Beefy Boxes and Bandwidth Generously Provided by pair Networks
good chemistry is complicated,
and a little bit messy -LW
 
PerlMonks  

comment on

( [id://3333]=superdoc: print w/replies, xml ) Need Help??
use HTTP::Request; use LWP::UserAgent; use HTML::TreeBuilder; $ua = LWP::UserAgent->new; $request = HTTP::Request->new(GET => 'http://slashdot.org/'); $resp = $ua->request($request); $tree = HTML::TreeBuilder->new; $tree->parse($resp->content); my @titles; my @authors; my @dept; foreach my $h ($tree->look_down('_tag', 'font', sub { return unless ($_[0]->attr('face') and $_[0]->attr('size') and $ +_[0]->attr('color')); my @c = $_[0]->content_list; return unless ref $c[0]; my @d = $c[0]->content_list; return 1 if not ref $d[0]; $#c == 0 and $c[0]->tag eq 'b' and $d[0]->tag ne 'map'; } )) { push @titles, $h->as_text; } foreach my $h ($tree->look_down('_tag', 'b', sub { my @c = $_[0]->content_list; @c == 3 and ref $c[1] and $c[1]->tag eq 'a' and $c[0] =~ /^Poste +d by/; } )) { push @authors, $h->as_text; } foreach my $h ($tree->look_down('_tag', 'b', sub { my @c = $_[0]->content_list; @c == 1 and $c[0] =~ /^from the .* dept\.$/; } )) { push @dept, $h->as_text; } for($i=0; $i<10; $i++) { print "$titles[$i]\n"; print "$authors[$i]\n"; print "$dept[$i]\n\n"; } $tree = $tree->delete;

In reply to Slashdot headlines by moxliukas

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post; it's "PerlMonks-approved HTML":



  • 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.
Log In?
Username:
Password:

What's my password?
Create A New User
Domain Nodelet?
Chatterbox?
and the web crawler heard nothing...

How do I use this?Last hourOther CB clients
Other Users?
Others chanting in the Monastery: (3)
As of 2024-04-20 02:54 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?

    No recent polls found