Difference between revisions of "Import CSV data into a wiki"

From Organic Design wiki
(must not include whitespace removal in split or tab separators will fail)
Line 35: Line 35:
 
$_ = <CSV>;
 
$_ = <CSV>;
 
/^\s*(.+?)\s*$/;
 
/^\s*(.+?)\s*$/;
@headings = split /\s*$sep\s*/i, $1;
+
@headings = split /$::sep/i, $1;
 
close CSV;
 
close CSV;
 
} else { die "Could not open CSV file!" }
 
} else { die "Could not open CSV file!" }
Line 55: Line 55:
 
while (<CSV>) {
 
while (<CSV>) {
 
/^\s*(.+?)\s*$/;
 
/^\s*(.+?)\s*$/;
@record = split /\s*$sep\s*/, $1;
+
@record = split /$::sep/, $1;
 
$tmpl  = "{{$template\n";
 
$tmpl  = "{{$template\n";
 
$tmpl  .= "|$headings[$_] = $record[$_]\n" for 0..$#headings;
 
$tmpl  .= "|$headings[$_] = $record[$_]\n" for 0..$#headings;

Revision as of 09:38, 27 March 2008

  1. !/usr/bin/perl
  2. Our Perl scripts.{{#security:*|sysop}}
  3. - Licenced under LGPL (http://www.gnu.org/copyleft/lesser.html)
  4. - Author: http://www.organicdesign.co.nz/nad
  5. - Source: http://www.organicdesign.co.nz/scraper.pl
  6. - Started: 2008-03-21

require('wiki.pl');

  1. Job, log and error files

$ARGV[0] or die "No job file specified!"; $ARGV[0] =~ /^(.+?)(\..+?)?$/; $::log = "$1.log"; $::err = "$1.err"; $::sep = ','; $::title = 0; $::template = 'Record';

  1. Parse the job file

if (open JOB,'<',$ARGV[0]) { for (<JOB>) { if (/^\*?\s*csv\s*:\s*(.+?)\s*$/i) { $::csv = $1 } if (/^\*?\s*wiki\s*:\s*(.+?)\s*$/i) { $::wiki = $1 } if (/^\*?\s*user\s*:\s*(.+?)\s*$/i) { $::user = $1 } if (/^\*?\s*pass\s*:\s*(.+?)\s*$/i) { $::pass = $1 } if (/^\*?\s*separator\s*:\s*(.+?)\s*$/i) { $::sep = $1 } if (/^\*?\s*title\s*:\s*(.+?)\s*$/i) { $::title = $1 } if (/^\*?\s*template\s*:\s*(.+?)\s*$/i) { $::template = $1 } } close JOB; } else { die "Couldn't parse job file!" }


if (open CSV,'<',$::csv) { $_ = <CSV>; /^\s*(.+?)\s*$/; @headings = split /$::sep/i, $1; close CSV; } else { die "Could not open CSV file!" }

  1. Log in to the wiki

wikiLogin($::wiki,$::user,$::pass) or exit;

  1. Open the CSV

if (open CSV,'<',$::csv) { <CSV> if defined @headings; } else { die "Could not open CSV file!" }

  1. Get batch size and current number (also later account for n-bots)
  1. todo: log batch start
  1. Process the records

$n = 1; while (<CSV>) { /^\s*(.+?)\s*$/; @record = split /$::sep/, $1; $tmpl = "{{$template\n"; $tmpl .= "|$headings[$_] = $record[$_]\n" for 0..$#headings; $tmpl .= "}}"; print "Processing record ".$n++."\n";

# Update the record $text = wikiRawPage($::wiki,$record[$::title],0); $text .= "\n$tmpl" unless $text =~ s/\{\{$template.+?\}\}/$tmpl/is; $done = wikiPageEdit($::wiki,$record[$::title],$text,"$template updated by csv2wiki.pl");

# log a row error if any }

close CSV;