Edison/mistral-ocr
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add feature to extract images as separate files

Browse Source
This commit is contained in:
Heiko Joerg Schick
2025-04-24 21:44:49 +02:00
parent 012755b7f4
commit 220864d52f
6 changed files with 197 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
mistral_ocr/__main__.py
+4
View File
@@ -32,6 +32,8 @@ def main():
convert_parser.add_argument("-d", "--output-dir", default="markdown_output", help="Directory to store markdown files")
convert_parser.add_argument("-o", "--output-file", help="Output filename for single file mode (default: document.md)")
convert_parser.add_argument("--images", action="store_true", help="Include images in markdown (if available)")
convert_parser.add_argument("--extract-images", action="store_true", help="Extract images to files instead of embedding them")
convert_parser.add_argument("--image-dir", help="Directory to store extracted images (default: output_dir/images)")
convert_parser.add_argument("--page-breaks", action="store_true", default=True, help="Include page break indicators between pages")
convert_parser.add_argument("--title-from-filename", action="store_true", default=True, help="Use filename as document title")
convert_parser.add_argument("--single-file", action="store_true", help="Create a single markdown file instead of one per page")
@@ -43,6 +45,8 @@ def main():
markdown_parser.add_argument("-d", "--output-dir", default="markdown_output", help="Directory to store markdown files")
markdown_parser.add_argument("-o", "--output-file", help="Path for output markdown file (implies --single-file)")
markdown_parser.add_argument("--images", action="store_true", help="Include extracted images in markdown (if available)")
markdown_parser.add_argument("--extract-images", action="store_true", help="Extract images to files instead of embedding them")
markdown_parser.add_argument("--image-dir", help="Directory to store extracted images (default: output_dir/images)")
markdown_parser.add_argument("--page-breaks", action="store_true", default=True, help="Include page break indicators between pages")
markdown_parser.add_argument("--title-from-filename", action="store_true", default=True, help="Use filename as document title")
markdown_parser.add_argument("--single-file", action="store_true", help="Create a single markdown file instead of one per page")