Merge pull request #4 from renan-siqueira/develop

Merge develop into main

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 renan-siqueira
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,65 @@
+# PDF Text Extraction Tool
+
+## Description
+
+This project facilitates the extraction of text from PDF files using various Python libraries. It is designed to be flexible, allowing the choice among different text extraction libraries and supporting both single PDF file and directory containing multiple PDF files.
+
+---
+
+## Project Structure
+
+```markdown
+- main.py
+- extractors/
+  - __init__.py
+  - pypdf2_extractor.py
+  - pdfminer_extractor.py
+  - pymupdf_extractor.py
+  - pdfplumber_extractor.py
+- helpers/
+  - __init__.py
+  - utils.py
+- json/
+  - params.json
+```
+
+---
+
+## Configuration
+
+- **Python:** This project is developed in Python. Ensure you have the latest version of Python installed.
+- **Dependencies:** The required libraries are listed in each extraction file within the `extractors` folder. Install them using `pip install <library>`.
+
+_Use the `requirements.txt` file to install all libraries at once_
+
+---
+
+## Usage
+
+1. **Initial Setup:** Edit the `json/params.json` file to set the input path (`input_path`), output path (`output_path`), desired libraries (`libraries`), and log level (`log_level`).
+
+Example `params.json`:
+
+```json
+{
+    "input_path": "/path/to/pdf/or/directory",
+    "output_path": "/path/to/output/directory",
+    "libraries": ["pypdf2", "pdfminer"],
+    "log_level": "INFO"
+}
+```
+
+2. **Execution:** Run the `main.py` script to start the text extraction process.
+
+```bash
+python main.py
+```
+
+---
+
+## Features
+
+- Text extraction from PDF files using various libraries.
+- Supports processing either a single file or multiple files in a directory.
+- Automatic output folder generation based on input.
+- Flexible configuration via the json/params.json file.

extractors/pdfminer_extractor.py

@@ -0,0 +1,5 @@
+from pdfminer.high_level import extract_text
+
+
+def extract_text(file_path):
+    return extract_text(file_path)

extractors/pdfplumber_extractor.py

@@ -0,0 +1,8 @@
+import pdfplumber
+
+
+def extract_text(file_path):
+    text = ""
+    with pdfplumber.open(file_path) as pdf:
+        text = ''.join(page.extract_text() or '' for page in pdf.pages)
+    return text

extractors/pymupdf_extractor.py

@@ -0,0 +1,8 @@
+import fitz as PyMuPDF
+
+
+def extract_text(file_path):
+    text = ""
+    with PyMuPDF.open(file_path) as doc:
+        text = ''.join(page.get_text() for page in doc)
+    return text

extractors/pypdf2_extractor.py

@@ -0,0 +1,9 @@
+import PyPDF2
+
+
+def extract_text(file_path):
+    text = ""
+    with open(file_path, 'rb') as file:
+        reader = PyPDF2.PdfReader(file)
+        text = ''.join(page.extract_text() or '' for page in reader.pages)
+    return text

helpers/utils.py

@@ -0,0 +1,3 @@
+def save_text_to_file(text, file_path):
+    with open(file_path, 'w', encoding='utf-8') as file:
+        file.write(text)

json/config.json

@@ -0,0 +1,6 @@
+{
+    "input_path": "/path/to/pdf/or/directory",
+    "output_path": "/path/to/output/directory",
+    "libraries": ["pypdf2", "pdfminer"],
+    "log_level": "INFO"
+}

main.py

@@ -0,0 +1,62 @@
+import json
+import os
+import logging
+from extractors import pypdf2_extractor, pdfminer_extractor, pymupdf_extractor, pdfplumber_extractor
+from helpers import utils
+
+
+def get_extractor(library_name):
+    return {
+        'pypdf2': pypdf2_extractor.extract_text,
+        'pdfminer': pdfminer_extractor.extract_text,
+        'pymupdf': pymupdf_extractor.extract_text,
+        'pdfplumber': pdfplumber_extractor.extract_text
+    }.get(library_name, None)
+
+
+def process_file(file_path, libraries, output_dir):
+    for library in libraries:
+        extractor = get_extractor(library)
+        if extractor:
+            try:
+                extracted_text = extractor(file_path)
+                output_file = os.path.join(output_dir, f"{os.path.basename(file_path).split('.')[0]}_{library}.txt")
+                utils.save_text_to_file(extracted_text, output_file)
+            except Exception as e:
+                logging.error(f"Error processing {file_path} with {library}: {e}")
+
+
+def create_output_dir(base_dir, input_path, is_single_file):
+    if is_single_file:
+        output_dir = os.path.join(base_dir, os.path.basename(input_path).split('.')[0])
+    else:
+        output_dir = os.path.join(base_dir, os.path.basename(input_path))
+    os.makedirs(output_dir, exist_ok=True)
+    return output_dir
+
+
+def main():
+    with open('json/config.json') as config_file:
+        config = json.load(config_file)
+
+    logging.basicConfig(level=config.get("log_level", "INFO"))
+
+    input_path = config["input_path"]
+    libraries = config["libraries"]
+    base_output_dir = config.get("output_path", "./output")
+
+    is_single_file = os.path.isfile(input_path) and input_path.endswith('.pdf')
+    output_dir = create_output_dir(base_output_dir, input_path, is_single_file)
+
+    if is_single_file:
+        process_file(input_path, libraries, output_dir)
+    elif os.path.isdir(input_path):
+        for filename in os.listdir(input_path):
+            if filename.endswith('.pdf'):
+                process_file(os.path.join(input_path, filename), libraries, output_dir)
+    else:
+        logging.error("Invalid input path")
+
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,13 @@
+cffi==1.16.0
+charset-normalizer==3.3.2
+cryptography==41.0.5
+pdfminer==20191125
+pdfminer.six==20221105
+pdfplumber==0.10.3
+Pillow==10.1.0
+pycparser==2.21
+pycryptodome==3.19.0
+PyMuPDF==1.23.6
+PyMuPDFb==1.23.6
+PyPDF2==3.0.1
+pypdfium2==4.24.0