i wish to scrape knowledge from one other web site that does not present api to my wordpress website, and i need when i enter the information url ($baseTarget) it seems immediately within the taxonomy enter post_tags, title description, class, picture and many others in new publish. i do not know make it, i’ve searched however have not discovered any outcomes.
scrape.php
<?php
namespace AppServices;
use vokuhelperHtmlDomParser;
class MALService
{
non-public $baseTarget="https://myanimelist.web";
non-public operate init($path)
{
$curl = curl_init($this->baseTarget . $path);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, TRUE);
curl_setopt($curl, CURLOPT_USERAGENT, 'Mozilla/5.0 (Home windows; U; Home windows NT 5.1; en-US; rv:1.8.1.13) Gecko/20080311 Firefox/2.0.0.13');
$html = curl_exec($curl);
curl_close($curl);
return HtmlDomParser::str_get_html($html);
}
public operate getCurrentAnimeSeason()
{
$html = $this->init('/anime/season');
$wrapper = $html->findOne('#contentWrapper');
$knowledge['seasonName'] = $wrapper->findOne('.season_nav > a')->innerText();
// Get the present anime season sorts
foreach ($wrapper->findMulti('.js-categories-seasonal > .seasonal-anime-list.js-seasonal-anime-list') as $index => $animeType) {
$typeName = $animeType->findOne('.anime-header')->innerText();
$knowledge['list'][$index] = [
'typeName' => $typeName,
'animes' => []
];
// Get the anime record from every sorts
foreach ($animeType->findMulti('.seasonal-anime.js-seasonal-anime') as $anime) {
// Get the genres anime
$genres = [];
foreach ($anime->findMulti('.genres-inner > .style') as $style) {
$genreName = $genre->findOne('a')->innerText();
// Skip 18+ anime
if (strtolower($genreName) == 'hentai') proceed 2;
$genres[] = $genreName;
}
// Get picture anime
$picture = $anime->findOne('.picture > a > img')->getAttribute('data-src');
$picture = $picture != null ? $picture : $anime->findOne('.picture > a > img')->getAttribute('src');
// Anime Information
$knowledge['list'][$index]['animes'][] = [
'title' => $anime->findOne('.h2_anime_title > a')->innerText(),
'url' => $anime->findOne('.h2_anime_title > a')->getAttribute('href'),
'image' => $image,
'score' => strip_tags($anime->findOne('.score.score-label')->innerText()),
'member' => strip_tags($anime->findOne('.member.fl-r')->innerText()),
'producer' => $anime->findOne('.producer > a')->innerText(),
'eps' => $anime->findOne('.eps > a > span')->innerText(),
'source' => $anime->findOne('.source')->innerText(),
'genres' => $genres
];
}
}
return $knowledge;
}
}