php 文本爬取

<?php

$all_wiki_urls = findAllWikiUrl();

$file = "";

$i = 1;
echo "总共: " .count($all_wiki_urls)."\n";

foreach ($all_wiki_urls as $title => $url){
    $text = matchMwParserOutput($title, $url);

    if ($text !== false){
        $file .= "$title\t$text\r\n";
        echo "词条 $title 转换完成, 当前位置: $i\n";
        $i++;
    }
}

file_put_contents("words_card1.txt", $file);


function matchMwParserOutput($title, $wiki_url)
{
    $content = file_get_contents($wiki_url);
    if (empty($content)){
        return "";
    }

    preg_match_all("/<div class=\"mw-parser-output\">[\s\S]*?<\/table>/", $content, $match);
    if (empty($match[0][0])) {
        return false;
    }
    $match_text = $match[0][0];

    $strip_text = strip_tags($match_text);

    $patten = array("\r\n", "\n", "\r", "卡牌总览", "遗物收集", "药水小样", "事件日志", "敌人图鉴", "	→点此查看数据页面");

    $final_string = str_replace($patten, "\t", $strip_text);

    return $final_string;
}

function findAllWikiUrl(){
    $base_url = "https://sts.huijiwiki.com/";

    $url = "https://sts.huijiwiki.com/wiki/%E4%B8%8A%E5%8B%BE%E6%8B%B3";

    $page_content = file_get_contents($url);

    preg_match_all("/<a href=\"(\/wiki\/.*?)\" title=\"(.*?)\">/", $page_content, $matches);

    $wikiArray = [];

    $length = count($matches[0]);

    for ($i = 0 ; $i < $length; $i++){
        if (strpos($matches[1][$i], "Icon_Rage.png") != false){
            continue;
        }
        if (strpos($matches[1][$i], "class") == false){
            $wikiArray[$matches[2][$i]] = $base_url. $matches[1][$i];
        }
    }

    return $wikiArray;
}