Google Play - App Details and Developer App Lists

import re, json, time, email.utils, urllib.parse, urllib.request, urllib.error
 
H = {"User-Agent": "browser-harness-skill/1.0 (Python urllib)", "Accept-Language": "en-US,en;q=0.9"}
HL, GL = "en_US", "US"          # language and store country (country sets currency and availability)
RETRY_CODES = {429, 500, 502, 503, 504}
MAX_WAIT = 120                  # seconds; a longer Retry-After stops the run instead of sleeping
 
def _retry_after(value):
    """Retry-After as seconds, or as an HTTP date; None if absent or unparseable."""
    if not value:
        return None
    if value.strip().isdigit():
        return int(value.strip())
    try:
        return max(0.0, email.utils.parsedate_to_datetime(value).timestamp() - time.time())
    except (TypeError, ValueError):
        return None
 
def fetch(url, tries=4):
    """GET. Retries 429/5xx and network errors with backoff, then raises.
    Raises at once if Retry-After asks for more than MAX_WAIT seconds.
    Other HTTP errors (404 included) raise urllib.error.HTTPError immediately."""
    for i in range(tries):
        req = urllib.request.Request(url, headers=H)
        try:
            with urllib.request.urlopen(req, timeout=20) as r:
                return r.read().decode()
        except urllib.error.HTTPError as e:
            if e.code not in RETRY_CODES or i == tries - 1:
                raise
            wait = _retry_after(e.headers.get("Retry-After"))
            if wait is not None and wait > MAX_WAIT:
                raise RuntimeError(f"HTTP {e.code}: server asked to wait {wait:.0f}s (> {MAX_WAIT}s); stopping") from e
            wait = wait if wait is not None else 2 ** (i + 1)
        except (urllib.error.URLError, TimeoutError, ConnectionError):
            if i == tries - 1:
                raise
            wait = 2 ** (i + 1)
        time.sleep(wait)
 
def callbacks(html):
    """Yield every AF_initDataCallback payload embedded in a Play page."""
    for m in re.finditer(r"AF_initDataCallback\(\{key: '(ds:\d+)', hash: '\d+', data:(.*?), sideChannel: \{\}\}\);</script>", html, re.S):
        try:
            yield m.group(1), json.loads(m.group(2))
        except ValueError:
            pass
 
def g(o, *path):
    """Safe nested index: returns None instead of raising."""
    for p in path:
        try:
            o = o[p]
        except (IndexError, KeyError, TypeError):
            return None
    return o
 
def num(x):
    return x if isinstance(x, (int, float)) and not isinstance(x, bool) else None
 
def text(x):
    return x if isinstance(x, str) else None
 
def ld_num(x):
    """JSON-LD numbers are strings ('4.34', '36528069'); None if absent or not a number."""
    try:
        return float(x) if x not in (None, "") else None
    except (TypeError, ValueError):
        return None
 
def first(*vals):
    return next((v for v in vals if v is not None), None)
 
def offer_fields(o):
    """[micros, currency, text] -> (price, currency, price_text). Free apps have micros 0 and an empty text."""
    o = o if isinstance(o, list) else []
    micros = num(g(o, 0))
    return ((micros / 1e6) if micros is not None else None, text(g(o, 1)),
            text(g(o, 2)) or ("Free" if micros == 0 else None))
 
def ld_app(html, app_id):
    """The JSON-LD SoftwareApplication block whose url carries id=<app_id>, or {}.
    A block with no url (or a url without id) is never assumed to be this app."""
    for m in re.finditer(r'<script type="application/ld\+json"[^>]*>(.*?)</script>', html, re.S):
        try:
            d = json.loads(m.group(1))
        except ValueError:
            continue
        for item in (d if isinstance(d, list) else [d]):
            if not isinstance(item, dict) or "applicationCategory" not in item:
                continue
            ids = urllib.parse.parse_qs(urllib.parse.urlparse(text(item.get("url")) or "").query).get("id")
            if ids == [app_id]:
                return item
    return {}
 
def ld_author(ld):
    a = ld.get("author")
    a = a[0] if isinstance(a, list) and a else a
    return text(a.get("name")) if isinstance(a, dict) else text(a)
 
def play_app(app_id):
    """Full detail record for one package name, or None if Play returns HTTP 404
    or the page has neither app data nor JSON-LD for this id."""
    url = "https://play.google.com/store/apps/details?" + urllib.parse.urlencode({"id": app_id, "hl": HL, "gl": GL})
    try:
        html = fetch(url)
    except urllib.error.HTTPError as e:
        if e.code == 404:
            return None
        raise
    a = next((g(d, 1, 2) for _, d in callbacks(html) if g(d, 1, 2, 77, 0) == app_id), None)
    ld = ld_app(html, app_id)
    if a is None and not ld:
        return None          # not an app page (removed app, region-locked, or an error page)
    price, currency, price_text = offer_fields(g(a, 57, 0, 0, 0, 0, 1, 0))
    agg = ld.get("aggregateRating") if isinstance(ld.get("aggregateRating"), dict) else {}
    offer = ld.get("offers")
    offer = offer[0] if isinstance(offer, list) and offer else offer
    offer = offer if isinstance(offer, dict) else {}
    ld_count = ld_num(agg.get("ratingCount"))
    price = first(price, ld_num(offer.get("price")))
    ads = g(a, 48)                   # ["Contains ads"] when the app has ads, null when it has none
    return {
        "app_id": app_id,
        "title": text(g(a, 0, 0)) or text(ld.get("name")),
        "developer": text(g(a, 68, 0)) or ld_author(ld),
        "developer_id": text(g(a, 68, 2)),
        "rating": first(num(g(a, 51, 0, 1)), ld_num(agg.get("ratingValue"))),
        "ratings_count": first(num(g(a, 51, 2, 1)), int(ld_count) if ld_count is not None else None),
        "installs": text(g(a, 13, 0)),
        "min_installs": num(g(a, 13, 1)),
        "installs_exact": num(g(a, 13, 2)),
        "price": price,
        "currency": currency or text(offer.get("priceCurrency")),
        "price_text": price_text or ("Free" if price == 0 else None),
        "category": text(g(a, 79, 0, 0, 0)),
        "category_id": text(g(a, 79, 0, 0, 2)) or text(ld.get("applicationCategory")),
        "updated": text(g(a, 145, 0, 0)),
        "updated_ts": num(g(a, 145, 0, 1, 0)),
        "version": text(g(a, 140, 0, 0, 0)) or ("Varies with device" if a else None),
        "content_rating": text(g(a, 9, 0)) or text(ld.get("contentRating")),
        "released": text(g(a, 10, 0)),
        "contains_ads": True if text(g(ads, 0)) else (False if a is not None and ads is None else None),
        "in_app_purchases": text(g(a, 19, 0)),
        "url": url,
    }
 
# --- 1) full records for a few package names, including one that does not exist ---
for app_id in ["com.spotify.music", "com.mojang.minecraftpe", "org.videolan.vlc", "com.example.does.not.exist"]:
    rec = play_app(app_id)
    print(json.dumps(rec) if rec else f"{app_id}: no record (HTTP 404, or no data for this id on the page)")
    time.sleep(1)
 
# --- 2) a batch of package names (for example from a developer page, block 3), one request per second ---
batch = ["com.whatsapp", "com.instagram.android", "com.google.android.youtube", "com.microsoft.teams", "com.rovio.baba",
         "com.ninjakiwi.bloonstd6", "com.mojang.minecraftedu", "com.duolingo", "com.netflix.mediaclient", "com.android.chrome"]
rows, missing = [], []
for app_id in batch:
    rec = play_app(app_id)
    if rec:
        rows.append(rec)
    else:
        missing.append(app_id)
    time.sleep(1)
print("detailed:", len(rows), "of", len(batch), "missing:", missing)
for r in rows[:5]:
    print(r["app_id"], "|", r["title"], "|", r["developer"], "|", r["rating"], r["ratings_count"], "|",
          r["installs"], "|", r["price_text"], "|", r["category"], "|", r["updated"], "|", r["version"], "|", r["content_rating"])

{"app_id": "com.spotify.music", "title": "Spotify: Music and Podcasts", "developer": "Spotify AB", "developer_id": "6523013212965523194", "rating": 4.3489933, "ratings_count": 36528069, "installs": "1,000,000,000+", "min_installs": 1000000000, "installs_exact": 3171683950, "price": 0.0, "currency": "USD", "price_text": "Free", "category": "Music & Audio", "category_id": "MUSIC_AND_AUDIO", "updated": "Oct 23, 2026", "updated_ts": 1792759042, "version": "Varies with device", "content_rating": "Teen", "released": "May 27, 2014", "contains_ads": true, "in_app_purchases": "$4.99 - $203.88 per item", "url": "https://play.google.com/store/apps/details?id=com.spotify.music&hl=en_US&gl=US"}
{"app_id": "com.mojang.minecraftpe", "title": "Minecraft: Dream it, Build it!", "developer": "Mojang", "developer_id": "4772240228547998649", "rating": 4.303256, "ratings_count": 5866778, "installs": "50,000,000+", "min_installs": 50000000, "installs_exact": 99618770, "price": 6.99, "currency": "USD", "price_text": "$6.99", "category": "Arcade", "category_id": "GAME_ARCADE", "updated": "Sep 25, 2026", "updated_ts": 1790357188, "version": "1.26.52.3", "content_rating": "Everyone 10+", "released": "Aug 15, 2011", "contains_ads": false, "in_app_purchases": "$0.99 - $49.99 per item", "url": "https://play.google.com/store/apps/details?id=com.mojang.minecraftpe&hl=en_US&gl=US"}
{"app_id": "org.videolan.vlc", "title": "VLC for Android", "developer": "Videolabs", "developer_id": "6364851808230428105", "rating": 4.042392, "ratings_count": 2009187, "installs": "500,000,000+", "min_installs": 500000000, "installs_exact": 515866848, "price": 0.0, "currency": "USD", "price_text": "Free", "category": "Video Players & Editors", "category_id": "VIDEO_PLAYERS", "updated": "Oct 14, 2026", "updated_ts": 1791980045, "version": "Varies with device", "content_rating": "Everyone", "released": "Feb 4, 2015", "contains_ads": false, "in_app_purchases": null, "url": "https://play.google.com/store/apps/details?id=org.videolan.vlc&hl=en_US&gl=US"}
com.example.does.not.exist: no record (HTTP 404, or no data for this id on the page)
detailed: 10 of 10 missing: []
com.whatsapp | WhatsApp | WhatsApp LLC | 4.624199 246257140 | 10,000,000,000+ | Free | Communication | Oct 19, 2026 | 2.26.41.77 | Everyone
com.instagram.android | Instagram | Instagram | 3.9892468 169555719 | 5,000,000,000+ | Free | Social | Oct 21, 2026 | Varies with device | Teen
com.google.android.youtube | YouTube | Google LLC | 3.8285916 172317597 | 10,000,000,000+ | Free | Video Players & Editors | Oct 20, 2026 | Varies with device | Teen
com.microsoft.teams | Microsoft Teams | Microsoft Corporation | 4.648416 8823533 | 500,000,000+ | Free | Business | Oct 22, 2026 | 1416/1.0.0.2026183002 | Everyone
com.rovio.baba | Angry Birds 2 | Rovio Entertainment Oy | 4.0748243 6320070 | 100,000,000+ | Free | Casual | Oct 20, 2026 | 26.7.1 | Everyone

import json, time, urllib.parse
 
def _retry(fn, *args, tries=3):
    """Call a harness helper, retrying only its timeouts: TimeoutError from the daemon IPC,
    or the 'Runtime.evaluate timed out' RuntimeError that js() raises. Other errors propagate."""
    for i in range(tries):
        try:
            return fn(*args)
        except (TimeoutError, RuntimeError) as e:
            if i == tries - 1 or not (isinstance(e, TimeoutError) or "timed out" in str(e)):
                raise
            time.sleep(2)
 
def open_play(path, params, ready_expr, timeout=30):
    """Navigate, then wait until the loaded document is THIS url (same path, same id) and ready_expr is true."""
    url = "https://play.google.com" + path + "?" + urllib.parse.urlencode(params)
    _retry(goto_url, url)
    check = f"""(() => {{
      const u = new URL(location.href);
      if (u.pathname !== {json.dumps(path)} || u.searchParams.get('id') !== {json.dumps(params["id"])}) return false;
      return document.readyState === 'complete' && Boolean({ready_expr});
    }})()"""
    deadline = time.time() + timeout
    while time.time() < deadline:
        if _retry(js, check):
            return url
        time.sleep(0.5)
    raise TimeoutError(f"{url} did not finish loading within {timeout}s")
 
def browser_app(app_id):
    """Same core fields from the rendered page: JSON-LD plus the labelled 'About this app' facts."""
    open_play("/store/apps/details", {"id": app_id, "hl": "en_US", "gl": "US"},
              "document.querySelector('script[type=\"application/ld+json\"]') || document.title.includes('Not Found')")
    return _retry(js, """(() => {
      const want = %s;
      let ld = {};
      for (const s of document.querySelectorAll('script[type="application/ld+json"]')) {
        try {
          const d = JSON.parse(s.textContent);
          for (const it of (Array.isArray(d) ? d : [d])) {
            const id = it && typeof it.url === 'string' && it.url && !it.url.startsWith('#') ? new URL(it.url, location.origin).searchParams.get('id') : null;
            if (it && it.applicationCategory && id === want) { ld = it; break; }
          }
        } catch (e) {}
      }
      const first = v => Array.isArray(v) ? v[0] : v;
      const n = v => (v === undefined || v === null || v === '' || isNaN(Number(v))) ? null : Number(v);
      const author = first(ld.author), offer = first(ld.offers) || {}, agg = ld.aggregateRating || {};
      const txt = document.body.innerText;
      const pick = re => { const m = txt.match(re); return m ? m[1].trim() : null; };
      return {
        app_id: new URL(location.href).searchParams.get('id'),
        title: ld.name || null,
        developer: typeof author === 'string' ? author : (author && author.name) || null,
        rating: n(agg.ratingValue),
        ratings_count: n(agg.ratingCount),
        price: n(offer.price),
        currency: offer.priceCurrency || null,
        category_id: ld.applicationCategory || null,
        content_rating: ld.contentRating || null,
        installs_badge: pick(/\\n([\\d.,]+[KMB]?\\+)\\n\\s*Downloads/),
        updated: pick(/Updated on\\n([^\\n]+)/),
        not_found: document.title.includes('Not Found') || !ld.name,
      };
    })()""" % json.dumps(app_id))
 
new_tab("about:blank")
for app_id in ["com.spotify.music", "com.mojang.minecraftpe", "com.example.does.not.exist"]:
    print(json.dumps(browser_app(app_id)))
    time.sleep(1)

{"app_id": "com.spotify.music", "title": "Spotify: Music and Podcasts", "developer": "Spotify AB", "rating": 4.348993301391602, "ratings_count": 36528068, "price": 0, "currency": "USD", "category_id": "MUSIC_AND_AUDIO", "content_rating": "Teen", "installs_badge": "1B+", "updated": "Oct 23, 2026", "not_found": false}
{"app_id": "com.mojang.minecraftpe", "title": "Minecraft: Dream it, Build it!", "developer": "Mojang", "rating": 4.303256034851074, "ratings_count": 5866776, "price": 6.99, "currency": "USD", "category_id": "GAME_ARCADE", "content_rating": "Everyone 10+", "installs_badge": "50M+", "updated": "Sep 25, 2026", "not_found": false}
{"app_id": "com.example.does.not.exist", "title": null, "developer": null, "rating": null, "ratings_count": null, "price": null, "currency": null, "category_id": null, "content_rating": null, "installs_badge": null, "updated": null, "not_found": true}

import json, time, urllib.parse
 
def _retry(fn, *args, tries=3):
    """Retry only harness timeouts (TimeoutError, or js()'s 'Runtime.evaluate timed out')."""
    for i in range(tries):
        try:
            return fn(*args)
        except (TimeoutError, RuntimeError) as e:
            if i == tries - 1 or not (isinstance(e, TimeoutError) or "timed out" in str(e)):
                raise
            time.sleep(2)
 
def open_play(path, params, ready_expr, timeout=30):
    """Navigate, then wait until the loaded document is THIS url (same path, same id) and ready_expr is true."""
    url = "https://play.google.com" + path + "?" + urllib.parse.urlencode(params)
    _retry(goto_url, url)
    check = f"""(() => {{
      const u = new URL(location.href);
      if (u.pathname !== {json.dumps(path)} || u.searchParams.get('id') !== {json.dumps(params["id"])}) return false;
      return document.readyState === 'complete' && Boolean({ready_expr});
    }})()"""
    deadline = time.time() + timeout
    while time.time() < deadline:
        if _retry(js, check):
            return url
        time.sleep(0.5)
    raise TimeoutError(f"{url} did not finish loading within {timeout}s")
 
NOT_FOUND = "document.title.includes('Not Found')"
FIRST_LOAD = 20                      # apps the developer page renders before any scrolling
 
def developer_name(app_id):
    """Developer name exactly as Play spells it (JSON-LD author of this app's page), or None if the app is not found."""
    open_play("/store/apps/details", {"id": app_id, "hl": "en_US", "gl": "US"},
              "document.querySelector('script[type=\"application/ld+json\"]') || " + NOT_FOUND)
    return _retry(js, """(() => {
      for (const s of document.querySelectorAll('script[type="application/ld+json"]')) {
        try {
          const d = JSON.parse(s.textContent);
          for (const it of (Array.isArray(d) ? d : [d])) {
            const id = it && typeof it.url === 'string' && it.url && !it.url.startsWith('#') ? new URL(it.url, location.origin).searchParams.get('id') : null;
            if (it && it.applicationCategory && id === %s) {
              const a = Array.isArray(it.author) ? it.author[0] : it.author;
              return typeof a === 'string' ? a : (a && a.name) || null;
            }
          }
        } catch (e) {}
      }
      return null;
    })()""" % json.dumps(app_id))
 
# one row per package name, in page order; card text is "title\ndeveloper\nrating\nstar"
CARDS_JS = r"""(() => {
  const rows = new Map();
  for (const a of document.querySelectorAll('a[href*="/store/apps/details?id="]')) {
    const id = new URL(a.href).searchParams.get('id');
    if (!id || rows.has(id)) continue;
    const l = a.innerText.split('\n').map(s => s.trim()).filter(Boolean);
    rows.set(id, {app_id: id, title: l[0] || null, developer: l[1] || null,
                  rating: /^\d(\.\d)?$/.test(l[2] || '') ? Number(l[2]) : null});
  }
  return [...rows.values()];
})()"""
 
def developer_apps(name, reads=5):
    """None if Play shows Not Found (name does not match a developer page exactly), else (apps, maybe_more).
    Reads only what the page renders on load; never scrolls (more apps would come from robots-disallowed /_/)."""
    open_play("/store/apps/developer", {"id": name, "hl": "en_US", "gl": "US"},
              "document.querySelector('a[href*=\"/store/apps/details?id=\"]') || " + NOT_FOUND)
    if _retry(js, NOT_FOUND):
        return None
    apps, prev = None, None
    for _ in range(reads):
        apps = _retry(js, CARDS_JS)
        if apps == prev:
            break
        prev = apps
        time.sleep(1)
    else:
        raise RuntimeError(f"developer_apps({name!r}): card list still changing after {reads} reads")
    if not apps:
        raise RuntimeError(f"developer_apps({name!r}): page loaded but no app cards found; markup changed?")
    maybe_more = len(apps) >= FIRST_LOAD
    if maybe_more:
        print(f"developer_apps({name!r}): page shows the first {len(apps)} apps; the developer may have more (not loaded: needs /_/)")
    return apps, maybe_more
 
new_tab("about:blank")
last = None
for app_id in ["com.google.android.youtube", "com.microsoft.teams", "com.rovio.baba", "com.mojang.minecraftpe"]:
    name = developer_name(app_id)
    if name is None:
        print(app_id, "-> app page not found, no developer name")
        continue
    time.sleep(1)
    got = developer_apps(name)
    if got is None:
        print(app_id, "->", repr(name), "developer page not found")
        continue
    apps, maybe_more = got
    other = sum(a["developer"] != name for a in apps)
    print(app_id, "->", repr(name), len(apps), "maybe_more:", maybe_more, "other developer:", other, [a["app_id"] for a in apps[:4]])
    last = apps
    time.sleep(1)
 
print("first row:", json.dumps(last[0]) if last else None)
print("wrong name:", developer_apps("Rovio Entertainment Corporation"))

developer_apps('Google LLC'): page shows the first 20 apps; the developer may have more (not loaded: needs /_/)
com.google.android.youtube -> 'Google LLC' 20 maybe_more: True other developer: 0 ['com.android.chrome', 'com.google.android.apps.messaging', 'com.google.android.googlequicksearchbox', 'com.google.android.gm']
developer_apps('Microsoft Corporation'): page shows the first 20 apps; the developer may have more (not loaded: needs /_/)
com.microsoft.teams -> 'Microsoft Corporation' 20 maybe_more: True other developer: 0 ['com.microsoft.office.outlook', 'com.microsoft.teams', 'com.microsoft.office.officehubrow', 'com.microsoft.skydrive']
com.rovio.baba -> 'Rovio Entertainment Oy' 16 maybe_more: False other developer: 0 ['com.rovio.baba', 'com.rovio.angrybirdsfriends', 'com.rovio.BadPiggies', 'com.rovio.dream']
com.mojang.minecraftpe -> 'Mojang' 3 maybe_more: False other developer: 0 ['com.mojang.minecraftpe', 'com.mojang.minecraftedu', 'com.mojang.minecraftedu_preview']
first row: {"app_id": "com.mojang.minecraftpe", "title": "Minecraft: Dream it, Build it!", "developer": "Mojang", "rating": 4.3}
wrong name: None