diff --git a/backend/src/utils/readability.py b/backend/src/utils/readability.py
index 8915098..e905f71 100644
--- a/backend/src/utils/readability.py
+++ b/backend/src/utils/readability.py
@@ -1,9 +1,13 @@
+import logging
import re
+import subprocess
from urllib.parse import urljoin
from markdownify import markdownify as md
from readabilipy import simple_json_from_html_string
+logger = logging.getLogger(__name__)
+
class Article:
url: str
@@ -53,7 +57,20 @@ class Article:
class ReadabilityExtractor:
def extract_article(self, html: str) -> Article:
- article = simple_json_from_html_string(html, use_readability=True)
+ try:
+ article = simple_json_from_html_string(html, use_readability=True)
+ except (subprocess.CalledProcessError, FileNotFoundError) as exc:
+ stderr = getattr(exc, "stderr", None)
+ if isinstance(stderr, bytes):
+ stderr = stderr.decode(errors="replace")
+ stderr_info = f"; stderr={stderr.strip()}" if isinstance(stderr, str) and stderr.strip() else ""
+ logger.warning(
+ "Readability.js extraction failed with %s%s; falling back to pure-Python extraction",
+ type(exc).__name__,
+ stderr_info,
+ exc_info=True,
+ )
+ article = simple_json_from_html_string(html, use_readability=False)
html_content = article.get("content")
if not html_content or not str(html_content).strip():
diff --git a/backend/tests/test_readability.py b/backend/tests/test_readability.py
new file mode 100644
index 0000000..9545ee2
--- /dev/null
+++ b/backend/tests/test_readability.py
@@ -0,0 +1,55 @@
+"""Tests for readability extraction fallback behavior."""
+
+import subprocess
+
+import pytest
+
+from src.utils.readability import ReadabilityExtractor
+
+
+def test_extract_article_falls_back_when_readability_js_fails(monkeypatch):
+ """When Node-based readability fails, extraction should fall back to Python mode."""
+
+ calls: list[bool] = []
+
+ def _fake_simple_json_from_html_string(html: str, use_readability: bool = False):
+ calls.append(use_readability)
+ if use_readability:
+ raise subprocess.CalledProcessError(
+ returncode=1,
+ cmd=["node", "ExtractArticle.js"],
+ stderr="boom",
+ )
+ return {"title": "Fallback Title", "content": "Fallback Content
"}
+
+ monkeypatch.setattr(
+ "src.utils.readability.simple_json_from_html_string",
+ _fake_simple_json_from_html_string,
+ )
+
+ article = ReadabilityExtractor().extract_article("test")
+
+ assert calls == [True, False]
+ assert article.title == "Fallback Title"
+ assert article.html_content == "Fallback Content
"
+
+
+def test_extract_article_re_raises_unexpected_exception(monkeypatch):
+ """Unexpected errors should be surfaced instead of silently falling back."""
+
+ calls: list[bool] = []
+
+ def _fake_simple_json_from_html_string(html: str, use_readability: bool = False):
+ calls.append(use_readability)
+ if use_readability:
+ raise RuntimeError("unexpected parser failure")
+ return {"title": "Should Not Reach Fallback", "content": "Fallback
"}
+
+ monkeypatch.setattr(
+ "src.utils.readability.simple_json_from_html_string",
+ _fake_simple_json_from_html_string,
+ )
+
+ with pytest.raises(RuntimeError, match="unexpected parser failure"):
+ ReadabilityExtractor().extract_article("test")
+ assert calls == [True]