page
                echo "Final Submit goes to:" . $wikiroot . "/index.php?title=" . $safetitle . "&action=submit";
                if($snoopy->submit($wikiroot . "/index.php?title=" . $safetitle . "&action=submit", $submit_vars)) {
                        $finalresults = $snoopy->results;
                }
                echo $finalresults;
        # End If Loop
        }
# End ForEach Loop
}
exit;
?>

[edit]