/**
* 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"];
}
}
/**
* 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 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][$hash];
// Does the cookie-domain match?
// Tail-matching, see http://curl.haxx.se/rfc/cookie_spec.html:
// A domain attribute of "acme.com" would match host names "anvil.acme.com" as well as "shipping.crate.acme.com"
if ($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;
}
/**
* 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 = db_query("SELECT * FROM {" . $this->table . "} WHERE source_domain = '" . $url_parts["domain"] . "' AND crawler_id = '" . $this->crawler_id . "';");
$rows = $result->fetchAllAssoc('id');
// $rows = $this->conn->query("SELECT * FROM " . $this->table . " WHERE source_domain = '".$url_parts["domain"]."' AND crawler_id = '" . $this->crawler_id . "';")->fetchAllAssoc('id');
// drupal_set_message('<pre>PHPCrawlerD7CookieCache::getCookiesForUrl ' . print_r($rows, 1) . '</pre>');
$cnt = count($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;
}
/**
* 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);
}
}
/**
* 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, $source_url);
}
/**
* Returns/reads the current crawler-status
*
* @return PHPCrawlerStatus The current crawlerstatus as a PHPCrawlerStatus-object
*/
public function getCrawlerStatus()
{
// Get crawler-status from file if crawler is multiprocessed
if ($this->multiprocess_mode == PHPCrawlerMultiProcessModes::MPMODE_CHILDS_EXECUTES_USERCODE) {
$this->crawlerStatus = PHPCrawlerUtils::deserializeFromFile($this->working_directory . "crawlerstatus.tmp");
if ($this->crawlerStatus == null) {
$this->crawlerStatus = new PHPCrawlerStatus();
}
}
return $this->crawlerStatus;
}
/**
* Returns the PHPCrawlerUrlPartsDescriptor-object for the given URL.
*
* @return PHPCrawlerUrlPartsDescriptor
*/
public static function fromURL($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 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[] = $tmp;
return true;
} else {
return false;
}
}
/**
* Adds a rule to the list of rules that decide which URLs found on a page should be ignored by the crawler.
*/
public function addURLFilterRule($regex)
{
$check = PHPCrawlerUtils::checkRegexPattern($regex);
// Check pattern
if ($check == true) {
$this->url_filter_rules[] = trim($regex);
}
return $check;
}
/**
* 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"]);
}
protected function addLinkToCache($link_raw, $link_code, $link_text = "")
{
//PHPCrawlerBenchmark::start("preparing_link_for_cache");
// If liks already was found and processed -> skip this link
if (isset($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
$UrlDescriptor = new PHPCrawlerURLDescriptor($url_rebuild, $link_raw, $link_code, $link_text, $this->SourceUrl->url_rebuild);
// 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");
}
function receivePage($url_to_crawl, $referer_url)
{
// Check if tmp-file was set by the user, otherwise set a default one
if ($this->tmp_file == "") {
$this->tmp_file = uniqid(time()) . ".tmp";
}
// Define some vars
$source_read = "";
$bytes_received = 0;
$stream_to_memory = false;
$stream_to_file = false;
// Split the url to crawl into its elements (host, path, port and stuff)
$url_parts = PHPCrawlerUtils::splitURL($url_to_crawl);
$protocol = $url_parts["protocol"];
$host = $url_parts["host"];
$path = $url_parts["path"];
$query = $url_parts["query"];
$file = $url_parts["file"];
$port = $url_parts["port"];
// If the host was already visited so far
// -> get the ip from our host-ip-array, otherwise
// get the IP and add the entry to the array.
if (isset($this->host_ip_table[$host])) {
$ip = $this->host_ip_table[$host];
} else {
$ip = $this->host_ip_table[$host] = gethostbyname($host);
// Host switched and wasnt "visited" before.
// So read the robots.txt-file for this new host (if wanted)
if ($this->use_robots_txt_files == true) {
$this->robotsTxtHandler->processRobotsTxt($protocol, $host, $port, $this->user_agent_string);
}
}
// Is this URL allowed to be requested by the robots.txt-file of this host?
$url_disallowed = false;
if ($this->use_robots_txt_files == true) {
$host_url = $protocol . $host . ":" . $port;
$url_disallowed = $this->robotsTxtHandler->checkIfUrlDisallowed($url_to_crawl, $host_url);
}
// Check the protocol (http or https) and build the
// host-string for fsockopen
if ($protocol == "https://") {
$host_str = "ssl://" . $ip;
} else {
$host_str = $ip;
}
// normal connect
// Check if an authentication should be send
$authentication = PHPCrawlerUtils::getAuthenticationForURL($this->basic_authentications, $url_to_crawl);
// Error-codes
// 0 - couldnt connect to server / page within timeout-time
// 1 - stopped reading from socket, read-timeout reached BEFORE EOF()
// Open socket-connection
if ($url_disallowed == false) {
$s = @fsockopen($host_str, $port, $e, $t, $this->socket_mean_timeout);
} else {
return false;
// Return false if the URL was completely ignored
}
if ($s == false) {
$error_string = $t;
$error_code = $e;
if ($t == "" && $e == "") {
$error_code = 0;
$error_string = "Couldn't connect to server";
}
} else {
$header_found = false;
// will get true if the header of the page was extracted
// Build header to send
$headerlines_to_send[] = "GET " . $path . $file . $query . " HTTP/1.0\r\n";
$headerlines_to_send[] = "HOST: " . $host . "\r\n";
// Referer
if ($referer_url != "") {
$headerlines_to_send[] = "Referer: {$referer_url}\r\n";
}
// Cookies
if ($this->handle_cookies == true) {
$cookie_string = PHPCrawlerUtils::buildHeaderCookieString($this->cookies, $host);
}
if (isset($cookie_string)) {
$headerlines_to_send[] = "Cookie: " . $cookie_string . "\r\n";
}
// Authentication
if (count($authentication) > 0) {
$auth_string = base64_encode($authentication["username"] . ":" . $authentication["password"]);
$headerlines_to_send[] = "Authorization: Basic " . $auth_string . "\r\n";
}
// Rest of header
$headerlines_to_send[] = "User-Agent: " . str_replace("\n", "", $this->user_agent_string) . "\r\n";
$headerlines_to_send[] = "Connection: close\r\n";
$headerlines_to_send[] = "\r\n";
// Now send the header
for ($x = 0; $x < count($headerlines_to_send); $x++) {
// Send header-line
fputs($s, $headerlines_to_send[$x]);
// Put together lines to $header_send
if (isset($header_send)) {
$header_send .= $headerlines_to_send[$x];
} else {
$header_send = $headerlines_to_send[$x];
}
}
unset($header_lines);
$status = socket_get_status($s);
// Now read from socket
// UNTIL timeout reached OR eof() OR content-type shouldnt be followed
// OR traffic-limit reached or ...
while (!isset($stop)) {
socket_set_timeout($s, $this->socket_read_timeout);
// Read from socket
$line_read = @fgets($s, 1024);
// The @ is to avoid the strange "SSL fatal protocol error"-warning that
// appears in some environments without any reasons
$source_read .= $line_read;
// do this anyway
// If we want the content in tmp-file -> write line to TMP-file
if ($header_found == true && $stream_to_file == true && $line_read) {
unset($check);
$check = @fwrite($fp, $line_read);
if ($check == false) {
$error_code = "2000";
$error_string = "Couldn't write to TMP-file " . $this->tmp_file;
}
}
// Count bytes of the content (not the header)
if ($header_found == true) {
$bytes_received = $bytes_received + strlen($line_read);
}
// Check for traffic limit and stop receiving if reached
if ($this->traffic_limit_complete_page == false && $this->traffic_limit_all > 0) {
if (strlen($source_read) + $this->traffic_all > $this->traffic_limit_all) {
$stop = true;
$received_completly = false;
$page_data["traffic_limit_reached"] = true;
}
}
// Check for pagesize-limit
if ($header_found == true && $bytes_received > $this->pagesize_limit && $this->pagesize_limit > 0) {
$stop = true;
$received_completly = false;
}
// "Cut" Header in seperate var $header and handle it
if ($header_found == false && substr($source_read, -4, 4) == "\r\n\r\n") {
$header = substr($source_read, 0, strlen($source_read) - 2);
$actual_content_type = PHPCrawlerUtils::getHeaderTag("content-type", $header);
$source_read = "";
$header_found = true;
// Get the http-status-code
$http_status_code = PHPCrawlerUtils::getHTTPStatusCode($header);
// Should this content-type be streamed into memory (true/false) ?
$stream_to_memory = PHPCrawlerUtils::decideStreamToMemory($header, $this->receive_to_memory_matches);
// Should this content-type be streamed into tmp-file (true/false) ?
$stream_to_file = PHPCrawlerUtils::decideStreamToTmpFile($header, $this->receive_to_file_matches);
// No ? then open TMP-file for the stream
if ($stream_to_file == true) {
$fp = @fopen($this->tmp_file, "w");
if ($fp == false) {
$error_code = "2000";
$error_string = "Couldn't open TMP-file" . $this->tmp_file;
}
}
// Header found here -> check if source should be followed (content-type)
$follow = PHPCrawlerUtils::decideFollow($header, $this->follow_content_type);
// no ?? then stop with this page !
if ($follow == false) {
$stop = true;
} else {
$received_completly = true;
// just init, may switch later on !
}
// Check if a cookie was send with the header and store it
// (if wanted)
if ($this->handle_cookies == true) {
PHPCrawlerUtils::getCookieData($header, $this->cookies, $host);
}
}
// end cut and handle header
// Get status of socket to check timeout and EOF
$status = socket_get_status($s);
// Now, if the source-buffer is filled or EOF is reached
// -> look for links in the buffer, put the found links into
// array $links_found_in_page and then empty the buffer BUT
// COPY THE LAST FEW BYTES of the old buffer into the new one !
// This has to be done because of links that take more than a single
// line !
// And yes, only makes sense if we dont want to have the whole content
// in memory anyway AND if the content-type is text/html!
if ($header_found == true && $stream_to_memory == false) {
if (strlen($source_read) >= 100000 || $status["eof"] == true) {
if (preg_match("/text\\/html/ i", $actual_content_type)) {
$links_found_in_buffer = PHPCrawlerUtils::findLinks($source_read, $links_found_in_page, $this->aggressive_link_extraction, $this->linktags_to_extract, $page_url_map);
$source_read = substr($source_read, -1500);
}
}
}
// Check timeout
if ($status["timed_out"] == true) {
$error_code = 1000;
// ahem..which int to give ??
$error_string = "socketstream timed out";
$stop = true;
$received_completly = false;
}
// Check eof
if ($status["eof"] == true) {
$stop = true;
}
}
fclose($s);
// close socket
if (isset($fp) && $fp != false) {
fclose($fp);
}
// close tmp file if used
}
// echo "Get page:".($this->getmicrotime() - $start);
// Now, HERE, if the whole content/source was received into memory,
// we are looking for the links in the complete source (faster)
// it only makes sense if content-type is text/html !
if ($stream_to_memory == true) {
unset($links_found_in_page);
if (preg_match("/text\\/html/ i", $actual_content_type)) {
// $start = $this->getmicrotime();
PHPCrawlerUtils::findLinks($source_read, $links_found_in_page, $this->aggressive_link_extraction, $this->linktags_to_extract, $page_url_map);
// echo "Find links:".($this->getmicrotime() - $start);
}
}
// Add the "refering_url" to the array-elements
if (isset($links_found_in_page)) {
for ($x = 0; $x < count($links_found_in_page); $x++) {
$links_found_in_page[$x]["referer_url"] = $url_to_crawl;
}
}
// Page crawled,
// return header, source, followed (true/false) and all we got here
unset($page_data);
if (isset($error_code)) {
$page_data["error_code"] = $error_code;
} else {
$page_data["error_code"] = false;
}
if (isset($error_string)) {
$page_data["error_string"] = $error_string;
} else {
$page_data["error_string"] = false;
}
if (isset($follow)) {
$page_data["received"] =& $follow;
} else {
$page_data["received"] = false;
}
if (isset($received_completly)) {
$page_data["received_completly"] =& $received_completly;
} else {
$page_data["received_completly"] = false;
}
$page_data["received_completely"] =& $page_data["received_completly"];
// Wrote "completely" it wrong in prev. version,
if (isset($bytes_received)) {
$page_data["bytes_received"] = $bytes_received;
} else {
$page_data["bytes_received"] = 0;
}
if (isset($header)) {
$page_data["header"] =& $header;
} else {
$page_data["header"] = false;
}
if (isset($http_status_code)) {
$page_data["http_status_code"] =& $http_status_code;
} else {
$page_data["http_status_code"] = false;
}
if (isset($actual_content_type)) {
$page_data["content_type"] = $actual_content_type;
} else {
$page_data["content_type"] = false;
}
// TMP-file infos and that
$page_data["content_tmp_file"] = $page_data["received_to_file"] = false;
$page_data["source"] = $page_data["content"] = $page_data["received_to_memory"] = false;
if (isset($page_data["received"])) {
if ($stream_to_file == true) {
$page_data["content_tmp_file"] = $this->tmp_file;
$page_data["received_to_file"] = true;
}
if ($stream_to_memory == true) {
$page_data["source"] =& $source_read;
$page_data["content"] =& $source_read;
$page_data["received_to_memory"] = true;
}
}
// Additional infos for the override-function handlePageData()
$page_data["protocol"] = $protocol;
$page_data["port"] = $port;
$page_data["host"] = $host;
$page_data["path"] = $path;
$page_data["file"] = $file;
$page_data["query"] = $query;
$page_data["header_send"] =& $header_send;
$page_data["referer_url"] = $referer_url;
// "Normailzed" URL and referer-URL (f.e. without port if port is 80 and protocol is http)
$page_data["url"] = $url_to_crawl;
// All links found in this page
$page_data["links_found"] =& $links_found_in_page;
// Increase SUM of traffic alltogether this instance received
$this->traffic_all = $this->traffic_all + strlen($page_data["header"]) + $page_data["bytes_received"];
// Set flag if traffic-limit is reached
if ($this->traffic_all > $this->traffic_limit_all && $this->traffic_limit_all != 0) {
$page_data["traffic_limit_reached"] = true;
}
if (!isset($page_data["traffic_limit_reached"])) {
$page_data["traffic_limit_reached"] = false;
}
return $page_data;
}
/**
* 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);
}
function addBasicAuthentication($expression, $username, $password)
{
$this->initCrawler();
$check = PHPCrawlerUtils::checkExpressionPattern($expression);
// Check pattern
if ($check == true) {
$c = count($this->pageRequest->basic_authentications);
$this->pageRequest->basic_authentications[$c]["match"] = $expression;
$this->pageRequest->basic_authentications[$c]["username"] = $username;
$this->pageRequest->basic_authentications[$c]["password"] = $password;
return true;
} else {
return false;
}
}
/**
* Returns the Robots.txt-URL related to the given URL
*
* @param PHPCrawlerURLDescriptor $Url The URL as PHPCrawlerURLDescriptor-object
* @return PHPCrawlerURLDescriptor Url of the related to the passed URL.
*/
public static function getRobotsTxtURL(PHPCrawlerURLDescriptor $Url)
{
$url_parts = PHPCrawlerUtils::splitURL($Url->url_rebuild);
$robots_txt_url = $url_parts["protocol"] . $url_parts["host"] . ":" . $url_parts["port"] . "/robots.txt";
return new PHPCrawlerURLDescriptor($robots_txt_url);
}
/**
* Adds a rule to the list of rules that decide in what kind of documents the crawler
* should search for links in (regarding their content-type)
*
* By default the crawler ONLY searches for links in documents of type "text/html".
* Use this method to add one or more other content-types the crawler should check for links.
*
* Example:
* <code>
* $crawler->addLinkSearchContentType("#text/css# i");
* $crawler->addLinkSearchContentType("#text/xml# i");
* </code>
* These rules let the crawler search for links in HTML-, CSS- ans XML-documents.
*
* <b>Please note:</b> It is NOT recommended to let the crawler checkfor links in EVERY document-
* type! This could slow down the crawling-process dramatically (e.g. if the crawler receives large
* binary-files like images and tries to find links in them).
*
* @param string $regex Regular-expression defining the rule
* @return bool TRUE if the rule was successfully added
*/
function addLinkSearchContentType($regex)
{
$this->initCrawler();
$check = PHPCrawlerUtils::checkExpressionPattern($regex);
// Check pattern
if ($check == true) {
$this->pageRequest->linksearch_content_types[] = trim($regex);
}
return $check;
}
function buidlNonFollowMatches($applying_lines, $base_url)
{
// First, get all "Disallow:"-pathes
$disallow_pathes = array();
for ($x = 0; $x < count($applying_lines); $x++) {
if (preg_match("#^Disallow:# i", $applying_lines[$x])) {
preg_match("#^Disallow:[ ]*(.*)#", $applying_lines[$x], $match);
$disallow_pathes[] = trim($match[1]);
}
}
// Works like this:
// The base-url is http://www.foo.com.
// The driective says: "Disallow: /bla/"
// This means: The nonFollowMatch is "#^http://www\.foo\.com/bla/#"
$normalized_base_url = PHPCrawlerUtils::normalizeURL($base_url);
$non_follow_expressions = array();
for ($x = 0; $x < count($disallow_pathes); $x++) {
// If the disallow-path is empty -> simply ignore it
if ($disallow_pathes[$x] == "") {
continue;
}
$non_follow_path_complpete = $normalized_base_url . substr($disallow_pathes[$x], 1);
// "http://www.foo.com/bla/"
$non_follow_exp = preg_quote($non_follow_path_complpete, "#");
// "http://www\.foo\.com/bla/"
$non_follow_exp = "#^" . $non_follow_exp . "#";
// "#^http://www\.foo\.com/bla/#"
$non_follow_expressions[] = $non_follow_exp;
}
return $non_follow_expressions;
}
function buildURL($link, $actual_url, $url_parts_actual = "")
{
// Important: Function has to return a FULL URL, ioncluing
// the port !!
if ($url_parts_actual == "") {
$url_parts_actual = phpcrawlerutils::splitURL($actual_url);
}
// Entities-replacements
$entities = array("'&(quot|#34);'i", "'&(amp|#38);'i", "'&(lt|#60);'i", "'&(gt|#62);'i", "'&(nbsp|#160);'i", "'&(iexcl|#161);'i", "'&(cent|#162);'i", "'&(pound|#163);'i", "'&(copy|#169);'i");
$replace = array("\"", "&", "<", ">", " ", chr(161), chr(162), chr(163), chr(169));
$link = str_replace("\n", "", $link);
$link = str_replace("\r", "", $link);
// Remove "#..." at end, but ONLY at the end,
// not if # is at the beginning !
$link = preg_replace("/^(.{1,})#.{0,}\$/", "\\1", $link);
// Cases
// Strange link like "//foo.htm" -> make it to "http://foo.html"
if (substr($link, 0, 2) == "//") {
$link = "http:" . $link;
$link = phpcrawlerutils::rebuildURL(phpcrawlerutils::splitURL($link));
} elseif (substr($link, 0, 1) == "/") {
$link = $url_parts_actual["protocol"] . $url_parts_actual["host"] . ":" . $url_parts_actual["port"] . $link;
} elseif (substr($link, 0, 2) == "./") {
$link = $url_parts_actual["protocol"] . $url_parts_actual["host"] . ":" . $url_parts_actual["port"] . $url_parts_actual["path"] . substr($link, 2);
} elseif (preg_match("/^[^\\/]{1,}(:\\/\\/)/", $link)) {
if (substr($link, 0, 7) == "http://" || substr($link, 0, 8) == "https://") {
$link = phpcrawlerutils::rebuildURL(phpcrawlerutils::splitURL($link));
} else {
$link = "";
}
// Kick out unsupported protocols
} elseif (preg_match("/^[a-zA-Z]{0,}:[^\\/]{0,1}/", $link)) {
$link = "";
} elseif (substr($link, 0, 3) == "../") {
$new_path = $url_parts_actual["path"];
while (substr($link, 0, 3) == "../") {
$new_path = preg_replace('/\\/[^\\/]{0,}\\/$/', "/", $new_path);
$link = substr($link, 3);
}
$link = $url_parts_actual["protocol"] . $url_parts_actual["host"] . ":" . $url_parts_actual["port"] . $new_path . $link;
} elseif (substr($link, 0, 1) == "#") {
$link = "";
} elseif ($link == "") {
$link = $actual_url;
} else {
$link = $url_parts_actual["protocol"] . $url_parts_actual["host"] . ":" . $url_parts_actual["port"] . $url_parts_actual["path"] . $link;
}
// Now, at least, replace all HTMLENTITIES with normal text !!
// Ie: HTML-Code of the link is: <a href="index.php?x=1&y=2">
// -> Link has to be "index.php?x=1&y=2"
$link = preg_replace($entities, $replace, $link);
$link = rawurldecode($link);
$link = str_replace(" ", "%20", $link);
// "Normalize" URL
$link = PHPCrawlerUtils::normalizeUrl($link);
return $link;
}
/**
* 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;
}
}
/**
* 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 $check;
}
function handleDocumentInfo($DocInfo)
{
echo "<table class=intbl>";
// Loop over the output-array and print info if wanted
@reset($this->output_array);
while (list($key) = @each($this->output_array)) {
if ($key == "requested_url") {
$str = '<a href="' . $DocInfo->url . '" target=blank>' . $DocInfo->url . '</a>';
echo "<tr><td width=130><nobr>Page requested:</nobr></td><td width=470>" . $str . "</td></tr>";
}
if ($key == "http_status_code") {
if ($DocInfo->http_status_code) {
$str = $DocInfo->http_status_code;
} else {
$str = "-";
}
echo "<tr><td>HTTP-Status:</td><td>" . $str . "</td></tr>";
}
if ($key == "content_type") {
if ($DocInfo->content_type) {
$str = $DocInfo->content_type;
} else {
$str = "-";
}
echo "<tr><td>Content-Type:</td><td>" . $str . "</td></tr>";
}
if ($key == "content_size") {
$str = PHPCrawlerUtils::getHeaderValue($DocInfo->header, "content-length");
if (trim($str) == "") {
$str = "??";
}
echo "<tr><td>Content-Size:</td><td >" . $str . " bytes</td></tr>";
}
if ($key == "content_received") {
if ($DocInfo->received == true) {
$str = "Yes";
} else {
$str = "No";
}
echo "<tr><td>Content received:</td><td >" . $str . "</td></tr>";
}
if ($key == "content_received_completely") {
if ($DocInfo->received_completely == true) {
$str = "Yes";
} else {
$str = "No";
}
echo "<tr><td><nobr>Received completely:</nobr></td><td >" . $str . "</td></tr>";
}
if ($key == "bytes_received") {
echo "<tr><td>Bytes received:</td><td>" . $DocInfo->bytes_received . " bytes</td></tr>";
}
if ($key == "referer_url") {
if ($DocInfo->referer_url == "") {
$str = "-";
} else {
$str =& $page_data["referer_url"];
}
echo "<tr><td><nobr>Refering URL</nobr>:</td><td >" . $str . "</td></tr>";
}
if ($key == "refering_linkcode") {
if ($DocInfo->refering_linkcode == "") {
$str = "-";
} else {
$str = htmlentities($DocInfo->refering_linkcode);
$str = str_replace("\n", "<br>", $str);
}
echo "<tr><td valign=top><nobr>Refering linkcode:</nobr></td><td >" . $str . "</td></tr>";
}
if ($key == "refering_link_raw") {
if ($DocInfo->refering_link_raw == "") {
$str = "-";
} else {
$str = $DocInfo->refering_link_raw;
}
echo "<tr><td><nobr>Refering Link RAW: </nobr></td><td >" . $str . "</td></tr>";
}
if ($key == "refering_linktext") {
if ($DocInfo->refering_linktext == "") {
$str = "-";
} else {
$str = $DocInfo->refering_linktext;
$str = htmlentities($str);
$str = str_replace("\n", "<br>", $str);
}
echo "<tr><td valign=top><nobr>Refering linktext</nobr>:</td><td >" . $str . "</td></tr>";
}
if ($key == "header_send") {
if ($DocInfo->header_send) {
$str = str_replace("\n", "<br>", trim($DocInfo->header_send));
} else {
$str = "-";
}
echo "<tr><td valign=top>Send header:</td><td >" . $str . "</td></tr>";
}
if ($key == "header") {
if ($DocInfo->header) {
$str = str_replace("\n", "<br>", trim($DocInfo->header));
} else {
$str = "-";
}
echo "<tr><td valign=top>Received header:</td><td >" . $str . "</td></tr>";
}
if ($key == "nr_found_links") {
$str = count($DocInfo->links_found);
echo "<tr><td valign=top>Links found:</td><td >" . $str . "</td></tr>";
}
if ($key == "all_found_links") {
echo "<tr><td valign=top>List of found links:</td>";
echo "<td>";
for ($x = 0; $x < count($DocInfo->links_found_url_descriptors); $x++) {
echo $DocInfo->links_found_url_descriptors[$x]->url_rebuild . "<br>";
}
if (count($DocInfo->links_found_url_descriptors) == 0) {
echo "-";
}
echo "</td>";
echo "</tr>";
}
if ($key == "received_to_file") {
if ($DocInfo->received_to_file) {
$str = "Yes";
} else {
$str = "No";
}
echo "<tr><td valign=top>Received to TMP-file:</td><td >" . $str . "</td></tr>";
}
if ($key == "tmpfile_name_size") {
if ($DocInfo->content_tmp_file) {
$str = $DocInfo->content_tmp_file . " (" . filesize($DocInfo->content_tmp_file) . " bytes)";
} else {
$str = "-";
}
echo "<tr><td valign=top>Content TMP-file:</td><td >" . $str . "</td></tr>";
}
if ($key == "received_to_memory") {
if ($DocInfo->received_to_memory) {
$str = "Yes";
} else {
$str = "No";
}
echo "<tr><td valign=top>Received to memory:</td><td >" . $str . "</td></tr>";
}
if ($key == "memory_content_size") {
echo "<tr><td valign=top>Memory-content-size:</td><td >" . strlen($DocInfo->source) . " bytes</td></tr>";
}
}
// Output error if theres one
if ($DocInfo->error_occured) {
echo "<tr>\n <td class=red>Error:</td>\n <td class=red>" . $DocInfo->error_string . "</td>\n </tr>";
}
echo "</table> <br>";
$this->flushOutput();
}
/**
* 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;
}
