feat: user about info

examples/about_account.py

@@ -0,0 +1,15 @@
+import asyncio
+
+from twscrape import API
+
+
+async def main():
+    api = API()
+    username = "sama"
+
+    info = await api.user_about(username)
+    print(info.dict() if info else "Not found")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

readme.md

@@ -85,6 +85,7 @@ async def main():
     # get user by login
     user_login = "xdevelopers"
     await api.user_by_login(user_login)  # User
+    await api.user_about(user_login)  # AccountAbout
 
     # user info
     user_id = 2244994945
@@ -245,6 +246,7 @@ twscrape tweet_details TWEET_ID
 twscrape tweet_replies TWEET_ID --limit=20
 twscrape retweeters TWEET_ID --limit=20
 twscrape user_by_login USERNAME
+twscrape user_about USERNAME
 twscrape user_media USER_ID --limit=20
 twscrape following USER_ID --limit=20
 twscrape followers USER_ID --limit=20

scripts/update_gql_ops.py

@@ -62,34 +62,53 @@ async def main():
 
     print("Fetching Twitter JS bundle...")
     all_pairs: dict[str, str] = {}
+    conflicts: list[tuple[str, str, str]] = []
+
+    def _add(op_name: str, op_id: str):
+        existing = all_pairs.get(op_name)
+        if existing is not None and existing != op_id:
+            conflicts.append((op_name, existing, op_id))
+        all_pairs[op_name] = op_id
+
+    rgs = [
+        r'queryId:"(.+?)".+?operationName:"(.+?)"',
+        r'params:\{id:"([^"]+)".+?name:"([^"]+)".+?operationKind:"',
+    ]
+
     for txt in await get_scripts():
-        for op_id, op_name in re.findall(r'queryId:"(.+?)".+?operationName:"(.+?)"', txt):
-            all_pairs[op_name] = op_id
+        for rg in rgs:
+            for op_id, op_name in re.findall(rg, txt):
+                _add(op_name, op_id)
+
+    if conflicts:
+        print("WARNING: conflicting IDs found for same operation (last one wins):")
+        for n, old_id, new_id in conflicts:
+            print(f"  {n}: {old_id} vs {new_id}")
 
     print(f"Found {len(all_pairs)} operations in bundle\n")
 
     updated = content
     changed, missing = [], []
 
-    for name, old_id in current_ops.items():
-        new_id = all_pairs.get(name)
+    for n, old_id in current_ops.items():
+        new_id = all_pairs.get(n)
         if new_id is None:
-            missing.append(name)
+            missing.append(n)
         elif new_id != old_id:
-            changed.append((name, old_id, new_id))
-            updated = updated.replace(f'"{old_id}/{name}"', f'"{new_id}/{name}"')
+            changed.append((n, old_id, new_id))
+            updated = updated.replace(f'"{old_id}/{n}"', f'"{new_id}/{n}"')
 
     if changed:
         print("Changed:")
-        for name, old_id, new_id in changed:
-            print(f"  OP_{name}: {old_id} → {new_id}")
+        for n, old_id, new_id in changed:
+            print(f"  OP_{n}: {old_id} → {new_id}")
     else:
         print("No ID changes.")
 
     if missing:
         print("\nNot found in bundle (possibly removed):")
-        for name in missing:
-            print(f"  OP_{name}")
+        for n in missing:
+            print(f"  OP_{n}")
 
     if changed and apply:
         API_FILE.write_text(updated)

scripts/update_mocked_data.py

@@ -36,6 +36,7 @@ def save_meta(meta: dict):
 
 COMMANDS = [
     ("user_by_login", lambda api: api.user_by_login_raw("xdevelopers")),
+    ("user_about", lambda api: api.user_about_raw("xdevelopers")),
     ("following", lambda api: _first(api.following_raw(2244994945, limit=10))),
     ("followers", lambda api: _first(api.followers_raw(2244994945, limit=10))),
     ("verified_followers", lambda api: _first(api.verified_followers_raw(2244994945, limit=10))),

tests/test_parser.py

@@ -216,6 +216,32 @@ async def test_user_by_login():
     assert str(doc.id) in txt
 
 
+async def test_user_about():
+    api = get_api()
+    mock_rep(api.user_about_raw, "raw_user_about")
+
+    doc = await api.user_about("xdevelopers")
+    assert doc is not None
+    assert doc.screen_name == "XDevelopers"
+    assert isinstance(doc.rest_id, int)
+    assert isinstance(doc.name, str) and len(doc.name) > 0
+    assert doc.account_based_in is not None
+    assert doc.location_accurate is not None
+    assert doc.affiliate_username is not None
+    assert doc.source is not None
+    assert isinstance(doc.username_changes, int)
+    assert isinstance(doc.username_last_changed_at, int)
+    assert doc.is_identity_verified is not None
+    assert isinstance(doc.verified_since_msec, int)
+
+    obj = doc.dict()
+    assert doc.screen_name == obj["screen_name"]
+
+    txt = doc.json()
+    assert isinstance(txt, str)
+    assert doc.screen_name in txt
+
+
 async def test_tweet_details():
     api = get_api()
     mock_rep(api.tweet_details_raw, "raw_tweet_details")

twscrape/api.py

@@ -5,25 +5,38 @@
 
 from .accounts_pool import AccountsPool
 from .logger import set_log_level
-from .models import Tweet, User, parse_trends, parse_tweet, parse_tweets, parse_user, parse_users
+from .models import (
+    AccountAbout,
+    Tweet,
+    User,
+    parse_about,
+    parse_trends,
+    parse_tweet,
+    parse_tweets,
+    parse_user,
+    parse_users,
+)
 from .queue_client import QueueClient
 from .utils import encode_params, find_obj, get_by_path
 
 # OP_{NAME} – {NAME} should be same as second part of GQL ID (required to auto-update script)
-OP_SearchTimeline = "Yw6L66Pw54NHKuq4Dp7b4Q/SearchTimeline"
-OP_UserByScreenName = "IGgvgiOx4QZndDHuD3x9TQ/UserByScreenName"
-OP_TweetDetail = "oCon7R-cgWRFy6EfZjaKfg/TweetDetail"
+OP_AboutAccountQuery = "zUnx-DLN9dkwOkNhTLySjg/AboutAccountQuery"
+OP_BlueVerifiedFollowers = "crKOXrAHR3W3aPuKEJG8GA/BlueVerifiedFollowers"
+OP_Bookmarks = "XD0ViOeSOW4YoeNTGjVaYw/Bookmarks"
 OP_Followers = "_orfRBQae57vylFPH0Huhg/Followers"
 OP_Following = "F42cDX8PDFxkbjjq6JrM2w/Following"
-OP_Retweeters = "TZsWuSj7vGmncVnq7KWDUQ/Retweeters"
-OP_UserTweets = "36rb3Xj3iJ64Q-9wKDjCcQ/UserTweets"
-OP_UserTweetsAndReplies = "D5eKzDa5ZoJuC1TCeAXbWA/UserTweetsAndReplies"
+OP_GenericTimelineById = "_dGVIf1cY6xFanFNPsAzPQ/GenericTimelineById"
 OP_ListLatestTweetsTimeline = "7UuJsFvnWuZo0HmxrzU42Q/ListLatestTweetsTimeline"
-OP_BlueVerifiedFollowers = "crKOXrAHR3W3aPuKEJG8GA/BlueVerifiedFollowers"
+OP_Retweeters = "TZsWuSj7vGmncVnq7KWDUQ/Retweeters"
+OP_SearchTimeline = "Yw6L66Pw54NHKuq4Dp7b4Q/SearchTimeline"
+OP_TweetDetail = "oCon7R-cgWRFy6EfZjaKfg/TweetDetail"
+OP_UserByRestId = "VQfQ9wwYdk6j_u2O4vt64Q/UserByRestId"
+OP_UserByScreenName = "IGgvgiOx4QZndDHuD3x9TQ/UserByScreenName"
 OP_UserCreatorSubscriptions = "-9O4xZ8ykY_Hf6kyHJX30A/UserCreatorSubscriptions"
 OP_UserMedia = "9EovraBTXJYGSEQXZqlLmQ/UserMedia"
-OP_Bookmarks = "XD0ViOeSOW4YoeNTGjVaYw/Bookmarks"
-OP_GenericTimelineById = "_dGVIf1cY6xFanFNPsAzPQ/GenericTimelineById"
+OP_UserTweets = "36rb3Xj3iJ64Q-9wKDjCcQ/UserTweets"
+OP_UserTweetsAndReplies = "D5eKzDa5ZoJuC1TCeAXbWA/UserTweetsAndReplies"
+
 
 GQL_URL = "https://x.com/i/api/graphql"
 GQL_FEATURES = {  # search values here (view source) https://x.com/
@@ -206,6 +219,16 @@ async def user_by_login(self, login: str, kv: KV = None) -> User | None:
         rep = await self.user_by_login_raw(login, kv=kv)
         return parse_user(rep) if rep else None
 
+    async def user_about_raw(self, username: str, kv: KV = None):
+        op = OP_AboutAccountQuery
+        kv = {"screenName": username, **(kv or {})}
+        ft = {"responsive_web_graphql_timeline_navigation_enabled": True}
+        return await self._gql_item(op, kv, ft)
+
+    async def user_about(self, username: str, kv: KV = None) -> AccountAbout | None:
+        rep = await self.user_about_raw(username, kv=kv)
+        return parse_about(rep) if rep else None
+
     # tweet_details
 
     async def tweet_details_raw(self, twid: int, kv: KV = None):

twscrape/cli.py

@@ -185,6 +185,7 @@ def c_lim(name: str, msg: str, a_name: str, a_msg: str, a_type: type = str):
     c_lim("tweet_replies", "Get replies  of a tweet", "tweet_id", "Tweet ID", int)
     c_lim("retweeters", "Get retweeters of a tweet", "tweet_id", "Tweet ID", int)
     c_one("user_by_login", "Get user data by username", "username", "Username")
+    c_one("user_about", "Get about info for username", "username", "Username")
     c_lim("following", "Get user following", "user_id", "User ID", int)
     c_lim("followers", "Get user followers", "user_id", "User ID", int)
     # https://x.com/xDaily/status/1701694747767648500

twscrape/models.py

@@ -80,6 +80,43 @@ def parse(obj: dict):
         return TextLink(url=url1, text=text, tcourl=url2)
 
 
+@dataclass
+class AccountAbout(JSONTrait):
+    screen_name: str
+    name: str
+    rest_id: int | None
+    account_based_in: str | None
+    location_accurate: bool | None
+    affiliate_username: str | None
+    source: str | None
+    username_changes: int | None
+    username_last_changed_at: int | None
+    is_identity_verified: bool | None
+    verified_since_msec: int | None
+
+    @staticmethod
+    def parse(obj: dict):
+        about = obj.get("about_profile") or {}
+        core = obj.get("core") or {}
+        verification = obj.get("verification_info", {}) or {}
+        reason = verification.get("reason", {}) or {}
+        return AccountAbout(
+            screen_name=core.get("screen_name", ""),
+            name=core.get("name", ""),
+            rest_id=int_or(obj, "rest_id"),
+            account_based_in=about.get("account_based_in"),
+            location_accurate=about.get("location_accurate"),
+            affiliate_username=about.get("affiliate_username"),
+            source=about.get("source"),
+            username_changes=int_or(about.get("username_changes") or {}, "count"),
+            username_last_changed_at=int_or(
+                about.get("username_changes") or {}, "last_changed_at_msec"
+            ),
+            is_identity_verified=verification.get("is_identity_verified"),
+            verified_since_msec=int_or(reason, "verified_since_msec"),
+        )
+
+
 @dataclass
 class UserRef(JSONTrait):
     id: int
@@ -769,6 +806,18 @@ def parse_trend(rep: httpx.Response) -> Trend | None:
         return None
 
 
+def parse_about(rep: httpx.Response | dict) -> AccountAbout | None:
+    try:
+        res = rep if isinstance(rep, dict) else rep.json()
+        obj = get_or(res, "data.user_result_by_screen_name.result")
+        if not obj:
+            return None
+        return AccountAbout.parse(obj)
+    except Exception as e:
+        logger.error(f"Failed to parse about profile - {type(e)}:\n{traceback.format_exc()}")
+        return None
+
+
 def parse_tweets(rep: httpx.Response, limit: int = -1) -> Generator[Tweet, None, None]:
     return _parse_items(rep, "tweet", limit)  # type: ignore