2021-04-08

HW3 Starter Example.

<nowiki> <?php namespace cpollett\test_composer; use seekquarry\yioop\library\CrawlConstants; use seekquarry\yioop\library\FetchUrl; use seekquarry\yioop\library\Library; use seekquarry\yioop\library\processors\HtmlProcessor; require_once "vendor/autoload.php"; Library::init(true); $summary_len = 1000; $max_links = 100; $sites = FetchUrl::getPages( [ [CrawlConstants::URL => "https://en.wikipedia.org/wiki/Indus_script"], ], // we could list more urls to download ); $html_processor = new HtmlProcessor([], $summary_len, $max_links, CrawlConstants::CENTROID_WEIGHTED_SUMMARIZER); $summary_info = $html_processor->process($sites[0][CrawlConstants::PAGE], $sites[0][CrawlConstants::URL]); echo $summary_info[CrawlConstants::DESCRIPTION]; </nowiki>
X