47 lines
1.6 KiB
Python
47 lines
1.6 KiB
Python
from __future__ import annotations
|
|
from dataclasses import dataclass
|
|
from datetime import datetime, timezone
|
|
from typing import Iterator
|
|
import requests
|
|
|
|
from personal_data.data import DeduplicateMode
|
|
from personal_data.fetchers import Scraper
|
|
from personal_data.secrets import wanikani_api_key
|
|
|
|
@dataclass(frozen=True)
|
|
class WaniKaniSummaryFetcher(Scraper):
|
|
dataset_name: str = "wanikani_summary"
|
|
|
|
@staticmethod
|
|
def deduplicate_mode() -> DeduplicateMode:
|
|
return DeduplicateMode.BY_ALL_COLUMNS
|
|
|
|
def scrape(self) -> Iterator[dict]:
|
|
token = wanikani_api_key()
|
|
headers = {
|
|
"Authorization": f"Bearer {token}",
|
|
"Wanikani-Revision": "20170710",
|
|
}
|
|
url = "https://api.wanikani.com/v2/summary"
|
|
response = requests.get(url, headers=headers)
|
|
response.raise_for_status()
|
|
data = response.json()
|
|
|
|
lessons = data.get("data", {}).get("lessons", [])
|
|
total_lessons = sum(len(lesson.get("subject_ids", [])) for lesson in lessons)
|
|
|
|
reviews = data.get("data", {}).get("reviews", [])
|
|
now = datetime.now(timezone.utc)
|
|
total_reviews = 0
|
|
for review in reviews:
|
|
available_at_str = review.get("available_at")
|
|
if available_at_str:
|
|
available_at = datetime.fromisoformat(available_at_str.replace("Z", "+00:00"))
|
|
if available_at <= now:
|
|
total_reviews += len(review.get("subject_ids", []))
|
|
|
|
yield {
|
|
"lessons_available": total_lessons,
|
|
"reviews_available": total_reviews,
|
|
}
|