Tcl

Extract all HTML Objects from a Web Page

See more MHT / HTML Email Examples

Demonstrates how to download a Web page (at a URL) and extract all HTML objects. Eg. images, links, CSS files, JavaScript files, etc. Tcl

load ./chilkat.dll

set success 0

# This example assumes the Chilkat API to have been previously unlocked.
# See Global Unlock Sample for sample code.

set mht [new_CkMht]

# Download a URL into an in-memory MHT web archive contained
# in a string variable.
# The following URL is randomly picked and was valid at the time of writing this example:
set mhtDoc [CkMht_getMHT $mht "https://www.tetonlodge.com/"]
if {[CkMht_get_LastMethodSuccess $mht] != 1} then {
    puts [CkMht_lastErrorText $mht]
    delete_CkMht $mht
    exit
}

# Extract the HTML and embedded objects:
set unpackDir "C:/AAWorkarea/mhtTesting/"
set htmlFilename "lodge.html"
set partsSubdir "objects"

# Extract to C:/AAWorkarea/mhtTesting/lodge.html.
# images and other embedded objects are placed in
# C:/AAWorkarea/mhtTesting/objects.  Directories are automatically
# created if they don't already exist.
set success [CkMht_UnpackMHTString $mht $mhtDoc $unpackDir $htmlFilename $partsSubdir]
if {$success != 1} then {
    puts [CkMht_lastErrorText $mht]
} else {
    puts "Unpacked!"
}


delete_CkMht $mht