def render_categories(
base_path: str,
links_by_category: LinksByCategory,
categories,
template,
):
logger.info("Rendering categories.")
for category_str, links in links_by_category.items():
category = categories[category_str]
file_path: str = join(base_path, cast(str, category["path"]),
"index.html")
root_path: str = get_category_root_path(category_str)
with open(file_path, "w") as file:
file.write(
htmlmin(
template.render(
site_title=ENV["SITE_TITLE"],
links=links,
root_path=root_path,
category=category,
categories=categories,
env=ENV,
),
**HTMLMIN_KWARGS,
))
for category_str, category in categories.items():
if category_str in links_by_category:
continue
file_path = join(base_path, category["path"], "index.html")
root_path = get_category_root_path(category_str)
with open(file_path, "w") as file:
file.write(
htmlmin(
template.render(
links=[],
root_path=root_path,
category=category,
categories=categories,
env=ENV,
),
**HTMLMIN_KWARGS,
))
def minify_html_file(filename):
"""Create a minified HTML file, overwriting the original.
:param str filename: The file to minify.
"""
with open(filename, encoding='utf-8') as f:
raw = f.read()
with open(filename, 'w', encoding='utf-8') as f:
logger.debug('Minifying: %s' % filename)
f.write(htmlmin(raw))
def render_links(
base_path: str,
links_by_category: LinksByCategory,
template: Template,
):
logger.info("Rendering links.")
force = strtobool(cast(str, ENV.get("FORCE_SCREENSHOT", "False")))
cleaner_js: str = """
document.getElementsByTagName('header')[0].style.background='none';
document.getElementsByTagName('form')[0].remove();
document.getElementById('page').style.margin=0;
document.getElementById('link_detail').style.margin=0;
text = document.getElementsByTagName('h1')[0].textContent;
document.getElementsByTagName('h1')[0].textContent=text.toUpperCase();
document.getElementsByTagName('header')[0].style.background='none';
document.getElementsByTagName('script')[0].remove();
document.getElementsByClassName('meta')[0].remove();
document.getElementsByClassName('socializer')[0].remove()
document.getElementsByTagName('p')[1].classList.remove('mb');
"""
browser = get_browser()
if browser is None:
logger.info("Not able to run Selenium. "
"Screenshots will not be generated.")
for category_str, links in links_by_category.items():
for link in links:
file_path = join(base_path, cast(str, link.file_path))
image_url: str = f"{link.file_path}.png"
with open(file_path, "w") as file:
file.write(
htmlmin(
template.render(
link=link,
root_path=get_category_root_path(category_str),
image_url=image_url,
env=ENV,
),
**HTMLMIN_KWARGS,
))
logger.debug(f'{file_path} written.')
image_path = join(base_path, image_url)
if force or not exists(image_path) and browser:
browser.get("file://" + join(base_path, file_path))
browser.execute_script(cleaner_js)
browser.save_screenshot(join(base_path, image_url))
if browser:
browser.close()
def render_sitemap(
root_path: str,
categories: Dict[str, Union[str, None, List[str]]],
links_by_category: LinksByCategory,
sitemap_template: Template,
):
logger.info("Rendering sitemap.")
with open(join(root_path, "sitemap.xml"), "w") as file:
file.write(
htmlmin(
sitemap_template.render(
root_path=root_path,
links_by_category=links_by_category,
categories=categories,
render_date=datetime.date.today(),
strftime=datetime.date.strftime,
),
**HTMLMIN_KWARGS,
))
def process_html(pathSelf, raw):
dependencies = re.finditer(r'(href|src)="(/?[^"/][^":]*\.(css|js|json))"', raw)
for match in dependencies:
dependency = match.group(0)
prop = match.group(1)
path = match.group(2)
pathResolved = resolve_path(pathSelf, path)
if pathResolved not in all_assets:
print("# Skipping:", pathResolved, file=sys.stderr)
continue
pathDigest = digestify_path(path, pathResolved)
raw = raw.replace(dependency, prop + '="' + pathDigest + '"')
meta.deps.add((pathSelf, pathResolved))
raw = process_includes(pathSelf, raw)
raw = process_paths(pathSelf, raw)
return htmlmin(raw,
remove_comments=True,
remove_optional_attribute_quotes=False,
)
def render_home(
base_path: str,
link_rows: List[LinkRow],
categories: Dict[str, Union[str, None, List[str]]],
template: Template,
):
logger.info("Rendering homepage.")
links = get_links_by_date(link_rows)
last_update = datetime.date.today()
file_path = join(base_path, "index.html")
with open(file_path, "w") as file:
file.write(
htmlmin(
template.render(
latest_links=links[:50],
root_path="./",
categories=categories,
last_update=last_update,
num_of_links=len(link_rows),
env=ENV,
),
**HTMLMIN_KWARGS,
))
def minifyHTMLProc(srcText):
srcText = srcText.replace("<script", "<script async")
return htmlmin(srcText)
