Sina News thieves

Sina News stealing 1.html headmetahttp-equivRefreshcontent60METAHTTP-EQUIVPragmaCONTENTno-cachemetahttp-equivContent-Typecontenttexthtml; charset ?????? Title Sina _ news capture program titleheadbodycenterimgalt Sina News thieves s Sina News thieves 1.






Sina _ news capture program




$ Host = "127.0.0.1"; // MYSQL host name
$ Namesql = "???? "; // MYSQL User name
$ Passsql = "???? "; // MYSQL password
$ Lib = "news"; // database name
$ Table = "news"; // database table name
$ Filename = "http://news.sina.com.cn/news1000/index.shtml"; // capture the news page
$ Keytop = "start of news"; // keyword of start of news
$ Keybottom = "end of news"; // keyword of end of news

$ Conn = mysql_connect ($ host, $ namesql, $ passsql );
Mysql_select_db ($ lib, $ conn );

$ Fp = fopen ($ filename, "r", 1 );
$ Flag = 0; $ add = ""; $ found = 0; $ end = 0; $ I = 0; $ temp [4] = "";
While (! $ End = 1 ){
While (! $ Flag = 1 ){
$ Word = fgetc ($ fp );
$ Add = $ add. $ word;
If ($ word = '<' and strlen ($ add) = 1) {$ flag = 0 ;}
If ($ word = '<' and strlen ($ add )! = 1) {$ flag = 1; $ add = substr ($ add, 0, strlen ($ add)-1 );}
If ($ word = '>') {$ flag = 1 ;}}

If (strchr ($ add, $ keytop) {$ found = 1 ;}
If (strchr ($ add, $ keybottom) {$ found = 0; $ end = 1 ;}
If (strchr ($ add, '<') = True and strchr ($ add, 'href ') = True) or strchr ($ add,' <') = False) and $ found = 1) {$ text [$ I] = $ add; $ I ++ ;}
If ($ word = '<' and $ flag = 1) {$ add = $ word; $ flag = 0;} else {$ add = ""; $ flag = 0 ;}}
Fclose ($ fp );

For ($ I = 1; $ I $ Temp [1] = $ text [$ I + 1]; $ temp [2] = $ text [$ I + 2]; $ temp [3] = $ text [$ I + 3]; $ temp [4] = $ text [$ I + 4];
$ Ins = "select * from $ table where TITLE = '$ temp [3]'";
$ List = mysql_query ($ ins, $ conn );
@ $ Count = mysql_num_rows ($ list );
If ($ count = 0 ){
$ Ins = "insert into $ table (TYPE, URL, TITLE, DATE) values ('$ temp [1]', '$ temp [2]', '$ temp [3]', '$ temp [4]') ";
$ List = mysql_query ($ ins, $ conn );}}
Mysql_close ($ conn );
?>






2. $ Handle = fopen ("http://news.sina.com.cn/news1000/", "r ");
$ Sign = 0;
While (! Feof ($ handle ))
{
$ Message = fgets ($ handle, 512 );
If ($ sign = 1)
{
Print ("$ message ");
}
If (ereg ("news start", $ message, $ result ))
{
$ Sign = 1;
}
Else if (ereg ("end of news", $ message, $ result ))
{
$ Sign = 0;
}
}
Fclose ($ handle );
?>