PHP xpath提取网页数据内容代码解析

  /
    初始化DOMXpath对象
   
    @param [type] $content 网页内容
    @param [array] $pathinfo 匹配信息
   
    @return void
   /
  private function _createXpathObj($content, $patinfo)
  {
    // 如果没有xpath配置项，不初始化xpath
    if (!$this->_existsXpathParse($patinfo)) {
      return;
    }
    try {
      $dom = new \DOMDocument();
      @$dom->loadHtml($content);
      $dom->normalize();
      $xpath = new \DOMXpath($dom);
      $this->xpathObj = $xpath;
    } catch (\Exception $e) {
      getService('logger')->warning('Parse html fail', ['content' => $content]);
    }
  }

  /
    获取Xpath解析值
   
    @param [type] $pat 匹配模式
   
    @return string
   /
  private function _getXpathField($pat)
  {
    $objs = $this->xpathObj->query($pat);
    if ($objs->length > 0) {
      $node = $objs->item(0);
      $outerHTML = $node->ownerDocument->saveHTML($node);
      return trim($outerHTML);
      # 作为示例 输出innerhtml
      //$innerHTML = '';
      //foreach ($node->childNodes as $childNode){
      //   $innerHTML .= $childNode->ownerDocument->saveHTML($childNode);
      /