PDF to Structured Data Conversion

Overview

Based on DDC methodology (Chapter 2.4), this skill transforms unstructured PDF documents into structured formats suitable for analysis and integration. Construction projects generate vast amounts of PDF documentation - specifications, BOMs, schedules, and reports - that need to be extracted and processed.

Book Reference: "Преобразование данных в структурированную форму" / "Data Transformation to Structured Form"

"Преобразование данных из неструктурированной в структурированную форму — это и искусство, и наука. Этот процесс часто занимает значительную часть работы инженера по обработке данных." — DDC Book, Chapter 2.4

ETL Process Overview

The conversion follows the ETL pattern:

1. Extract: Load the PDF document
2. Transform: Parse and structure the content
3. Load: Save to CSV, Excel, or JSON

Quick Start

import pdfplumber
import pandas as pd

# Extract table from PDF
with pdfplumber.open("construction_spec.pdf") as pdf:
    page = pdf.pages[0]
    table = page.extract_table()
    df = pd.DataFrame(table[1:], columns=table[0])
    df.to_excel("extracted_data.xlsx", index=False)

Installation

# Core libraries
pip install pdfplumber pandas openpyxl

# For scanned PDFs (OCR)
pip install pytesseract pdf2image
# Also install Tesseract OCR: https://github.com/tesseract-ocr/tesseract

# For advanced PDF operations
pip install pypdf

Native PDF Extraction (pdfplumber)

Extract All Tables from PDF

import pdfplumber
import pandas as pd

def extract_tables_from_pdf(pdf_path):
    """Extract all tables from a PDF file"""
    all_tables = []

    with pdfplumber.open(pdf_path) as pdf:
        for page_num, page in enumerate(pdf.pages):
            tables = page.extract_tables()
            for table_num, table in enumerate(tables):
                if table and len(table) > 1:
                    # First row as header
                    df = pd.DataFrame(table[1:], columns=table[0])
                    df['_page'] = page_num + 1
                    df['_table'] = table_num + 1
                    all_tables.append(df)

    if all_tables:
        return pd.concat(all_tables, ignore_index=True)
    return pd.DataFrame()

# Usage
df = extract_tables_from_pdf("material_specification.pdf")
df.to_excel("materials.xlsx", index=False)

Extract Text with Layout

import pdfplumber

def extract_text_with_layout(pdf_path):
    """Extract text preserving layout structure"""
    full_text = []

    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            text = page.extract_text()
            if text:
                full_text.append(text)

    return "\n\n--- Page Break ---\n\n".join(full_text)

# Usage
text = extract_text_with_layout("project_report.pdf")
with open("report_text.txt", "w", encoding="utf-8") as f:
    f.write(text)

Extract Specific Table by Position

import pdfplumber
import pandas as pd

def extract_table_from_area(pdf_path, page_num, bbox):
    """
    Extract table from specific area on page

    Args:
        pdf_path: Path to PDF file
        page_num: Page number (0-indexed)
        bbox: Bounding box (x0, top, x1, bottom) in points
    """
    with pdfplumber.open(pdf_path) as pdf:
        page = pdf.pages[page_num]
        cropped = page.within_bbox(bbox)
        table = cropped.extract_table()

        if table:
            return pd.DataFrame(table[1:], columns=table[0])
    return pd.DataFrame()

# Usage - extract table from specific area
# bbox format: (left, top, right, bottom) in points (1 inch = 72 points)
df = extract_table_from_area("drawing.pdf", 0, (50, 100, 550, 400))

Scanned PDF Processing (OCR)

Extract Text from Scanned PDF

import pytesseract
from pdf2image import convert_from_path
import pandas as pd

def ocr_scanned_pdf(pdf_path, language='eng'):
    """
    Extract text from scanned PDF using OCR

    Args:
        pdf_path: Path to scanned PDF
        language: Tesseract language code (eng, deu, rus, etc.)
    """
    # Convert PDF pages to images
    images = convert_from_path(pdf_path, dpi=300)

    extracted_text = []
    for i, image in enumerate(images):
        text = pytesseract.image_to_string(image, lang=language)
        extracted_text.append({
            'page': i + 1,
            'text': text
        })

    return pd.DataFrame(extracted_text)

# Usage
df = ocr_scanned_pdf("scanned_specification.pdf", language='eng')
df.to_csv("ocr_results.csv", index=False)

OCR Table Extraction

import pytesseract
from pdf2image import convert_from_path
import pandas as pd
import cv2
import numpy as np

def ocr_table_from_scanned_pdf(pdf_path, page_num=0):
    """Extract table from scanned PDF using OCR with table detection"""
    # Convert specific page to image
    images = convert_from_path(pdf_path, first_page=page_num+1,
                                last_page=page_num+1, dpi=300)
    image = np.array(images[0])

    # Convert to grayscale
    gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)

    # Apply thresholding
    _, binary = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY_INV)

    # Extract text with table structure
    custom_config = r'--oem 3 --psm 6'
    text = pytesseract.image_to_string(gray, config=custom_config)

    # Parse text into table structure
    lines = text.strip().split('\n')
    data = [line.split() for line in lines if line.strip()]

    if data:
        # Assume first row is header
        df = pd.DataFrame(data[1:], columns=data[0] if len(data[0]) > 0 else None)
        return df
    return pd.DataFrame()

# Usage
df = ocr_table_from_scanned_pdf("scanned_bom.pdf")
print(df)

Construction-Specific Extractions

Bill of Materials (BOM) Extraction

import pdfplumber
import pandas as pd
import re

def extract_bom_from_pdf(pdf_path):
    """Extract Bill of Materials from construction PDF"""
    all_items = []

    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            tables = page.extract_tables()
            for table in tables:
                if not table or len(table) < 2:
                    continue

                # Find header row (look for common BOM headers)
                header_keywords = ['item', 'description', 'quantity', 'unit', 'material']
                for i, row in enumerate(table):
                    if row and any(keyword in str(row).lower() for keyword in header_keywords):
                        # Found header, process remaining rows
                        headers = [str(h).strip() for h in row]
                        for data_row in table[i+1:]:
                            if data_row and any(cell for cell in data_row if cell):
                                item = dict(zip(headers, data_row))
                                all_items.append(item)
                        break

    return pd.DataFrame(all_items)

# Usage
bom = extract_bom_from_pdf("project_bom.pdf")
bom.to_excel("bom_extracted.xlsx", index=False)

Project Schedule Extraction

import pdfplumber
import pandas as pd
from datetime import datetime

def extract_schedule_from_pdf(pdf_path):
    """Extract project schedule/gantt data from PDF"""
    with pdfplumber.open(pdf_path) as pdf:
        all_tasks = []

        for page in pdf.pages:
            tables = page.extract_tables()
            for table in tables:
                if not table:
                    continue

                # Look for schedule-like table
                headers = table[0] if table else []

                # Check if it looks like a schedule
                schedule_keywords = ['task', 'activity', 'start', 'end', 'duration']
                if any(kw in str(headers).lower() for kw in schedule_keywords):
                    for row in table[1:]:
                        if row and any(cell for cell in row if cell):