add missing string id representation to models #116

readme.md

@@ -13,7 +13,7 @@
 Twitter GraphQL API implementation with [SNScrape](https://github.com/JustAnotherArchivist/snscrape) data models.
 
 <div align="center">
-  <img src="https://miro.medium.com/v2/resize:fit:1400/format:webp/1*0erkeMBhl_qqRofIeU5jMQ.png" alt="example of cli usage" width="560px">
+  <img src=".github/example.png" alt="example of cli usage" width="560px">
 </div>
 
 ## Install

tests/test_parser.py

@@ -4,7 +4,7 @@
 
 from twscrape import API, gather
 from twscrape.logger import set_log_level
-from twscrape.models import Tweet, User, parse_tweet
+from twscrape.models import Tweet, User, UserRef, parse_tweet
 
 BASE_DIR = os.path.dirname(__file__)
 DATA_DIR = os.path.join(BASE_DIR, "mocked-data")
@@ -49,18 +49,33 @@ async def cb_gen(*args, **kwargs):
 
 def check_tweet(doc: Tweet | None):
     assert doc is not None
-    assert doc.id is not None
-    assert doc.id_str is not None
     assert isinstance(doc.id, int)
     assert isinstance(doc.id_str, str)
-    assert doc.id == int(doc.id_str)
+    assert str(doc.id) == doc.id_str
 
     assert doc.url is not None
     assert doc.id_str in doc.url
     assert doc.user is not None
 
+    assert isinstance(doc.conversationId, int)
+    assert isinstance(doc.conversationIdStr, str)
+    assert str(doc.conversationId) == doc.conversationIdStr
+
+    if doc.inReplyToTweetId is not None:
+        assert isinstance(doc.inReplyToTweetId, int)
+        assert isinstance(doc.inReplyToTweetIdStr, str)
+        assert str(doc.inReplyToTweetId) == doc.inReplyToTweetIdStr
+
+    if doc.inReplyToUser:
+        check_user_ref(doc.inReplyToUser)
+
+    if doc.mentionedUsers:
+        for x in doc.mentionedUsers:
+            check_user_ref(x)
+
     obj = doc.dict()
     assert doc.id == obj["id"]
+    assert doc.id_str == obj["id_str"]
     assert doc.user.id == obj["user"]["id"]
 
     assert "url" in obj
@@ -104,10 +119,9 @@ def check_tweet(doc: Tweet | None):
 
 def check_user(doc: User):
     assert doc.id is not None
-    assert doc.id_str is not None
     assert isinstance(doc.id, int)
     assert isinstance(doc.id_str, str)
-    assert doc.id == int(doc.id_str)
+    assert str(doc.id) == doc.id_str
 
     assert doc.username is not None
     assert doc.descriptionLinks is not None
@@ -127,6 +141,19 @@ def check_user(doc: User):
     assert str(doc.id) in txt
 
 
+def check_user_ref(doc: UserRef):
+    assert isinstance(doc.id, int)
+    assert isinstance(doc.id_str, str)
+    assert str(doc.id) == doc.id_str
+
+    assert doc.username is not None
+    assert doc.displayname is not None
+
+    obj = doc.dict()
+    assert doc.id == obj["id"]
+    assert doc.id_str == obj["id_str"]
+
+
 async def test_search():
     api = API()
     mock_rep(api.search_raw, "raw_search", as_generator=True)

twscrape/models.py

@@ -84,13 +84,19 @@ def parse(obj: dict):
 @dataclass
 class UserRef(JSONTrait):
     id: int
+    id_str: str
     username: str
     displayname: str
     _type: str = "snscrape.modules.twitter.UserRef"
 
     @staticmethod
     def parse(obj: dict):
-        return UserRef(id=int(obj["id_str"]), username=obj["screen_name"], displayname=obj["name"])
+        return UserRef(
+            id=int(obj["id_str"]),
+            id_str=obj["id_str"],
+            username=obj["screen_name"],
+            displayname=obj["name"],
+        )
 
 
 @dataclass
@@ -163,6 +169,7 @@ class Tweet(JSONTrait):
     likeCount: int
     quoteCount: int
     conversationId: int
+    conversationIdStr: str
     hashtags: list[str]
     cashtags: list[str]
     mentionedUsers: list[UserRef]
@@ -173,6 +180,7 @@ class Tweet(JSONTrait):
     place: Optional[Place] = None
     coordinates: Optional[Coordinates] = None
     inReplyToTweetId: int | None = None
+    inReplyToTweetIdStr: str | None = None
     inReplyToUser: UserRef | None = None
     source: str | None = None
     sourceUrl: str | None = None
@@ -217,6 +225,7 @@ def parse(obj: dict, res: dict):
             likeCount=obj["favorite_count"],
             quoteCount=obj["quote_count"],
             conversationId=int(obj["conversation_id_str"]),
+            conversationIdStr=obj["conversation_id_str"],
             hashtags=[x["text"] for x in get_or(obj, "entities.hashtags", [])],
             cashtags=[x["text"] for x in get_or(obj, "entities.symbols", [])],
             mentionedUsers=[UserRef.parse(x) for x in get_or(obj, "entities.user_mentions", [])],
@@ -229,6 +238,7 @@ def parse(obj: dict, res: dict):
             place=Place.parse(obj["place"]) if obj.get("place") else None,
             coordinates=Coordinates.parse(obj),
             inReplyToTweetId=int_or(obj, "in_reply_to_status_id_str"),
+            inReplyToTweetIdStr=get_or(obj, "in_reply_to_status_id_str"),
             inReplyToUser=_get_reply_user(obj, res),
             source=obj.get("source", None),
             sourceUrl=_get_source_url(obj),