0

以下片段来自“ http://pdfx.cs.man.ac.uk/usage ”。这个非常棒的工具，它将 pdf 格式的科学论文转换为 xml。

curl --data-binary @"/path/to/my.pdf"
     -H "Content-Type: application/pdf" 
     -L "http://pdfx.cs.man.ac.uk"

这段代码是 unix 命令行代码，我想要它的 PHP 版本。我试过了

$pdfFile = fopen('jucs_18_05_0623_0649_hasan.pdf', 'r');
$fileSize = filesize ('jucs_18_05_0623_0649_hasan.pdf');
$url="http://pdfx.cs.man.ac.uk";
$ch=curl_init();
curl_setopt($ch, CURLOPT_URL, $url); 
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); // 
curl_setopt($ch, CURLOPT_TIMEOUT, 100);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_PUT, true);
curl_setopt($ch, CURLOPT_INFILE, $pdfFile);
curl_setopt($ch, CURLOPT_INFILESIZE, $fileSize);
curl_setopt($ch, CURLOPT_VERBOSE, true);

$fp = fopen("test.xml", "w");
curl_setopt($ch, CURLOPT_FILE, $fp);

if (! $res = curl_exec($ch))
    echo "Error: ".curl_error($ch);
else {
    echo "Success";
}   
curl_close($ch);

问题是 test.xml 的输出是索引文件 html 代码，而不是所提供文章的转换 xml 版本。

等待您的专家意见...

提前致谢

4

1 回答 1

1

放不需要。需要内容长度。

<?php
$pdfFile = fopen('1.pdf', 'r');
$fileSize = filesize ('1.pdf');
$url="http://pdfx.cs.man.ac.uk";
$ch=curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //
curl_setopt($ch, CURLOPT_TIMEOUT, 100);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_HTTPHEADER, array("Content-Type: application/pdf","Content-length: ".$fileSize));
curl_setopt($ch, CURLOPT_INFILE, $pdfFile);
curl_setopt($ch, CURLOPT_INFILESIZE, $fileSize);
curl_setopt($ch, CURLOPT_VERBOSE, true);

$fp = fopen("test.xml", "w");
curl_setopt($ch, CURLOPT_FILE, $fp);

if (! $res = curl_exec($ch))
    echo "Error: ".curl_error($ch);
else {
    echo "Success";
}
curl_close($ch);
?>
于 2012-10-04T13:19:59.450 回答