Because I need to do a function,implement get page connection put into arrayIn Train of thought: 1, get static + without parameter: HTM HTML asp php jsp CGI A, including absolute path processing: direct access Preg_match_all ()? b, which contains the relative path, the path gets the processing parameters: Depending on the situation (. Or.. ) processing to get an absolute path 2, get the parameter: 3, after filtering: selected some can read the suffix such as asp,php,html, etc. The connection is repeated for deletion. 4, run code directly on the laggards forum» website Building Column The first page of the connection is taken down to the array $e, $e[o][0] is the first connection; $e[o][1] is the 2nd
Code: |
|
? $e=clinchgeturl ("http://im286.com/forumdisplay.php?fid=1"); Var_dump ($e); function Clinchgeturl ($url) { $url= "http://127.0.0.1/1.htm"; $rootpath= "http://fsrootpathfsfsf/yyyyyy/"; Var_dump ($RRR); if (eregi) (' (.) *[\.] (.) * ', $url)) { $roopath=split ("\/", $url); $rootpath= "http://". $roopath[2]. " /"; $nnn=count ($roopath) -1;for ($yu=3;$yu<$nnn;$yu++) {$rootpath.=$roopath[$yu]. " /";} Var_dump ($rootpath); http:, ', 127.0.0.1,xnml,index.php } Else{$rootpath=$url;//var_dump ($rootpath); } if (Isset ($url)) { echo "$url has the following walks to connect:<br>"; $fcontents = file ($url); while (list (, $line) =each ($fcontents)) { while (Eregi (href[[:space:]]*=[[:space:]]*)? [ [: Alnum:]:@/._-]+[\?]? [^\ "]*"] ", $line,$regs)") { $REGS[1] = eregi_replace (' (href[[:space:]]*=[[:space:]]*\ "?) ([[: alnum:]:@/._-]+) (\ "?) '," \\2 ", $regs[1]); $REGS[1] = eregi_replace (' (href[[:space:]]*=[[:space:]]*[\ "]?) ([: Alnum:]:@/._-]+[\?]? [^\ "]*" (\.*) [^\] \/]* ([\ "]?) '," \\2 ", $regs[1]); if (!eregi (' ^http:\/\/', $regs[1])) { if (eregi (' ^\.\. ', $regs[1])) { $roopath=eregi_replace (' (http:\/\/)? ( [[: alnum:]:@/._-]+) [[: alnum:]+] (\.*) [[: alnum:]+] ', "http:\/\/\\2", $url); $roopath=split ("\/", $rootpath); $rootpath= "http://". $roopath[2]. " /"; echo "This is fundamental d:". \ n "; $nnn=count ($roopath) -1;for ($yu=3;$yu<$nnn;$yu++) {$rootpath.=$roopath[$yu]. " /";} Var_dump ($rootpath); if (eregi (' ^\.\.[ \/[:alnum:]] ', $regs[1 ') { echo "This is. /directory/: "." \ n "; $regs[1]= ". /xx/xxxxxx.xx "; $rr=split ("\/", $regs[1]); For ($oooi=1;$oooi<count ($RR); $oooi++) $RRR=$REGS[1]; {$rrr.= "/". $rr[$oooi]; $rrr = Eregi_replace ("^[\.") [\.] [\/] ",", $rrr); //} $regs[1]=$rootpath.$rrr; } }else{ if (eregi (' ^[[:alnum:]] ', $regs[1])) {$regs[1]=$rootpath.$regs[1];} else{$regs[1] = eregi_replace ("^[\/]", ', $regs[1]); $regs[1]=$rootpath.$regs[1]; } } $line = $regs[2]; if (eregi) (' (.) *[\.] (htm|shtm|html|asp|aspx|php|jsp|cgi) (.) * ', $regs[1]) { $OUT[0][]=$REGS[1]; } } } }for ($ouou=0;$ouou<count) ($out[0); $ouou++) { if ($out[0][$ouou]==$out[0][$ouou+1]) { $sameurlsum=1; echo "Sameurlsum=1:"; For ($sameurl=1;$sameurl<count ($out[0]); $sameurl++) { if ($out[0][$ouou+$sameurl]==$out[0][$ouou+$sameurl+1]) {$sameurlsum++;} Else{break;} } For ($p=$ouou;$p<count ($out[0]); $p++) {$out[0][$p]=$out[0][$p+$sameurlsum];} } } $i=0; while ($out[0][++$i]) { Echo $root.$out[0][$i]. " \ r \ n "; $outed[0][$i]=$out[0][$i]; } Unset ($out); $out=$outed; return $out; } ?> |
|
|