Yahoo Backlink Information

yahoo_appid = 'LinkHarvester'; // Configuration $columns = 2; $autocheck = 4; // Greater than this number will be auto-checked. // If there is no depth selected, set it to 5 be default if ($depth > 5) { // Do Nothing } else { $depth = 5; } $alreadyfiltered = $depth * 50; $filteredstart = $alreadyfiltered + 100; // Close out the page function done() { echo ''; exit; } // Function to display links with all options and information function show_links ($links) { $count = 0; global $columns, $autocheck, $hostcount, $query; foreach($links as $host => $info) { if (!is_numeric(strpos($info['page']['url'],'http://'))) { $url = 'http://' . $info['page']['url']; } else { $url = $info['page']['url']; } if ($count % $columns == 0) echo " \n"; $count++; $hostcount++; if ($info['links'] > $autocheck) { $checked = ' checked'; } else { $checked = ''; } echo " "; echo "[W] "; echo "[A] "; echo "[G] "; echo "[T] "; echo "[H] "; echo "[D] "; echo "[Y] "; echo "[S] "; echo "[M] "; if ($info['links'] > $autocheck) { echo "" . $host . " "; echo "(" . $info['links'] . ") " . $info['ip'] . "\n"; } else { echo "" . $host . " "; echo "(" . $info['links'] . ") " . $info['ip'] . "\n"; } if (($count % $columns == 0) || ($count == count($edu))) echo " \n"; } } ?> Yahoo Backlink Information

Link Harvester is a free open source link analysis tool from www.seobook.com. Link Harvester returns:

unique linking domains
their IP addresses & unique c block addresses of the links
links from .gov, .mil, .edu, or .ac.uk domains. Links from these domains are likely rated better in authority type algorithms such as Hilltop or TrustRank.
Link Harvester also bolds and autochecks domains that link from 5 or more pages. You can then requery the Yahoo! database and spider deeper than the 1,000 link limit.
Link Harvester uses the Yahoo! API, provides CSV outputs, and is an open source tool. If you are a heavy user or the query limit (5,000 daily requests) is exceeded feel free to host your own copy of Link Harvester on your site. Setup should take under a minute.
Here is the source code. Please note, your host must support DOM XML to host this tool.
Link Harvester also links to the Internet Archives, WhoIs Source, and Google cache near each link.
Questions, comments, feedback? Let me know what you think.
403 errors means the tool is used up for the day.
please try one of the mirrors or mirror the tool on your server if you use it frequently
tool mirrors: thanks to Todd , Donna, Martin & Christoph

URL (ex. www.site.com):
Link Type:	Query Depth:	Engine:

result_num = 1; if ($engine == 'msn') { $gamy->query = 'linkdomain:' . $domain[host]; $gamy->search_msn(); $totaldomainresults = $gamy->totals['msn']; $gamy->query = 'http://' . $domain[host]; $gamy->search_msn(); $totalpagesindexed = $gamy->totals['msn']; $gamy->query = 'link:http://' . $domain[host]; $gamy->search_msn(); $totalhomeresults = $gamy->totals['msn']; } else { $gamy->query = 'linkdomain:' . $domain[host]; $gamy->search_yahoo(); $totaldomainresults = $gamy->totals['yahoo']; $gamy->query = 'http://' . $domain[host]; $gamy->search_yahoo(); $totalpagesindexed = $gamy->totals['yahoo']; $gamy->query = 'link:http://' . $domain[host]; $gamy->search_yahoo(); $totalhomeresults = $gamy->totals['yahoo']; } if ($linktype == 'link') { $gamy->query = 'link:http://' . $domain[host]; } elseif ($linktype == 'domain') { $gamy->query = 'linkdomain:' . $domain[host]; } elseif ($linktype == 'deep') { $gamy->query = 'linkdomain:' . $domain[host] . ' -link:http://' . $domain[host] . ' -link:http://' . str_replace('www.','',$domain[host]); } $filtered_sites = array(); $filtered_cblocks = array(); for($i = 0; $i < $filteredstart; $i++) { if (isset($_GET['x'.$i])) { $site = str_replace('www.','',$_GET['x'.$i]); $gamy->exclude_site($site); array_push($filtered_sites,$site); $cblock = substr(gethostbyname($site),0,strrpos(gethostbyname($site),'.')); $filtered_cblocks[$cblock]++; } } $manual_sites = explode("\n",$manual_filter); foreach ($manual_sites AS $site) { if (strlen($site) > 1) { $gamy->exclude_site($site); array_push($filtered_sites,$site); $cblock = substr(gethostbyname($site),0,strrpos(gethostbyname($site),'.')); $filtered_cblocks[$cblock]++; } } echo "

"; $gamy->result_num = $depth * 50; if ($engine == 'yahoo') { $gamy->search_yahoo(); $totalresults = $gamy->totals['yahoo']; } elseif ($engine == 'both') { $gamy->search_msn(); $gamy->search_yahoo(); $totalresults = $gamy->totals['msn']; $totalresults += $gamy->totals['yahoo']; } else { $gamy->search_msn(); $totalresults = $gamy->totals['msn']; } foreach($gamy->search_results AS $value) { $parsed = parse_url('http://' . $value['url']); $host = $parsed['host']; if ((substr($host,-4,4) == '.edu') || (substr($host,-7,4) == '.edu') || (substr($host,-6,6) == '.ac.uk')) { $edu[$host]['links']++; if ($edu[$host]['page'] == '') $edu[$host]['page'] = $value; if ($edu[$host]['ip'] == '') $edu[$host]['ip'] = gethostbyname($host); $cblock = substr($edu[$host]['ip'],0,strrpos($edu[$host]['ip'],'.')); $edu_cblocks[$cblock]++; } else if ((substr($host,-4,4) == '.gov') || (substr($host,-7,4) == '.gov') || (substr($host,-4,4) == '.mil') || (substr($host,-7,4) == '.mil')) { $gov[$host]['links']++; if ($gov[$host]['page'] == '') $gov[$host]['page'] = $value; if ($gov[$host]['ip'] == '') $gov[$host]['ip'] = gethostbyname($host); $cblock = substr($gov[$host]['ip'],0,strrpos($gov[$host]['ip'],'.')); $gov_cblocks[$cblock]++; } else { $def[$host]['links']++; if ($def[$host]['page'] == '') $def[$host]['page'] = $value; if ($def[$host]['ip'] == '') $def[$host]['ip'] = gethostbyname($host); $cblock = substr($def[$host]['ip'],0,strrpos($def[$host]['ip'],'.')); $def_cblocks[$cblock]++; } } echo "Enter sitenames you want to filter:
\n"; echo "

Showing "; echo count($edu) + count($gov) + count($def) . " unique domains from the first $alreadyfiltered results of $totalresults total results

\n"; $deeplinks = $totaldomainresults - $totalhomeresults; if ($totaldomainresults > 0) $deeplinkpercentage = round($deeplinks / $totaldomainresults * 100); else $deeplinkpercentage = 0; ?>

"; echo "Links To Homepage: " . $totalhomeresults . "
"; echo "

"; echo "Pages Indexed: " . $totalpagesindexed . "
"; echo "Deep Link Percentage: " . $deeplinkpercentage . "%
"; ?>

= 1) { $count = 0; echo "" . count($filtered_sites) . " Filtered Sites with " . count($filtered_cblocks) . " Unique C Block Addresses

\n"; foreach($filtered_sites as $site) { if ($count % $columns == 0) echo " \n"; $count++; echo " \n"; $alreadyfiltered++; if ($count % $columns == 0) echo " \n"; } echo "

"; echo "[W] "; echo "[A] "; echo "[H] "; echo "[D] "; echo "[Y] "; echo "[S] "; echo "[M] "; echo "" . $site . " "; echo gethostbyname($site) . "

\n"; } if ($edu){ echo "" . count($edu) . " Unique Educational Domains (*.edu) with " . count($edu_cblocks) . " Unique C Block Addresses

\n"; show_links($edu); echo "

\n"; } if ($gov){ echo "" . count($gov) . " Unique Goverment Domains (*.gov, *.mil) with " . count($gov_cblocks) . " Unique C Block Addresses

\n"; show_links($gov); echo "

\n"; } if ($def) { echo "" . count($def) . " Unique Commerical Domains (*.com, *.net, etc) with " . count($def_cblocks) . " Unique C Block Addresses

\n"; show_links($def); echo "

<?php

echo "Site Name, Links To Domain, Links To Homepage, Pages Indexed, Deep Link Percentage\n";
echo $_GET['query'] . ', ' . $totaldomainresults . ", " . $totalhomeresults . ", " . $totalpagesindexed . ", " . $deeplinkpercentage . "\n\n";

echo "Filtered Sites\n\n";
echo "Domain Name, Page Linked From, Number of Links, IP Address\n";
foreach($filtered_sites AS $site) {
  echo "$site, N/A, N/A, " . gethostbyname($site) . "\n";
}
echo "\nUnique Educational Domains, Unique C Block Address\n";
echo count($edu) . ", " . count($edu_cblocks) . "\n";
if ($edu){
  echo "Domain Name, Page Linked From, Number of Links, IP Address\n";
  foreach($edu as $host => $info) {
    echo $host . ", " . str_replace(',','%2C',$info['page']['url']) . ", " . $info['links'] . ", " . $info['ip'] . "\n";
  }
}
echo "\nUnique Government Domains, Unique C Block Address\n";
echo count($gov) . ", " . count($gov_cblocks) . "\n";
if ($gov){
  echo "Domain Name, Page Linked From, Number of Links, IP Address\n";
  foreach($gov as $host => $info) {
    echo $host . ", " . str_replace(',','%2C',$info['page']['url']) . ", " . $info['links'] . ", " . $info['ip'] . "\n";
  }
}
echo "\nUnique Commercial Domains, Unique C Block Address\n";
echo count($def) . ", " . count($def_cblocks) . "\n";
if ($def){
  echo "Domain Name, Page Linked From, Number of Links, IP Address\n";
  foreach($def as $host => $info) {
    echo $host . ", " . str_replace(',','%2C',$info['page']['url']) . ", " . $info['links'] . ", " . $info['ip'] . "\n";
  }
}
?>