fix: resolve issue #651 - crawl error with None content handling (#652)

* fix: resolve issue #651 - crawl error with None content handling Fixed issue #651 by adding comprehensive null-safety checks and error handling to the crawl system. The fix prevents the ‘TypeError: Incoming markup is of an invalid type: None’ crash by: 1. Validating HTTP responses from Jina API 2. Handling None/empty content at extraction stage 3. Adding fallback handling in Article markdown/message conversion 4. Improving error diagnostics with detailed logging 5. Adding 16 new tests with 100% coverage for critical paths * Update src/crawler/readability_extractor.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/crawler/article.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-04-22 05:34:45 +08:00 · 2025-10-24 17:06:54 +08:00
parent 2001a7c223
commit 975b344ca7
8 changed files with 328 additions and 9 deletions
--- a/tests/unit/crawler/test_readability_extractor.py
+++ b/tests/unit/crawler/test_readability_extractor.py
@@ -0,0 +1,103 @@
+# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
+# SPDX-License-Identifier: MIT
+
+from unittest.mock import patch
+from src.crawler.readability_extractor import ReadabilityExtractor
+
+
+class TestReadabilityExtractor:
+    @patch("src.crawler.readability_extractor.simple_json_from_html_string")
+    def test_extract_article_with_valid_content(self, mock_simple_json):
+        # Arrange
+        mock_simple_json.return_value = {
+            "title": "Test Article",
+            "content": "<p>Article content</p>",
+        }
+        extractor = ReadabilityExtractor()
+
+        # Act
+        article = extractor.extract_article("<html>test</html>")
+
+        # Assert
+        assert article.title == "Test Article"
+        assert article.html_content == "<p>Article content</p>"
+
+    @patch("src.crawler.readability_extractor.simple_json_from_html_string")
+    def test_extract_article_with_none_content(self, mock_simple_json):
+        # Arrange
+        mock_simple_json.return_value = {
+            "title": "Test Article",
+            "content": None,
+        }
+        extractor = ReadabilityExtractor()
+
+        # Act
+        article = extractor.extract_article("<html>test</html>")
+
+        # Assert
+        assert article.title == "Test Article"
+        assert article.html_content == "<p>No content could be extracted from this page</p>"
+
+    @patch("src.crawler.readability_extractor.simple_json_from_html_string")
+    def test_extract_article_with_empty_content(self, mock_simple_json):
+        # Arrange
+        mock_simple_json.return_value = {
+            "title": "Test Article",
+            "content": "",
+        }
+        extractor = ReadabilityExtractor()
+
+        # Act
+        article = extractor.extract_article("<html>test</html>")
+
+        # Assert
+        assert article.title == "Test Article"
+        assert article.html_content == "<p>No content could be extracted from this page</p>"
+
+    @patch("src.crawler.readability_extractor.simple_json_from_html_string")
+    def test_extract_article_with_whitespace_only_content(self, mock_simple_json):
+        # Arrange
+        mock_simple_json.return_value = {
+            "title": "Test Article",
+            "content": "   \n  \t  ",
+        }
+        extractor = ReadabilityExtractor()
+
+        # Act
+        article = extractor.extract_article("<html>test</html>")
+
+        # Assert
+        assert article.title == "Test Article"
+        assert article.html_content == "<p>No content could be extracted from this page</p>"
+
+    @patch("src.crawler.readability_extractor.simple_json_from_html_string")
+    def test_extract_article_with_none_title(self, mock_simple_json):
+        # Arrange
+        mock_simple_json.return_value = {
+            "title": None,
+            "content": "<p>Article content</p>",
+        }
+        extractor = ReadabilityExtractor()
+
+        # Act
+        article = extractor.extract_article("<html>test</html>")
+
+        # Assert
+        assert article.title == "Untitled"
+        assert article.html_content == "<p>Article content</p>"
+
+    @patch("src.crawler.readability_extractor.simple_json_from_html_string")
+    def test_extract_article_with_empty_title(self, mock_simple_json):
+        # Arrange
+        mock_simple_json.return_value = {
+            "title": "",
+            "content": "<p>Article content</p>",
+        }
+        extractor = ReadabilityExtractor()
+
+        # Act
+        article = extractor.extract_article("<html>test</html>")
+
+        # Assert
+        assert article.title == "Untitled"
+        assert article.html_content == "<p>Article content</p>"