Last active
April 8, 2024 17:16
-
-
Save djsegal/2c6d7aaf432303a76e4829071b3c1261 to your computer and use it in GitHub Desktop.
Convert PDF of CSV file to JSON with hardcoded keys for each entry
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import fitz # PyMuPDF | |
import json | |
def pdf_to_json(pdf_path, json_path): | |
doc = fitz.open(pdf_path) | |
data_list = [] | |
for page_num in range(len(doc)): | |
page = doc.load_page(page_num) | |
text = page.get_text().replace("а́\n-", "а́-") | |
for line in text.split('\n'): | |
if line == "": | |
continue | |
parts = line.split(',', 1) | |
assert len(parts) == 2 | |
lr, location = parts[0].strip(), parts[1].strip().strip("\"").strip() | |
data_list.append({"lr": lr, "location": location}) | |
with open(json_path, 'w', encoding='utf-8') as json_file: | |
json_file.write('[\n') | |
for i, item in enumerate(data_list): | |
# Customized JSON string for each item with separators and indent for readability | |
json_str = json.dumps(item, ensure_ascii=False, separators=(',', ': ')).replace('","', '", "') | |
json_file.write(f' {json_str}') | |
if i < len(data_list) - 1: | |
json_file.write(',\n') | |
else: | |
json_file.write('\n') | |
json_file.write(']') | |
print(f"PDF content has been successfully converted to JSON and saved to: \n{json_path}") | |
# Example usage | |
pdf_path = 'path_to_your_pdf.pdf' # Update this with the actual path to your PDF file | |
json_path = pdf_path.replace(".pdf", ".json") | |
pdf_to_json(pdf_path, json_path) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment