#!/usr/bin/perl
use WWW::Mechanize;
my $mech = WWW::Mechanize->new();
my $url = ('http://www.folkeferie.dk/da/ferier/Aktuelle-chartertilbud-
+--afbudsrejser/');
$mech->get($url);
my $hsh={};
$links = $mech->find_all_links(url_regex=>qr/templates\/textPage\.aspx
+\?id/i, text_regex=>qr/Afbudsrejser/i);
foreach my $link (@$links) {
$url = $link->url_abs();
$mech->get($url);
my $content = $mech->content();
while ($content=~/tr class="bgrow1"><td>(.*?)<\/td><td cla
+ss="countryValue">(.*?)<\/td><td class="destnameValue">(.*?)<\/td><td
+ class="hotelNameValue">(.*?)<\/td><td class="durationValue">(.*?)<\/
+td><td align="RIGHT" class="priceValue"><a target="_blank" href="(.*?
+)">(.*?)<\/a><\/td>/gisxm) {
$hsh->{'url'} = $6;
$hsh->{'crap_id'} = '';
$hsh->{'date'} = $1;
$hsh->{'country'} = $2;
$hsh->{'destination'} = $3;
$hsh->{'trip_type'} = $4;
$hsh->{'trip_length'} = $5;
$hsh->{'price'}=$7;
print "$hsh->{'date'}, $hsh->{'country'}, $hsh->{'destina
+tion'}, $hsh->{'trip_type'}, $hsh->{'trip_length'}, $hsh->{'price'},
+$hsh->{'crap_id'}, $hsh->{'url'}, $airport\n\n";
}
}
Please have a look in this code and also check the link and tell me how can I scrape the details from here.
Regards
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.
|