Convert Article, PDF, and Summary to use dataclasses

instaparser/article.py

@@ -2,9 +2,11 @@
 Article class representing a parsed article from Instaparser.
 """
 
+from dataclasses import dataclass, field
 from typing import Any
 
 
+@dataclass(repr=False)
 class Article:
     """
     Represents a parsed article from Instaparser.
@@ -27,30 +29,25 @@ class Article:
         markdown: The markdown body (if output was 'markdown')
     """
 
-    def __init__(self, data: dict[str, Any]):
-        """
-        Initialize an Article from API response data.
-
-        Args:
-            data: Dictionary containing article data from the API
-        """
-        self.url = data.get("url")
-        self.title = data.get("title")
-        self.site_name = data.get("site_name")
-        self.author = data.get("author")
-        self.date = data.get("date")
-        self.description = data.get("description")
-        self.thumbnail = data.get("thumbnail")
-        self.words = data.get("words", 0)
-        self.is_rtl = data.get("is_rtl", False)
-        self.images = data.get("images", [])
-        self.videos = data.get("videos", [])
-
-        self.html = data.get("html")
-        self.text = data.get("text")
-        self.markdown = data.get("markdown")
-
-        self.body = self.html or self.text or self.markdown
+    url: str | None = None
+    title: str | None = None
+    site_name: str | None = None
+    author: str | None = None
+    date: Any | None = None
+    description: str | None = None
+    thumbnail: str | None = None
+    words: int = 0
+    is_rtl: bool = False
+    images: list = field(default_factory=list)
+    videos: list = field(default_factory=list)
+    html: str | None = None
+    text: str | None = None
+    markdown: str | None = None
+
+    @property
+    def body(self) -> str | None:
+        """The article body (html if available, otherwise text, then markdown)."""
+        return self.html or self.text or self.markdown
 
     def __repr__(self) -> str:
         return f"<Article url={self.url!r} title={self.title!r}>"

instaparser/client.py

@@ -141,8 +141,22 @@ def Article(self, url: str, content: str | None = None, output: str = "html", us
 
         response = self.session.post(endpoint, json=payload)
         data = self._handle_response(response)
-
-        return Article(data)
+        return Article(
+            url=data.get("url"),
+            title=data.get("title"),
+            site_name=data.get("site_name"),
+            author=data.get("author"),
+            date=data.get("date"),
+            description=data.get("description"),
+            thumbnail=data.get("thumbnail"),
+            words=data.get("words", 0),
+            is_rtl=data.get("is_rtl", False),
+            images=data.get("images", []),
+            videos=data.get("videos", []),
+            html=data.get("html"),
+            text=data.get("text"),
+            markdown=data.get("markdown"),
+        )
 
     def Summary(
         self,
@@ -271,5 +285,18 @@ def PDF(
         else:
             raise InstaparserValidationError("Either 'url' or 'file' must be provided")
 
-        data = self._handle_response(response)
-        return PDF(data)
+        result = self._handle_response(response)
+        return PDF(
+            url=result.get("url"),
+            title=result.get("title"),
+            site_name=result.get("site_name"),
+            author=result.get("author"),
+            date=result.get("date"),
+            description=result.get("description"),
+            thumbnail=result.get("thumbnail"),
+            words=result.get("words", 0),
+            images=result.get("images", []),
+            html=result.get("html"),
+            text=result.get("text"),
+            markdown=result.get("markdown"),
+        )

instaparser/pdf.py

@@ -2,11 +2,12 @@
 PDF class representing a parsed PDF from Instaparser.
 """
 
-from typing import Any
+from dataclasses import dataclass
 
 from .article import Article
 
 
+@dataclass(repr=False)
 class PDF(Article):
     """
     Represents a parsed PDF from Instaparser.
@@ -15,17 +16,7 @@ class PDF(Article):
     PDFs always have is_rtl=False and videos=[].
     """
 
-    def __init__(self, data: dict[str, Any]):
-        """
-        Initialize a PDF from API response data.
-
-        Args:
-            data: Dictionary containing PDF data from the API
-        """
-        # Call parent constructor
-        super().__init__(data)
-
-        # PDFs always have is_rtl=False and videos=[]
+    def __post_init__(self) -> None:
         self.is_rtl = False
         self.videos = []