php采集页面指定标签里面的内容

/*
* 参数说明: $tag_id:所要获取的元素Tag Id $url:所要获取页面的Url $tag:所要获取的标签 $data
*/
function getWebTag($tag_id, $url = false, $tag = ‘div‘, $data = false) {
    if ($url !== false) {
        $data = file_get_contents ( $url );
    }
    $charset_pos = stripos ( $data, ‘charset‘ );
    if ($charset_pos) {
        if (stripos ( $data, ‘utf-8‘, $charset_pos )) {
            $data = iconv ( ‘utf-8‘, ‘utf-8‘, $data );
        } else if (stripos ( $data, ‘gb2312‘, $charset_pos )) {
            $data = iconv ( ‘gb2312‘, ‘utf-8‘, $data );
        } else if (stripos ( $data, ‘gbk‘, $charset_pos )) {
            $data = iconv ( ‘gbk‘, ‘utf-8‘, $data );
        }
    }
    preg_match_all ( ‘/ $pre_div ) {
        $divs [( int ) $pre_div [1]] = ‘p‘;
        $divs [( int ) $suf_matches [0] [$index] [1]] = ‘s‘;
    }
    // 对div进行排序
    $sort = array_keys ( $divs );
    asort ( $sort );
    $count = count ( $pre_matches [0] );
    foreach ( $pre_matches [0] as $index => $pre_div ) {
        // 
‘;
            break;
        }
    }
    return $hitDivString;
}

echo getWebTag ( ‘id="content"‘, ‘http://www.cdlyh.com/article/read/id/12345.html‘, ‘div‘ );


 
php采集页面指定标签里面的内容
标签：==   false   sort   file   标签   read   turn   元素   foreach   
原文地址：https://www.cnblogs.com/zhaoying/p/12881155.html