orgmode-to-gemini-blog/enrich_html.py

#!/bin/python3
import argparse
import os
from utils import *
from website_config import configs_sites

parser = argparse.ArgumentParser(description="Générer un site Web à partir de fichiers HTML.")
parser.add_argument("blog_name", help="Le chemin vers le dossier contenant les fichiers HTML.")

parser.add_argument("--style", default="templates/style_general.css", help="Le chemin vers le fichier de style CSS.")
args = parser.parse_args()

# Style CSS minimaliste
style_file = args.style

blog_name = args.blog_name.replace('html-websites/', '')
html_pages =  'html-websites/'+blog_name
source_blog = f"sources/{blog_name}"
header_content_path = f"{source_blog}/templates/converted/header_page.html"
footer_content_path = f"{source_blog}/templates/converted/footer_page.html"
static_page_path = f"{source_blog}/templates/html/static.html"

enable_header=True

mylog('---------- blog name ', blog_name)
template_content = configs_sites[blog_name]

after_article = ''

inline_the_css = False
# inline_the_css=True


def enrich_one_file(html_content: str, partials: dict = {"header_page": "", "footer_content": ""}) -> str:
    """
        Enrich a single HTML file by removing certain parts, extracting the body content, and incorporating a template.
        The function also includes options to inline the CSS and customize the HTML content based on the provided partials.

        Parameters:
        html_content (str): The original HTML content to be enriched.
        partials (dict, optional): A dictionary containing partial HTML content for the header and footer. The default values are empty strings.

        Returns:
        str: The enriched HTML content.
        """
    # remove some parts
    html_content = extract_body_content(html_content)
    html_content = remove_properties_section(html_content)
    html_content = remove_article_head_properties_orgmode(html_content)
    html_content = remove_hint_html(html_content)


    if inline_the_css is True:
        mylog(' ----------- enrich_html: include css inline in each html page')
        with open(os.path.join(root_path, file), "r") as f:
            css_content = f.read()
            css_content = "<style type='text/css'>{css_content}</style>"
            template_content["CSS_INLINE_CONTENT"] = css_content
    template_content["PAGE_SLUG"] = find_slug_in_file_basename(file)
    # remplir le template
    html_content = f"""
    
    <!DOCTYPE html>
<html>
    <head>
        <meta charset="UTF-8">
        <meta name="viewport" content="width=device-width, initial-scale=1">
        <meta property="og:image" content="{template_content['SITE_ICON']}">
        <meta property="og:locale" content="{template_content['LOCALE']}">
        <meta property="og:description" content="{template_content['BLOG_SUBTITLE']}">
        <meta property="og:url" content="{template_content['NDD']}">
        <meta property="og:site_name" content="{template_content['TITLE']}">
        <link rel="alternate" type="application/atom+xml" title="Cipher Bliss » Flux" href="{template_content['NDD']}/feed/">
        <link href="/style.css" rel="stylesheet">
        <script src="main_script.js"></script>
        <meta charset="utf-8">
        <meta name="viewport" content="width=device-width, initial-scale=1">
        <title>{template_content['TITLE']}</title>
        <meta name="author" content="{template_content['AUTHOR']}">
        <link rel="alternate" type="application/rss+xml" title="{template_content['BLOG_TITLE']} » Flux"
            href="{template_content['NDD']}/feed/">
        <meta property="og:title" content="{template_content['PAGE_TITLE']}">
        <meta property="og:locale" content="{template_content['LOCALE']}">
        <!-- Description de la page -->
        <meta name="description" content="{template_content['PAGE_TITLE']}">
        <meta name="reply-to" content="{template_content['EMAIL']}">
        <link rel="icon" type="{template_content['SITE_ICON_TYPE']}" href="{template_content['SITE_ICON']}">
    </head>

    <body>
        <div id="page" class="page__{template_content["PAGE_SLUG"]}">
            <header id="masthead" class="site-header">
                <div class="header-image" style="background: url({template_content['BANNIERE_ENTETE']})">
                    <a href="/">
                    <img src="{template_content['SITE_ICON']}" class="site-icon img">
                    </a>
                    <h1 class="blog-title">{template_content['BLOG_TITLE']}</h1>
                    <p class="blog-subtitle">{template_content['BLOG_SUBTITLE']}</p>
                    <div class="template-header">
                    
                    </div>
                </div>
                    <nav class="navbar is-fixed-top is-dark" role="navigation" aria-label="main navigation">
                        <div class="navbar-brand">
                            <a class="navbar-item" href="{template_content['NDD']}">
                                {template_content['NDD']}
                            </a>
                        </div>

                        <div id="navbarBasicExample" class="navbar-menu">
                            <div class="navbar-start">
                                <a class="logo" href="{template_content['NDD']}">
                                    <img src="{template_content['SITE_ICON']}"
                                        class="img-fluid">
                                </a>
                                {template_content['NAVIGATION']}
                            </div>
                            <div class="navbar-end">
                                <div class="navbar-item">
                                    <form role="search" method="get" class="search-form" action="/" id="recherche">
                                        <label>
                                            <input class="search-field" placeholder="Recherche" value="" name="s"
                                                type="search">
                                        </label>
                                        <input class="is-hidden search-submit" value="Rechercher" type="submit">
                                    </form>
                                </div>
                            </div>
                        </div>
                    </nav>
            </header>
            <main class="body-wrap boxed-container">
                <article class="content">
                    {html_content}
                    <p class="after-article">
                    {after_article}
                    </p>
                </article>
            </main>
            <footer class="site-footer has-top-divider">
                <div class="container">
                    <div class="site-footer-inner">
                        <div class="site-foot">
                        </div>
                        <nav class="footer-nav">
                            {template_content['NAVIGATION']}
                            <a href="/tags/">Tags</a>
                            <a href=""{template_content['NDD']}/feed/">Flux Atom</a>
                        </nav>
                    </div>
                </div>
            </footer>
        </div>
    </body>
    <!-- généré avec orgmode-to-gemini-blog par Tykayn -->
</html>
 
"""
    # {partials['footer_page']}
    # {partials['header_page']}
    return html_content


def ouvrir_fichier(chemin_fichier):
    if os.path.exists(chemin_fichier):
        with open(chemin_fichier, 'r') as fichier:
            # Faire quelque chose avec le fichier ouvert
            contenu = fichier.read()
            return contenu
    else:
        print(f"Le fichier {chemin_fichier} n'existe pas.")
        return ''

liste_fichiers_du_blog_convertis = os.walk(html_pages)
mylog('fichiers à enrichir:', liste_fichiers_du_blog_convertis)

count_articles=0
# Parcourir tous les fichiers HTML dans le dossier du blog donné
for root_path, dirs, files in liste_fichiers_du_blog_convertis :

    # Prendre les templates partiaux pour chaque site web
    partials = {
        "header_content": "",
        "footer_content": "",
    }

    print(len(files))
    partials["header_content"] = ouvrir_fichier(os.path.join('sources',blog_name, 'templates', 'header_page.org'))
    partials["footer_content"] = ouvrir_fichier(os.path.join('sources',blog_name, 'templates', 'footer_page.org'))

    for file in files:
        # mylog(file)
        # if file == "index.html":
        #     template_content['no_header']=True

        if file.endswith(".html"):
            # mylog(' ----------- enrich_html: file:'+ os.path.join(root_path, file))
            count_articles+=1
            mylog(' ----------- enrich_html: CSS inline: ', inline_the_css)

            # Ouvrir le fichier HTML en mode lecture
            with open(os.path.join(root_path, file), "r") as f:
                html_content = f.read()

            html_content = enrich_one_file(html_content, partials)
            html_path_enriched = os.path.join(root_path, file)
            mylog(' ----------- enrich_html: html_path_enriched ============> ', html_path_enriched)
            # Écrire le contenu modifié dans le fichier HTML
            with open(html_path_enriched, "w") as f:
                f.write(html_content)
                mylog('\n ----------- enrich_html: html écrit ', html_path_enriched)

print('articles listés :',count_articles)
change enrich template 2024-11-03 11:42:44 +01:00			`#!/bin/python3`
			`import argparse`
refacto 2024-11-14 13:32:56 +01:00			`import os`
up style 2024-11-14 16:22:34 +01:00			`from utils import *`
variabilize blog params 2024-11-12 00:55:21 +01:00			`from website_config import configs_sites`
separate hard to convert files 2024-11-04 00:13:58 +01:00
change enrich template 2024-11-03 11:42:44 +01:00			`parser = argparse.ArgumentParser(description="Générer un site Web à partir de fichiers HTML.")`
replace org content, make global style for generated site 2024-11-09 00:19:43 +01:00			`parser.add_argument("blog_name", help="Le chemin vers le dossier contenant les fichiers HTML.")`
refacto 2024-11-14 13:32:56 +01:00
up 2024-11-08 18:16:36 +01:00			`parser.add_argument("--style", default="templates/style_general.css", help="Le chemin vers le fichier de style CSS.")`
change enrich template 2024-11-03 11:42:44 +01:00			`args = parser.parse_args()`
up readme 2024-11-03 10:29:30 +01:00
separate hard to convert files 2024-11-04 00:13:58 +01:00			`# Style CSS minimaliste`
change enrich template 2024-11-03 11:42:44 +01:00			`style_file = args.style`
up 2024-11-08 18:05:08 +01:00
refacto 2024-11-14 13:32:56 +01:00			`blog_name = args.blog_name.replace('html-websites/', '')`
up style 2024-11-14 16:22:34 +01:00			`html_pages = 'html-websites/'+blog_name`
replace org content, make global style for generated site 2024-11-09 00:19:43 +01:00			`source_blog = f"sources/{blog_name}"`
site builder ok 2024-11-11 00:58:44 +01:00			`header_content_path = f"{source_blog}/templates/converted/header_page.html"`
			`footer_content_path = f"{source_blog}/templates/converted/footer_page.html"`
add scss converter 2024-11-10 00:01:15 +01:00			`static_page_path = f"{source_blog}/templates/html/static.html"`

up style 2024-11-14 16:22:34 +01:00			`enable_header=True`

auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`mylog('---------- blog name ', blog_name)`
refacto 2024-11-14 13:32:56 +01:00			`template_content = configs_sites[blog_name]`

			`after_article = ''`

			`inline_the_css = False`
			`# inline_the_css=True`
site builder ok 2024-11-11 00:58:44 +01:00
up style and template 2024-11-10 00:16:15 +01:00
up tkblog source 2024-11-15 01:45:11 +01:00			`def enrich_one_file(html_content: str, partials: dict = {"header_page": "", "footer_content": ""}) -> str:`
			`"""`
			`Enrich a single HTML file by removing certain parts, extracting the body content, and incorporating a template.`
			`The function also includes options to inline the CSS and customize the HTML content based on the provided partials.`

			`Parameters:`
			`html_content (str): The original HTML content to be enriched.`
			`partials (dict, optional): A dictionary containing partial HTML content for the header and footer. The default values are empty strings.`

			`Returns:`
			`str: The enriched HTML content.`
			`"""`
try finding article name from content 2024-11-11 00:02:50 +01:00			`# remove some parts`
up tkblog source 2024-11-15 01:45:11 +01:00			`html_content = extract_body_content(html_content)`
site builder ok 2024-11-11 00:58:44 +01:00			`html_content = remove_properties_section(html_content)`
			`html_content = remove_article_head_properties_orgmode(html_content)`
			`html_content = remove_hint_html(html_content)`

up style and template 2024-11-10 00:16:15 +01:00
site builder ok 2024-11-11 00:58:44 +01:00			`if inline_the_css is True:`
auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`mylog(' ----------- enrich_html: include css inline in each html page')`
copy style 2024-11-08 23:19:39 +01:00			`with open(os.path.join(root_path, file), "r") as f:`
			`css_content = f.read()`
			`css_content = "<style type='text/css'>{css_content}</style>"`
up style 2024-11-14 16:22:34 +01:00			`template_content["CSS_INLINE_CONTENT"] = css_content`
up atom feed generate 2024-11-18 11:18:50 +01:00			`template_content["PAGE_SLUG"] = find_slug_in_file_basename(file)`
try finding article name from content 2024-11-11 00:02:50 +01:00			`# remplir le template`
more complex template html 2024-11-10 18:03:31 +01:00			`html_content = f"""`
add scss converter 2024-11-10 00:01:15 +01:00
more complex template html 2024-11-10 18:03:31 +01:00			`<!DOCTYPE html>`
			`<html>`
			`<head>`
			`<meta charset="UTF-8">`
			`<meta name="viewport" content="width=device-width, initial-scale=1">`
variabilize blog params 2024-11-12 00:55:21 +01:00			`<meta property="og:image" content="{template_content['SITE_ICON']}">`
			`<meta property="og:locale" content="{template_content['LOCALE']}">`
			`<meta property="og:description" content="{template_content['BLOG_SUBTITLE']}">`
			`<meta property="og:url" content="{template_content['NDD']}">`
			`<meta property="og:site_name" content="{template_content['TITLE']}">`
up atom feed generate 2024-11-18 11:18:50 +01:00			`<link rel="alternate" type="application/atom+xml" title="Cipher Bliss » Flux" href="{template_content['NDD']}/feed/">`
more complex template html 2024-11-10 18:03:31 +01:00			`<link href="/style.css" rel="stylesheet">`
script js pour recherche par moteur externe 2024-11-16 00:44:19 +01:00			`<script src="main_script.js"></script>`
more complex template html 2024-11-10 18:03:31 +01:00			`<meta charset="utf-8">`
			`<meta name="viewport" content="width=device-width, initial-scale=1">`
variabilize blog params 2024-11-12 00:55:21 +01:00			`<title>{template_content['TITLE']}</title>`
			`<meta name="author" content="{template_content['AUTHOR']}">`
			`<link rel="alternate" type="application/rss+xml" title="{template_content['BLOG_TITLE']} » Flux"`
			`href="{template_content['NDD']}/feed/">`
			`<meta property="og:title" content="{template_content['PAGE_TITLE']}">`
			`<meta property="og:locale" content="{template_content['LOCALE']}">`
more complex template html 2024-11-10 18:03:31 +01:00			`<!-- Description de la page -->`
variabilize blog params 2024-11-12 00:55:21 +01:00			`<meta name="description" content="{template_content['PAGE_TITLE']}">`
			`<meta name="reply-to" content="{template_content['EMAIL']}">`
			`<link rel="icon" type="{template_content['SITE_ICON_TYPE']}" href="{template_content['SITE_ICON']}">`
more complex template html 2024-11-10 18:03:31 +01:00			`</head>`

			`<body>`
up style 2024-11-14 16:22:34 +01:00			`<div id="page" class="page__{template_content["PAGE_SLUG"]}">`
more complex template html 2024-11-10 18:03:31 +01:00			`<header id="masthead" class="site-header">`
variabilize blog params 2024-11-12 00:55:21 +01:00			`<div class="header-image" style="background: url({template_content['BANNIERE_ENTETE']})">`
style sass 2024-11-10 18:43:38 +01:00			`<a href="/">`
variabilize blog params 2024-11-12 00:55:21 +01:00			`<img src="{template_content['SITE_ICON']}" class="site-icon img">`
style sass 2024-11-10 18:43:38 +01:00			`</a>`
variabilize blog params 2024-11-12 00:55:21 +01:00			`<h1 class="blog-title">{template_content['BLOG_TITLE']}</h1>`
			`<p class="blog-subtitle">{template_content['BLOG_SUBTITLE']}</p>`
refacto 2024-11-14 13:32:56 +01:00			`<div class="template-header">`

			`</div>`
more complex template html 2024-11-10 18:03:31 +01:00			`</div>`
			`<nav class="navbar is-fixed-top is-dark" role="navigation" aria-label="main navigation">`
			`<div class="navbar-brand">`
variabilize blog params 2024-11-12 00:55:21 +01:00			`<a class="navbar-item" href="{template_content['NDD']}">`
script js pour recherche par moteur externe 2024-11-16 00:44:19 +01:00			`{template_content['NDD']}`
more complex template html 2024-11-10 18:03:31 +01:00			`</a>`
			`</div>`

			`<div id="navbarBasicExample" class="navbar-menu">`
			`<div class="navbar-start">`
unify slugs 2024-11-15 23:55:20 +01:00			`<a class="logo" href="{template_content['NDD']}">`
variabilize blog params 2024-11-12 00:55:21 +01:00			`<img src="{template_content['SITE_ICON']}"`
more complex template html 2024-11-10 18:03:31 +01:00			`class="img-fluid">`
			`</a>`
variabilize blog params 2024-11-12 00:55:21 +01:00			`{template_content['NAVIGATION']}`
more complex template html 2024-11-10 18:03:31 +01:00			`</div>`
			`<div class="navbar-end">`
			`<div class="navbar-item">`
script js pour recherche par moteur externe 2024-11-16 00:44:19 +01:00			`<form role="search" method="get" class="search-form" action="/" id="recherche">`
more complex template html 2024-11-10 18:03:31 +01:00			`<label>`
			`<input class="search-field" placeholder="Recherche" value="" name="s"`
			`type="search">`
			`</label>`
			`<input class="is-hidden search-submit" value="Rechercher" type="submit">`
			`</form>`
			`</div>`
			`</div>`
			`</div>`
			`</nav>`
			`</header>`
			`<main class="body-wrap boxed-container">`
			`<article class="content">`
			`{html_content}`
site builder ok 2024-11-11 00:58:44 +01:00			`<p class="after-article">`
			`{after_article}`
			`</p>`
more complex template html 2024-11-10 18:03:31 +01:00			`</article>`
			`</main>`
			`<footer class="site-footer has-top-divider">`
			`<div class="container">`
			`<div class="site-footer-inner">`
refacto 2024-11-14 13:32:56 +01:00			`<div class="site-foot">`
			`</div>`
			`<nav class="footer-nav">`
			`{template_content['NAVIGATION']}`
auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`<a href="/tags/">Tags</a>`
up atom feed generate 2024-11-18 11:18:50 +01:00			`<a href=""{template_content['NDD']}/feed/">Flux Atom</a>`
refacto 2024-11-14 13:32:56 +01:00			`</nav>`
more complex template html 2024-11-10 18:03:31 +01:00			`</div>`
			`</div>`
			`</footer>`
			`</div>`
replace org content, make global style for generated site 2024-11-09 00:19:43 +01:00			`</body>`
more complex template html 2024-11-10 18:03:31 +01:00			`<!-- généré avec orgmode-to-gemini-blog par Tykayn -->`
			`</html>`

add scss converter 2024-11-10 00:01:15 +01:00			`"""`
refacto 2024-11-14 13:32:56 +01:00			`# {partials['footer_page']}`
			`# {partials['header_page']}`
			`return html_content`


			`def ouvrir_fichier(chemin_fichier):`
			`if os.path.exists(chemin_fichier):`
			`with open(chemin_fichier, 'r') as fichier:`
			`# Faire quelque chose avec le fichier ouvert`
			`contenu = fichier.read()`
			`return contenu`
			`else:`
up conf for several websites 2024-11-18 13:10:30 +01:00			`print(f"Le fichier {chemin_fichier} n'existe pas.")`
			`return ''`
up 2024-11-08 18:05:08 +01:00
up style 2024-11-14 16:22:34 +01:00			`liste_fichiers_du_blog_convertis = os.walk(html_pages)`
auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`mylog('fichiers à enrichir:', liste_fichiers_du_blog_convertis)`
up style 2024-11-14 16:22:34 +01:00
auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`count_articles=0`
up style 2024-11-14 16:22:34 +01:00			`# Parcourir tous les fichiers HTML dans le dossier du blog donné`
			`for root_path, dirs, files in liste_fichiers_du_blog_convertis :`
replace org content, make global style for generated site 2024-11-09 00:19:43 +01:00
refacto 2024-11-14 13:32:56 +01:00			`# Prendre les templates partiaux pour chaque site web`
			`partials = {`
			`"header_content": "",`
			`"footer_content": "",`
			`}`

up style 2024-11-14 16:22:34 +01:00			`print(len(files))`
			`partials["header_content"] = ouvrir_fichier(os.path.join('sources',blog_name, 'templates', 'header_page.org'))`
			`partials["footer_content"] = ouvrir_fichier(os.path.join('sources',blog_name, 'templates', 'footer_page.org'))`
refacto 2024-11-14 13:32:56 +01:00
up readme 2024-11-03 10:29:30 +01:00			`for file in files:`
auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`# mylog(file)`
			`# if file == "index.html":`
			`# template_content['no_header']=True`
up style 2024-11-14 16:22:34 +01:00
up readme 2024-11-03 10:29:30 +01:00			`if file.endswith(".html"):`
auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`# mylog(' ----------- enrich_html: file:'+ os.path.join(root_path, file))`
			`count_articles+=1`
			`mylog(' ----------- enrich_html: CSS inline: ', inline_the_css)`
refacto 2024-11-14 13:32:56 +01:00
			`# Ouvrir le fichier HTML en mode lecture`
			`with open(os.path.join(root_path, file), "r") as f:`
			`html_content = f.read()`

			`html_content = enrich_one_file(html_content, partials)`
			`html_path_enriched = os.path.join(root_path, file)`
auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`mylog(' ----------- enrich_html: html_path_enriched ============> ', html_path_enriched)`
refacto 2024-11-14 13:32:56 +01:00			`# Écrire le contenu modifié dans le fichier HTML`
			`with open(html_path_enriched, "w") as f:`
			`f.write(html_content)`
auto detect tags and move pictures after resizing 2024-11-15 15:58:19 +01:00			`mylog('\n ----------- enrich_html: html écrit ', html_path_enriched)`

			`print('articles listés :',count_articles)`