content-extraction 0.2.0__tar.gz → 0.3.1__tar.gz

{content_extraction-0.2.0 → content_extraction-0.3.1}/PKG-INFO

@@ -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 → content_extraction-0.3.1}/pyproject.toml

@@ -5,13 +5,21 @@ build-backend = "setuptools.build_meta"
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools.package-data]
+"content_extraction" = ["process_document.sh"]
+
 [project]
 name = "content_extraction"
-version = "0.2.0"
+version = "0.3.1"
 description = "Project dedicated to content extraction from unstructured files that contain some useful information."
 readme = "README.md"
-requires-python = ">=3.13"
-dependencies = ["beautifulsoup4>=4.13.4", "lxml>=6.0.0", "python-pptx>=1.0.2"]
+requires-python = ">=3.12"
+dependencies = [
+    "beautifulsoup4>=4.13.4",
+    "lxml>=6.0.0",
+    "python-pptx>=1.0.2",
+    "requests>=2.32.4",
+]
 
 [dependency-groups]
 dev = [

content_extraction-0.3.1/src/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 → content_extraction-0.3.1}/src/content_extraction.egg-info/PKG-INFO

@@ -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 → content_extraction-0.3.1}/src/content_extraction.egg-info/SOURCES.txt

@@ -10,6 +10,7 @@ src/content_extraction/fix_ocr.py
 src/content_extraction/logging_config.py
 src/content_extraction/parse_html.py
 src/content_extraction/process.py
+src/content_extraction/process_document.sh
 src/content_extraction/semantic_chunk_html.py
 src/content_extraction/split_and_create_digest.py
 src/content_extraction.egg-info/PKG-INFO

{content_extraction-0.2.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/requires.txt

@@ -1,3 +1,4 @@
 beautifulsoup4>=4.13.4
 lxml>=6.0.0
 python-pptx>=1.0.2
+requests>=2.32.4