ウェブサイトをMarkdownに変換: クロールして全ページをエクスポート

import os
import pathlib
import time
from urllib.parse import urlparse

import requests

API = "https://webreaderapi.com/api/v1"
HEADERS = {"Authorization": "Bearer " + os.environ["WEBREADER_API_KEY"]}
SITE = "https://www.example.com/"
OUT = pathlib.Path("export")


def target_path(url):
    path = urlparse(url).path.strip("/") or "index"
    return OUT / (path + ".md")


def front_matter(page):
    fields = {"title": page.get("title", ""), "source": page["final_url"], "date": page.get("published_at") or ""}
    lines = ["---"] + [key + ": " + repr(value) for key, value in fields.items()] + ["---", ""]
    return "\n".join(lines)


job = requests.post(API + "/crawl", headers=HEADERS, json={"url": SITE, "limit": 2000, "max_depth": 5}, timeout=60).json()
cursor, delay, written = None, 5, 0
while True:
    params = {"cursor": cursor} if cursor else {}
    batch = requests.get(API + "/jobs/" + job["job_id"], headers=HEADERS, params=params, timeout=60).json()
    for page in batch.get("results", []):
        if "markdown" not in page:
            continue
        dest = target_path(page["final_url"])
        dest.parent.mkdir(parents=True, exist_ok=True)
        dest.write_text(front_matter(page) + page["markdown"] + "\n", encoding="utf-8")
        written += 1
    cursor = batch.get("next_cursor")
    if batch["status"] == "done" and not cursor:
        break
    if not cursor:
        time.sleep(delay)
        delay = min(delay * 2, 60)
print(written, "files in", OUT)