#!/bin/bash # bash check-network.sh || ! echo "skipping online unit tests" || exit 77 # http://code.google.com/p/httrack/issues/detail?id=4&can=1 bash crawl-test.sh --errors 0 --files 4 \ --found ut.httrack.com/parsing/back5e1f.gif \ --found ut.httrack.com/parsing/events.html \ --found ut.httrack.com/parsing/fade230f4.gif \ --found ut.httrack.com/parsing/fade3860.gif \ httrack http://ut.httrack.com/parsing/events.html # http://code.google.com/p/httrack/issues/detail?id=2&can=1 bash crawl-test.sh --errors 0 --files 3 \ --found ut.httrack.com/parsing/background-image.css \ --found ut.httrack.com/parsing/background-image.html \ --found ut.httrack.com/parsing/fade.gif \ httrack http://ut.httrack.com/parsing/background-image.html # javascript parsing bash crawl-test.sh --errors 0 --files 3 \ --found ut.httrack.com/parsing/back.gif \ --found ut.httrack.com/parsing/fade.gif \ --found ut.httrack.com/parsing/javascript.html \ httrack http://ut.httrack.com/parsing/javascript.html # handling of + before query string bash crawl-test.sh --errors 0 --files 6 \ --found ut.httrack.com/parsing/escaping.html \ --found "ut.httrack.com/parsing/foo bar30f4.html" \ --found "ut.httrack.com/parsing/foo bar5e1f.html" \ --found "ut.httrack.com/parsing/foo+bar+plus3860.html" \ --found "ut.httrack.com/parsing/foo barae52.html" \ --found "ut.httrack.com/parsing/foo bar7b30.html" \ httrack http://ut.httrack.com/parsing/escaping.html # handling of # encoded in filename # see http://code.google.com/p/httrack/issues/detail?id=25 bash crawl-test.sh --errors 2 --files 4 \ --found "ut.httrack.com/parsing/escaping2.html" \ --found "ut.httrack.com/parsing/++foo++bar++plus++.html" \ --found "ut.httrack.com/parsing/foo#bar#.html" \ --found "ut.httrack.com/parsing/foo bar.html" \ httrack http://ut.httrack.com/parsing/escaping2.html