-
-
Save asciirobot/a6d22fcca9d06e8fa01c77593d343785 to your computer and use it in GitHub Desktop.
Perl script to fetch all topics in a phpBB forum and save them to disk
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/perl | |
use strict; | |
use warnings; | |
require LWP::UserAgent; | |
use POSIX qw/ceil/; | |
my $ua = LWP::UserAgent->new(agent => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:10.0.2) Gecko/20100101 Firefox/10.0.2'); | |
$ua->timeout(10); | |
my $sid = '<sid goes here>'; | |
$ua->default_header('Host' => '<host>'); | |
$ua->default_header('Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'); | |
$ua->default_header('Accept-Language' => 'en-us,en;q=0.5'); | |
$ua->default_header('Accept-Encoding' => 'gzip, deflate'); | |
$ua->default_header('DNT' => '1'); | |
$ua->default_header('Connection' => 'keep-alive'); | |
$ua->default_header('Cache-Control' => 'max-age=0'); | |
#$ua->default_header(); | |
my $max_topic_id = 20000; | |
my $posts_per_topic_page = 30; | |
my $topics_per_forum_page = 50; | |
my $output_file_name_base = 'sitename-'; | |
my $base_url = 'http://hostname.com/forums/viewtopic.php'; | |
my %status = (); | |
for (my $i = 1; $i <= $max_topic_id; $i++) { | |
my $posts_in_topic = 0; | |
my $url = $base_url . '?sid=' .$sid . '&t='.$i; | |
my $response = $ua->get($url ); | |
if ($response->is_success) { | |
my $page_content = $response->decoded_content; | |
# [ 621 posts ] | |
if ($page_content =~ /topic does not exist/) { | |
print STDERR "$url: Topic $i does not exist\n"; | |
$status{'invalid topic'}++; | |
} elsif ($page_content =~ /not authorised/) { | |
print STDERR "$url: Not authorized\n"; | |
$status{'unauthorized'}++; | |
} elsif ($page_content =~ /requires you to be registered and logged in/) { | |
print STDERR "$url: Login prompt.\n"; | |
$status{'login message'}++; | |
} elsif ($page_content =~ /forum you selected does not exist/) { | |
print STDERR "$url: Forum does not exist\n"; | |
$status{'forum dne'}++; | |
} else { | |
$posts_in_topic = ($page_content =~ / ([\d,]+) post(s?) /)[0]; | |
$posts_in_topic =~ s/,//; | |
$status{'valid post'}++; | |
# print "Topic #$i contains $posts_in_topic posts\n"; | |
my $title = ($page_content =~ /<title>(.+)<\/title>/)[0]; | |
$title =~ s/[^\w\s]+//g; | |
$title =~ s/\s+/_/g; | |
# <td class="postbottom" align="center">Sat Nov 01, 2008 9:00 pm</td> | |
my ($crap, $wd, $month, $day, $year) = ($page_content =~ />((\w{3}) (\w{3}) (\d{2}), (\d{4})) \d+:\d{2} ..<\/td/); | |
my $date_str = "$year-$month-$day"; | |
my $output_filename = sprintf("$output_file_name_base"."topic-%05d-page-000-$date_str-$title.html",$i); | |
open(FILE, ">$output_filename") or die $!; | |
print FILE $page_content; | |
close(FILE); | |
print "Saved $output_filename ($posts_in_topic total posts)\n"; | |
if ($posts_in_topic > $posts_per_topic_page) { | |
my $total_pages = ceil($posts_in_topic / $posts_per_topic_page); | |
for (my $j = 1; $j < $total_pages; $j++) { | |
my $start = $j * $posts_per_topic_page; | |
my $page_url = $url . '&start='.$start; | |
my $page_filename = sprintf("$output_file_name_base".'topic-%05d-page-%03d.html',$i, $j); | |
my $page_response = $ua->get($page_url, ':content_file' => $page_filename); | |
if ($page_response->is_success) { | |
print "Saved $page_filename\n"; | |
} else { | |
print STDERR "Error fetching $page_url: {$response->status_line}\n"; | |
} | |
} | |
} | |
# print $page_content; | |
} | |
} else { | |
print STDERR "Error fetching $url: {$response->status_line}\n"; | |
$status{'error:'.$response->status_line}++; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment