From c7898d86561d26b796d0b2b73eb7121ce73c1e26 Mon Sep 17 00:00:00 2001
From: lookshe <github@lookshe.org>
Date: Sun, 21 Sep 2014 00:35:30 +0200
Subject: one example for analysing webpages with scraper

---
 download_webscraper.pl | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 download_webscraper.pl

diff --git a/download_webscraper.pl b/download_webscraper.pl
new file mode 100644
index 0000000..a8bd1ea
--- /dev/null
+++ b/download_webscraper.pl
@@ -0,0 +1,35 @@
+#!/usr/bin/perl
+
+#use strict;
+#use warnings;
+use Web::Scraper;
+use URI;
+use HTML::Entities;
+use Encode;
+use URI::Escape;
+use LWP::UserAgent;
+
+my $scrap;
+
+my $wikiurl = "http://www.bildung-lsa.de/unterricht/zentrale_leistungserhebungen__schriftliche_pruefungen__zentrale_klassenarbeiten__vergleichsarbeiten____/schriftliche_abiturpruefung.html";
+
+my $ua = new LWP::UserAgent;
+my $req = HTTP::Request->new('GET', $wikiurl);
+my $res = $ua->request($req);
+my $url = $res->request->uri;
+
+binmode(STDOUT, ":utf8");
+
+
+   $scrap = scraper {
+      process '//a[@class="subjectlink"]', 'href[]' => '@href';
+   };
+   $url = URI->new($wikiurl);
+
+   my $res = $scrap->scrape($url);
+   my $href = $res->{'href'};
+   for ($i = 0; $i <= $#$href; $i++)
+   {
+         my $url = $$href[$i];
+         system("wget -q \"$url\"");
+   }
-- 
cgit v1.2.3