#!/usr/bin/env python3 # The MIT License (MIT) # # Copyright (c) 2018 Sunaina Pai # # Permission is hereby granted, free of charge, to any person obtaining # a copy of this software and associated documentation files (the # "Software"), to deal in the Software without restriction, including # without limitation the rights to use, copy, modify, merge, publish, # distribute, sublicense, and/or sell copies of the Software, and to # permit persons to whom the Software is furnished to do so, subject to # the following conditions: # # The above copyright notice and this permission notice shall be # included in all copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. # IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY # CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """Make static website/blog with Python.""" import sys import os import shutil import re import glob import json import datetime import time from email import utils from pathlib import Path import unicodedata import locale import requests import commonmark # set user locale locale.setlocale(locale.LC_ALL, "") def fread(filename): """Read file and close the file.""" with open(filename, "r") as f: return f.read() def fwrite(filename, text): """Write content to file and close the file.""" basedir = os.path.dirname(filename) if not os.path.isdir(basedir): os.makedirs(basedir) with open(filename, "w") as f: f.write(text) def log(msg, *args): """Log message with specified arguments.""" sys.stderr.write(msg.format(*args) + "\n") def truncate(text, words=25): """Remove tags and truncate text to the specified number of words.""" return " ".join(re.sub("(?s)<.*?>", " ", text).split()[:words]) def read_headers(text): """Parse headers in text and yield (key, value, end-index) tuples.""" for match in re.finditer(r"\s*\s*|.+", text): if not match.group(1): break yield match.group(1), match.group(2), match.end() def rfc_2822_format(date_str): """Convert yyyy-mm-dd date string to RFC 2822 format date string.""" d = datetime.datetime.strptime(date_str, "%Y-%m-%d") dtuple = d.timetuple() dtimestamp = time.mktime(dtuple) return utils.formatdate(dtimestamp) def slugify(value): """ Converts to lowercase, removes non-word characters (alphanumerics and underscores) and converts spaces to hyphens. Also strips leading and trailing whitespace. """ value = ( unicodedata.normalize("NFKD", value).encode("ascii", "ignore").decode("ascii") ) value = re.sub("[^\w\s-]", "", value).strip().lower() return re.sub("[-\s]+", "-", value) def read_content(filename): """Read content and metadata from file into a dictionary.""" # Read file content. text = fread(filename) # Read metadata and save it in a dictionary. date_slug = os.path.basename(filename).split(".")[0] match = re.search(r"^(?:(\d\d\d\d-\d\d-\d\d)-)?(.+)$", date_slug) content = {"date": match.group(1) or "1970-01-01", "slug": match.group(2)} # Read headers. end = 0 for key, val, end in read_headers(text): content[key] = val # slugify post title content["slug"] = slugify(content["title"]) # Separate content from headers. text = text[end:] # Convert Markdown content to HTML. if filename.endswith((".md", ".mkd", ".mkdn", ".mdown", ".markdown")): text = commonmark.commonmark(text) # Update the dictionary with content and RFC 2822 date. content.update({"content": text, "rfc_2822_date": rfc_2822_format(content["date"])}) return content def clean_html_tag(text): """Remove HTML tags.""" while True: original_text = text text = re.sub("<\w+.*?>", "", text) text = re.sub("<\/\w+>", "", text) if original_text == text: break return text def render(template, **params): """Replace placeholders in template with values from params.""" return re.sub( r"{{\s*([^}\s]+)\s*}}", lambda match: str(params.get(match.group(1), match.group(0))), template, ) def get_categories(page_params): cat = [] for s in page_params["category"].split(" "): if s.strip(): cat.append(s.strip()) return cat def make_pages(src, dst, layout, **params): """Generate pages from page content.""" items = [] for src_path in glob.glob(src): content = read_content(src_path) page_params = dict(params, **content) items.append(content) dst_path = render(dst, **page_params) output = render(layout, **page_params) log("Rendering {} => {} ...", src_path, dst_path) fwrite(dst_path, output) return sorted(items, key=lambda x: x["date"], reverse=True) def get_friendly_date(date_str): dt = datetime.datetime.strptime(date_str, "%Y-%m-%d") return dt.strftime("%d %b %Y") def make_posts( src, src_pattern, dst, layout, category_layout, comment_layout, **params ): """Generate posts from posts directory.""" items = [] for posix_path in Path(src).glob(src_pattern): src_path = str(posix_path) content = read_content(src_path) page_params = dict(params, **content) page_params["header"] = "" page_params["footer"] = "" page_params["date_path"] = page_params["date"].replace("-", "/") page_params["friendly_date"] = get_friendly_date(page_params["date"]) page_params["year"] = page_params["date"].split("-")[0] page_params["post_url"] = page_params["year"] + "/" + page_params["slug"] # categories categories = get_categories(page_params) out_cats = [] for category in categories: out_cat = render(category_layout, category=category, url=slugify(category)) out_cats.append(out_cat.strip()) page_params["categories"] = categories page_params["category_label"] = "".join(out_cats) summary_index = page_params["content"].find("