Consolidate all models into models.py (#14)

Also convert Summary to a dataclass for consistency

Author: jparise

instaparser/__init__.py

@@ -4,7 +4,6 @@
 A Python client library for the Instaparser API.
 """
 
-from .article import Article
 from .client import InstaparserClient
 from .exceptions import (
     InstaparserAPIError,
@@ -13,8 +12,7 @@
     InstaparserRateLimitError,
     InstaparserValidationError,
 )
-from .pdf import PDF
-from .summary import Summary
+from .models import PDF, Article, Summary
 
 __version__ = "1.0.1"
 

instaparser/client.py

@@ -12,15 +12,13 @@
 from urllib.parse import urlencode, urljoin
 from urllib.request import Request, urlopen
 
-from .article import Article
 from .exceptions import (
     InstaparserAPIError,
     InstaparserAuthenticationError,
     InstaparserRateLimitError,
     InstaparserValidationError,
 )
-from .pdf import PDF
-from .summary import Summary
+from .models import PDF, Article, Summary
 
 
 def _encode_multipart_formdata(

instaparser/article.py instaparser/models.pyinstaparser/article.py renamed to instaparser/models.py

@@ -1,6 +1,4 @@
-"""
-Article class representing a parsed article from Instaparser.
-"""
+"""Model classes representing parsed results from Instaparser."""
 
 from dataclasses import dataclass, field
 from typing import Any
@@ -54,3 +52,41 @@ def __repr__(self) -> str:
 
     def __str__(self) -> str:
         return self.body or ""
+
+
+@dataclass(repr=False)
+class PDF(Article):
+    """
+    Represents a parsed PDF from Instaparser.
+
+    Inherits from Article since most fields are the same.
+    PDFs always have is_rtl=False and videos=[].
+    """
+
+    def __post_init__(self) -> None:
+        self.is_rtl = False
+        self.videos = []
+
+    def __repr__(self) -> str:
+        return f"<PDF url={self.url!r} title={self.title!r}>"
+
+
+@dataclass(repr=False)
+class Summary:
+    """
+    Represents a summary result from Instaparser.
+
+    Attributes:
+        key_sentences: List of key sentences extracted from the article
+        overview: Concise summary of the article
+    """
+
+    key_sentences: list[str]
+    overview: str
+
+    def __repr__(self) -> str:
+        overview = self.overview[:50] + "..." if len(self.overview) > 50 else self.overview
+        return f"<Summary overview={overview!r} key_sentences={len(self.key_sentences)}>"
+
+    def __str__(self) -> str:
+        return self.overview

instaparser/pdf.py

@@ -6,14 +6,14 @@
 import pytest
 
 from instaparser import InstaparserClient
-from instaparser.article import Article
 from instaparser.client import _encode_multipart_formdata
 from instaparser.exceptions import (
     InstaparserAPIError,
     InstaparserAuthenticationError,
     InstaparserRateLimitError,
     InstaparserValidationError,
 )
+from instaparser.models import Article
 
 API_KEY = "test-api-key-12345"
 BASE_URL = "https://api.test.instaparser.com"

instaparser/summary.py

@@ -1,8 +1,8 @@
 """
-Tests for Article class.
+Tests for model classes.
 """
 
-from instaparser.article import Article
+from instaparser.models import PDF, Article, Summary
 
 
 class TestArticle:
@@ -60,3 +60,60 @@ def test_str_returns_empty_when_no_body(self):
         """Test __str__ returns empty string when body is None."""
         article = Article()
         assert str(article) == ""
+
+
+class TestPDF:
+    """Tests for PDF class."""
+
+    def test_inherits_from_article(self):
+        """Test that PDF inherits from Article."""
+        assert issubclass(PDF, Article)
+
+    def test_forces_is_rtl_false(self):
+        """Test that PDF always sets is_rtl to False, even if True is passed."""
+        pdf = PDF(is_rtl=True)
+        assert pdf.is_rtl is False
+
+    def test_forces_videos_empty(self):
+        """Test that PDF always sets videos to [], even if videos are passed."""
+        pdf = PDF(videos=["https://example.com/video.mp4"])
+        assert pdf.videos == []
+
+    def test_repr(self):
+        """Test __repr__ includes class name, url, and title."""
+        pdf = PDF(url="https://example.com/doc.pdf", title="Test PDF")
+        repr_str = repr(pdf)
+        assert "PDF" in repr_str
+        assert "https://example.com/doc.pdf" in repr_str
+        assert "Test PDF" in repr_str
+
+    def test_str_returns_body(self):
+        """Test that __str__ is inherited from Article and returns body."""
+        pdf = PDF(html="<p>Content</p>")
+        assert str(pdf) == "<p>Content</p>"
+
+
+class TestSummary:
+    """Tests for Summary class."""
+
+    def test_repr_truncates_long_overview(self):
+        """Test __repr__ truncates overview longer than 50 characters."""
+        summary = Summary(
+            key_sentences=["Sentence 1", "Sentence 2"],
+            overview="This is a test overview that is longer than 50 characters for truncation",
+        )
+        repr_str = repr(summary)
+        assert "..." in repr_str
+        assert "key_sentences=2" in repr_str
+
+    def test_repr_does_not_truncate_short_overview(self):
+        """Test __repr__ does not add ellipsis for short overview."""
+        summary = Summary(key_sentences=["Sentence"], overview="Short")
+        repr_str = repr(summary)
+        assert "..." not in repr_str
+        assert "key_sentences=1" in repr_str
+
+    def test_str_returns_overview(self):
+        """Test __str__ returns the overview."""
+        summary = Summary(key_sentences=["Sentence"], overview="The overview")
+        assert str(summary) == "The overview"