/**
* Returns all cookies from the cache that are adressed to the given URL
*
* @param string $target_url The target-URL
* @return array Numeric array conatining all matching cookies as PHPCrawlerCookieDescriptor-objects
*/
public function getCookiesForUrl($target_url)
{
$url_parts = PHPCrawlerUtils::splitURL($target_url);
$target_domain = $url_parts["domain"];
// e.g. acme.com
$return_cookies = array();
// Iterate over all cookies of this domain
@reset($this->cookies[$target_domain]);
while (list($hash) = @each($this->cookies[$target_domain])) {
$Cookie = $this->cookies[$target_domain][$hash];
// Does the cookie-domain match?
// Tail-matching, see http://curl.haxx.se/rfc/cookie_spec.html:
// A domain attribute of "acme.com" would match host names "anvil.acme.com" as well as "shipping.crate.acme.com"
// Seems like ".acme.com" should also match "anvil.acme.com", so just remove the dot
$Cookie->domain = preg_replace("#^.#", "", $Cookie->domain);
if ($Cookie->domain == $url_parts["host"] || preg_match("#" . preg_quote($Cookie->domain) . "\$#", $url_parts["host"])) {
// Does the path match?
if (preg_match("#^" . preg_quote($Cookie->path) . "#", $url_parts["path"])) {
$return_cookies[$Cookie->name] = $Cookie;
// Use cookie-name as index to avoid double-cookies
}
}
}
// Convert to numeric array
$return_cookies = array_values($return_cookies);
return $return_cookies;
}
/**
* Initiates an new PHPCrawlerResponseHeader.
*
* @param string $header_string A complete response-header as it was send by the server
* @param string $source_url The URL of the website the header was recevied from.
* @internal
*/
public function __construct($header_string, $source_url)
{
$this->header_raw = $header_string;
$this->source_url = $source_url;
$this->http_status_code = PHPCrawlerUtils::getHTTPStatusCode($header_string);
$this->content_type = strtolower(PHPCrawlerUtils::getHeaderValue($header_string, "content-type"));
$this->content_length = strtolower(PHPCrawlerUtils::getHeaderValue($header_string, "content-length"));
$this->cookies = PHPCrawlerUtils::getCookiesFromHeader($header_string, $source_url);
$this->transfer_encoding = strtolower(PHPCrawlerUtils::getHeaderValue($header_string, "transfer-encoding"));
$this->content_encoding = strtolower(PHPCrawlerUtils::getHeaderValue($header_string, "content-encoding"));
}
/**
* Returns the PHPCrawlerUrlPartsDescriptor-object for the given URL.
*
* @return PHPCrawlerUrlPartsDescriptor
*/
public static function fromURL($url)
{
$parts = PHPCrawlerUtils::splitURL($url);
$tmp = new PHPCrawlerUrlPartsDescriptor();
$tmp->protocol = $parts["protocol"];
$tmp->host = $parts["host"];
$tmp->path = $parts["path"];
$tmp->file = $parts["file"];
$tmp->domain = $parts["domain"];
$tmp->port = $parts["port"];
$tmp->auth_username = $parts["auth_username"];
$tmp->auth_password = $parts["auth_password"];
return $tmp;
}
/**
* Adds a rule to the list of rules that decide what kind of documents should get
* checked for links in (regarding their content-type)
*
* @param string $regex Regular-expression defining the rule
* @return bool TRUE if the rule was successfully added
*/
public function addLinkSearchContentType($regex)
{
$check = PHPCrawlerUtils::checkRegexPattern($regex);
// Check pattern
if ($check == true) {
$this->linksearch_content_types[] = trim($regex);
}
return $check;
}
/**
* Returns all cookies from the cache that are adressed to the given URL
*
* @param string $target_url The target-URL
* @return array Numeric array conatining all matching cookies as PHPCrawlerCookieDescriptor-objects
*/
public function getCookiesForUrl($target_url)
{
PHPCrawlerBenchmark::start("getting_cookies_from_cache");
$url_parts = PHPCrawlerUtils::splitURL($target_url);
$return_cookies = array();
$Result = $this->PDO->query("SELECT * FROM cookies WHERE source_domain = '" . $url_parts["domain"] . "';");
$rows = $Result->fetchAll(PDO::FETCH_ASSOC);
$Result->closeCursor();
$cnt = count($rows);
for ($x = 0; $x < $cnt; $x++) {
// Does the cookie-domain match?
// Tail-matching, see http://curl.haxx.se/rfc/cookie_spec.html:
// A domain attribute of "acme.com" would match host names "anvil.acme.com" as well as "shipping.crate.acme.com"
if ($rows[$x]["domain"] == $url_parts["host"] || preg_match("#" . preg_quote($rows[$x]["domain"]) . "\$#", $url_parts["host"])) {
// Does the path match?
if (preg_match("#^" . preg_quote($rows[$x]["path"]) . "#", $url_parts["path"])) {
$Cookie = new PHPCrawlerCookieDescriptor($rows[$x]["source_url"], $rows[$x]["name"], $rows[$x]["value"], $rows[$x]["expires"], $rows[$x]["path"], $rows[$x]["domain"]);
$return_cookies[$Cookie->name] = $Cookie;
// Use cookie-name as index to avoid double-cookies
}
}
}
// Convert to numeric array
$return_cookies = array_values($return_cookies);
PHPCrawlerBenchmark::stop("getting_cookies_from_cache");
return $return_cookies;
}
/**
* Returns the default Robots.txt-URL related to the given URL
*
* @param string $url The URL
* @return string Url of the related robots.txt file
*/
public static function getRobotsTxtURL($url)
{
$url_parts = PHPCrawlerUtils::splitURL($url);
$robots_txt_url = $url_parts["protocol"] . $url_parts["host"] . ":" . $url_parts["port"] . "/robots.txt";
return $robots_txt_url;
}
/**
* Checks whether the hostname of the given URL is already cached
*
* @param PHPCrawlerURLDescriptor $URL The URL
* @return bool
*/
public function urlHostInCache(PHPCrawlerURLDescriptor $URL)
{
$url_parts = PHPCrawlerUtils::splitURL($URL->url_rebuild);
return $this->hostInCache($url_parts["host"]);
}
/**
* Adds a basic-authentication (username and password) to the list of authentications that will be send
* with requests.
*
* @param string $url_regex Regular expression defining the URL(s) the authentication should be send to.
* @param string $username The username
* @param string $password The password
*
* @return bool
*/
public function addBasicAuthentication($url_regex, $username, $password)
{
// Check regex
$regex_okay = PHPCrawlerUtils::checkRegexPattern($url_regex);
if ($regex_okay == true) {
// Add authentication to basic_authentications-array
$tmp = array();
$tmp["url_regex"] = $url_regex;
$tmp["username"] = $username;
$tmp["password"] = $password;
$this->basic_authentications[] = $tmp;
return true;
} else {
return false;
}
}
/**
* Adds a Link-Priority-Level
*
* @param string $regex
* @param int $level
*/
public function addLinkPriority($regex, $level)
{
$c = count($this->url_priorities);
$this->url_priorities[$c]["match"] = trim($regex);
$this->url_priorities[$c]["level"] = trim($level);
// Sort url-priortie-array so that high priority-levels come firts.
PHPCrawlerUtils::sort2dArray($this->url_priorities, "level", SORT_DESC);
}
/**
* Adds a link to the LinkFinder-internal link-cache
*
* @param string $link_raw The link like it was found
* @param string $link_code The html-code of the link like it was found (i.e. <a href="the_link.html">Link</a>)
* @param string $link_text The linktext like it was found
* @param bool $is_redirect_url Flag indicatin whether the found URL is target of an HTTP-redirect
*/
protected function addLinkToCache($link_raw, $link_code, $link_text = "", $is_redirect_url = false)
{
//PHPCrawlerBenchmark::start("preparing_link_for_cache");
// If liks already was found and processed -> skip this link
if (isset($this->found_links_map[$link_raw])) {
return;
}
// Rebuild URL from link
$url_rebuild = PHPCrawlerUtils::buildURLFromLink($link_raw, $this->baseUrlParts);
// If link coulnd't be rebuild
if ($url_rebuild == null) {
return;
}
// Create an PHPCrawlerURLDescriptor-object with URL-data
$url_link_depth = $this->SourceUrl->url_link_depth + 1;
$UrlDescriptor = new PHPCrawlerURLDescriptor($url_rebuild, $link_raw, $link_code, $link_text, $this->SourceUrl->url_rebuild, $url_link_depth);
// Is redirect-URL?
if ($is_redirect_url == true) {
$UrlDescriptor->is_redirect_url = true;
}
// Add the PHPCrawlerURLDescriptor-object to LinkCache
$this->LinkCache->addURL($UrlDescriptor);
// Add the PHPCrawlerURLDescriptor-object to found-links-array
$map_key = $link_raw;
$this->found_links_map[$map_key] = true;
//PHPCrawlerBenchmark::stop("preparing_link_for_cache");
}
/**
* Adds a regular expression togehter with a priority-level to the list of rules that decide what links should be prefered.
*
* Links/URLs that match an expression with a high priority-level will be followed before links with a lower level.
* All links that don't match with any of the given rules will get the level 0 (lowest level) automatically.
*
* The level can be any positive integer.
*
* <b>Example:</b>
*
* Telling the crawler to follow links that contain the string "forum" before links that contain ".gif" before all other found links.
* <code>
* $crawler->addLinkPriority("/forum/", 10);
* $cralwer->addLinkPriority("/\.gif/", 5);
* </code>
*
* @param string $regex Regular expression definig the rule
* @param int $level The priority-level
*
* @return bool TRUE if a valid preg-pattern is given as argument and was succsessfully added, otherwise it returns FALSE.
* @section 10 Other settings
*/
function addLinkPriority($regex, $level)
{
$check = PHPCrawlerUtils::checkRegexPattern($regex);
// Check pattern
if ($check == true && preg_match("/^[0-9]*\$/", $level)) {
$c = count($this->link_priority_array);
$this->link_priority_array[$c]["match"] = trim($regex);
$this->link_priority_array[$c]["level"] = trim($level);
return true;
} else {
return false;
}
}
/**
* Sets/writes the current crawler-status
*
* @param PHPCrawlerStatus $crawler_status The status to set
*/
public function setCrawlerStatus(PHPCrawlerStatus $crawler_status)
{
$this->crawlerStatus = $crawler_status;
// Write crawler-status back to file
if ($this->write_status_to_file == true) {
PHPCrawlerUtils::serializeToFile($this->working_directory . "crawlerstatus.tmp", $crawler_status);
}
}
/**
* Adds a rule to the list of rules that decide which URLs found on a page should be ignored by the crawler.
*/
public function addURLFilterRule($regex)
{
$check = PHPCrawlerUtils::checkRegexPattern($regex);
// Check pattern
if ($check == true) {
$this->url_filter_rules[] = trim($regex);
}
return $check;
}
/**
* Initiates a new PHPCrawlerCookieDescriptor-object.
*
* @param string $source_url URL the cookie was send from.
* @param string $name Cookie-name
* @param string $value Cookie-value
* @param string $expires Expire-string, e.g. "Sat, 08-Aug-2020 23:59:08 GMT"
* @param string $path Cookie-path
* @param string $domain Cookie-domain
* @internal
*/
public function __construct($source_url, $name, $value, $expires = null, $path = null, $domain = null)
{
// For cookie-specs, see e.g. http://curl.haxx.se/rfc/cookie_spec.html
$this->name = $name;
$this->value = $value;
$this->expires = $expires;
$this->path = $path;
$this->domain = $domain;
$source_url_parts = PHPCrawlerUtils::splitURL($source_url);
// Source-domain
$this->source_domain = $source_url_parts["domain"];
// Source-URL
$this->source_url = $source_url;
// Send-time
$this->cookie_send_time = PHPCrawlerBenchmark::getmicrotime();
// Expire-date to timetsamp
if ($this->expires != null) {
$this->expire_timestamp = @strtotime($this->expires);
}
// If domain doesn't start with "." -> add it (see RFC)
if ($this->domain != null && substr($this->domain, 0, 1) != ".") {
$this->domain = "." . $this->domain;
}
// Comeplete missing values
// If domain no set -> domain is the host of the source-url WITHOUT leading "."! (see RFC)
if ($this->domain == null) {
$this->domain = $source_url_parts["host"];
}
// If path not set
if ($this->path == null) {
$this->path = $source_url_parts["path"];
}
}