main.py

import requests
import json
import csv
import re
import os
from dotenv import load_dotenv

load_dotenv()

subjectid = os.getenv("SUBJECT_ID")
cookies = {
    "JOSSO_SESSIONID": os.getenv("JOSSO_SESSIONID"),
    "GDPR": "required"
}
headers = {
    "Accept": "application/json, text/plain, */*",
    "Content-Type": "application/json",
    "Origin": "https://lernen.phase-6.de",
    "Referer": "https://lernen.phase-6.de/v2/",
    "User-Agent": "Mozilla/5.0",
    "X-CLIENTID": os.getenv("X_CLIENTID"),
    "X-JAUTHTOKEN": os.getenv("X_JAUTHTOKEN"),
    "X-LBTOKEN": os.getenv("X_LBTOKEN")
}

txt_file = f"{subjectid}.txt"
csv_file = f"{subjectid}.csv"

url = "https://lernen.phase-6.de/server.integration/cardList"
payload = {
    "cards": [],
    "subjectId": subjectid,
    "units": []
}

r = requests.post(url, headers=headers, cookies=cookies, json=payload)
r.raise_for_status()

data = r.json()

with open(txt_file, "w", encoding="utf-8") as f:
    json.dump(data, f, ensure_ascii=False, indent=2)

print(f"Response saved: {txt_file}")

audio_regex = re.compile(r"\[\{\~.*?:audio~\}\]")

cards_list = data.get("replyContent", {}).get("cards", [])

with open(csv_file, "w", newline="", encoding="utf-8") as csvfile:
    writer = csv.writer(csvfile, delimiter=",", quotechar='"', quoting=csv.QUOTE_MINIMAL)
    writer.writerow(["Deutsch", "Spanisch", "Beispiel", "LearningDirection", "UnitID"])

    for c in cards_list:
        if not isinstance(c, dict):
            continue
        content = c.get("cardContent")
        if not content:
            continue

        de = content.get("question", "")
        es = audio_regex.sub("", content.get("answer", ""))
        example = content.get("answerExample", "")
        learning_direction = c.get("learningDirection", "")
        unit_id = c.get("unitIdString", "")

        writer.writerow([de, es, example, learning_direction, unit_id])

print(f"CSV created: {csv_file}")