PDFlib pCOS サンプル集(クックブック)
pCOS インターフェースで、ページに含まれる Web リンクとその URL を抽出するサンプルプログラムです。
必要な製品:pCOS インターフェース(PDI、PPS、TET、PLOP、PLOP DS、TET PDF IFilter に内蔵されています。)
/*
* Retrieve bounding box and URL of all Web links on all pages.
*
* Required software: pCOS interface 8 (PDFlib+PDI/PPS 9, TET 4.1, PLOP 5.0)
* Required data: PDF document
*/
package com.pdflib.cookbook.pcos.interactive;
import com.pdflib.IpCOS;
import com.pdflib.cookbook.pcos.pcos_cookbook_example;
public class weblinks extends pcos_cookbook_example {
/* This is where the data files are. Adjust as necessary. */
private final static String SEARCH_PATH = "../input";
public void example_code(IpCOS p, int doc) throws Exception {
System.out.println("File name: " + p.pcos_get_string(doc, "filename"));
int pagecount = (int) p.pcos_get_number(doc, "length:pages");
for (int page = 0; page < pagecount; page++) {
String objtype = p.pcos_get_string(doc, "type:pages[" + page
+ "]/Annots");
if (objtype.equals("null"))
continue;
int anncount = (int) p.pcos_get_number(doc, "length:pages[" + page
+ "]/Annots");
if (anncount == 0)
continue;
for (int ann = 0; ann < anncount; ann++) {
String subtype = p.pcos_get_string(doc, "pages[" + page
+ "]/Annots[" + ann + "]/Subtype");
if (!subtype.equals("Link"))
continue;
objtype = p.pcos_get_string(doc, "type:pages[" + page
+ "]/Annots[" + ann + "]/A/URI");
if (objtype.equals("string")) {
String url = p.pcos_get_string(doc, "pages[" + page
+ "]/Annots[" + ann + "]/A/URI");
System.out.println("Page " + (page + 1) + ": " + url);
System.out.print(" link rectangle=[");
for (int j = 0; j < 4; j++) {
System.out.print(p.pcos_get_number(doc, "pages[" + page
+ "]" + "/Annots[" + ann + "]/Rect[" + j + "]")
+ (j<3 ? " " : ""));
}
System.out.println("]");
}
}
}
}
public weblinks(String[] argv, String readable_name, String search_path) {
super(argv, readable_name, search_path);
}
public static void main(String argv[]) {
weblinks example = new weblinks(argv, "Weblink data", SEARCH_PATH);
example.execute();
}
}
(Nov 10, 2010 - Sep 30, 2022)