A php text collection class-php Tutorial

A php text collection class

$ C = new Collection (); $ C-> url = 'http: // bbs.it-home.org/subject_search? Cat = 1001 & search_text = % E5 % B9 % B4 % E8 % BD % BB % E4 % BA '; $ C-> startFlag =' '; $ C-> endFlag =' '; $ C-> init (); $ C-> regExp = "| (.*) (.*) | Uis "; $ C-> parse (); Print_rr ($ C-> result ); */ Php text collection files: <% /** Module name: php text collection class **/ Class Collection { // Public portal Var $ url; // url to be analyzed Var $ content; // read content Var $ regExp; // the regular expression of the part to be obtained Var $ codeFrom; // encoding of the original text Var $ codeTo; // encoding to be converted Var $ timeout; // Collection wait time Var $ startFlag; // The marker that is collected from the document is 0 by default. when collecting entries, only text blocks between $ startFlag and $ endFlag are searched and collected. Var $ endFlag; // the marker for collecting end-of-article data. by default, only text blocks between $ startFlag and $ endFlag are searched and collected at the end of the article. Var $ block; // text block between $ startFlag and $ endFlag // Export private Var $ result; // output result // Initialize the collector Function init (){ If (empty ($ url )) $ This-> getFile (); $ This-> convertEncoding (); } // Collect required content Function parse (){ $ This-> getBlock (); Preg_match_all ($ this-> regExp, $ this-> block, $ this-> result, PREG_SET_ORDER ); Return $ this-> block; } // Handle errors Function error ($ msg ){ Echo $ msg; } // If the remote webpage is successfully read, the system returns the object; if the remote webpage fails, the system returns false. Function getFile (){ $ Datalines = @ file ($ this-> url ); If (! $ Datalines ){ $ This-> error ("can't read the url:". $ this-> url ); Return false; } Else { $ Importdata = implode ('', $ datalines ); $ Importdata = str_replace (array ("\ r \ n", "\ r"), "\ n", $ importdata ); $ This-> content = $ importdata; } } // Obtain the required text block Function getBlock (){ If (! Empty ($ this-> startFlag )) $ This-> block = substr ($ this-> content, strpos ($ this-> content, $ this-> startFlag )); If (! Empty ($ this-> endFlag )) $ This-> block = substr ($ this-> block, 0, strpos ($ this-> block, $ this-> endFlag )); } // Content encoding conversion Function convertEncoding (){ If (! Empty ($ this-> codeTo )) $ This-> codeFrom = mb_detect_encoding ($ this-> content ); // If a conversion scheme is specified, the conversion is executed. If (! Empty ($ this-> codeTo )) $ This-> content = mb_convert_encoding ($ this-> content, $ this-> codeTo, $ this-> codeFrom) or $ this-> error ("can't convert Encoding "); } } // End of class ?>