Mathpix API for Handwriting to Markdown Converion via Python

convertpdf.py

import json
import time
import argparse
import requests

options = {
    "conversion_formats": {"md": True},
    "math_inline_delimiters": ["$", "$"],
    "rm_spaces": True,
    "enable_spell_check":True,
    "improve_mathpix":False,
    "metadata":{
        "improve_mathpix":False,
    },
}

def get_conversation_status(app_id, app_key, pdf_id):
    status = requests.get(f"https://api.mathpix.com/v3/converter/{pdf_id}",
    headers={
        "app_id": app_id,
        "app_key": app_key,
    }                  )
    completed = json.loads(status.text)['status']
    return completed

def get_processing_status(app_id, app_key, pdf_id):
    status = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}",
    headers={
        "app_id": app_id,
        "app_key": app_key,
    }                  )
    completed = json.loads(status.text)['status']
    return completed

    

def main(
        file_path:str, # pdf file path
        app_id:str = "mathpix_id", # Mathpix App ID
        app_key:str = "mathpix_api_key" # mathpix app key
):
    r = requests.post("https://api.mathpix.com/v3/pdf",
        headers={
            "app_id":  app_id,
            "app_key": app_key
        },
        data={
            "options_json": json.dumps(options),
            "metadata": {
                "improve_mathpix": False
              },
        },
        files={
            "file": open(file_path,"rb")
        },
        
    )
    pdf_id = json.loads(r.text)['pdf_id']

    while get_processing_status(app_id, app_key, pdf_id) != 'completed':
        time.sleep(1)


    while get_conversation_status(app_id, app_key, pdf_id) != 'completed':
        time.sleep(1)

    converted = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}.md",
        headers={
            "app_id": app_id,
            "app_key": app_key,
        })
    print(converted.text)
    
main("split page path (File Path)", "mathpix_id", "mathpix_api_key")