小技巧

gistfile1.txt

editplus正则查找php函数
^[ \t]*(public |private |protected |static )[ \t]*(static[ \t]*)?function[ \t].*\([^;]*$

preg_match_all("~href=\"([^\"]+\.css)(?:.*?)\"[^>]*>~isx",$html,$links); 捕获html的link style链接

function get_all_url($code){
        preg_match_all('/<as+href=["|']?([^>"' ]+)["|']?s*[^>]*>([^>]+)</a>/i',$code,$arr);
        return array('name'=>$arr[2],'url'=>$arr[1]);
}

/*======================================================================*\
	Function:	_expandlinks
	Purpose:	expand each link into a fully qualified URL
	Input:		$links			the links to qualify
				$URI			the full URI to get the base from
	Output:		$expandedLinks	the expanded links
\*======================================================================*/

	function _expandlinks($links,$URI)
	{
		
		preg_match("/^[^\?]+/",$URI,$match);

		$match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|","",$match[0]);
		$match = preg_replace("|/$|","",$match);
		$match_part = parse_url($match);
		$match_root =
		$match_part["scheme"]."://".$match_part["host"];
				
		$search = array( 	"|^http://".preg_quote($this->host)."|i",
							"|^(\/)|i",
							"|^(?!http://)(?!mailto:)|i",
							"|/\./|",
							"|/[^\/]+/\.\./|"
						);
						
		$replace = array(	"",
							$match_root."/",
							$match."/",
							"/",
							"/"
						);			
				
		$expandedLinks = preg_replace($search,$replace,$links);

		return $expandedLinks;
	}

preg_match_all("~href="([^\"]+.css)(?:.?)"[^>]>~isx",$html,$links); 捕获html的link style链接

preg_match_all("/url(\s_(?:["'])?(._?)\s*(?:["'])?)/isx", $c, $imagesURLArray); ?:表示不存储 ?表示0，1
preg_match_all("/src=(?:["'])([^'\"]+)/i", $cssContent, $imagesURLArray);

匹配CSS里的图片

$c = file_get_contents('meituan.css');
preg_match_all("/url(\s_(?:["'])?(._?)\s*(?:["'])?)|src=(?:["'])([^'\"]+)/isx", $c, $imagesURLArray);
$imagesURLArray = array_unique(array_filter(array_merge((array)$imagesURLArray[1], $imagesURLArray[2])));
usort($imagesURLArray, "cmp");
function cmp($a, $b) {
if (strlen($a) == strlen($b)) {
return 0;
}
return (strlen($a) > strlen($b)) ? -1 : 1;
}
d($imagesURLArray);

PHP完美的提取链接正则

今天把Snoopy里的提取链接函数挖出来,并加强了一下
function match_links($document) {
preg_match_all("'<\s_a\s.?href\s=\s_(["'])?(?(1)(.?)\1|([^\s>]+))[^>]>?(.*?)'isx",$document,$links);
while(list($key,$val) = each($links[2])) {
if(!empty($val))
$match['link'][] = $val;
}
while(list($key,$val) = each($links[3])) {
if(!empty($val))
$match['link'][] = $val;
}
while(list($key,$val) = each($links[4])) {
if(!empty($val))
$match['content'][] = $val;
}
while(list($key,$val) = each($links[0])) {
if(!empty($val))
$match['all'][] = $val;
}
return $match;
}

editplus 正则查找所有注释行

^[\t ]*[//|\/\*|*].*\n

komodo正则替换smarty变量
<{($.*)}>