1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
|
import os
import sys
import shutil
from dotenv import load_dotenv
from markdown_parser import parse_md
from datetime import datetime
def md2html(filename, env_vars):
"""
Create the html webpage from template and markdown content
filename: file to transform into HTML
env_vars: dictionnary of env variables
return: a dictionnary containing title, metadata, local path, content for HTML
"""
# Getting parsed content of markdown file & page template
data = parse_md(filename, env_vars)
template = open(env_vars['templates_folder'] + "/" + env_vars["lang"] + "/page_template.html", 'r').read()
# Generating the HTML page
output = open(env_vars['pages_path'] + '/' + env_vars["lang"] + "/" + filename.split('.')[0] + '.html', 'w')
output.write(template.replace("$CONTENT", data['content']).replace("$TITLE", data['title']).replace("$DATE", data['date']).replace("$DESC", data['description']))
output.close()
return data
def generate_page_XML(data, env_vars):
"""
Generate a RSS / Atom post for the page
data: dictionnary generated by the markdown parser
env_vars: dictionnary of env variables
return: RSS / Atom post
"""
template = open(env_vars['templates_folder'] + "/" + env_vars["lang"] + "/atom_post_template.xml", 'r').read()
date = datetime.strptime(data['date'], "%d-%m-%Y").isoformat() + "Z"
return template.replace("$TITLE", data['title']).replace("$DATE", date).replace("$CONTENT", data['content']).replace("$URL", env_vars['website_url'] + data['filepath'])
def generate_atom_feed(posts, env_vars):
"""
Generate a RSS / Atom feed
posts: list of data get from markdown pages
env_vars: dictionnary of env variables
"""
# Generate RSS / Atom post
atom_content = ""
for post in posts:
# Checking if there is metadata, if not we don't create a RSS / Atom post
if post['date'] != '01-01-0001':
atom_content += generate_page_XML(post, env_vars)
# Generate RSS / atom feed
template = open(env_vars['templates_folder'] + "/" + env_vars["lang"] + "/atom_feed_template.xml", 'r').read()
output = open(env_vars['parent_path'] + "/atom_" + env_vars["lang"] + ".xml", "w")
output.write(template.replace('$CONTENT', atom_content).replace('$DATE', datetime.today().strftime("%Y-%m-%d")))
output.close()
def generate_tags_pages(tags_dict, env_vars):
"""
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
env_vars: dictionnary of env variables
"""
if not os.path.exists(env_vars['pages_path'] + "/" + env_vars["lang"] + '/tags'):
os.mkdir(env_vars['pages_path'] + "/" + env_vars["lang"] + '/tags')
# Going on every tag and creating it's page
for tag, pages in tags_dict.items():
template = open(env_vars['templates_folder'] + "/" + env_vars["lang"] + "/tags_template.html", 'r').read()
# Generating the HTML page
output = open(env_vars['pages_path'] + "/" + env_vars["lang"] + '/tags/' + tag.replace(' ', '_') + '.html', 'w')
# Adding all links for page with this tag
content = "<ul>\n"
for page in pages:
content += '\t\t\t\t<li><a href="' + '../../../' + page[1] + '">' + page[0] + '</a></li>\n'
content += "\t\t\t</ul>\n"
output.write(template.replace("$CONTENT", content).replace("$TITLE", tag))
output.close()
pass
def generate_index(data, env_vars):
"""
Generate the main page
data: list of data get from markdown pages
env_vars: dictionnary of env variables
"""
# Create the index content
tags_dict = {}
index_content = "<ul>\n"
# Getting data of each page
for page in data:
# Checking if there is metadata, if not we don't add the page in the index
if page['date'] != '01-01-0001':
index_content += ('\t\t\t\t<li><a href="' + page['filepath'] + '">' + page['title'] + '</a><p>'
+ page['date'] + '</p></li>\n')
# Adding page into tags categorie
for tag in page['tags']:
if tag not in tags_dict:
tags_dict[tag] = []
tags_dict[tag].append([page['title'], page['filepath']])
index_content += '\t\t\t</ul>\n\t\t\t<h2>Tags:</h2>\n\t\t\t<div class="tags">\n\t\t\t\t<ul>\n'
# Adding tags browsing into the page
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'] + '/', '') + "/" + env_vars["lang"] + '/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>'
# Generate main page
template = open(env_vars['templates_folder'] + "/" + env_vars["lang"] + "/index_template.html", 'r').read()
output = open(env_vars['parent_path'] + "/index_" + env_vars["lang"] + ".html", 'w')
output.write(template.replace('$CONTENT', index_content))
output.close()
def check_env():
"""Check environment variables are set and not empty"""
env = ['PARENT_PATH', 'PAGES_PATH', 'MARKDOWN_PATH', 'TEMPLATES_FOLDER', 'WEBSITE_URL', 'LANGS']
for variable in env:
if variable not in os.environ:
print(
f"{color['red']}{variable} isn't present in the .env file, please fix this {color['end']}")
sys.exit()
if (os.environ.get(variable) or '') == '':
print(
f"{color['red']}{variable} isn't setup in the .env file, please fix this {color['end']}")
sys.exit()
if __name__ == "__main__":
# Load .env file into python environment
load_dotenv()
# Color for print
color = {'red': '\033[1;31m', 'green': '\033[1;32m', 'end': '\033[0m'}
# Checking if all environment variable are present & setup
check_env()
# Getting env variable
env_vars = {'parent_path': os.environ.get('PARENT_PATH'), 'pages_path': os.environ.get('PAGES_PATH'), 'markdown_path': os.environ.get('MARKDOWN_PATH'), 'templates_folder': os.environ.get('TEMPLATES_FOLDER'), 'website_url': os.environ.get('WEBSITE_URL')}
langs = os.environ.get('LANGS').lower().split(',')
# Checking if generate folder exist to remove previouly generated content, if not create it
if os.path.exists(env_vars['pages_path']):
shutil.rmtree(env_vars['pages_path'])
for lang in langs:
os.remove(env_vars['parent_path'] + "/atom_" + lang + ".xml")
os.remove(env_vars['parent_path'] + "/index_" + lang + ".html")
else:
os.mkdir(env_vars['pages_path'])
for lang in langs:
os.mkdir(env_vars['pages_path'] + "/" + lang)
# Generate for each lang
for lang in langs:
env_vars['lang'] = lang
data = [] # A list for data generated by md2html
# Generate all markdown file
for file in os.listdir(env_vars['markdown_path'] + "/" + lang):
# Generating HTML page
print(f"{color['green']}Generating file: {file} in {lang} {color['end']}")
data.append(md2html(file, env_vars))
sorted_data = sorted(data, key=lambda x: datetime.strptime(x['date'], '%d-%m-%Y'))
# Generating atom feed
print(f"{color['green']}Generating RSS / Atom feed in {lang} {color['end']}")
generate_atom_feed(sorted_data, env_vars)
# Generating index
print(f"{color['green']}Generating main page in {lang} :{color['end']}")
generate_index(sorted_data, env_vars)
|
