mikebyrne
-
Posts
780 -
Joined
-
Last visited
Posts posted by mikebyrne
-
-
ahhhhhhhhhhhhhhhhhhhhhhhhhhhhh
I'm now getting
Parse error: parse error in C:\xampp\htdocs\pdf2txt_test.php on line 67
Line 67 is
if (isset($chunk['data'])) { -
I'm getting the error
Parse error: parse error in C:\xampp\htdocs\pdf2txt_test.php on line 14
Line14 is
file_put_contents($path . 'txtfile.txt', pdf2txt($path . 'Athy Register.pdf'));
-
I get the following
File txtfile.txt has been created succesfully and contains
(Can't find txtfile.txt on pc)
-
Thanks
I'm just getting a mountain of nonsense ie
%PDF-1.2 %âãÏÓ 1 0 obj << /Type /Catalog /Pages 2 0 R /PageMode /UseNone /ViewerPreferences << /FitWindow true /PageLayout /SinglePage /NonFullScreenPageMode /UseNone >> >> endobj 2 0 obj << /Type /Pages /Kids [ 8 0 R 30 0 R 40 0 R 44 0 R 48 0 R 52 0 R 56 0 R 60 0 R 64 0 R 68 0 R 72 0 R 76 0 R 80 0 R 84 0 R 88 0 R 92 0 R 96 0 R 100 0 R 104 0 R 108 0 R 112 0 R 116 0 R 120 0 R 124 0 R 128 0 R 132 0 R 136 0 R 140 0 R 144 0 R 148 0 R 152 0 R 156 0 R 160 0 R 164 0 R 168 0 R 172 0 R 176 0 R 180 0 R 184 0 R 188 0 R 192 0 R 196 0 R 200 0 R 204 0 R 208 0 R 212 0 R 216 0 R 220 0 R 224 0 R 228 0 R 232 0 R 236 0 R 240 0 R 244 0 R 248 0 R 252 0 R 256 0 R 260 0 R 264 0 R 268 0 R 272 0 R 276 0 R 280 0 R 284 0 R 288 0 R 292 0 R 296 0 R 300 0 R 304 0 R 308 0 R 312 0 R 316 0 R 320 0 R 324 0 R 328 0 R 332 0 R 336 0 R 340 0 R 344 0 R 348 0 R 352 0 R 368 0 R 372 0 R 376 0 R 380 0 R ] /Count 85 /MediaBox 3 0 R /CropBox 4 0 R >> endobj 3 0 obj [ 0 0 595 841 ] endobj 4 0 obj [ 0 0 595 841 ] endobj 5 0 obj << /Length 1701 /Filter [ /FlateDecode ] >> stream xœÅ™ÛrÛ6†ïù¸«3ã*�€@{åSÓC’¦–ÓÜø¦)‹ .I9£Çë›'@‰±"³S{ÆÚßZ°X`I¤�êßÖˆóàõeò”ÆÉõ›s×Cu±0ø5øÊš‹º¿Ë‹�Cð% ,L„äBaȬȂeðxþJÂPd¯„ÌŠþJ#€¥X9®[Fî*ã—ëàSP<-ˆðP7°²œê;G+F"‹‡iäTÖ*ÊÕe™stÂv¯.Ý4+‚¸Yí©ãàü&@&‚™þ·þQÁq+nòàä:yHë&©@¹WY7eUƒWàæ¯àêFÃy) ¼Fõ¼Pxób5ð†!Ä=/¢ï/X•Uœ€UUæêëf ~J¶�C(@SªÙöÿ‹à΀Bª9C!5 ÊY+²VPÁ”pnV91ì†2Άù”i.Ê¢nÒf“ñö‡]TAõrÂ"ìPèPÕÜÖ͉cQ íQ „|ˆz‘6[ðZÁnŠf&ƒz8L§SŽÍ:¾T·1 ú[šÝË*™ t1Gó¨z«l ㋢îÁ²Ü4뉀cÎúµiDpLqp'Ž x¢ŽRå±Gù¡Ì²´x�—jƒ¨Ò¸Ù¹Jv3Q|EZtK‡BÏ®u³âHRŒ9íçôjS•‰,ÀYe©Ì“¢y&©Ôeð€ãÁs».Œ›Ç’‡‘èçX„l2©ÀÛ2–Y» +ë¬JäT¦9ö6·,¼SØ:¾ŒÞ[Çcú³f½Â³‹¢Å³«¢ƒ5+¡ÇK–…Ÿfãe!ëfÏe—B°K¯VÙ£ß9Z1ËìòKÏø¼9ó-&ÅB÷¨¨ÄÔ·ØÖmTžP¢Ê„× Ö‰¬Ìçf…?J)!¥n£%ŠÜ·‹,Ù¤eq{Rß¾Ú Ê€BsÑ1µ*¸Çµb”£p‰k‚r^nkð^6°Œ×e™©(]—ªÜ€hŠ\å#ÖV!Hzr+f!UF_'ÇSä(±:9b¹sCÎÈáäá¹ÊG¬¢˜÷äVÌB¾/…'ÉɹÊG¬Â¤OK'f!ÇœNN§È1d¨Ã³JÚ%¨³gáV?‡s³ý܆'÷A`¬KNgÏ@ŠÊoHÍhZãä>§aÔ女ç€&ø²’O@kœÜçtB•Ø´µç€F~E²”©ªýþL‹XÕ€ßÕàç²~L™‚½µJO“û˜Vp»dtöÌ\ÝÍ{Ìq©nßÓx>ßËr%Ÿ;pLîS:AQ—†Îž™2x(òÄIc`rŸÒ Œ»töÈ8‡"O1&÷)ˆT!Ü";{äHpr(òÄÙb`rŸÒ FºüsöÈÌ/¹¿†L÷Õ¹7õk¨—³±!E†SUó#a¼FU
-
I've put the print_r after each function but im still getting a blank screen
<?php // Function : pdf2txt() // Arguments : $filename - Filename of the PDF you want to extract // Description : Reads a pdf file, extracts data streams, and manages // their translation to plain text - returning the plain // text at the end // Authors : Jonathan Beckett, 2005-05-02 // : Sven Schuberth, 2007-03-29 $pdftext = pdf2txt('C:\Users\Mike\Desktop\Athy Register.pdf'); function pdf2txt($filename){ $data = getFileData($filename); $s=strpos($data,"%")+1; $version=substr($data,$s,strpos($data,"%",$s)-1); if(substr_count($version,"PDF-1.2")==0) return handleV3($data); else return handleV2($data); } // handles the verson 1.2 function handleV2($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $j = -1; foreach($a_obj as $obj){ $a_filter = getDataArray($obj,"<<",">>"); if ((is_array($a_filter)) && (count($a_filter) > 0)) { $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if ((is_array($a_data)) && (count($a_data) > 0)) { $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); } } } // decode the chunks foreach($a_chunks as $chunk){ // look at each chunk and decide how to decode it - by looking at the contents of the filter $a_filter = split("/",$chunk["filter"]); if (isset($chunk['data'])) { // look at the filter to find out which encoding has been used if (substr($chunk["filter"],"FlateDecode")!==false){ $data =@ gzuncompress($chunk["data"]); if (trim($data)!=""){ $result_data .= ps2txt($data); } else { //$result_data .= "x"; } } } } if (isset($result_data)) { return $result_data; } else { return false; } } //handles versions >1.2 function handleV3($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $result_data=""; foreach($a_obj as $obj){ //check if it a string if(substr_count($obj,"/GS1")>0){ //the strings are between ( and ) preg_match_all("|\((.*?)\)|",$obj,$field,PREG_SET_ORDER); if(is_array($field)) foreach($field as $data) $result_data.=$data[1]; } } return $result_data; print_r ($a_result); } function ps2txt($ps_data){ $result = ""; $a_data = getDataArray($ps_data,"[","]"); if (is_array($a_data)){ foreach ($a_data as $ps_text){ $a_text = getDataArray($ps_text,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } } else { // the data may just be in raw format (outside of [] tags) $a_text = getDataArray($ps_data,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } return $result; print_r ($result); } function getFileData($filename){ $handle = fopen($filename,"rb"); $data = fread($handle, filesize($filename)); fclose($handle); return $data; print_r ($data); } function getDataArray($data,$start_word,$end_word){ $start = 0; $end = 0; $a_result = array(); while ($start!==false && $end!==false){ $start = strpos($data,$start_word,$end); if ($start!==false){ $end = strpos($data,$end_word,$start); if ($end!==false){ // data is between start and end $a_result[] = substr($data,$start,$end-$start+strlen($end_word)); } } } return $a_result; print_r ($a_result); } error_reporting(E_ALL); ini_set('display_errors', TRUE); file_put_contents('txtfile.txt', pdf2txt('Athy Register.pdf')); ?> -
Would i need to dump the data into seperate files after every function? (to see whats happening at each stage)
If so, how would i code that?
-
That seemed to fix the problem. I'm getting a blank screen but the textfile isnt created??
-
Down to only ONE error now!
Notice: Undefined variable: result_data in C:\xampp\htdocs\pdf2txt_test.php on line 71
Line 71 is
return $result_data;
-
That throws up the error
Notice: Undefined index: data in C:\xampp\htdocs\pdf2txt_test.php on line 57
Line 57 is
if ($chunk["data"]!=""){ -
Something like
if ((is_array($a_data)) && (count($a_data) > 0)) { -
I've replaced that line but im still getting two errors
Notice: Undefined offset: 0 in C:\xampp\htdocs\pdf2txt_test.php on line 44
Notice: Undefined offset: 0 in C:\xampp\htdocs\pdf2txt_test.php on line 46
Its got rid of one error
Line 44 is
$a_chunks[$j]["data"] = substr($a_data[0],
Line 46 is
strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); -
Im working on a pdf to textfile program and I'm getting the following errora
Notice: Undefined offset: 0 in C:\xampp\htdocs\pdf2txt_test.php on line 40
Notice: Undefined offset: 0 in C:\xampp\htdocs\pdf2txt_test.php on line 44
Notice: Undefined offset: 0 in C:\xampp\htdocs\pdf2txt_test.php on line 46
The lines are in the function
function handleV2($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $j = -1; foreach($a_obj as $obj){ $a_filter = getDataArray($obj,"<<",">>"); if (is_array($a_filter)){ $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if (is_array($a_data)){ $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); }My complete code is:
<?php // Function : pdf2txt() // Arguments : $filename - Filename of the PDF you want to extract // Description : Reads a pdf file, extracts data streams, and manages // their translation to plain text - returning the plain // text at the end // Authors : Jonathan Beckett, 2005-05-02 // : Sven Schuberth, 2007-03-29 $pdftext = pdf2txt('C:\Users\Mike\Desktop\Athy Register.pdf'); function pdf2txt($filename){ $data = getFileData($filename); $s=strpos($data,"%")+1; $version=substr($data,$s,strpos($data,"%",$s)-1); if(substr_count($version,"PDF-1.2")==0) return handleV3($data); else return handleV2($data); } // handles the verson 1.2 function handleV2($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $j = -1; foreach($a_obj as $obj){ $a_filter = getDataArray($obj,"<<",">>"); if (is_array($a_filter)){ $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if (is_array($a_data)){ $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); } } } // decode the chunks foreach($a_chunks as $chunk){ // look at each chunk and decide how to decode it - by looking at the contents of the filter $a_filter = split("/",$chunk["filter"]); if ($chunk["data"]!=""){ // look at the filter to find out which encoding has been used if (substr($chunk["filter"],"FlateDecode")!==false){ $data =@ gzuncompress($chunk["data"]); if (trim($data)!=""){ $result_data .= ps2txt($data); } else { //$result_data .= "x"; } } } } return $result_data; } //handles versions >1.2 function handleV3($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $result_data=""; foreach($a_obj as $obj){ //check if it a string if(substr_count($obj,"/GS1")>0){ //the strings are between ( and ) preg_match_all("|\((.*?)\)|",$obj,$field,PREG_SET_ORDER); if(is_array($field)) foreach($field as $data) $result_data.=$data[1]; } } return $result_data; } function ps2txt($ps_data){ $result = ""; $a_data = getDataArray($ps_data,"[","]"); if (is_array($a_data)){ foreach ($a_data as $ps_text){ $a_text = getDataArray($ps_text,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } } else { // the data may just be in raw format (outside of [] tags) $a_text = getDataArray($ps_data,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } return $result; } function getFileData($filename){ $handle = fopen($filename,"rb"); $data = fread($handle, filesize($filename)); fclose($handle); return $data; } function getDataArray($data,$start_word,$end_word){ $start = 0; $end = 0; $a_result = array(); while ($start!==false && $end!==false){ $start = strpos($data,$start_word,$end); if ($start!==false){ $end = strpos($data,$end_word,$start); if ($end!==false){ // data is between start and end $a_result[] = substr($data,$start,$end-$start+strlen($end_word)); } } } return $a_result; } error_reporting(E_ALL); ini_set('display_errors', TRUE); file_put_contents('txtfile.txt', pdf2txt('Athy Register.pdf')); ?>Any help on this would be great
-
I'm noe getting the error
Notice: Undefined offset: 0 in C:\xampp\htdocs\pdf2txt_test.php on line 40
Notice: Undefined offset: 0 in C:\xampp\htdocs\pdf2txt_test.php on line 44
Notice: Undefined offset: 0 in C:\xampp\htdocs\pdf2txt_test.php on line 46
The lines are in the function
function handleV2($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $j = -1; foreach($a_obj as $obj){ $a_filter = getDataArray($obj,"<<",">>"); if (is_array($a_filter)){ $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if (is_array($a_data)){ $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); } -
Thanks that seemed to fix it
Im now getting the error
Notice: Undefined variable: a_result in C:\xampp\htdocs\pdf2txt_test.php on line 140
line 140 is in the function
function getDataArray($data,$start_word,$end_word){ $start = 0; $end = 0; unset($a_result); while ($start!==false && $end!==false){ $start = strpos($data,$start_word,$end); if ($start!==false){ $end = strpos($data,$end_word,$start); if ($end!==false){ // data is between start and end $a_result[] = substr($data,$start,$end-$start+strlen($end_word)); } } } return $a_result; -
That seems to have fixed the problem with the code not loading bt im getting the error
Notice: Undefined variable: j in C:\xampp\htdocs\pdf2txt_test.php on line 38
$j++;
Any idea how I can fix this?
-
I'm a function noobie, how should it be written?
-
I'm trying to modify a piece of code to allow me to take the contents of a pdf document and send the output to a textfile
My code is
<?php // Function : pdf2txt() // Arguments : $filename - Filename of the PDF you want to extract // Description : Reads a pdf file, extracts data streams, and manages // their translation to plain text - returning the plain // text at the end // Authors : Jonathan Beckett, 2005-05-02 // : Sven Schuberth, 2007-03-29 function pdf2txt($filename){ $pdftext = pdf2txt('C:\Users\Mike\Desktop\Athy Database\Athy Register.pdf'); $data = getFileData($filename); $s=strpos($data,"%")+1; $version=substr($data,$s,strpos($data,"%",$s)-1); if(substr_count($version,"PDF-1.2")==0) return handleV3($data); else return handleV2($data); } // handles the verson 1.2 function handleV2($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); foreach($a_obj as $obj){ $a_filter = getDataArray($obj,"<<",">>"); if (is_array($a_filter)){ $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if (is_array($a_data)){ $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); } } } // decode the chunks foreach($a_chunks as $chunk){ // look at each chunk and decide how to decode it - by looking at the contents of the filter $a_filter = split("/",$chunk["filter"]); if ($chunk["data"]!=""){ // look at the filter to find out which encoding has been used if (substr($chunk["filter"],"FlateDecode")!==false){ $data =@ gzuncompress($chunk["data"]); if (trim($data)!=""){ $result_data .= ps2txt($data); } else { //$result_data .= "x"; } } } } return $result_data; } //handles versions >1.2 function handleV3($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $result_data=""; foreach($a_obj as $obj){ //check if it a string if(substr_count($obj,"/GS1")>0){ //the strings are between ( and ) preg_match_all("|\((.*?)\)|",$obj,$field,PREG_SET_ORDER); if(is_array($field)) foreach($field as $data) $result_data.=$data[1]; } } return $result_data; } function ps2txt($ps_data){ $result = ""; $a_data = getDataArray($ps_data,"[","]"); if (is_array($a_data)){ foreach ($a_data as $ps_text){ $a_text = getDataArray($ps_text,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } } else { // the data may just be in raw format (outside of [] tags) $a_text = getDataArray($ps_data,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } return $result; } function getFileData($filename){ $handle = fopen($filename,"rb"); $data = fread($handle, filesize($filename)); fclose($handle); return $data; } function getDataArray($data,$start_word,$end_word){ $start = 0; $end = 0; unset($a_result); while ($start!==false && $end!==false){ $start = strpos($data,$start_word,$end); if ($start!==false){ $end = strpos($data,$end_word,$start); if ($end!==false){ // data is between start and end $a_result[] = substr($data,$start,$end-$start+strlen($end_word)); } } } return $a_result; } error_reporting(E_ALL); ini_set('display_errors', TRUE); file_put_contents('txtfile.txt', pdf2txt('Athy Register.pdf')); ?>When I run the code it jst seems to freeze, any idea why??
-
Im running the code in Firefox, Using XAMPP (Apachi), the address im using is
-
I've used php for quite a whhile now but this think is driving me mental!
I didn't remove any php tags and the output is in the browser
The code looks like this
<?php // Function : pdf2txt() // Arguments : $filename - Filename of the PDF you want to extract // Description : Reads a pdf file, extracts data streams, and manages // their translation to plain text - returning the plain // text at the end // Authors : Jonathan Beckett, 2005-05-02 // : Sven Schuberth, 2007-03-29 function pdf2txt($filename){ $pdftext = pdf2txt('C:\Users\Mike\Desktop\Athy Database\Athy Register.pdf'); $data = getFileData($filename); $s=strpos($data,"%")+1; $version=substr($data,$s,strpos($data,"%",$s)-1); if(substr_count($version,"PDF-1.2")==0) return handleV3($data); else return handleV2($data); } // handles the verson 1.2 function handleV2($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); foreach($a_obj as $obj){ $a_filter = getDataArray($obj,"<<",">>"); if (is_array($a_filter)){ $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if (is_array($a_data)){ $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); } } } // decode the chunks foreach($a_chunks as $chunk){ // look at each chunk and decide how to decode it - by looking at the contents of the filter $a_filter = split("/",$chunk["filter"]); if ($chunk["data"]!=""){ // look at the filter to find out which encoding has been used if (substr($chunk["filter"],"FlateDecode")!==false){ $data =@ gzuncompress($chunk["data"]); if (trim($data)!=""){ $result_data .= ps2txt($data); } else { //$result_data .= "x"; } } } } return $result_data; } //handles versions >1.2 function handleV3($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $result_data=""; foreach($a_obj as $obj){ //check if it a string if(substr_count($obj,"/GS1")>0){ //the strings are between ( and ) preg_match_all("|\((.*?)\)|",$obj,$field,PREG_SET_ORDER); if(is_array($field)) foreach($field as $data) $result_data.=$data[1]; } } return $result_data; } function ps2txt($ps_data){ $result = ""; $a_data = getDataArray($ps_data,"[","]"); if (is_array($a_data)){ foreach ($a_data as $ps_text){ $a_text = getDataArray($ps_text,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } } else { // the data may just be in raw format (outside of [] tags) $a_text = getDataArray($ps_data,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } return $result; } function getFileData($filename){ $handle = fopen($filename,"rb"); $data = fread($handle, filesize($filename)); fclose($handle); return $data; } function getDataArray($data,$start_word,$end_word){ $start = 0; $end = 0; unset($a_result); while ($start!==false && $end!==false){ $start = strpos($data,$start_word,$end); if ($start!==false){ $end = strpos($data,$end_word,$start); if ($end!==false){ // data is between start and end $a_result[] = substr($data,$start,$end-$start+strlen($end_word)); } } } return $a_result; } error_reporting(E_ALL); ini_set('display_errors', TRUE); file_put_contents('txtfile.txt', pdf2txt('Athy Register.pdf')); ?> -
Im getting the following output
>"); if (is_array($a_filter)){ $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if (is_array($a_data)){ $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); } } } // decode the chunks foreach($a_chunks as $chunk){ // look at each chunk and decide how to decode it - by looking at the contents of the filter $a_filter = split("/",$chunk["filter"]); if ($chunk["data"]!=""){ // look at the filter to find out which encoding has been used if (substr($chunk["filter"],"FlateDecode")!==false){ $data =@ gzuncompress($chunk["data"]); if (trim($data)!=""){ $result_data .= ps2txt($data); } else { //$result_data .= "x"; } } } } return $result_data; } //handles versions >1.2 function handleV3($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $result_data=""; foreach($a_obj as $obj){ //check if it a string if(substr_count($obj,"/GS1")>0){ //the strings are between ( and ) preg_match_all("|\((.*?)\)|",$obj,$field,PREG_SET_ORDER); if(is_array($field)) foreach($field as $data) $result_data.=$data[1]; } } return $result_data; } function ps2txt($ps_data){ $result = ""; $a_data = getDataArray($ps_data,"[","]"); if (is_array($a_data)){ foreach ($a_data as $ps_text){ $a_text = getDataArray($ps_text,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } } else { // the data may just be in raw format (outside of [] tags) $a_text = getDataArray($ps_data,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } return $result; } function getFileData($filename){ $handle = fopen($filename,"rb"); $data = fread($handle, filesize($filename)); fclose($handle); return $data; } function getDataArray($data,$start_word,$end_word){ $start = 0; $end = 0; unset($a_result); while ($start!==false && $end!==false){ $start = strpos($data,$start_word,$end); if ($start!==false){ $end = strpos($data,$end_word,$start); if ($end!==false){ // data is between start and end $a_result[] = substr($data,$start,$end-$start+strlen($end_word)); } } } return $a_result; } error_reporting(E_ALL); ini_set('display_errors', TRUE); file_put_contents('txtfile.txt', pdf2txt('Athy Register.pdf')); ?>
-
replace
// modify the paths file_put_contents('C:\Users\Mike\Desktop\txtfile.txt', pdf2txt('C:\Users\Mike\Desktop\Athy Database\Athy Register.pdf')); /code] with [code] file_put_contents('txtfile.txt', pdf2txt('Athy Register.pdf'));??
-
I run the code to take text from a pdf and place it into a text file but I get a blank screen with no errors.
The textfile is not created on the either??
Any ideas why its not working?
<?php // Function : pdf2txt() // Arguments : $filename - Filename of the PDF you want to extract // Description : Reads a pdf file, extracts data streams, and manages // their translation to plain text - returning the plain // text at the end // Authors : Jonathan Beckett, 2005-05-02 // : Sven Schuberth, 2007-03-29 function pdf2txt($filename){ $pdftext = pdf2txt('C:\Users\Mike\Desktop\Athy Database\Athy Register.pdf'); $data = getFileData($filename); $s=strpos($data,"%")+1; $version=substr($data,$s,strpos($data,"%",$s)-1); if(substr_count($version,"PDF-1.2")==0) return handleV3($data); else return handleV2($data); } // handles the verson 1.2 function handleV2($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); foreach($a_obj as $obj){ $a_filter = getDataArray($obj,"<<",">>"); if (is_array($a_filter)){ $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if (is_array($a_data)){ $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); } } } // decode the chunks foreach($a_chunks as $chunk){ // look at each chunk and decide how to decode it - by looking at the contents of the filter $a_filter = split("/",$chunk["filter"]); if ($chunk["data"]!=""){ // look at the filter to find out which encoding has been used if (substr($chunk["filter"],"FlateDecode")!==false){ $data =@ gzuncompress($chunk["data"]); if (trim($data)!=""){ $result_data .= ps2txt($data); } else { //$result_data .= "x"; } } } } return $result_data; } //handles versions >1.2 function handleV3($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $result_data=""; foreach($a_obj as $obj){ //check if it a string if(substr_count($obj,"/GS1")>0){ //the strings are between ( and ) preg_match_all("|\((.*?)\)|",$obj,$field,PREG_SET_ORDER); if(is_array($field)) foreach($field as $data) $result_data.=$data[1]; } } return $result_data; } function ps2txt($ps_data){ $result = ""; $a_data = getDataArray($ps_data,"[","]"); if (is_array($a_data)){ foreach ($a_data as $ps_text){ $a_text = getDataArray($ps_text,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } } else { // the data may just be in raw format (outside of [] tags) $a_text = getDataArray($ps_data,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } return $result; } function getFileData($filename){ $handle = fopen($filename,"rb"); $data = fread($handle, filesize($filename)); fclose($handle); return $data; } function getDataArray($data,$start_word,$end_word){ $start = 0; $end = 0; unset($a_result); while ($start!==false && $end!==false){ $start = strpos($data,$start_word,$end); if ($start!==false){ $end = strpos($data,$end_word,$start); if ($end!==false){ // data is between start and end $a_result[] = substr($data,$start,$end-$start+strlen($end_word)); } } } return $a_result; } error_reporting(E_ALL); ini_set('display_errors', TRUE); // modify the paths file_put_contents('C:\Users\Mike\Desktop\txtfile.txt', pdf2txt('C:\Users\Mike\Desktop\Athy Database\Athy Register.pdf')); ?> -
Does anyone have any idea why this code doesnt produce an error report or pass the pdf conents to the textfile??
-
I run the test file and I get the blank screen with no errors but the textfile is not created on the desktop??
My code looks like this:
<?php // Function : pdf2txt() // Arguments : $filename - Filename of the PDF you want to extract // Description : Reads a pdf file, extracts data streams, and manages // their translation to plain text - returning the plain // text at the end // Authors : Jonathan Beckett, 2005-05-02 // : Sven Schuberth, 2007-03-29 function pdf2txt($filename){ $pdftext = pdf2txt('C:\Users\Mike\Desktop\Athy Database\Athy Register.pdf'); $data = getFileData($filename); $s=strpos($data,"%")+1; $version=substr($data,$s,strpos($data,"%",$s)-1); if(substr_count($version,"PDF-1.2")==0) return handleV3($data); else return handleV2($data); } // handles the verson 1.2 function handleV2($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); foreach($a_obj as $obj){ $a_filter = getDataArray($obj,"<<",">>"); if (is_array($a_filter)){ $j++; $a_chunks[$j]["filter"] = $a_filter[0]; $a_data = getDataArray($obj,"stream\r\n","endstream"); if (is_array($a_data)){ $a_chunks[$j]["data"] = substr($a_data[0], strlen("stream\r\n"), strlen($a_data[0])-strlen("stream\r\n")-strlen("endstream")); } } } // decode the chunks foreach($a_chunks as $chunk){ // look at each chunk and decide how to decode it - by looking at the contents of the filter $a_filter = split("/",$chunk["filter"]); if ($chunk["data"]!=""){ // look at the filter to find out which encoding has been used if (substr($chunk["filter"],"FlateDecode")!==false){ $data =@ gzuncompress($chunk["data"]); if (trim($data)!=""){ $result_data .= ps2txt($data); } else { //$result_data .= "x"; } } } } return $result_data; } //handles versions >1.2 function handleV3($data){ // grab objects and then grab their contents (chunks) $a_obj = getDataArray($data,"obj","endobj"); $result_data=""; foreach($a_obj as $obj){ //check if it a string if(substr_count($obj,"/GS1")>0){ //the strings are between ( and ) preg_match_all("|\((.*?)\)|",$obj,$field,PREG_SET_ORDER); if(is_array($field)) foreach($field as $data) $result_data.=$data[1]; } } return $result_data; } function ps2txt($ps_data){ $result = ""; $a_data = getDataArray($ps_data,"[","]"); if (is_array($a_data)){ foreach ($a_data as $ps_text){ $a_text = getDataArray($ps_text,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } } else { // the data may just be in raw format (outside of [] tags) $a_text = getDataArray($ps_data,"(",")"); if (is_array($a_text)){ foreach ($a_text as $text){ $result .= substr($text,1,strlen($text)-2); } } } return $result; } function getFileData($filename){ $handle = fopen($filename,"rb"); $data = fread($handle, filesize($filename)); fclose($handle); return $data; } function getDataArray($data,$start_word,$end_word){ $start = 0; $end = 0; unset($a_result); while ($start!==false && $end!==false){ $start = strpos($data,$start_word,$end); if ($start!==false){ $end = strpos($data,$end_word,$start); if ($end!==false){ // data is between start and end $a_result[] = substr($data,$start,$end-$start+strlen($end_word)); } } } return $a_result; } error_reporting(E_ALL); ini_set('display_errors', TRUE); // modify the paths file_put_contents('C:\Users\Mike\Desktop\txtfile.txt', pdf2txt('C:\Users\Mike\Desktop\Athy Database\Athy Register.pdf')); ?>
Undefined offset error help
in PHP Coding Help
Posted
Thats fixed the error and produces the txt file but the contents of the file is empty??