hugo-from-hedgedoc/generate_v2.py

import io
import os
from bs4 import BeautifulSoup, Comment
import markdown
import ipdb

parent_dir = "./content"


def parse_markdown_file(file_path):
    with open(file_path, "r") as file:
        markdown_text = file.read()
        html = markdown.markdown(markdown_text)
        print(html)
        headings = []
        current_level = 0
        for line in html.split("\n"):
            if line.startswith("<h1>"):
                current_level = 1
                headings.append(
                    {"level": current_level, "text": line[4:-5], "children": []}
                )
            elif line.startswith("<h2>"):
                if current_level < 2:
                    current_level = 2
                    headings[-1]["children"].append(
                        {"level": current_level, "text": line[4:-5], "children": []}
                    )
                else:
                    headings[-1]["children"].append(
                        {"level": current_level, "text": line[4:-5], "children": []}
                    )
            elif line.startswith("<h3>"):
                if current_level < 3:
                    current_level = 3
                    headings[-1]["children"][-1]["children"].append(
                        {"level": current_level, "text": line[4:-5], "children": []}
                    )
                else:
                    headings[-1]["children"][-1]["children"].append(
                        {"level": current_level, "text": line[4:-5], "children": []}
                    )
        return headings


def parse_markdown_file_2(file_path):
    with open(file_path, "r", encoding="utf-8") as f:
        content = f.read()
    html = markdown.markdown(content)
    print(html)
    soup = BeautifulSoup(html, "html.parser")
    headings = []

    def parse_element(element, level):
        print(element)
        if element.name == "h1":
            heading = {
                "text": element.text.strip(),
                "level": level,
                "subheadings": [],
                "links": [],
            }
            headings.append(heading)
        elif element.name == "h2":
            subheading = {
                "text": element.text.strip(),
                "level": level,
                "subheadings": [],
                "links": [],
            }
            headings[-1]["subheadings"].append(subheading)
        elif element.name == "h3":
            subsubheading = {"text": element.text.strip(), "level": level, "links": []}
            headings[-1]["subheadings"][-1]["subheadings"].append(subsubheading)
        elif element.name == "ul":
            links = []
            for li in element.find_all("li"):
                link = li.find("a")
                if link is not None:
                    links.append({"text": link.text.strip(), "url": link["href"]})
            if level == 1:
                headings[-1]["links"].extend(links)
            elif level == 2:
                headings[-1]["subheadings"][-1]["links"].extend(links)
            elif level == 3:
                headings[-1]["subheadings"][-1]["subheadings"][-1]["links"].extend(
                    links
                )

        for child in element.children:
            if isinstance(child, str) or isinstance(child, Comment):
                continue
            parse_element(child, level + 1)

    parse_element(soup, 0)

    return headings


headings = parse_markdown_file_2("content/posts/my-first-post.md")
print(headings)
for heading in headings:
    print(f"Titre de niveau {heading['level']}: {heading['text']}")
    for subheading in heading["children"]:
        print(f"   Sous-titre de niveau {subheading['level']}: {subheading['text']}")
        for subsubheading in subheading["children"]:
            print(
                f"      Sous-sous-titre de niveau {subsubheading['level']}: {subsubheading['text']}"
            )