Basic Sitemap Generator

sitemap.py

#!/usr/bin/env python3

# The MIT License (MIT)
#
# Copyright (c) 2020 novov
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the "Software"), to deal in the
# Software without restriction, including without limitation the rights to use, copy, modify, merge,
# publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom
# the Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all copies or
# substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT
# NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT
# OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

import json, os

def searchHTML(directory,priorities,auto,root = "/"):
    result = {}
    basepriority = 0.6 if root == "/" and auto else 0.5
    
    with os.scandir(directory) as files:
        for file in files: 
            name = root + file.name
            priority = priorities[name] if name in priorities else basepriority
            
            if priority < 0.1: continue
            elif file.name == "index.html" and auto: priority += 0.1
            
            priority = clamp(priority,0,1)
            
            if file.name.endswith(".html"):
                result[name] = priority
            elif file.is_dir():
                newdir = directory + file.name + "/"
                newroot = root + file.name + "/"
                result.update(searchHTML(newdir,priorities,auto,newroot))
      
    return result
    
def clamp(n, minn, maxn):
    return max(min(maxn, n), minn)
    	
 
def main():
    parampath = os.path.split(os.path.realpath(__file__))[0] + '/sitemap.json';
    
    if os.path.isfile(parampath): 
        with open(parampath, 'r') as f: 
            params = json.loads(f.read())
    else: return -1
    
    text = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">"
    entry = """
    <url>
        <loc>{0}{1}</loc>        
        <priority>{2:.1f}</priority>
    </url>"""
                   
    for name, priority in searchHTML(params["site_path"],params["priorities"],params["automate_priorities"]).items():
        text += entry.format(params["site_url"],name,priority)
        
    text += "\n</urlset>" 
    with open(params["site_path"] + params["output_path"], 'w') as f: f.write(text)

if __name__ == '__main__': main()