exportPdfFromHtml.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

"""Transforms all HTML files into PDF files.

Transforms all HTML files into PDF files, so they can offered as PDF hand out 
of the HTML documentation.
Script can run independently or get called from another script "generator.py".
Only precondition is, that in the subdirectory "_www" HTML files are existing.

USAGE:
1)  Call as a stand alone script:
    python.exe exportPdfFromHtml.py
    just call the main() function
2)  Call as imported script from other scripts:
    import exportPdfFromHtml
    exportPdfFromHtml.run()

Expects following directory tree:

project_root_directory
├── _www ... here are all generated HTML files which get exported to PDFs
├── _pdf ... here all exported PDFs are stored by this script
└── exportPdfFromHtml.py ... Python exporter script for PDFs

It is strongly recommended to setup all necessary parameters in the 
init() function, before running it for the first time.

Expects following directory tree for the external application installation:

User_home_directory parameters
└── installations
    └── wkhtmltox
        └── bin
            └── wkhtmltopdf.exe
"""

import os
import shutil
import subprocess
import time
from config_exportPdfFromHtml import init

# ---------------------------
def run():
    """
    Use this function from other scripts to start all PDF transformations
    """
    print("DEBUG: run()")

    parameters = init()

    # check if precondition is fulfilled: file path "_www" exists
    aPath = parameters['html_input_path']
    if not os.path.isdir(aPath):
        print("FATAL: No HTML files to transform into PDFs found!")
        print("INFO:  Maybe you need to run the HTML generator first?")
        exit(1)

    # delete PDF export path and create a new one to get filled
    #cleanup(parameters)

    handle_all_files(parameters)


# ---------------------------
def cleanup(parameters):
    """
    delete PDF export path and create a new one to get filled

    Parameter
    ---------
    parameters (dict)
        dictionary with globallly useed script parameters

    Returns
    -------
        none
    """
    aPath = parameters['pdf_output_path']
    if os.path.isdir(aPath):
        shutil.rmtree(aPath)
        print("DEBUG: aPath deleted:", aPath)
    
    os.makedirs(aPath)
    print("DEBUG: aPath created:", aPath)
    
    print("DEBUG: cleanup()")


# ---------------------------
def wait_for_file_written(file_path) -> bool:
    """
    checks if file got written within of 5 seconds timeout

    Parameter
    ---------
    file_path (str)
        absolut path to the file

    Returns
    -------
    bool
        True  file got written
        False file not written, due to timeout or no permission
    """
    print("DEBUG: wait_for_file_written()")
    timeout = 0
    SLEEP_TIME = 0.2 # 200 millisoconds
    MAX_TIMEOUT = 25 # 25 * 200ms = 5 sec
    
    while True:
        if os.path.exists(file_path):
            return True # file got written
        else:
            time.sleep(0.2)
            timeout += 1
            
            if timeout > MAX_TIMEOUT:
                print("FATAL: timeout exceeded!")
                return False # file not written after timeout

# ---------------------------
def handle_all_files(parameters):
    """
    Loops through all files in the input directory. Depending from the file
    extension the corresponding tranformer function for pdf transformation gets
    called
    
    Parameter
    ---------
    parameters (dict)
        dictionary with globallly useed script parameters

    Returns
    -------
        none
    """

    print("DEBUG: handle_all_files()")

    files = os.listdir(parameters['html_input_path'])
    
    for filename in files:
        filepath = os.path.join(parameters['html_input_path'], filename)
        
        if os.path.isfile(filepath):
            if filename.endswith(".html"):
                # Handle HTML files
                print("DEBUG: Handle", filename)
                filename = filename[:-5]
                export_html_to_pdf(parameters, filename)

# ---------------------------
def export_html_to_pdf(parameters, filename):
    """"
    exports HTML file into a PDF file
    
    Parameter
    ---------

    Returns
    --------
        none
    """
    print("DEBUG: export_html_to_pdf()")
    
    html_file_path = os.path.join(parameters['html_input_path'], 
        filename + ".html")
        
    pdf_file_path = os.path.join(parameters['pdf_output_path'], 
            filename + ".pdf")

    command = [
        parameters['wkhtmltopdf_app_path'],
        html_file_path,
        "--enable-local-file-access",
        pdf_file_path
    ]
    subprocess.run(command)

    if wait_for_file_written(pdf_file_path):
        print("PDF written to", pdf_file_path)
    else:
        print("ERROR:", pdf_file_path)

# ---------------------------
# MAIN
# ---------------------------
if __name__ == '__main__':
    """
    
    """
    print("DEBUG: MAIN started")

    run()

    print("DEBUG: MAIN done")