Google Play reviews API: export any app's reviews to CSV

export TOOLZERHUB_API_KEY=your_key
curl -G -H "x-api-key: $TOOLZERHUB_API_KEY" \
  --data-urlencode "package_id_or_url=com.spotify.music" \
  --data-urlencode "count=150" \
  --data-urlencode "sort=newest" \
  "https://api.toolzerhub.com/v1/google-play/reviews"

{
  "review_id": "ad1b2e6e-8e39-4642-b638-5c4a6d9ece5b",
  "score": 4,
  "text": "keyboard too small what can I do to make bigger?",
  "timestamp": 1793727042,
  "helpful_count": 0,
  "developer_reply": {
    "author": "Spotify AB",
    "text": "Hi. Thanks for bringing this up. We're open to feedback, and we'd love to get some more info about this. If you have the time, give our Customer Service a shout. You can find them by heading to support.spotify.com and searching \"Contact us\".",
    "timestamp": 1793728440
  },
  "app_version": "9.1.94.1929"
}

import csv
import os
import sys
import time
from collections import Counter
from datetime import datetime, timezone

import requests

BASE = "https://api.toolzerhub.com/v1/google-play"
HEADERS = {"x-api-key": os.environ.get("TOOLZERHUB_API_KEY", "")}
FIELDS = ["review_id", "date", "score", "app_version", "helpful_count", "author", "text",
          "replied", "reply_text"]


def get(path, params, tries=3):
    for attempt in range(tries):
        r = requests.get(f"{BASE}/{path}", headers=HEADERS, params=params, timeout=60)
        if r.status_code in (429, 500, 502, 503, 504) and attempt < tries - 1:
            time.sleep(5 * (attempt + 1))
            continue
        r.raise_for_status()
        return r.json()["data"]


def main(app, pages="5", out="reviews.csv", sort="newest"):
    # Each call returns up to 150 reviews; next_token goes back in as token.
    params = {"package_id_or_url": app, "count": 150, "sort": sort}
    rows, calls = [], 0
    for _ in range(int(pages)):
        data = get("reviews", params)
        calls += 1
        if not data or not data["reviews"]:
            break
        for r in data["reviews"]:
            reply = r.get("developer_reply") or {}
            rows.append({
                "review_id": r["review_id"],
                "date": datetime.fromtimestamp(r["timestamp"], timezone.utc).date().isoformat(),
                "score": r["score"], "app_version": r.get("app_version"),
                "helpful_count": r.get("helpful_count"), "author": r["author"],
                "text": r.get("text"), "replied": bool(reply),
                "reply_text": reply.get("text") if isinstance(reply, dict) else reply,
            })
        if not data.get("next_token"):
            break
        params["token"] = data["next_token"]
    with open(out, "w", newline="", encoding="utf-8-sig") as f:
        writer = csv.DictWriter(f, fieldnames=FIELDS)
        writer.writeheader()
        writer.writerows(rows)
    stars = Counter(r["score"] for r in rows)
    days = sorted({r["date"] for r in rows})
    print(f"{len(rows)} reviews in {calls} calls, {days[0]} to {days[-1]}, saved to {out}")
    print("stars:", " ".join(f"{s}*={stars[s]}" for s in range(5, 0, -1)),
          f"| replied: {sum(r['replied'] for r in rows)}")


if __name__ == "__main__":
    if len(sys.argv) < 2:
        sys.exit("usage: python google_play_reviews.py com.spotify.music [pages] [file.csv] [newest|helpful|rating]")
    if not HEADERS["x-api-key"]:
        sys.exit("set TOOLZERHUB_API_KEY first")
    main(*sys.argv[1:])