by Reinhard Max
This little script sends it's command line arguments as a query to the online dictionary at http://dict.leo.org and writes the parsed result to stdout. It uses Tcl's http package and the htmlparse and ncgi packages from Tcllib.
package require http
package require htmlparse
package require ncgi
set table {{English German}}
set max 0
proc max {a b} { expr {$a > $b ? $a : $b} }
proc HTML {tag close options body} {
switch -- $close$tag {
TR {set ::TR ""}
TD {set ::TD ""}
/TR {if {[llength $::TR]} {lappend ::table $::TR }}
/TD {if {[llength $::TD]} {lappend ::TR [join $::TD]}}
default {append ::TD [string map { { }} $body]}
}
}
proc main {argv} {
set url "http://dict.leo.org/?search=[::ncgi::encode $argv]"
set tok [::http::geturl $url]
set data [::http::data $tok]
::http::cleanup $tok
foreach line [split $data "\n"] {
if {[string match "*search results*" $line]} break
}
::htmlparse::parse -cmd HTML $line
set max 0
foreach row $::table {
foreach c $row {set max [max $max [string length $c]]}
}
incr max
set sep [string repeat = $max]
set ::table [linsert $::table 1 [list $sep $sep]]
foreach row $::table {
foreach {c1 c2} $row break
puts [format "%-*s %-*s" $max $c1 $max $c2]
}
puts ""
}
main $argvWeb scraping | Using Tcl to write WWW client side applications