首页 / 网页编程 / PHP / php基于Snoopy解析网页html的方法

set_time_limit（0）;$user = array（"20517", "20518"）;header（"content-Type: text/html; charset=utf-8"）;require_once "./Snoopy.php";$snoopy = new Snoopy（）;//$uri = "http://www.juzimi.com/meitumeiju";$uri = "http://www.juzimi.com/meitumeiju?page=1";$snoopy->fetch（$uri）;$con = $snoopy->getResults（）;$doc = new DOMDocument（）;$doc->loadHTML（$con）;/* make a result array ... */$result = [];/* go through all nodes which have class="baby" ... */$i = 0;foreach（ （ new DOMXPath（ $doc ） ）->query（ "//*[@id="bdshare"]" ） as $element ） {$row = $doc->saveHTML（$element）;$start = stripos（$row, "{"）;$end = stripos（$row, "}"）;$len = $end - $start + 1;$json = substr（$row, $start, $len）;$json = str_replace（""", """, $json）;$obj = json_decode（$json）;$pic = $obj->pic;$desc = $obj->desc;$filename = "/Uploads/meiju/card" . date（"ymdhis"） . $i . ".png";$file = "/alidata/www/test" . $filename;$image = file_get_contents（$pic）;file_put_contents（$file, $image）;}