content-extraction 0.1.0__py3-none-any.whl → 0.2.0__py3-none-any.whl

content_extraction/file_handlers.py

@@ -50,7 +50,7 @@ def process_pdf(file_path: str, output_dir: str):
     """
     logger.info(f'[Processing PDF file] started for: "{file_path}"')
     # This path assumes the script is located at src/scripts/process_document.sh
-    script_path = os.path.join(os.path.dirname(__file__), '..', 'scripts', 'process_document.sh')
+    script_path = os.path.join(os.path.dirname(__file__), 'process_document.sh')
     output_html_path = os.path.join(output_dir, 'index.html')  # Define output_html_path
     logger.debug(f'[Processing PDF file] script path: "{script_path}"; output_html_path: "{output_html_path}"')
 

content_extraction/process.py

@@ -0,0 +1,59 @@
+import argparse
+import sys
+import logging
+
+from content_extraction.logging_config import setup_logging
+from content_extraction.file_handlers import process_file
+
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    """
+    Main function to process the input file/URL and generate structured output.
+    """
+    setup_logging()
+    parser = argparse.ArgumentParser(
+        description='Process various document types (PDF, PPTX, DOCX, MD, HTML, URL) and extract content into a structured HTML format.',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Run from the project root directory (`content-extraction/`)
+
+  # Process a local PDF file
+  python src/process.py my_document.pdf -o ./output_folder
+
+  # Process a PowerPoint file silently
+  python src/process.py my_slides.pptx --silent
+
+  # Process a remote URL, letting the script determine the type
+  python src/process.py https://example.com/document.pdf
+
+  # Process a remote URL, forcing the type to be treated as HTML
+  python src/process.py https://example.com/some-page --force-ext html
+""",
+    )
+
+    parser.add_argument('input_path', help='Path to the input file or a URL to process.')
+    parser.add_argument(
+        '-o',
+        '--output',
+        default='output',
+        help="Path to the output directory (defaults to 'output').",
+    )
+    parser.add_argument(
+        '--force-ext',
+        default=None,
+        help="Force the handler for a specific file extension (e.g., 'pdf', 'pptx') when auto-detection is ambiguous or incorrect.",
+    )
+
+    args = parser.parse_args()
+
+    logger.info(f'Processing file: {args.input_path}')
+    process_file(args.input_path, args.output, args.force_ext)
+    logger.info('Processing complete.')
+
+
+if __name__ == '__main__':
+    sys.exit(main())

{content_extraction-0.1.0.dist-info → content_extraction-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: content_extraction
-Version: 0.1.0
+Version: 0.2.0
 Summary: Project dedicated to content extraction from unstructured files that contain some useful information.
 Requires-Python: >=3.13
 Description-Content-Type: text/markdown

{content_extraction-0.1.0.dist-info → content_extraction-0.2.0.dist-info}/RECORD

@@ -3,13 +3,14 @@ content_extraction/common_std_io.py,sha256=mSRaiI4OrnttEQ8Y92-LsJnAHEI3xLKnJvmXD
 content_extraction/do_ocr.py,sha256=lrqwPYQlPuUHabirH_RzKbzHgYUPPpNeHDe_u4h9LEY,6886
 content_extraction/dspy_modules.py,sha256=0aAokJQNzczfowoUNK3BPMi_U18eXM9thHvciWaE5b0,732
 content_extraction/extract_from_pptx.py,sha256=IWd81sn7ZsyaQZdXP5Cgbk7GspcDYEjMnBkti-pTHQY,6572
-content_extraction/file_handlers.py,sha256=mO4HWiA_ZEKkV8KZP4fOz_nGnxDpghkqAhS0ADG9Oqk,11149
+content_extraction/file_handlers.py,sha256=fEAm0Iie5qc5ex4IhOQJGWkjZK12dfzuCabkmHF1GVM,11132
 content_extraction/fix_ocr.py,sha256=2xJ4c3VsGSy1l-qAukvhaV8QOp6yu5BY99Gb0DwamWQ,8009
 content_extraction/logging_config.py,sha256=GN1wuJJEspQ3z-FZIg134obsHweuiicZfz2an13a9_I,296
 content_extraction/parse_html.py,sha256=mOrZKXX59YcdWWhmbnoTnfXpwrg0znk38x0DMJIVes8,3137
+content_extraction/process.py,sha256=iLcmSjWhEg_DbgnftnVIfybIeLCuTEI57gasot0MtDk,1809
 content_extraction/semantic_chunk_html.py,sha256=iJPspKkrt95lL46JpC_9fgT8GfV8cz04TWEnU99rbBw,5786
 content_extraction/split_and_create_digest.py,sha256=bKZL9Axc74zLH_VrlNjd46ZiVTQQrAY5iNJCotO-8v8,4253
-content_extraction-0.1.0.dist-info/METADATA,sha256=3dQRIhF8zxiifsp3Fxpo8BCKqvV9N3xtjyCAkNlwQ_I,6201
-content_extraction-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-content_extraction-0.1.0.dist-info/top_level.txt,sha256=a0I0EwSzsyd3p_aAENozn9i4I3aBn12XtrbqIvfzZec,19
-content_extraction-0.1.0.dist-info/RECORD,,
+content_extraction-0.2.0.dist-info/METADATA,sha256=O0GNY4Ksv4Idb5pzCbQtYc0upufn_JoadEukGJRSUc0,6201
+content_extraction-0.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+content_extraction-0.2.0.dist-info/top_level.txt,sha256=a0I0EwSzsyd3p_aAENozn9i4I3aBn12XtrbqIvfzZec,19
+content_extraction-0.2.0.dist-info/RECORD,,