我有一个包含大量链接的网页.我想编写一个脚本,将脚本中包含的所有数据转储到本地文件中.
有人用PHP做过吗？一般准则和陷阱就足以作为答案.
咩.不要使用正则表达式解析HTML.
这是一个受Tatu's启发的DOM版本:
loadHTMLFile($url);
$anchors = $dom->getElementsByTagName('a');
foreach ($anchors as $element) {
$href = $element->getAttribute('href');
if (0 !== strpos($href, 'http')) {
$path = '/' . ltrim($href, '/');
if (extension_loaded('http')) {
$href = http_build_url($url, array('path' => $path));
} else {
$parts = parse_url($url);
$href = $parts['scheme'] . '://';
if (isset($parts['user']) && isset($parts['pass'])) {
$href .= $parts['user'] . ':' . $parts['pass'] . '@';
}
$href .= $parts['host'];
if (isset($parts['port'])) {
$href .= ':' . $parts['port'];
}
$href .= dirname($parts['path'], 1).$path;
}
}
crawl_page($href, $depth - 1);
}
echo "URL:",$url,PHP_EOL,"CONTENT:",PHP_EOL,$dom->saveHTML(),PHP_EOL,PHP_EOL;
}
crawl_page("http://hobodave.com", 2);
编辑:我修复了Tatu版本的一些错误(现在使用相对URL).
编辑:我添加了一些新功能,阻止它两次跟踪相同的URL.
编辑:现在回显输出到STDOUT,以便您可以将其重定向到您想要的任何文件
编辑:修正了乔治在答案中指出的错误.相对网址将不再附加到网址路径的末尾,而是覆盖它.感谢George为此.请注意,George的答案不包括以下任何一项:https,user,pass或port.如果您加载了http PECL扩展,则可以使用http_build_url完成此操作.否则,我必须使用parse_url手动粘合在一起.再次感谢乔治.
这里我的实现基于上面的例子/答案.
它是基于阶级的
使用卷曲
支持HTTP身份验证
跳过不属于基本域的URL
返回每页的Http标头响应代码
每页的返回时间
CRAWL CLASS:
class crawler
{
protected $_url;
protected $_depth;
protected $_host;
protected $_useHttpAuth = false;
protected $_user;
protected $_pass;
protected $_seen = array();
protected $_filter = array();
public function __construct($url, $depth = 5)
{
$this->_url = $url;
$this->_depth = $depth;
$parse = parse_url($url);
$this->_host = $parse['host'];
}
protected function _processAnchors($content, $url, $depth)
{
$dom = new DOMDocument('1.0');
@$dom->loadHTML($content);
$anchors = $dom->getElementsByTagName('a');
foreach ($anchors as $element) {
$href = $element->getAttribute('href');
if (0 !== strpos($href, 'http')) {
$path = '/' . ltrim($href, '/');
if (extension_loaded('http')) {
$href = http_build_url($url, array('path' => $path));
} else {
$parts = parse_url($url);
$href = $parts['scheme'] . '://';
if (isset($parts['user']) && isset($parts['pass'])) {
$href .= $parts['user'] . ':' . $parts['pass'] . '@';
}
$href .= $parts['host'];
if (isset($parts['port'])) {
$href .= ':' . $parts['port'];
}
$href .= $path;
}
}
// Crawl only link that belongs to the start domain
$this->crawl_page($href, $depth - 1);
}
}
protected function _getContent($url)
{
$handle = curl_init($url);
if ($this->_useHttpAuth) {
curl_setopt($handle, CURLOPT_HTTPAUTH, CURLAUTH_ANY);
curl_setopt($handle, CURLOPT_USERPWD, $this->_user . ":" . $this->_pass);
}
// follows 302 redirect, creates problem wiht authentication
// curl_setopt($handle, CURLOPT_FOLLOWLOCATION, TRUE);
// return the content
curl_setopt($handle, CURLOPT_RETURNTRANSFER, TRUE);
/* Get the HTML or whatever is linked in $url. */
$response = curl_exec($handle);
// response total time
$time = curl_getinfo($handle, CURLINFO_TOTAL_TIME);
/* Check for 404 (file not found). */
$httpCode = curl_getinfo($handle, CURLINFO_HTTP_CODE);
curl_close($handle);
return array($response, $httpCode, $time);
}
protected function _printResult($url, $depth, $httpcode, $time)
{
ob_end_flush();
$currentDepth = $this->_depth - $depth;
$count = count($this->_seen);
echo "N::$count,CODE::$httpcode,TIME::$time,DEPTH::$currentDepth URL::$url
";
ob_start();
flush();
}
protected function isValid($url, $depth)
{
if (strpos($url, $this->_host) === false
|| $depth === 0
|| isset($this->_seen[$url])
) {
return false;
}
foreach ($this->_filter as $excludePath) {
if (strpos($url, $excludePath) !== false) {
return false;
}
}
return true;
}
public function crawl_page($url, $depth)
{
if (!$this->isValid($url, $depth)) {
return;
}
// add to the seen URL
$this->_seen[$url] = true;
// get Content and Return Code
list($content, $httpcode, $time) = $this->_getContent($url);
// print Result for current Page
$this->_printResult($url, $depth, $httpcode, $time);
// process subPages
$this->_processAnchors($content, $url, $depth);
}
public function setHttpAuth($user, $pass)
{
$this->_useHttpAuth = true;
$this->_user = $user;
$this->_pass = $pass;
}
public function addFilterPath($path)
{
$this->_filter[] = $path;
}
public function run()
{
$this->crawl_page($this->_url, $this->_depth);
}
}
用法:
// USAGE
$startURL = 'http://YOUR_URL/';
$depth = 6;
$username = 'YOURUSER';
$password = 'YOURPASS';
$crawler = new crawler($startURL, $depth);
$crawler->setHttpAuth($username, $password);
// Exclude path with the following structure to be processed
$crawler->addFilterPath('customer/account/login/referer');
$crawler->run();
看看PHP Crawler
http://sourceforge.net/projects/php-crawler/
看看它是否有帮助.
以它最简单的形式:
function crawl_page($url, $depth = 5) {
if($depth > 0) {
$html = file_get_contents($url);
preg_match_all('~~', $html, $matches);
foreach($matches[1] as $newurl) {
crawl_page($newurl, $depth - 1);
}
file_put_contents('results.txt', $newurl."\n\n".$html."\n\n", FILE_APPEND);
}
}
crawl_page('http://www.domain.com/index.php', 5);
该函数将从页面获取内容,然后抓取所有找到的链接并将内容保存到"results.txt".函数接受第二个参数depth,它定义了应该遵循链接的时间.如果您只想解析给定页面中的链接,请在那里传递1.
当可以使用wget时，为什么要为此使用PHP ，例如
wget -r -l 1 http://www.example.com
有关如何解析内容的信息，请参见解析HTML并使用search函数作为示例的最佳方法。之前已经多次回答过如何解析HTML的问题。
通过对hobodave代码的一些小改动,这里有一个可用于抓取页面的代码片段.这需要在服务器中启用curl扩展.
");
preg_match_all("/]*?href[\s]?=[\s\"\']+"."(.*?)[\"\']+.*?>"."([^<]+|.*?)?<\/a>/", $stripped_file, $matches, PREG_SET_ORDER );
foreach($matches as $match){
$href = $match[1];
if (0 !== strpos($href, 'http')) {
$path = '/' . ltrim($href, '/');
if (extension_loaded('http')) {
$href = http_build_url($href , array('path' => $path));
} else {
$parts = parse_url($href);
$href = $parts['scheme'] . '://';
if (isset($parts['user']) && isset($parts['pass'])) {
$href .= $parts['user'] . ':' . $parts['pass'] . '@';
}
$href .= $parts['host'];
if (isset($parts['port'])) {
$href .= ':' . $parts['port'];
}
$href .= $path;
}
}
crawl_page($href, $depth - 1);
}
}
echo "Crawled {$href}";
}
crawl_page("http://www.sitename.com/",3);
?>
我在此爬虫脚本教程中解释了本教程
京公网安备 11010802040832号 | 京ICP备19059560号-6 