content-extraction 0.2.0__py3-none-any.whl → 0.3.1__py3-none-any.whl

content_extraction/process_document.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+# Fail immediately if any command fails
+set -e
+
+# Check if the correct number of arguments is provided
+if [ "$#" -ne 2 ]; then
+  echo "Usage: $0 <input_file_path> <output_directory>"
+  exit 1
+fi
+
+INPUT_FILE="$1"
+OUTPUT_DIR="$2"
+
+# Step 1: Perform OCR and save the result to the directory
+echo "Performing OCR on $INPUT_FILE..."
+python -m content_extraction.do_ocr "$INPUT_FILE" -o "$OUTPUT_DIR"
+
+# Step 2: Combine the OCR pages into a single file
+echo "Combining pages into a single Markdown file..."
+cd "$OUTPUT_DIR"
+ls page-*.md | sort | xargs -I{} sh -c 'cat "{}"; echo; echo' > combined.md
+
+# Step 3: Extract headings from the combined Markdown file
+echo "Extracting headings from combined.md..."
+grep "^#" combined.md > headings.md
+
+# Step 4: Fix any OCR errors using provided script
+echo "Fixing OCR errors..."
+fixed_text=$(python -m content_extraction.fix_ocr combined.md headings.md)
+echo "$fixed_text" > fixed.md
+
+# Step 5: Render the markdown file to HTML
+pandoc fixed.md -s -f markdown -t html -o index.html
+
+echo "All processes completed successfully. Output saved in $OUTPUT_DIR"

{content_extraction-0.2.0.dist-info → content_extraction-0.3.1.dist-info}/METADATA

@@ -1,12 +1,13 @@
 Metadata-Version: 2.4
 Name: content_extraction
-Version: 0.2.0
+Version: 0.3.1
 Summary: Project dedicated to content extraction from unstructured files that contain some useful information.
-Requires-Python: >=3.13
+Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 Requires-Dist: beautifulsoup4>=4.13.4
 Requires-Dist: lxml>=6.0.0
 Requires-Dist: python-pptx>=1.0.2
+Requires-Dist: requests>=2.32.4
 
 # HTML Content Extraction Tool
 

{content_extraction-0.2.0.dist-info → content_extraction-0.3.1.dist-info}/RECORD

@@ -8,9 +8,10 @@ content_extraction/fix_ocr.py,sha256=2xJ4c3VsGSy1l-qAukvhaV8QOp6yu5BY99Gb0DwamWQ
 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/process_document.sh,sha256=QbQOrV7isiEyxin1PBNGYmCbfVQ_eW-JgsbuQV4VB2o,1106
 content_extraction/semantic_chunk_html.py,sha256=iJPspKkrt95lL46JpC_9fgT8GfV8cz04TWEnU99rbBw,5786
 content_extraction/split_and_create_digest.py,sha256=bKZL9Axc74zLH_VrlNjd46ZiVTQQrAY5iNJCotO-8v8,4253
-content_extraction-0.2.0.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,,
+content_extraction-0.3.1.dist-info/METADATA,sha256=VHBxKGh7uzDMgv1b9Gxq-FmiLHA-VVzyPH2l7wJcwFI,6233
+content_extraction-0.3.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+content_extraction-0.3.1.dist-info/top_level.txt,sha256=a0I0EwSzsyd3p_aAENozn9i4I3aBn12XtrbqIvfzZec,19
+content_extraction-0.3.1.dist-info/RECORD,,