/[Grep]/lib/Grep/Source.pm
This is repository of my old source code which isn't updated any more. Go to git.rot13.org for current projects!
ViewVC logotype

Diff of /lib/Grep/Source.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 91 by dpavlin, Fri Feb 23 21:52:29 2007 UTC revision 92 by dpavlin, Sat Feb 24 11:16:05 2007 UTC
# Line 194  sub scrape { Line 194  sub scrape {
194          die "no uri" unless ($uri);          die "no uri" unless ($uri);
195          die "feed is not a Grep::Model::Feed but ", ref $feed unless $feed->isa('Grep::Model::Feed');          die "feed is not a Grep::Model::Feed but ", ref $feed unless $feed->isa('Grep::Model::Feed');
196    
197          my $mech = WWW::Mechanize->new();          sub mech_warn {
198                    my $m = shift || return;
199                    warn $m;
200            }
201    
202            my $mech = WWW::Mechanize->new(
203                    cookie_jar => {},
204                    onwarn => \&mech_warn,
205                    onerror => \&mech_warn,
206            );
207    
208          $mech->get( $uri );          $mech->get( $uri );
209    
210          $self->save( 'get.html', $mech->content );          $self->save( 'get.html', $mech->content );
211    
212          if ( $args->{submit_form} ) {          if ( my $form = $args->{submit_form} ) {
213                  warn "submit form on $uri\n";                  warn "submit form on $uri with ", dump( $form ),"\n";
214                  $mech->submit_form( %{ $args->{submit_form} } ) or die "can't submit form";                  $mech->submit_form( %$form ) or die "can't submit form ", dump( $form );
215                  $self->save( 'submit.html', $mech->content );                  $self->save( 'submit.html', $mech->content );
216          }          }
217    
# Line 249  sub scrape { Line 258  sub scrape {
258                                  my $page_tree = HTML::TreeBuilder->new or die "can't create page tree";                                  my $page_tree = HTML::TreeBuilder->new or die "can't create page tree";
259                                  $page_tree->parse( $mech->content ) or die "can't parse page at $page_uri";                                  $page_tree->parse( $mech->content ) or die "can't parse page at $page_uri";
260    
261                                  my ( $el,$attr,$value ) = @{ $args->{scrape} };                                  ( $el,$attr,$value ) = @{ $args->{scrape} };
262                                  my $div = $page_tree->look_down( '_tag', $el, sub { ( $_[0]->attr( $attr ) || '' ) eq $value } );                                  $div = $page_tree->look_down( '_tag', $el, sub { ( $_[0]->attr( $attr ) || '' ) eq $value } );
263    
264                                  die "can't find <$el $attr=\"$value\">" unless ($div);                                  die "can't find <$el $attr=\"$value\">" unless ($div);
265    

Legend:
Removed from v.91  
changed lines
  Added in v.92

  ViewVC Help
Powered by ViewVC 1.1.26