|
|
Posted by Matt M. on 02/09/05 23:39
did you try this?
<?php
$test = pdf2string("<pathtoPDFfile>");
echo "$test";
# Returns a -1 if uncompression failed
function pdf2string($sourcefile)
{
$fp = fopen($sourcefile, 'rb');
$content = fread($fp, filesize($sourcefile));
fclose($fp);
# Locate all text hidden within the stream and endstream tags
$searchstart = 'stream';
$searchend = 'endstream';
$pdfdocument = "";
$pos = 0;
$pos2 = 0;
$startpos = 0;
# Iterate through each stream block
while( $pos !== false && $pos2 !== false )
{
# Grab beginning and end tag locations if they have not yet been parsed
$pos = strpos($content, $searchstart, $startpos);
$pos2 = strpos($content, $searchend, $startpos + 1);
if( $pos !== false && $pos2 !== false )
{
# Extract compressed text from between stream tags and uncompress
$textsection = substr($content, $pos + strlen($searchstart) +
2, $pos2 - $pos - strlen($searchstart) - 1);
$data = @gzuncompress($textsection);
# Clean up text via a special function
$data = ExtractText($data);
# Increase our PDF pointer past the section we just read
$startpos = $pos2 + strlen($searchend) - 1;
if( $data === false ) { return -1; }
$pdfdocument = $pdfdocument . $data;
}
}
return $pdfdocument;
}
function ExtractText($postScriptData)
{
while( (($textStart = strpos($postScriptData, '(', $textStart)) &&
($textEnd = strpos($postScriptData, ')', $textStart + 1)) &&
substr($postScriptData, $textEnd - 1) != '\\') )
{
$plainText .= substr($postScriptData, $textStart + 1, $textEnd -
$textStart - 1);
if( substr($postScriptData, $textEnd + 1, 1) == ']' ) // This
adds quite some additional spaces between the words
{
$plainText .= ' ';
}
$textStart = $textStart < $textEnd ? $textEnd : $textStart + 1;
}
return stripslashes($plainText);
}
?>
Navigation:
[Reply to this message]
|