Polarstep to Markdown

generate_markdown.py

import json
from dataclasses import dataclass
import inspect
from datetime import date, datetime

@dataclass
class Step:
    "Class for representing a PolarStep Step"
    description: str
    media: list
    name: str
    start_time: str

    @property
    def filename(self):
        return f"{datetime.fromisoformat(self.start_time).date().isoformat()}.md"

    @property
    def media_urls(self):
        urls = [media.get('path') for media in self.media]
        return urls

    @property
    def image_mark(self):
        lines = ""
        for img in self.media:
            url = img.get("path", "").split("/")[-1]
            lines+= f"![]({url})\n"
        return lines

    @classmethod
    def from_dict(cls, env):      
        return cls(**{
            k: v for k, v in env.items() 
            if k in inspect.signature(cls).parameters
        })

    def __str__(self):
        return f"# {self.name}\n\n{self.description}\n\n{self.image_mark}"




# Dump of the biggest JSON seen while visiting the polarstep page
data = {}
with open("polar.json", "r", encoding="utf-8") as f:
    data = json.loads(f.read())

steps = data.get("steps",{})

def generate_markdown(steps):
    for step_data in steps:
        step = Step.from_dict(step_data)
        with open(step.filename, "w", encoding="utf-8") as f:
            f.write(str(step))

def download_media(steps):
    import wget
    for step_data in steps:
        step = Step.from_dict(step_data)
        if step.media_urls:
            for url in step.media_urls:
                wget.download(url)
            
generate_markdown(steps)
download_media(steps)

This script download all the images in full resolution and put each step description in a <step_date>.md file.

Each file have this structure :

# <Name of the step>

<Description of the step>

![](img 1)
...
![](img N)