/**
* 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 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($level);
return true;
} else {
return false;
}
}
/**
* Adds a rule to the list of rules that decide which URLs found on a page should be ignored by the crawler.
*/
public function addURLFilterRule($regex)
{
$check = PHPCrawlerUtils::checkRegexPattern($regex);
// Check pattern
if ($check == true) {
$this->url_filter_rules[] = trim($regex);
}
return $check;
}
/**
* 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;
}
