pdf_miner_example.py

import requests
from pdfminer.high_level import extract_text
from collections import Counter
import re

# Step 1: Download and save the PDF
pdf_url = "https://arxiv.org/pdf/1509.02971.pdf"
response = requests.get(pdf_url)
pdf_filename = "nasa_flight_plan.pdf"

with open(pdf_filename, "wb") as pdf_file:
    pdf_file.write(response.content)

# Extract text from the PDF
extracted_text = extract_text(pdf_filename)

#  Process the text
# Split into sections based on page numbers or headings
sections = extracted_text.split("\n\n")  # Use double newlines as section separators


# Count word frequencies (ignoring common stop words for simplicity)
words = re.findall(r"\b\w+\b", extracted_text.lower())
stop_words = {
    "the",
    "and",
    "of",
    "to",
    "a",
    "in",
    "on",
    "for",
    "is",
    "with",
    "this",
    "that",
}
word_frequencies = Counter(word for word in words if word not in stop_words)

#  Display results
print("\n--- Extracted Text Summary ---")
print(f"Total Sections: {len(sections)}")


print("\n--- Top 10 Most Frequent Words ---")
for word, freq in word_frequencies.most_common(10):
    print(f"{word}: {freq}")

print("\n--- Sample Section ---")
print(sections[1] if len(sections) > 1 else "No sections found.")