Grab content from ORM api

fetch-example.py

import aiohttp
import sys
import asyncio
import os


# Before you start, get a content token from https://learning.oreilly.com/account/api-tokens/
# You'll need the account manager role on your user membership.  If you're not an account manager
# then you'll need to request on from the U&A team of someone who can create tokens
# Then create an environment variable called ORM_AUTH_TOKEN with the token as the value
async def async_fetch_url(session, url, format="json"):
    headers = {"Authorization": f"Token {os.getenv('ORM_AUTH_TOKEN')}"}
    async with session.get(url, headers=headers) as r:
        if format == "html":
            return await r.text()
        else:
            return await r.json()


# Grab the metadata for a book, then get all metadata for each chapter, then get the content of each chapter
async def fetch_book(work):
    async with aiohttp.ClientSession() as session:
        metadata = await async_fetch_url(
            session, f"https://learning.oreilly.com/api/v1/book/{work}/"
        )
        # Fetch the metadata about each chapter
        chapters_metadata = await asyncio.gather(
            *[async_fetch_url(session, url) for url in metadata["chapters"]]
        )
        # Fetch content of each chapter based on the medata file.  This maps 1:1 to the metadata
        chapters_content = await asyncio.gather(
            *[
                async_fetch_url(session, chapter["content"], "html")
                for chapter in chapters_metadata
            ]
        )
        return metadata, chapters_metadata, chapters_content


if __name__ == "__main__":
    metadata, chapters_metadata, chapters_content = asyncio.run(fetch_book(sys.argv[1]))
    for chapter in chapters_content:
        print(chapter)