def render_html(self, data):
template = self.templateEnv.get_template(data["file"])
if "page_data" not in data:
data["page_data"] = dict()
html = minify_html.minify(template.render(data["page_data"]),
minify_js=True)
return html
def render(
self,
template: str,
content_file: Optional[pathlib.Path] = None,
render_args: Dict[str, Any] = {},
outfile: Optional[pathlib.Path] = None,
) -> None:
args = self._args.copy()
args.update(render_args)
if content_file:
self._render_args_from_rst(content_file, args)
if not outfile:
outfile = content_file.relative_to(
self._content_root).with_suffix('.html')
if not outfile:
raise ValueError(
'Neither `content_file` not `outfile` were supplied')
outfile = self._outdir.joinpath(outfile)
root = pathlib.Path(os.path.relpath(self._outdir, outfile.parent))
static = root / 'static'
args['root'] = root
args['css'] = static / 'css'
args['img'] = static / 'img'
args['js'] = static / 'js'
try:
html = self._templates.get_template(template).render(**args)
except Exception as e:
html = mako.exceptions.html_error_template().render().decode()
raise e
finally:
self._write(outfile,
minify_html.minify(html) if self._minify else html)
def html_validator(html: str) -> str:
html = stripBr(html)
# validate invalid HTML first, since minify_html is not so robust
html = BeautifulSoup(html, 'lxml').decode()
html = minify(html,
do_not_minify_doctype=True,
keep_closing_tags=True,
keep_spaces_between_attributes=True,
ensure_spec_compliant_unquoted_attribute_values=True,
remove_processing_instructions=True)
html = replaceInvalidSpace(html)
return html
def minify_html(file_name):
with open(file_name, "r") as in_file:
content = in_file.read()
print(file_name, "size:", len(content))
minified_content = minify_html_module.minify(content,
minify_js=False,
minify_css=True)
print(file_name, "new size:", len(minified_content))
print(file_name, "gain:",
str((len(minified_content) / len(content) * 100).__round__(2)) + "%")
with open(file_name, "w") as out_file:
out_file.write(minified_content)
"""url = "https://htmlcompressor.com/compress"
def process_response(self, request, response):
s = response.content.decode("utf-8")
try:
s = minify_html.minify(s)
except:
s = htmlmin.minify(s, remove_comments=True, remove_all_empty_space=True)
response.content = s
response["Content-Length"] = len(response.content)
duration = time.time() - self.ts
response["X-Duration"] = duration*1000
return response
def main():
# where is the server
port = 62435
handler = http.server.SimpleHTTPRequestHandler
server = socketserver.TCPServer(("", port), handler)
thread = threading.Thread(target=server.serve_forever)
thread.daemon = True # so the server dies when the program exits
thread.start()
local_page = f'http://localhost:{port}/dynamic_page.html'
html = load_page_firefox(local_page)
server.shutdown() # kill the server since we are done with it
soup = bs(html, "html.parser")
update_page(soup)
try:
minified = minify_html.minify(str(soup),
minify_js=False,
minify_css=False)
with open('index.html', 'w', encoding='utf-8') as f:
f.write(f"<!DOCTYPE html>{minified}")
except SyntaxError as e:
print(e)
def build_dist_html(input_html,
output_html,
data_json_file=None,
compress=False):
"""
Creates a single distributable HTML file.
Reads the input_html and internalizes all CSS, JS, and data files into the output html. For web ressources: First
try to load a local file, else try to download file.
:param input_html: the input html file that defines all dependencies
:param output_html: the bundled HTML file
:return: None
"""
original_html_text = Path(input_html).read_text(encoding="utf-8")
soup = BeautifulSoup(original_html_text)
# Find link tags. example: <link rel="stylesheet" href="css/somestyle.css">
for tag in soup.find_all('link', href=True):
if tag.has_attr('href'):
file_text = Path(tag['href']).read_text(encoding="utf-8")
# remove the tag from soup
tag.extract()
# insert style element
new_style = soup.new_tag('style')
new_style.string = file_text
soup.html.head.append(new_style)
# Find script tags. example: <script src="js/somescript.js"></script>
for tag in soup.find_all('script', src=True):
if tag.has_attr('src'):
path = tag['src']
path = replace_by_local_file(path)
if path.startswith("http"):
response = requests.get(path)
response.raise_for_status()
file_text = response.text
else:
file_text = Path(path).read_text()
# try to replace data with PLACEHOLDER_JSON_DATA
if data_json_file is not None and "collapsible_tree" in path:
file_text = replace_data_in_file(data_json_file, file_text)
# remove the tag from soup
tag.extract()
# insert script element
new_script = soup.new_tag('script')
new_script.string = file_text
soup.html.body.append(new_script)
# Find image tags.
for tag in soup.find_all('img', src=True):
if tag.has_attr('src'):
file_content = Path(tag['src']).read_bytes()
# replace filename with base64 of the content of the file
base64_file_content = base64.b64encode(file_content)
tag['src'] = "data:image/png;base64, {}".format(
base64_file_content.decode('ascii'))
out_text = str(soup)
if compress:
try:
import minify_html
out_text = minify_html.minify(out_text,
minify_js=True,
minify_css=True)
except Exception as e:
logger.warning("Error during output compression.")
logger.exception(e)
# Save onefile
with open(output_html, "w", encoding="utf-8") as outfile:
outfile.write(out_text)
for c in i["value"]:
span_error += "<span>" + c + "</span>"
new_content = new_content.replace("$ERROR_SPAN", span_error)
if error_code in custom_text:
name = custom_text[error_code][0]
description = custom_text[error_code][1]
else:
name = i["description"]
description = "" if disable_generic_description else i["details"][
0]["description"]
new_content = new_content.replace("$ERROR_NAME", name)
new_content = new_content.replace("$ERROR_DESC", description)
with open(i["value"] + ".html", "w") as output_file:
try:
minified = minify_html.minify(new_content,
minify_js=False,
minify_css=True)
except SyntaxError as e:
print(e)
output_file.write(minified)
with open("snippets/error_pages_content.conf", "w") as epc:
for i in json["values"]:
v = int(i["value"])
if v < 400 or v > 599:
continue
print("error_page %d /error/%d.html;" % (v, v), file=epc)
print("error_page 495 http://$host;", file=epc)
print("error_page 496 http://$host;", file=epc)
print("error_page 497 https://$host$request_uri;", file=epc)
after `pip install`ing [`Pygments`](https://pygments.org/).
"""
import sys
import markdown as md
import minify_html as mh
import astdocs
headers = """
<!DOCTYPE html>
<html>
<head>
<link rel="stylesheet" href="styles-body.css">
<link rel="stylesheet" href="styles-code.css">
</head>
<body>
"""
footer = """
</body>
</html>
"""
mdwn = astdocs.render(sys.argv[1])
html = md.markdown(mdwn, extensions=["codehilite", "fenced_code", "toc"])
mini = mh.minify(f"{headers}{html}{footer}")
print(mini)
