llama_parse_pdf_folder.py

import os

from llama_parse import LlamaParse  # pip install llama-parse
from llama_index.core import SimpleDirectoryReader  # pip install llama-index
source_directory = r'\data'
target_directory = r'\tables'

parser = LlamaParse(
    api_key="...",  # can also be set in your env as LLAMA_CLOUD_API_KEY
    result_type="markdown",  # "markdown" and "text" are available
    verbose=True,
    num_workers=9, 
    language="en",
    parsing_instruction="Electrical engineering codes"
)
file_extractor = {".pdf": parser}
reader = SimpleDirectoryReader(source_directory, file_extractor=file_extractor)
documents = reader.load_data()

for doc in documents:
    file_name = doc.metadata['file_name']
    txt_file_name = os.path.splitext(file_name)[0] + "-lp.txt"
    txt_file_path = os.path.join(target_directory, txt_file_name)
    print(doc.text)
    with open(txt_file_path, 'w', encoding='utf-8') as txt_file:
        txt_file.write(doc.text)