Oxbian/BlogGenerator
1
0
Fork 0
Code Issues Pull Requests Activity

Updating function name for more python style name

Browse Source
This commit is contained in:
Oxbian 2023-07-05 23:03:11 +02:00
parent 71623ad067
commit 107578e6dc
2 changed files with 118 additions and 97 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
generator.py
View File

@ -1,9 +1,10 @@
import os import os
import shutil import shutil
from dotenv import load_dotenv from dotenv import load_dotenv
from markdown_parser import * from markdown_parser import parse_md
from datetime import datetime from datetime import datetime
def md2html(filename, env_vars): def md2html(filename, env_vars):
""" """
Create the html webpage from template and markdown content Create the html webpage from template and markdown content
@ -12,19 +13,20 @@ def md2html(filename, env_vars):
return: a dictionnary containing title, metadata, local path, content for HTML return: a dictionnary containing title, metadata, local path, content for HTML
""" """
# Getting parsed content of markdown file & page template # Getting parsed content of markdown file & page template
data = parsemd(filename, env_vars) data = parse_md(filename, env_vars)
template = open(env_vars['template_page'], 'r').read() template = open(env_vars['template_page'], 'r').read()
# Generating the HTML page # Generating the HTML page
output = open(env_vars['pages_path'] + '/' + filename.split('.')[0] + '.html', 'w') output = open(env_vars['pages_path'] + '/' +
output.write(template.replace("$CONTENT", data['content']).replace("$TITLE", data['title']). filename.split('.')[0] + '.html', 'w')
replace("$DATE", data['date']).replace("$DESC", data['description'])) output.write(template.replace("$CONTENT", data['content']).replace(
"$TITLE", data['title']).replace("$DATE", data['date']).replace("$DESC", data['description']))
output.close() output.close()
return data return data
def generatePageXML(data, env_vars): def generate_page_XML(data, env_vars):
""" """
Generate a RSS / Atom post for the page Generate a RSS / Atom post for the page
data: dictionnary generated by the markdown parser data: dictionnary generated by the markdown parser
@ -33,11 +35,10 @@ def generatePageXML(data, env_vars):
""" """
template = open(env_vars['template_atom_post'], 'r').read() template = open(env_vars['template_atom_post'], 'r').read()
date = datetime.strptime(data['date'], "%d-%m-%Y").isoformat() + "Z" date = datetime.strptime(data['date'], "%d-%m-%Y").isoformat() + "Z"
return template.replace("$TITLE", data['title']).replace("$DATE", date).replace("$CONTENT", return template.replace("$TITLE", data['title']).replace("$DATE", date).replace("$CONTENT", data['content']).replace("$URL", env_vars['website_url'] + data['filepath'])
data['content']).replace("$URL", env_vars['website_url'] + data['filepath'])
def generateAtomFeed(posts, env_vars): def generate_atom_feed(posts, env_vars):
""" """
Generate a RSS / Atom feed Generate a RSS / Atom feed
posts: list of data get from markdown pages posts: list of data get from markdown pages
@ -48,16 +49,17 @@ def generateAtomFeed(posts, env_vars):
for post in posts: for post in posts:
# Checking if there is metadata, if not we don't create a RSS / Atom post # Checking if there is metadata, if not we don't create a RSS / Atom post
if post['date'] != '01-01-0001': if post['date'] != '01-01-0001':
atom_content += generatePageXML(post, env_vars) atom_content += generate_page_XML(post, env_vars)
# Generate RSS / atom feed # Generate RSS / atom feed
template = open(env_vars['template_atom_feed'], 'r').read() template = open(env_vars['template_atom_feed'], 'r').read()
output = open(env_vars['parent_path'] + '/atom.xml', 'w') output = open(env_vars['parent_path'] + '/atom.xml', 'w')
output.write(template.replace('$CONTENT', atom_content).replace('$DATE', datetime.today().strftime("%Y-%m-%d"))) output.write(template.replace('$CONTENT', atom_content).replace(
'$DATE', datetime.today().strftime("%Y-%m-%d")))
output.close() output.close()
def generateTagsPages(tags_dict, env_vars): def generate_tags_pages(tags_dict, env_vars):
""" """
Generate page for each tag, which link to each content tagged Generate page for each tag, which link to each content tagged
tags_dict: A dictionnary with tag name as key, and a list of post (title & url) with that tag tags_dict: A dictionnary with tag name as key, and a list of post (title & url) with that tag
@ -70,20 +72,23 @@ def generateTagsPages(tags_dict, env_vars):
for tag, pages in tags_dict.items(): for tag, pages in tags_dict.items():
template = open(env_vars['template_tags'], 'r').read() template = open(env_vars['template_tags'], 'r').read()
# Generating the HTML page # Generating the HTML page
output = open(env_vars['pages_path'] + '/tags/' + tag.replace(' ', '_') + '.html', 'w') output = open(env_vars['pages_path'] + '/tags/' +
tag.replace(' ', '_') + '.html', 'w')
# Adding all links for page with this tag # Adding all links for page with this tag
content = "<ul>\n" content = "<ul>\n"
for page in pages: for page in pages:
content += '\t\t\t\t<li><a href="' + '../../' + page[1] + '">' + page[0] + '</a></li>\n' content += '\t\t\t\t<li><a href="' + '../../' + \
page[1] + '">' + page[0] + '</a></li>\n'
content += "\t\t\t</ul>\n" content += "\t\t\t</ul>\n"
output.write(template.replace("$CONTENT", content).replace("$TITLE", tag)) output.write(template.replace(
"$CONTENT", content).replace("$TITLE", tag))
output.close() output.close()
pass pass
def generateIndex(data, env_vars): def generate_index(data, env_vars):
""" """
Generate the main page Generate the main page
data: list of data get from markdown pages data: list of data get from markdown pages
@ -110,8 +115,9 @@ def generateIndex(data, env_vars):
# Adding tags browsing into the page # Adding tags browsing into the page
for tag in list(tags_dict.keys()): for tag in list(tags_dict.keys()):
index_content += ('\t\t\t\t\t<li><a href="' + env_vars['pages_path'].replace(env_vars['parent_path'] + '/', '') + '/tags/' + tag.replace(' ', '_') + '.html' + '">' + tag + '</a></li>\n') index_content += ('\t\t\t\t\t<li><a href="' + env_vars['pages_path'].replace(
generateTagsPages(tags_dict, env_vars) env_vars['parent_path'] + '/', '') + '/tags/' + tag.replace(' ', '_') + '.html' + '">' + tag + '</a></li>\n')
generate_tags_pages(tags_dict, env_vars)
index_content += '\t\t\t\t</ul>\n\t\t\t</div>' index_content += '\t\t\t\t</ul>\n\t\t\t</div>'
# Generate main page # Generate main page
@ -133,18 +139,18 @@ if __name__=="__main__":
'TEMPLATE_ATOM_FEED', 'WEBSITE_URL', 'TEMPLATE_INDEX', 'TEMPLATE_TAGS'] 'TEMPLATE_ATOM_FEED', 'WEBSITE_URL', 'TEMPLATE_INDEX', 'TEMPLATE_TAGS']
for variable in env: for variable in env:
if variable not in os.environ: if variable not in os.environ:
print(f"{color['red']}{variable} isn't present in the .env file, please fix this {color['end']}") print(
f"{color['red']}{variable} isn't present in the .env file, please fix this {color['end']}")
quit() quit()
if (os.environ.get(variable) or '') == '': if (os.environ.get(variable) or '') == '':
print(f"{color['red']}{variable} isn't setup in the .env file, please fix this {color['end']}") print(
f"{color['red']}{variable} isn't setup in the .env file, please fix this {color['end']}")
quit() quit()
# Getting env variable # Getting env variable
env_vars = { 'parent_path' : os.environ.get('PARENT_PATH'), 'pages_path' : os.environ.get('PAGES_PATH') env_vars = {'parent_path': os.environ.get('PARENT_PATH'), 'pages_path': os.environ.get('PAGES_PATH'), 'markdown_path': os.environ.get('MARKDOWN_PATH'), 'template_page': os.environ.get('TEMPLATE_PAGE'), 'template_atom_post': os.environ.get(
, 'markdown_path' : os.environ.get('MARKDOWN_PATH'), 'template_page' : os.environ.get('TEMPLATE_PAGE') 'TEMPLATE_ATOM_POST'), 'template_atom_feed': os.environ.get('TEMPLATE_ATOM_FEED'), 'website_url': os.environ.get('WEBSITE_URL'), 'template_index': os.environ.get('TEMPLATE_INDEX'), 'template_tags': os.environ.get('TEMPLATE_TAGS')}
, 'template_atom_post' : os.environ.get('TEMPLATE_ATOM_POST'), 'template_atom_feed' : os.environ.get('TEMPLATE_ATOM_FEED')
, 'website_url' : os.environ.get('WEBSITE_URL'), 'template_index' : os.environ.get('TEMPLATE_INDEX'), 'template_tags' : os.environ.get('TEMPLATE_TAGS') }
# Checking if generate folder exist to remove previouly generated content, if not create it # Checking if generate folder exist to remove previouly generated content, if not create it
if os.path.exists(env_vars['pages_path']): if os.path.exists(env_vars['pages_path']):
@ -167,8 +173,8 @@ if __name__=="__main__":
# Generating atom feed # Generating atom feed
print(f"{color['green']}Generating RSS / Atom feed {color['end']}") print(f"{color['green']}Generating RSS / Atom feed {color['end']}")
generateAtomFeed(data, env_vars) generate_atom_feed(data, env_vars)
# Generating index # Generating index
print(f"{color['green']}Generating main page {color['end']}") print(f"{color['green']}Generating main page {color['end']}")
generateIndex(data, env_vars) generate_index(data, env_vars)

111
markdown_parser.py
View File

@ -1,135 +1,150 @@
import html import html
def parseline(line):
def parse_line(line):
""" """
Parse a line of texte to replace HTML specialchars, link, and strong / emphased of markdown for HTML Parse a line of texte to replace HTML specialchars, link, and strong
/ emphased of markdown for HTML
return: the line ready for HTML return: the line ready for HTML
""" """
# Change &, <, > for HTML support # Change &, <, > for HTML support
html.escape(line) html.escape(line)
# Checking if there is strong or emphasized # Checking if there is strong or emphasized
while '*' in line: while "*" in line:
line = line.replace('*', '<em>', 1) line = line.replace("*", "<em>", 1)
line = line.replace('*', '</em>', 1) line = line.replace("*", "</em>", 1)
while '**' in line: while "**" in line:
line = line.replace('**', '<strong>', 1) line = line.replace("**", "<strong>", 1)
line = line.replace('**', '</strong>', 1) line = line.replace("**", "</strong>", 1)
# Checking if there is image # Checking if there is image
while '![' in line and ']' in line: while "![" in line and "]" in line:
title = line.split(']')[0].split('[')[1] title = line.split("]")[0].split("[")[1]
link = line.split(']')[1].split('(')[1].split(')')[0] link = line.split("]")[1].split("(")[1].split(")")[0]
line = line.replace('![' + title + '](' + link + ')', '<img src="' + link + '" alt="' + title + '"/>') line = line.replace(
"![" + title + "](" + link + ")",
'<img src="' + link + '" alt="' + title + '"/>',
)
# Checkinf if there is link # Checking if there is link
while '[' in line and ']' in line: while "[" in line and "]" in line:
title = line.split(']')[0].split('[')[1] title = line.split("]")[0].split("[")[1]
link = line.split(']')[1].split('(')[1].split(')')[0] link = line.split("]")[1].split("(")[1].split(")")[0]
line = line.replace('[' + title + '](' + link + ')', '<a href="' + link + '">' + title + '</a>') line = line.replace(
"[" + title + "](" + link + ")", '<a href="' + link + '">' + title + "</a>"
)
return line return line
def parsemd(filepath, env_vars): def parse_md(filepath, env_vars):
""" """
Parse the markdown file and return the content to put into the template page Parse a markdown file and return the content to put into the template page
env_vars: dictionnary of environment variable env_vars: dictionnary of environment variable
filepath: Filepath of the markdown file filepath: Filepath of the markdown file
return: a dictionnary containing title, metadata, local path, content for HTML return: a dictionnary containing title, metadata, local path, content
""" """
content = {'content': '', 'title': '', 'date': '01-01-0001', 'description': '', 'tags' : [], 'filepath': env_vars['pages_path'].replace(env_vars['parent_path'] + '/', '') content = {
+ '/' + filepath.split('.')[0] + '.html'} "content": "",
"title": "",
"date": "01-01-0001",
"description": "",
"tags": [],
"filepath": env_vars["pages_path"].replace(env_vars["parent_path"] + "/", "")
+ "/"
+ filepath.split(".")[0]
+ ".html",
}
inmeta, inquote, inpre, inul = False, False, False, False inmeta, inquote, inpre, inul = False, False, False, False
# Reading the content of the file and transform into html # Reading the content of the file and transform into html
for line in open(env_vars['markdown_path'] + '/' + filepath, "r"): for line in open(env_vars["markdown_path"] + "/" + filepath, "r"):
line = line.strip() line = line.strip()
# Open the metadata # Open the metadata
if line.startswith('---'): if line.startswith("---"):
if inmeta: if inmeta:
inmeta = False inmeta = False
else: else:
inmeta = True inmeta = True
# Getting the date metadata # Getting the date metadata
if inmeta and line.startswith('date:'): if inmeta and line.startswith("date:"):
content['date'] = line.split(':')[1].strip() content["date"] = line.split(":")[1].strip()
# Getting the description metadata # Getting the description metadata
if inmeta and line.startswith('description:'): if inmeta and line.startswith("description:"):
content['description'] = line.split(':')[1].strip() content["description"] = line.split(":")[1].strip()
# Getting the tags metadata # Getting the tags metadata
if inmeta and line.startswith('tags:'): if inmeta and line.startswith("tags:"):
tags = line.split(':')[1].split(',') tags = line.split(":")[1].split(",")
# Removing leading and ending white spaces # Removing leading and ending white spaces
for i in range(0, len(tags)): for i in range(0, len(tags)):
tags[i] = tags[i].strip() tags[i] = tags[i].strip()
content['tags'] = tags content["tags"] = tags
# Close quote if not quoting # Close quote if not quoting
if inquote and not line.startswith(">"): if inquote and not line.startswith(">"):
content['content'] += "</blockquote>\n" content["content"] += "</blockquote>\n"
inquote = False inquote = False
# Close list if not listing # Close list if not listing
if inul and not line.startswith("-"): if inul and not line.startswith("-"):
content['content'] += "</li>\n</ul>\n" content["content"] += "</li>\n</ul>\n"
inul = False inul = False
# Checking if it's a code block # Checking if it's a code block
if line.startswith("```"): if line.startswith("```"):
if inpre: if inpre:
content['content'] += "</code></pre>\n" content["content"] += "</code></pre>\n"
content['content'] += "<pre><code>" + line.lstrip("```") content["content"] += "<pre><code>" + line.lstrip("```")
inpre = True inpre = True
# Checking if it's a quote # Checking if it's a quote
elif line.startswith(">"): elif line.startswith(">"):
if inquote: if inquote:
content['content'] += parseline(line.lstrip("> ")) content["content"] += parse_line(line.lstrip("> "))
else: else:
content['content'] += "<blockquote>" + parseline(line.lstrip("> ")) content["content"] += "<blockquote>" + parse_line(line.lstrip("> "))
inquote = True inquote = True
# Checking if it's a list # Checking if it's a list
elif line.startswith("-") and not line.startswith("---"): elif line.startswith("-") and not line.startswith("---"):
if inul: if inul:
content['content'] += "</li>\n" content["content"] += "</li>\n"
content['content'] += "\t<li>" + parseline(line.lstrip("- ")) content["content"] += "\t<li>" + parse_line(line.lstrip("- "))
else: else:
content['content'] += "<ul>\n\t<li>" + parseline(line.lstrip("- ")) content["content"] += "<ul>\n\t<li>" + parse_line(line.lstrip("- "))
inul = True inul = True
# Checking if it's a title # Checking if it's a title
elif line.startswith("###"): elif line.startswith("###"):
content['content'] += "<h3>" + parseline(line.lstrip("# ")) + "</h3>\n" content["content"] += "<h3>" + parse_line(line.lstrip("# ")) + "</h3>\n"
elif line.startswith("##"): elif line.startswith("##"):
content['content'] += "<h2>" + parseline(line.lstrip("# ")) + "</h2>\n" content["content"] += "<h2>" + parse_line(line.lstrip("# ")) + "</h2>\n"
elif line.startswith("#"): elif line.startswith("#"):
content['title'] += parseline(line.lstrip("# ")) content["title"] += parse_line(line.lstrip("# "))
# else it's a paragraph # else it's a paragraph
elif line != " " and line != "" and not inmeta and not line.startswith("---"): elif line != " " and line != "" and not inmeta and not line.startswith("---"):
content['content'] += "<p>" + parseline(line) + "</p>\n" content["content"] += "<p>" + parse_line(line) + "</p>\n"
# Checking all balise are closed # Checking all balise are closed
if inquote: if inquote:
content['content'] += "</blockquote>\n" content["content"] += "</blockquote>\n"
inquote = False inquote = False
if inul: if inul:
content['content'] += "</li>\n</ul>\n" content["content"] += "</li>\n</ul>\n"
inul = False inul = False
if inpre: if inpre:
content['content'] += "</code></pre>\n" content["content"] += "</code></pre>\n"
inpre = False inpre = False
return content return content