diff options
author | Daniel Stenberg <daniel@haxx.se> | 2002-11-21 15:09:04 +0000 |
---|---|---|
committer | Daniel Stenberg <daniel@haxx.se> | 2002-11-21 15:09:04 +0000 |
commit | dee84f448faf1f247b128f204183c4dd15be148f (patch) | |
tree | e0c906bd072944f6b58d164397924b89e35c768b /perl | |
parent | 16077116034e4e2a8554ff6ab2da65db8e16de06 (diff) |
new name, supports <textarea> and the <option> tags within <select> better
Diffstat (limited to 'perl')
-rwxr-xr-x | perl/contrib/formfind | 191 | ||||
-rwxr-xr-x | perl/contrib/formfind.pl.in | 273 |
2 files changed, 191 insertions, 273 deletions
diff --git a/perl/contrib/formfind b/perl/contrib/formfind new file mode 100755 index 000000000..0363c1ee5 --- /dev/null +++ b/perl/contrib/formfind @@ -0,0 +1,191 @@ +#!/usr/bin/env perl +# +# formfind.pl +# +# This script gets a HTML page from the specified URL and presents form +# information you may need in order to machine-make a respond to the form. +# +# Written to use 'curl' for URL fetching. +# +# Author: Daniel Stenberg <daniel@haxx.se> +# Version: 0.2 Nov 18, 2002 +# +# HISTORY +# +# 0.1 - Nov 12 1998 - Created now! +# 0.2 - Nov 18 2002 - Enhanced. Removed URL support, use only stdin. +# + +$in=""; + +$usestdin = 1; + +if($ARGV[0] eq "-h") { + print "Usage: $0 < HTML\n"; + exit; +} +# If you need a proxy for web access, edit your .curlrc file to feature +# -x <proxy:port> + +# linkchecker, URL will be appended to the right of this command line +# this is the one using HEAD: +$linkcheck = "curl -s -m 20 -I"; + +# as a second attempt, this will be used. This is not using HEAD but will +# get the whole frigging document! +$linkcheckfull = "curl -s -m 20 -i"; + +# htmlget, URL will be appended to the right of this command line +$htmlget = "curl -s"; + +# urlget, URL will be appended to the right of this command line +# this stores the file with the remote file name in the current dir +$urlget = "curl -O -s"; + +sub namevalue { + my ($tag)=@_; + my $name=$tag; + if($name =~ /name *=/i) { + $name=~ s/.*name *= *(\"|)([^ \">]*).*/$2/gi; + } + else { + # no name given + $name=""; + } + # get value tag + my $value= $tag; + if($value =~ /value *=/i) { + $value=~ s/.*value *= *(\"|)([^ \">]*).*/$2/gi; + } + else { + $value=""; + } + return ($name, $value); +} + + +while(<STDIN>) { + $line = $_; + push @indoc, $line; + $line=~ s/\n//g; + $line=~ s/\r//g; + $in=$in.$line; +} + +while($in =~ /[^<]*(<[^>]+>)/g ) { + # we have a tag in $1 + $tag = $1; + + if($tag =~ /^<!--/) { + # this is a comment tag, ignore it + } + else { + if(!$form && + ($tag =~ /^< *form/i )) { + $method= $tag; + if($method =~ /method *=/i) { + $method=~ s/.*method *= *(\"|)([^ \">]*).*/$2/gi; + } + else { + $method="get"; # default method + } + $action= $tag; + $action=~ s/.*action *= *(\"|)([^ \">]*).*/$2/gi; + + $method=uc($method); + + $enctype=$tag; + if ($enctype =~ /enctype *=/) { + $enctype=~ s/.*enctype *= *(\'|\"|)([^ \"\'>]*).*/$2/gi; + + if($enctype eq "multipart/form-data") { + $enctype="multipart form upload [use -F]" + } + $enctype = "\n--- type: $enctype"; + } + else { + $enctype=""; + } + + print "--- FORM report. Uses $method to URL \"$action\"$enctype\n"; + $form=1; + } + elsif($form && + ($tag =~ /< *\/form/i )) { + + print "--- end of FORM\n"; + $form=0; + if( 0 ) { + print "*** Fill in all or any of these: (default assigns may be shown)\n"; + for(@vars) { + $var = $_; + $def = $value{$var}; + print "$var=$def\n"; + } + print "*** Pick one of these:\n"; + for(@alts) { + print "$_\n"; + } + } + undef @vars; + undef @alts; + } + elsif($form && + ($tag =~ /^< *(input|select)/i)) { + $mtag = $1; + + ($name, $value)=namevalue($tag); + + if($mtag =~ /select/i) { + print "Select: $name\n"; + push @vars, "$name"; + $select = 1; + } + else { + $type=$tag; + if($type =~ /type *=/i) { + $type =~ s/.*type *= *(\"|)([^ \">]*).*/$2/gi; + } + else { + $type="text"; # default type + } + $type=uc($type); + if(lc($type) eq "reset") { + # reset types are for UI only, ignore. + } + elsif($name eq "") { + # let's read the value parameter + + print "Button: \"$value\" ($type)\n"; + push @alts, "$value"; + } + else { + $info=""; + if($value ne "") { + $info="=$value"; + } + print "Input: $name$info ($type)\n"; + push @vars, "$name"; + # store default value: + $value{$name}=$value; + } + } + } + elsif($form && + ($tag =~ /^< *textarea/i)) { + my ($name, $value)=namevalue($tag); + + print "Textarea: $name\n"; + } + elsif($select) { + if($tag =~ /^< *\/ *select/i) { + print "[end of select]\n"; + $select = 0; + } + elsif($tag =~ /[^\/] *option/i ) { + my ($name, $value)=namevalue($tag); + print " One option (name \"$name\") = \"$value\"\n"; + } + } + } +} diff --git a/perl/contrib/formfind.pl.in b/perl/contrib/formfind.pl.in deleted file mode 100755 index 6428e991e..000000000 --- a/perl/contrib/formfind.pl.in +++ /dev/null @@ -1,273 +0,0 @@ -#!@PERL@ -# -# formfind.pl -# -# This script gets a HTML page from the specified URL and presents form -# information you may need in order to machine-make a respond to the form. -# -# Written to use 'curl' for URL fetching. -# -# Author: Daniel Stenberg <Daniel.Stenberg@sth.frontec.se> -# Version: 0.1 Nov 12, 1998 -# -# HISTORY -# -# 0.1 - Created now! -# -# TODO -# respect file:// URLs for local file fetches! - -$in=""; - -$usestdin = 0; -if($ARGV[0] eq "" ) { - $usestdin = 1; -} -else { - $geturl = $ARGV[0]; -} - -if(($geturl eq "") && !$usestdin) { - print "Usage: $0 <full source URL>\n", - " Use a traling slash for directory URLs!\n"; - exit; -} -# If you need a proxy for web access, edit your .curlrc file to feature -# -x <proxy:port> - -# linkchecker, URL will be appended to the right of this command line -# this is the one using HEAD: -$linkcheck = "curl -s -m 20 -I"; - -# as a second attempt, this will be used. This is not using HEAD but will -# get the whole frigging document! -$linkcheckfull = "curl -s -m 20 -i"; - -# htmlget, URL will be appended to the right of this command line -$htmlget = "curl -s"; - -# urlget, URL will be appended to the right of this command line -# this stores the file with the remote file name in the current dir -$urlget = "curl -O -s"; - -# Parse the input URL and split it into the relevant parts: - -sub SplitURL { - my $inurl = $_[0]; - - if($inurl=~ /^([^:]+):\/\/([^\/]*)\/(.*)\/(.*)/ ) { - $getprotocol = $1; - $getserver = $2; - $getpath = $3; - $getdocument = $4; - } - elsif ($inurl=~ /^([^:]+):\/\/([^\/]*)\/(.*)/ ) { - $getprotocol = $1; - $getserver = $2; - $getpath = $3; - $getdocument = ""; - - if($getpath !~ /\//) { - $getpath =""; - $getdocument = $3; - } - - } - elsif ($inurl=~ /^([^:]+):\/\/(.*)/ ) { - $getprotocol = $1; - $getserver = $2; - $getpath = ""; - $getdocument = ""; - } - else { - print "Couldn't parse the specified URL, retry please!\n"; - exit; - } -} - - -if(!$usestdin) { - - &SplitURL($geturl); -#print "protocol = $getprotocol\n"; -#print "server = $getserver\n"; -#print "path = $getpath\n"; -#print "document = $getdocument\n"; -#exit; - - open(HEADGET, "$linkcheck $geturl|") || - die "Couldn't get web page for some reason"; - headget: - while(<HEADGET>) { -# print $_; - if($_ =~ /HTTP\/.*3\d\d /) { - $pagemoved=1; - } - elsif($pagemoved && - ($_ =~ /^Location: (.*)/)) { - $geturl = $1; - - &SplitURL($geturl); - - $pagemoved++; - last headget; - } - } - close(HEADGET); - - if($pagemoved == 1) { - print "Page is moved but we don't know where. Did you forget the ", - "traling slash?\n"; - exit; - } - - open(WEBGET, "$htmlget $geturl|") || - die "Couldn't get web page for some reason"; - - while(<WEBGET>) { - $line = $_; - push @indoc, $line; - $line=~ s/\n//g; - $line=~ s/\r//g; -# print $line."\n"; - $in=$in.$line; - } - - close(WEBGET); -} -else { - while(<STDIN>) { - $line = $_; - push @indoc, $line; - $line=~ s/\n//g; - $line=~ s/\r//g; - $in=$in.$line; - } -} - - getlinkloop: - while($in =~ /[^<]*(<[^>]+>)/g ) { - # we have a tag in $1 - $tag = $1; - - if($tag =~ /^<!--/) { - # this is a comment tag, ignore it - } - else { - if(!$form && - ($tag =~ /^< *form/i )) { - $method= $tag; - if($method =~ /method *=/i) { - $method=~ s/.*method *= *(\"|)([^ \">]*).*/$2/gi; - } - else { - $method="get"; # default method - } - $action= $tag; - $action=~ s/.*action *= *(\"|)([^ \">]*).*/$2/gi; - - $method=uc($method); - - $enctype=$tag; - if ($enctype =~ /enctype *=/) { - $enctype=~ s/.*enctype *= *(\'|\"|)([^ \"\'>]*).*/$2/gi; - - if($enctype eq "multipart/form-data") { - $enctype="multipart form upload [use -F]" - } - $enctype = "\n--- type: $enctype"; - } - else { - $enctype=""; - } - - print "--- FORM report. Uses $method to URL \"$action\"$enctype\n"; -# print "TAG: $tag\n"; -# print "METHOD: $method\n"; -# print "ACTION: $action\n"; - $form=1; - } - elsif($form && - ($tag =~ /< *\/form/i )) { -# print "TAG: $tag\n"; - print "--- end of FORM\n"; - $form=0; - if( 0 ) { - print "*** Fill in all or any of these: (default assigns may be shown)\n"; - for(@vars) { - $var = $_; - $def = $value{$var}; - print "$var=$def\n"; - } - print "*** Pick one of these:\n"; - for(@alts) { - print "$_\n"; - } - } - undef @vars; - undef @alts; - } - elsif($form && - ($tag =~ /^< *(input|select)/i)) { - $mtag = $1; -# print "TAG: $tag\n"; - - $name=$tag; - if($name =~ /name *=/i) { - $name=~ s/.*name *= *(\"|)([^ \">]*).*/$2/gi; - } - else { - # no name given - $name=""; - } - # get value tag - $value= $tag; - if($value =~ /value *=/i) { - $value=~ s/.*value *= *(\"|)([^ \">]*).*/$2/gi; - } - else { - $value=""; - } - - if($mtag =~ /select/i) { - print "Select: $name\n"; - push @vars, "$name"; - $select = 1; - } - else { - $type=$tag; - if($type =~ /type *=/i) { - $type =~ s/.*type *= *(\"|)([^ \">]*).*/$2/gi; - } - else { - $type="text"; # default type - } - $type=uc($type); - if(lc($type) eq "reset") { - # reset types are for UI only, ignore. - } - elsif($name eq "") { - # let's read the value parameter - - print "Button: \"$value\" ($type)\n"; - push @alts, "$value"; - } - else { - $info=""; - if($value ne "") { - $info="=$value"; - } - print "Input: $name$info ($type)\n"; - push @vars, "$name"; - # store default value: - $value{$name}=$value; - } - } - } - elsif($select && - ($tag =~ /^< *\/ *select/i)) { - $select = 0; - } - } - } - |