Tag Archives: PDF parsing

Extract Highlighted Data from PDF using Python – Example CIS Windows Server 2022 Benchmark pdf

10 Jul

In this blog post, we will explore how to extract highlighted data from a PDF using Python. Before we go ahead lets understand what is the usecase, you have the (CIS_Microsoft_Windows_Server_2022_Benchmark_v2.0.0.pdf) which is 1065 pages and you are reviewing the the policy against your enivornment and highlighting the pdf with specific color codes. For example, I use four colors for the following purposes:

  • Red Color – Missing Policies
  • Yellow Color – All existing policies
  • Pink – Policies not applicable
  • Green – Upgraded policies

Example of the highlighted text:

You dont have to use the same color codes like I have done but you get the idea. Once you have done the heavy lifting of reviewing the document and happy with the analysis. The next steps is you want to extract the highlighted data into a csv format so that the teams can review and action them.

Pre-requsites

We will use the PyMuPDF & Pandas library to parse the PDF file and extract the highlighted text. Additionally, we will apply this technique to the CIS Windows Server 2022 Benchmark PDF as an example.

Before we begin, make sure you have installed the necessary dependencies. You can install PyMuPDF and Pandas using pip:

pip install fitz
pip install pandas

First, I created a small script to go within the document pdf and detect the colors. I had to do this although, to my eyes, the colors are RED, Yellow, etc., the RGD color codes seem slightly different.

import fitz  # PyMuPDF

# Open the PDF
doc = fitz.open('CIS_Microsoft_Windows_Server_2022_Benchmark_v2.0.0.pdf')

# Set to store unique colors
unique_colors = set()

# Loop through every page
for i in range(len(doc)):
    page = doc[i]
    # Get the annotations (highlights are a type of annotation)
    annotations = page.annots()
    for annotation in annotations:
        if annotation.type[1] == 'Highlight':
            # Get the color of the highlight
            color = annotation.colors['stroke']  # Returns a RGB tuple
            unique_colors.add(color)

# Print all unique colors
for color in unique_colors:
    print(color)

You will get the following output post executing the script make sure you put the exact name of the PDF file and within the IDE of your choice cd to the directory where the above (CheckColor.py) resides.

Now we have the color codes it’s time to go ahead and extract the highlighted text. We iterate through each page of the PDF and check for any highlighted annotations. If an annotation is found, we extract the content and accumulate it in the extracted_text variable, followed by export to the csv.

Main Code

Replace "CIS_Microsoft_Windows_Server_2022_Benchmark_v2.0.0.pdf" with the actual path to your PDF file. 

import fitz  # PyMuPDF
import pandas as pd

# Open the PDF
doc = fitz.open('CIS_Microsoft_Windows_Server_2022_Benchmark_v2.0.0.pdf')

# Define the RGB values for your colors
PINK = (0.9686269760131836, 0.6000000238418579, 0.8196079730987549)
YELLOW = (1.0, 0.9411770105361938, 0.4000000059604645)
GREEN = (0.49019598960876465, 0.9411770105361938, 0.4000000059604645)
RED = (0.9215689897537231, 0.2862749993801117, 0.2862749993801117)

color_definitions = {"Pink": PINK, "Yellow": YELLOW, "Green": GREEN, "Red": RED}

# Create separate lists for each color
data_by_color = {"Pink": [], "Yellow": [], "Green": [], "Red": []}

# Loop through every page
for i in range(len(doc)):
    page = doc[i]
    annotations = page.annots()
    for annotation in annotations:
        if annotation.type[1] == 'Highlight':
            color = annotation.colors['stroke']  # Returns a RGB tuple
            if color in color_definitions.values():
                # Get the detailed structure of the page
                structure = page.get_text("dict")

                # Extract highlighted text line by line
                content = []
                for block in structure["blocks"]:
                    for line in block["lines"]:
                        for span in line["spans"]:
                            r = fitz.Rect(span["bbox"])
                            if r.intersects(annotation.rect):
                                content.append(span["text"])
                
                content = " ".join(content)

                # Append the content to the appropriate color list
                for color_name, color_rgb in color_definitions.items():
                    if color == color_rgb:
                        data_by_color[color_name].append(content)

# Convert each list to a DataFrame and write to a separate .csv file
for color_name, data in data_by_color.items():
    if data:
        df = pd.DataFrame(data, columns=["Text"])
        df.to_csv(f'highlighted_text_{color_name.lower()}.csv', index=False)

After running the script, the extracted highlighted text will be saved under multiple csv files like the below screenshot:

You can now extract the highlighted text from the PDF using the above technique. Feel free to modify and adapt this code to suit your specific requirements. Extracting highlighted data from PDFs can be a powerful data analysis and research technique.

I hope you will find this helpful information for extracting data out from any PDF files. Please let me know if I have missed any steps or details, and I will be happy to update the post.

Thanks,
Aresh Sarkari

Tags: , , , , ,