/**
* @brief Search for chached embeddable data of an url otherwise fetch it
- *
+ *
* @param type $url The url of the page which should be scraped
* @param type $no_guessing If true the parse doens't search for
* preview pictures
* @param type $do_oembed The false option is used by the function fetch_oembed()
* to avoid endless loops
- *
+ *
* @return array which contains needed data for embedding
* string 'url' => The url of the parsed page
* string 'type' => Content type
* if $no_geuessing = false
* array'images' = Array of preview pictures
* string 'keywords' => The tags which belong to the content
- *
+ *
* @see ParseUrl::getSiteinfo() for more information about scraping
- * embeddable content
+ * embeddable content
*/
public static function getSiteinfoCached($url, $no_guessing = false, $do_oembed = true) {
}
/**
* @brief Parse a page for embeddable content information
- *
+ *
* This method parses to url for meta data which can be used to embed
* the content. If available it prioritizes Open Graph meta tags.
* If this is not available it uses the twitter cards meta tags.
* As fallback it uses standard html elements with meta informations
* like \<title\>Awesome Title\</title\> or
* \<meta name="description" content="An awesome description"\>
- *
+ *
* @param type $url The url of the page which should be scraped
* @param type $no_guessing If true the parse doens't search for
* preview pictures
* @param type $do_oembed The false option is used by the function fetch_oembed()
* to avoid endless loops
* @param type $count Internal counter to avoid endless loops
- *
+ *
* @return array which contains needed data for embedding
* string 'url' => The url of the parsed page
* string 'type' => Content type
* if $no_geuessing = false
* array'images' = Array of preview pictures
* string 'keywords' => The tags which belong to the content
- *
+ *
* @todo https://developers.google.com/+/plugins/snippet/
* @verbatim
* <meta itemprop="name" content="Awesome title">
* <meta itemprop="description" content="An awesome description">
* <meta itemprop="image" content="http://maple.libertreeproject.org/images/tree-icon.png">
- *
+ *
* <body itemscope itemtype="http://schema.org/Product">
* <h1 itemprop="name">Shiny Trinket</h1>
* <img itemprop="image" src="{image-url}" />
/**
* @brief Convert tags from CSV to an array
- *
+ *
* @param string $string Tags
* @return array with formatted Hashtags
*/
/**
* @brief Add a hasht sign to a string
- *
+ *
* This method is used as callback function
- *
+ *
* @param string $tag The pure tag name
* @param int $k Counter for internal use
*/
/**
* @brief Add a scheme to an url
- *
+ *
* The src attribute of some html elements (e.g. images)
* can miss the scheme so we need to add the correct
* scheme
- *
+ *
* @param string $url The url which possibly does have
* a missing scheme (a link to an image)
* @param string $scheme The url with a correct scheme
* (e.g. the url from the webpage which does contain the image)
- *
+ *
* @return string The url with a scheme
*/
private static function completeUrl($url, $scheme) {
/**
* @brief Curl wrapper
- *
+ *
* If binary flag is true, return binary results.
* Set the cookiejar argument to a string (e.g. "/tmp/friendica-cookies.txt")
* to preserve cookies from one request to the next.
- *
+ *
* @param string $url URL to fetch
* @param boolean $binary default false
* TRUE if asked to return binary results (file download)
* @param integer $timeout Timeout in seconds, default system config value or 60 seconds
* @param string $accept_content supply Accept: header with 'accept_content' as the value
* @param string $cookiejar Path to cookie jar file
- *
+ *
* @return string The fetched content
*/
function fetch_url($url,$binary = false, &$redirects = 0, $timeout = 0, $accept_content=Null, $cookiejar = 0) {
/**
* @brief Post request to $url
- *
+ *
* @param string $url URL to post
* @param mixed $params
* @param string $headers HTTP headers
* @param integer $redirects Recursion counter for internal use - default = 0
* @param integer $timeout The timeout in seconds, default system config value or 60 seconds
- *
+ *
* @return string The content
*/
function post_url($url,$params, $headers = null, &$redirects = 0, $timeout = 0) {
/**
* @brief Check URL to se if ts's real
- *
+ *
* Take a URL from the wild, prepend http:// if necessary
* and check DNS to see if it's real (or check if is a valid IP address)
- *
+ *
* @param string $url The URL to be validated
* @return boolean True if it's a valid URL, fals if something wrong with it
*/
/**
* @brief Checks that email is an actual resolvable internet address
- *
+ *
* @param string $addr The email address
* @return boolean True if it's a valid email address, false if it's not
*/
/**
* @brief Check if URL is allowed
- *
+ *
* Check $url against our list of allowed sites,
* wildcards allowed. If allowed_sites is unset return true;
- *
+ *
* @param string $url URL which get tested
* @return boolean True if url is allowed otherwise return false
*/
/**
* @brief Check if email address is allowed to register here.
- *
+ *
* Compare against our list (wildcards allowed).
- *
+ *
* @param type $email
* @return boolean False if not allowed, true if allowed
* or if allowed list is not configured
/**
* @brief Encodes content to json
- *
+ *
* This function encodes an array to json format
* and adds an application/json HTTP header to the output.
* After finishing the process is getting killed.
projects / friendica.git / commitdiff