Hi,<div><br></div><div>I'm scraping a web page (code below) using HTML::TreeBuilder. I'm trying to get the info between the <td> </td>, but embedded in some of the values is a ’ like:</div><div>
<br></div><div><td align="left" nowrap>Today’s Volume</td></div><div><br></div><div>What I want to do is remove the "’" or convert to a single quote, within the HTML::TreeBuilder object, figuring that's probably a more reliable approach. </div>
<div><br></div><div>What I'm currently doing is just converting to text and doing a regex</div><div><br></div><div>my $text = $cell->as_text;</div><div>$text =~ s/Today.s Volume/Today's Volume/;</div><div><br>
</div>
<div>Any suggestions on how to do this?</div><div><br></div><div>Thanks</div><div>Jay</div><div><br></div><div><br></div><div><br></div><div><br></div><div><div>use strict;</div><div><br></div><div>use WWW::Mechanize;</div>
<div>use HTML::TreeBuilder 5 -weak;</div><div>use Data::Dumper;</div><div><br></div><div>my $mech = retrieve_graham_quote("DELL");</div><div>my $info = parse_page($mech);</div><div><br></div><div><br></div><div>
sub retrieve_graham_quote {</div><div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>my $ticker = shift;</div><div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>my $base_url = '<a href="http://www.grahaminvestor.com/quotes/?ticker=">http://www.grahaminvestor.com/quotes/?ticker=</a>';</div>
<div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>my $mech = WWW::Mechanize->new();</div><div><span class="Apple-tab-span" style="white-space:pre"> </span>$mech->get( $base_url.$ticker );</div>
<div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>return $mech;</div><div><br></div><div>}</div><div><br></div><div>sub parse_page {</div><div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>my $mech = shift;</div>
<div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>my $tree = HTML::TreeBuilder->new;</div><div><span class="Apple-tab-span" style="white-space:pre"> </span>$tree->parse($mech->content());</div>
<div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>my $table = $tree->look_down('_tag','table');</div><div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>foreach my $row ($table->look_down('_tag', 'tr')) {</div>
<div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>foreach my $cell ($row->look_down('_tag', 'td')) {</div><div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>my $text = $cell->as_text;</div>
<div><span class="Apple-tab-span" style="white-space:pre"> </span></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>$text =~ s/Today.s Volume/Today's Volume/;</div><div><span class="Apple-tab-span" style="white-space:pre"> </span></div>
<div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>print "-", $text,"\n";</div><div><span class="Apple-tab-span" style="white-space:pre"> </span>print "-", $cell->as_HTML,"\n";</div>
<div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>}</div><div><span class="Apple-tab-span" style="white-space:pre"> </span>}</div><div><br></div><div>}</div></div><div><br></div>