Archives/wikiteam
2
0
Fork 0
mirror of https://github.com/WikiTeam/wikiteam synced 2024-11-04 12:00:28 +00:00
Code Issues Projects Releases Wiki Activity

A major update - checkalive.pl now checks for api.php and writes it to the list if found.

Browse Source 
git-svn-id: https://wikiteam.googlecode.com/svn/trunk@965 31edc4fc-5e31-b4c4-d58b-c8bc928bcb95
This commit is contained in:
scottdb56 2014-02-27 05:50:28 +00:00
parent 575c9dd3ea
commit b9be07936a
2 changed files with 214 additions and 78 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

266
listsofwikis/checkalive.pl
View File

@ -1,117 +1,247 @@
#!/usr/bin/perl
# Name: checkalive.pl v1.2
# Description: This script will go thru a list of URLs & determine
# if they are online & if they are Mediawiki wikis. It should work
# with: "/index.php/Main_Page", "index.php", "api.php" and even pages
# such as: "/wiki/Pagina_principale".
# Name: checkalive.pl v2.0
# Description: This script will go thru a list of URLs & determine if they are online & if they are Mediawiki wikis.
# It should work with: "/index.php/Main_Page", "index.php", "api.php" and even pages such as: "/wiki/Pagina_principale".
# If the URl is not "api.php", it will look for it, check it, and output it if found to be a valid api.php. If not found,
# it will output the URL with "index.php" if that's available.
#
# Created: 12/14/2013
# Most recently updated: 01/26/2014 (It's a work-in-progress...)
# Most recently updated: 02/25/2014
# Copyright (c) 2013-2014 by Scott D. Boyd - scottdb56@gmail.com
# ====================================================================
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# ===========================================================================================================================
# This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
# ====================================================================
# This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty
# of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
#
# NOTE: The following three Perl modules need to be installed on your computer.
# Search for them on cpan.org or use your Linux distro's package manager.
# You should have received a copy of the GNU General Public License along with this program. If not,
# see <http://www.gnu.org/licenses/>.
# ===========================================================================================================================
#
# NOTE: The following four Perl modules need to be installed on your computer.
# Search for them on cpan.org or use your Linux distro's package manager.
use LWP::Simple;
use LWP::UserAgent;
use Crypt::SSLeay;
my $slp=2; # You can change this number for seconds to sleep between requests (currently 2 seconds)
my $urllist="my-URL-list.txt";
use Mojo::URL;
my $slp=2; # You can change this number for seconds to sleep between requests (currently 2 seconds)
my $urllist="URL-list.txt";
my $alivelist="alive-wikis.txt";
my $deadlist="dead-wikis.txt";
my $pwrdby1="Powered by MediaWiki";
my $pwrdby2="poweredby_mediawiki";
my $genmw="meta name\=\"generator\" content\=\"MediaWiki";
my $mwapi="MediaWiki API documentation page";
my $lw=0; my $dw=0;
my $mwapi2="API Home Page"; # found in an older version of the api
my $indexphp="index.php";
my $apiphp="api.php";
my $wapiphp="w\/api.php";
my $wikiapiphp="wiki\/api.php";
my $apiurl="";
my $live=0; my $dead=0;
my $a=1; my $b=0; my $c=0;
my $flag=0;
my $ua = LWP::UserAgent->new;
$ua->agent("Mozilla/5.0"); # use this user-agent to get into wikis that block spiders & robots
$ua->agent("Mozilla/5.0"); # use this user-agent to get into wikis that block spiders & robots
$ua->timeout(30);
$ua->show_progress(1);
# Here's where most of the work takes place:
open (MYURLLIST,"<$urllist")
or die "Cannot open the URL-list file: $!";
open (ALIVEFILE,">$alivelist");
open (DEADFILE,">$deadlist");
while (<MYURLLIST>) {
if ((/\#(.*?)/) || (/^\s*$/)) { # check to see if line is a comment or a blank line
next; # if so - skip it
if ((/\#(.*?)/) || (/^\s*$/)) { # check to see if line is a comment or a blank line
next; # if so - skip it
} else {
$url=$_; # assign the current line to $url
$url=$_; # assign the current line to $url
chomp $url;
$req = HTTP::Request->new(GET => $url); # --|
$req->header('Accept' => 'text/html'); # |-- some of these lines
$res = $ua->request($req); # send request |-- were adapted from
if ($res->is_success) { # if the URL still exists |-- lwpcook.pod
print "Got it! "; # |
$doc=$res->content; # |
&ParsePage; # go to "ParsePage" sub-routine |
} else { # |
$errormsg=$res->status_line; # --|
$req = HTTP::Request->new(GET => $url); # --|
$req->header('Accept' => 'text/html'); # |-- some of these lines
$res = $ua->request($req); # send request |-- were adapted from
if ($res->is_success) { # if the URL still exists |-- lwpcook.pod
print "Got it! "; # |
$doc=$res->content; # |
print "Parsing the document... ";
if (($doc=~/$pwrdby1/i) || ($doc=~/$pwrdby2/i)) { # if the page contains: "Powered by MediaWiki"
print "It's alive and powered by Mediawiki\n"; # or: "poweredby_mediawiki"
$flag=1;$live++; # then it's a MediaWiki wiki
& Check4api;
} elsif ($doc=~/$genmw/i) { # if the content generator is MediaWiki
print "It's alive and powered by Mediawiki\n"; # then it's a MediaWiki wiki
$flag=1;$live++;
& Check4api;
} elsif ($doc=~/$mwapi/i) { # if the api.php contains: "MediaWiki API documentation page"
print "It's alive and powered by Mediawiki\n"; # then it's a MediaWiki wiki
print ALIVEFILE "$url\n";
$flag=1;$live++;
} elsif ($doc=~/$mwapi2/i) { # if the api.php contains: "API Home Page" (older version)
print "It's alive and powered by Mediawiki\n"; # then it's a MediaWiki wiki
print ALIVEFILE "$url\n";
$flag=1;$live++;
}
unless ($flag) {
print "It's alive but NOT powered by MediaWiki\n";
print DEADFILE "$url is alive but NOT powered by Mediawiki\n"; $dead++;
}
$flag=0;
} else {
$errormsg=$res->status_line;
if (substr($errormsg,0,3) eq "500") { # if response-code 500
print DEADFILE "$url\n"; $dw++;
print DEADFILE "$url\n"; $dead++;
} elsif (substr($errormsg,0,3) eq "401") { # if Unauthorized (code 401)
print DEADFILE "$url\n"; $dw++;
print DEADFILE "$url\n"; $dead++;
} elsif (substr($errormsg,0,3) eq "403") { # if forbidden (code 403)
print DEADFILE "$url is alive but access is denied.\n"; $dw++;
print DEADFILE "$url is alive but access is denied.\n"; $dead++;
} elsif (substr($errormsg,0,3) eq "404") { # if URL is dead (code 404)
print DEADFILE "$url\n"; $dw++;
print DEADFILE "$url\n"; $dead++;
} elsif (substr($errormsg,0,3) eq "406") { # if Not Acceptable (code 406)
print DEADFILE "$url\n"; $dw++;
print DEADFILE "$url\n"; $dead++;
}
}
$c++; $b=$c/10;
if ($b==$a) {
print "Checked $c URLs -- "; # print the progress every 10 URLs
print "Checked $c URLs -- "; # print the progress every 10 URLs
$a++;
}
if ($slp > 0) {
print "Pausing for $slp seconds...\n\n"; sleep $slp;
} else { # don't pause - go on to the next URL
}
&PauseRoutine;
}
}
close DEADFILE; close ALIVEFILE; close MYURLLIST;
print "\nFinished! I found $lw live wikis and $dw dead or non-Mediawiki wikis.\n";
print "\nFinished! I found $live live wikis and $dead dead or non-Mediawiki wikis.\n";
# Here's the sub-routine
# ======================
sub ParsePage {
print "Parsing the document... ";
if (($doc=~/$pwrdby1/i) || ($doc=~/$pwrdby2/i)) { # if the page contains: "Powered by MediaWiki"
print "It's alive and powered by Mediawiki\n"; # or: "poweredby_mediawiki"
print ALIVEFILE "$url\n"; # then it's a MediaWiki wiki
$flag=1;$lw++;
} elsif ($doc=~/$genmw/i) { # if the content generator is MediaWiki
print "It's alive and powered by Mediawiki\n"; # then it's a MediaWiki wiki
print ALIVEFILE "$url\n";
$flag=1;$lw++;
} elsif ($doc=~/$mwapi/i) { # if the api.php contains: "MediaWiki API documentation page"
print "It's alive and powered by Mediawiki\n"; # then it's a MediaWiki wiki
print ALIVEFILE "$url\n";
$flag=1;$lw++;
# Here's the sub-routines
# =======================
sub Check4api {
$pos=rindex($url,"\/"); # $pos will contain the position of the final "/" (counting from zero)
$base_plus=substr($url,0,($pos+1)); # $base_plus will contain everything up to & including the final "/"
my $len1=length($url); my $len2=length($base_plus);
if ($len2 < 10) { # if $base_plus contains only "http://" or "https://"
$base_plus=$url; # then assign $url to $base_plus
my $tail=substr $base_plus, -1;
if (!($tail=~/\//)) { # if the last character of $base_plus is not a "/"
$base_plus=$base_plus."\/" ; # then add it
}
}
unless ($flag) {
print "It's alive but NOT powered by MediaWiki\n";
print DEADFILE "$url is alive but NOT powered by Mediawiki\n"; $dw++;
$apiurl=$base_plus.$apiphp; # $apiurl is our new URL with api.php tacked on the end
&PauseRoutine; & Fetch_api; # pause & then try to get api.php
if ($res->is_success) {
print "Found api.php... "; $doc=$res->content;
&Parse_api;
}else{ # if no api.php...
$apiurl=$base_plus.$wapiphp; # modify the URL
&PauseRoutine; & Fetch_api; # pause & then try to get /w/api.php
if ($res->is_success) {
print "Found api.php... "; $doc=$res->content;
&Parse_api;
}else{ # if no /w/api.php...
$apiurl=$base_plus.$wikiapiphp; # modify the URL
&PauseRoutine; & Fetch_api; # pause & then try to get /wiki/api.php
if ($res->is_success) {
print "Found api.php... "; $doc=$res->content;
&Parse_api;
}else{
if (/https:\/\//) {
$scheme="https://";
} else {
$scheme="http://";
}
$url = Mojo::URL->new($url);
$base = $url->host; # extract just the host from $url & assign it to $base
$base=$scheme.$base;
my $tail=substr $base, -1;
if (!($tail=~/\//)) { # if the last character of $base_plus is not a "/"
$base=$base."\/" ; # then add it
}
$apiurl=$base.$apiphp; # $apiurl is our new URL with api.php tacked on the end
&PauseRoutine; & Fetch_api; # pause & then try to get api.php
if ($res->is_success) {
print "Found api.php... "; $doc=$res->content;
&Parse_api;
}else{ # if no api.php...
$apiurl=$base.$wapiphp; # modify the URL
&PauseRoutine; & Fetch_api; # pause & then try to get /w/api.php
if ($res->is_success) {
print "Found api.php... "; $doc=$res->content;
&Parse_api;
}else{ # if no /w/api.php...
$apiurl=$base.$wikiapiphp; # modify the URL
&PauseRoutine; & Fetch_api; # pause & then try to get /wiki/api.php
if ($res->is_success) {
print "Found api.php... "; $doc=$res->content;
&Parse_api;
}else{
if (!($url=~/index.php/i)) { # if the URL does not end with index.php...
print "There is no api.php -- I'll try index.php...\n";
$indexurl=$base_plus.$indexphp; # then tack on index.php...
$req = HTTP::Request->new(GET => $indexurl); # and try to get it
$req->header('Accept' => 'text/html');
$res = $ua->request($req); # send request
if ($res->is_success) {
$doc=$res->content;
if (($doc=~/$pwrdby1/i) || ($doc=~/$pwrdby2/i)) { # if the page contains: "Powered by MediaWiki"
print ALIVEFILE "$indexurl\n"; # or: "poweredby_mediawiki"
}elsif ($doc=~/$genmw/i) { # if the content generator is MediaWiki
print ALIVEFILE "$indexurl\n";
}else{
print "There is no api.php OR index.php for $url\n";
print ALIVEFILE "$url\n";
}
}else{
print ALIVEFILE "$url\n";
}
}else{
print "There is no api.php for $url\n";
print ALIVEFILE "$url\n";
}
}
}
}
}
}
}
$flag=0;
}
sub Fetch_api {
$req = HTTP::Request->new(GET => $apiurl);
$req->header('Accept' => 'text/html');
$res = $ua->request($req); # send request
}
sub Parse_api {
print "Parsing the document...\n ";
if ($doc=~/$mwapi/i) { # if the api.php contains: "MediaWiki API documentation page"
print ALIVEFILE "$apiurl\n"; # then it's a MediaWiki wiki - print it to the list
}elsif ($doc=~/$mwapi2/i) { # if the api.php contains: "API Home Page" (older version)
print "Found a valid api.php and writing it to the list\n"; # delete this line after testing
print ALIVEFILE "$apiurl\n"; # then it's a MediaWiki wiki - print it to the list
}else{
print "This api.php is not valid.\n"; # then try to get index.php
$indexurl=$base_plus.$indexphp;
print "Trying to get $indexurl...\n";
$req = HTTP::Request->new(GET => $indexurl);
$req->header('Accept' => 'text/html');
$res = $ua->request($req); # send request
if ($res->is_success) {
$doc=$res->content;
if (($doc=~/$pwrdby1/i) || ($doc=~/$pwrdby2/i)) { # if the page contains: "Powered by MediaWiki"
print ALIVEFILE "$indexurl\n"; # or: "poweredby_mediawiki"
}elsif ($doc=~/$genmw/i) { # if the content generator is MediaWiki
print ALIVEFILE "$indexurl\n";
}else{
print "There is no api.php OR index.php for $url\n";
print ALIVEFILE "$url\n";
}
}
}
}
sub PauseRoutine {
if ($slp > 0) {
print "Pausing for $slp seconds...\n\n"; sleep $slp;
} else { } # don't pause - go on to the next URL
}

26
listsofwikis/readme-checkalive.txt
View File

@ -1,9 +1,11 @@
Description
-----------
checkalive.pl is a Perl script that will go thru a list of URLs & determine if
they are online and if they are Mediawiki wikis. It should work with
"index.php/Main_Page", "index.php" and "api.php". As of 01/23/2014, I have
started using version numbers.
checkalive.pl is a Perl script that will go thru a list of URLs & determine if they are
online & if they are Mediawiki wikis. It should work with: "/index.php/Main_Page",
"index.php", "api.php" and even pages such as: "/wiki/Pagina_principale". If the URl is
not "api.php", it will look for it, check it, and output it if found to be a valid api.php.
If not found, it will output the URL with "index.php" if that's available.
As of 01/23/2014, I have started using version numbers.
Required programs and modules
-----------------------------
@ -12,10 +14,13 @@ be on your system. You will also need to have the following Perl modules install
LWP::Simple
LWP::UserAgent
Crypt::SSLeay
Mojo::URL
The first two are contained in LWP - The World-Wide Web library for Perl
(aka: libwww-perl-6.x), available at CPAN, or through your Linux distro's package manager.
(aka: libwww-perl-6.x), available at CPAN, (http://www.cpan.org)or through your Linux
distro's package manager.
Crypt::SSLeay (OpenSSL support for LWP) is also available at CPAN. This module
is needed to properly handle any URLs beginning with "https".
Mojo::URL is available at CPAN as well. It's needed to extract the domain name from a URL.
Configuration
-------------
@ -31,6 +36,12 @@ There are several variables you can change, or you can just use them as-is:
and will be noted as such.
Any other variable that you want to change - you do so at your own risk.
Starting the script
-------------------
If you want to use the default configuration noted above, at a command prompt, simply
type: "perl checkalive.pl" (without the quotes). You must be in the same directory (or
folder) as the script and the URL list that you want to check.
Issues
------
The script does NOT have a "resume" feature at this time. If you are running through a
@ -38,8 +49,3 @@ list of 1000's of URLs, and the script crashes, or you kill it, your lists of al
dead URLs will NOT BE SAVED TO DISK. I suggest breaking up your list into smaller lists
of a few hundred URLs in each list until I can implement a resume feature.
The LWP library does transparent redirect handling, so I can't capture the new URL that
is displayed on screen as the script is running. Therefore, any of the URLs that get
redirected to a new URL will have the original URL saved to the appropriate list(whether
it's dead or alive).