smartdocloader 1.0.0

An advanced universal document loader - load TXT, CSV, JSON, XML, YAML, INI, HTML, PDF, DOCX, PPTX, XLSX with smart auto-detection

smartdocloader

An advanced universal document loader for Python. Smart auto-detection, batch loading, content search, and support for 11+ file formats.

Installation

pip install smartdocloader

For YAML support:

pip install smartdocloader[yaml]

Features

• Auto-detection: Automatically detects file type and uses the right loader
• Batch loading: Load multiple files in one call
• 11 formats supported: TXT, CSV, JSON, XML, YAML, INI, HTML, PDF, DOCX, PPTX, XLSX
• Content search: Search within loaded data
• Export: Convert loaded data to JSON
• File comparison: Compare content of two files
• Advanced options: Page ranges for PDFs, sheet selection for Excel, table extraction from Word

---

Quick Start

from smartdocloader import auto_load

# Just pass any file - it auto-detects the format
data = auto_load("report.pdf")
data = auto_load("data.csv")
data = auto_load("config.yaml")

---

All Supported Formats

Format	Extensions	Module
Plain Text	.txt	text_loader
CSV	.csv	text_loader
JSON	.json	text_loader
XML	.xml	text_loader
YAML	.yaml, .yml	text_loader
INI/Config	.ini, .cfg	text_loader
HTML	.html, .htm	text_loader
PDF	.pdf	doc_loader
Word	.docx	doc_loader
PowerPoint	.pptx	doc_loader
Excel	.xlsx	doc_loader

---

Modules & Functions

Module 1: text_loader

Function	Description
load_txt(filepath, encoding)	Load plain text file
load_csv(filepath, delimiter, encoding)	Load CSV as list of dicts
load_json(filepath, encoding)	Load and parse JSON
load_xml(filepath)	Load XML as nested dict
load_yaml(filepath, encoding)	Load YAML data
load_ini(filepath, encoding)	Load INI as nested dict
load_html(filepath, encoding)	Extract text from HTML

Module 2: doc_loader

Function	Description
load_pdf(filepath, page_range)	Extract text from PDF (optional page range)
load_pdf_pages(filepath)	Get text per page as a list
load_pdf_metadata(filepath)	Get PDF metadata (author, title, etc.)
load_docx(filepath, include_tables)	Load Word document paragraphs
load_docx_with_styles(filepath)	Load with style/formatting info
load_pptx(filepath, include_notes)	Load PowerPoint slides
load_xlsx(filepath, sheet_name)	Load Excel data from specific sheet
load_xlsx_sheets(filepath)	List all sheet names

Module 3: smart_loader

Function	Description
auto_load(filepath)	Auto-detect format and load
batch_load(filepaths)	Load multiple files at once
get_file_info(filepath)	Get file metadata (size, type, etc.)
supported_formats()	List all supported extensions

Module 4: utils

Function	Description
search_content(data, keyword)	Search within loaded content
convert_to_text(data)	Convert any loaded data to plain text
word_count(data)	Count words in loaded content
export_to_json(data, output_path)	Export loaded data to JSON file
compare_files(filepath1, filepath2)	Compare two files

---

Usage Examples

Auto-Loading (Smart Detection)

from smartdocloader import auto_load

# Just pass any file path - format is auto-detected
pdf_content = auto_load("report.pdf")
csv_data = auto_load("students.csv")
config = auto_load("settings.yaml")

print(pdf_content[:100])

Batch Loading Multiple Files

from smartdocloader import batch_load

files = ["data.csv", "report.pdf", "config.json", "notes.txt"]
results = batch_load(files)

for filepath, content in results.items():
    if "error" in content if isinstance(content, dict) else False:
        print(f"Failed: {filepath} - {content['error']}")
    else:
        print(f"Loaded: {filepath}")

Loading PDFs with Options

from smartdocloader import load_pdf, load_pdf_pages, load_pdf_metadata

# Load entire PDF
full_text = load_pdf("book.pdf")

# Load only pages 0-4 (first 5 pages)
intro = load_pdf("book.pdf", page_range=(0, 5))

# Get text per page
pages = load_pdf_pages("book.pdf")
print(f"Page 1: {pages[0][:100]}")
print(f"Total pages: {len(pages)}")

# Get metadata
meta = load_pdf_metadata("book.pdf")
print(f"Author: {meta['author']}")
print(f"Title: {meta['title']}")
print(f"Pages: {meta['page_count']}")

Loading Word Documents

from smartdocloader import load_docx, load_docx_with_styles

# Basic loading
paragraphs = load_docx("report.docx")
for p in paragraphs:
    print(p)

# With tables included
content = load_docx("report.docx", include_tables=True)
for item in content:
    print(item)

# With style information
styled = load_docx_with_styles("report.docx")
for para in styled:
    if para["bold"]:
        print(f"[BOLD] {para['text']}")
    else:
        print(f"       {para['text']}")

Loading Excel with Sheet Selection

from smartdocloader import load_xlsx, load_xlsx_sheets

# See available sheets
sheets = load_xlsx_sheets("financials.xlsx")
print(f"Sheets: {sheets}")

# Load specific sheet
q1_data = load_xlsx("financials.xlsx", sheet_name="Q1")
for row in q1_data:
    print(row)

Loading PowerPoint with Notes

from smartdocloader import load_pptx

slides = load_pptx("lecture.pptx", include_notes=True)
for slide in slides:
    print(f"--- Slide {slide['slide_number']} ---")
    for text in slide["text"]:
        print(f"  {text}")
    if "notes" in slide and slide["notes"]:
        print(f"  [Notes: {slide['notes']}]")

Loading YAML Configuration

from smartdocloader import load_yaml

config = load_yaml("docker-compose.yml")
print(config["services"])

Loading INI/Config Files

from smartdocloader import load_ini

settings = load_ini("app.ini")
print(settings["database"]["host"])
print(settings["database"]["port"])

Loading HTML (Text Extraction)

from smartdocloader import load_html

text = load_html("page.html")
print(text)  # Clean text without HTML tags

Searching Within Loaded Content

from smartdocloader import auto_load, search_content

# Load any file
data = auto_load("students.csv")

# Search for a keyword
matches = search_content(data, "Ahmed")
print(f"Found {len(matches)} matches:")
for match in matches:
    print(f"  {match}")

Converting to Plain Text

from smartdocloader import auto_load, convert_to_text

# Load structured data
data = auto_load("grades.xlsx")

# Convert to flat text
text = convert_to_text(data)
print(text)

Exporting to JSON

from smartdocloader import auto_load, export_to_json

# Load a Word document
data = auto_load("report.docx")

# Export as JSON for further processing
export_to_json(data, "report_output.json")

Comparing Two Files

from smartdocloader import compare_files

result = compare_files("version1.txt", "version2.txt")
print(f"Identical: {result['identical']}")
print(f"File 1: {result['file1_lines']} lines, {result['file1_words']} words")
print(f"File 2: {result['file2_lines']} lines, {result['file2_words']} words")

Getting File Info

from smartdocloader import get_file_info

info = get_file_info("report.pdf")
print(f"Name: {info['name']}")
print(f"Size: {info['size_readable']}")
print(f"Supported: {info['is_supported']}")

Listing Supported Formats

from smartdocloader import supported_formats

formats = supported_formats()
print(f"Supported: {', '.join(formats)}")

---

Error Handling

from smartdocloader import auto_load

try:
    data = auto_load("unknown.xyz")
except ValueError as e:
    print(f"Format error: {e}")
except FileNotFoundError as e:
    print(f"File missing: {e}")
except Exception as e:
    print(f"Error: {e}")

---

Requirements

• Python >= 3.7
• PyPDF2
• python-docx
• python-pptx
• openpyxl
• pyyaml (optional, for YAML support)

---

License

MIT