mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-12 07:56:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

Extract inline images from PDFs

Browse Source
This commit is contained in:
apriestman 2020-10-09 16:47:48 -04:00
parent 2d239849b1
commit 89fcf04cb7
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
Core/src/org/sleuthkit/autopsy/modules/embeddedfileextractor/PDFAttachmentExtractor.java
View File

@ -34,6 +34,7 @@ import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@ -79,6 +80,12 @@ final class PDFAttachmentExtractor {
ParseContext parseContext = new ParseContext();
parseContext.set(Parser.class, parser);
PDFParserConfig pdfConfig = new PDFParserConfig();
pdfConfig.setExtractInlineImages(true);
pdfConfig.setExtractUniqueInlineImagesOnly(true);
parseContext.set(PDFParserConfig.class, pdfConfig);
//Keep track of the attachment files as they are being extracted and written to disk.
NewResourceWatcher watcher = new NewResourceWatcher();
parseContext.set(EmbeddedDocumentExtractor.class, new EmbeddedAttachmentHandler(outputDir, parentID, watcher));