1:
2:
3:
4:
5:
6:
7:
8:
9:
10:
11:
12:
13:
14:
15:
16:
17:
18:
19:
20:
21:
22:
23:
24:
25:
26:
27:
28:
29:
30:
31:
32:
33:
34:
35:
36:
37:
38:
39:
40:
41:
42:
43:
44:
45:
46:
47:
48:
49:
50:
51:
52:
53:
54:
55:
56:
57:
58:
59:
60:
61:
62:
63:
64:
65:
66:
67:
68:
69:
70:
71:
72:
73:
74:
75:
76:
77:
78:
79:
80:
81:
82:
83:
84:
85:
86:
87:
88:
89:
90:
91:
92:
93:
94:
95:
96:
97:
98:
99:
100:
101:
102:
103:
104:
105:
106:
107:
108:
109:
110:
111:
112:
113:
114:
115:
116:
117:
118:
119:
120:
121:
122:
123:
124:
125:
126:
127:
128:
129:
130:
131:
132:
133:
134:
135:
136:
137:
138:
139:
140:
141:
142:
143:
144:
145:
146:
|
<?
// get file over URL?file=
$file=pdf2text($_GET['file']);
foreach($file as $k => $v)
{
echo "$k: $v <br>";
}
function pdf2text($source)
{
// read pdf-file
if(function_exists('file_get_contents'))
{
$content=file_get_contents($source);
}else{
$content='';
$handle=fopen($source,'r');
while(!feof($handle))
{
$line=fgets($handle, 4096);
$content.=$line;
}
fclose($handle);
}
$content2=array();
// title of file
if(preg_match_all('|/Title(.?)((.*))|Ui',$content,$title))
{
$content2['Title']=$title[2][0];
}
// subject of file
if(preg_match_all('|/Subject(.?)((.*))|Ui',$content,$subject))
{
$content2['Subject']=$subject[2][0];
}
// creator of file
if(preg_match_all('|/Creator(.?)((.*))|Ui',$content,$creator))
{
$content2['Creator']=$creator[2][0];
}
// producer of file
if(preg_match_all('|/Producer(.?)((.*))|Ui',$content,$producer))
{
$content2['Producer']=$producer[2][0];
}
// author of file
if(preg_match_all('|/Author(.?)((.*))|Ui',$content,$author))
{
$content2['Author']=$author[2][0];
}
// find stream-sections
// uses part of the function pdf2string from <a href="http://de.php.net/manual/de/ref.pdf.php#56492<br">http://de.php.net/manual/de/ref.pdf.php#56492<br</a> />
$searchstart = 'stream';
$searchend = 'endstream';
$text = '';
$pos = 0;
$pos2 = 0;
$startpos = 0;
while ($pos !== false && $pos2 !== false)
{
$pos = strpos($content, $searchstart, $startpos);
$pos2 = strpos($content, $searchend, $startpos + 1);
if($pos !== false && $pos2 !== false)
{
if($content[$pos] == 0x0d && $content[$pos + 1] == 0x0a)
{
$pos += 2;
}else if ($content[$pos] == 0x0a){
$pos++;
}
if($content[$pos2 - 2] == 0x0d && $content[$pos2 - 1] == 0x0a)
{
$pos2 -= 2;
}else if ($content[$pos2 - 1] == 0x0a){
$pos2--;
}
$textsection = substr($content, $pos + strlen($searchstart) + 2, $pos2 - $pos - strlen($searchstart) - 1);
/*if(function_exists('convert_uudecode'))
{
$data= convert_uudecode($textsection);
}else*/{
$data = @gzuncompress($textsection);
}
$text.= pdfExtractText($data);
$startpos = $pos2 + strlen($searchend) - 1;
}
}
$content2['Text']=$text;
return $content2;
}
function pdfExtractText($data)
{
$data=preg_replace('|T[cjdJm](.*)TD|Us','<br>',$data);
$data=str_replace('(', '##BEGINBRACKET##', $data);
$data=str_replace('[', '##BEGINSBRACKET##', $data);
$data=str_replace(')', '##ENDBRACKET##', $data);
$data=str_replace(']', '##ENDSBRACKET##', $data);
$data=str_replace('(','',$data);
$data=str_replace(')','',$data);
// Translate special characters and put back brackets.
$trans = array(
'...' => '…',
'205' => '…',
'221' => chr(145),
'222' => chr(146),
'223' => chr(147),
'224' => chr(148),
'226' => '-',
'200' => '�',
'374' => 'ü',
'334' => 'Ü',
'366' => 'ö',
'337' => 'ß',
'344' => 'ä',
'267' => '•',
'##BEGINBRACKET##' => '(',
'##BEGINSBRACKET##' => '[',
'##ENDBRACKET##' => ')',
'##ENDSBRACKET##' => ']',
chr(133) => '-',
chr(141) => chr(147),
chr(142) => chr(148),
chr(143) => chr(145),
chr(144) => chr(146),
);
$data = strtr($data, $trans);
return $data;
}
?>
|
