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>

src/crawler/article.py

@@ -18,20 +18,36 @@ class Article:
         markdown = ""
         if including_title:
             markdown += f"# {self.title}\n\n"
-        markdown += md(self.html_content)
+        
+        if self.html_content is None or not str(self.html_content).strip():
+            markdown += "*No content available*\n"
+        else:
+            markdown += md(self.html_content)
+        
         return markdown
 
     def to_message(self) -> list[dict]:
         image_pattern = r"!\[.*?\]\((.*?)\)"
 
         content: list[dict[str, str]] = []
-        parts = re.split(image_pattern, self.to_markdown())
+        markdown = self.to_markdown()
+        
+        if not markdown or not markdown.strip():
+            return [{"type": "text", "text": "No content available"}]
+        
+        parts = re.split(image_pattern, markdown)
 
         for i, part in enumerate(parts):
             if i % 2 == 1:
                 image_url = urljoin(self.url, part.strip())
                 content.append({"type": "image_url", "image_url": {"url": image_url}})
             else:
-                content.append({"type": "text", "text": part.strip()})
+                text_part = part.strip()
+                if text_part:
+                    content.append({"type": "text", "text": text_part})
 
+        # If after processing all parts, content is still empty, provide a fallback message.
+        if not content:
+            content = [{"type": "text", "text": "No content available"}]
+        
         return content

src/crawler/crawler.py

@@ -1,11 +1,14 @@
 # Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
 # SPDX-License-Identifier: MIT
 
+import logging
 
 from .article import Article
 from .jina_client import JinaClient
 from .readability_extractor import ReadabilityExtractor
 
+logger = logging.getLogger(__name__)
+
 
 class Crawler:
     def crawl(self, url: str) -> Article:
@@ -19,9 +22,19 @@ class Crawler:
         #
         # Instead of using Jina's own markdown converter, we'll use
         # our own solution to get better readability results.
-        jina_client = JinaClient()
-        html = jina_client.crawl(url, return_format="html")
-        extractor = ReadabilityExtractor()
-        article = extractor.extract_article(html)
+        try:
+            jina_client = JinaClient()
+            html = jina_client.crawl(url, return_format="html")
+        except Exception as e:
+            logger.error(f"Failed to fetch URL {url} from Jina: {repr(e)}")
+            raise
+        
+        try:
+            extractor = ReadabilityExtractor()
+            article = extractor.extract_article(html)
+        except Exception as e:
+            logger.error(f"Failed to extract article from {url}: {repr(e)}")
+            raise
+        
         article.url = url
         return article

src/crawler/jina_client.py

@@ -23,4 +23,11 @@ class JinaClient:
             )
         data = {"url": url}
         response = requests.post("https://r.jina.ai/", headers=headers, json=data)
+        
+        if response.status_code != 200:
+            raise ValueError(f"Jina API returned status {response.status_code}: {response.text}")
+        
+        if not response.text or not response.text.strip():
+            raise ValueError("Jina API returned empty response")
+        
         return response.text

src/crawler/readability_extractor.py

@@ -1,15 +1,28 @@
 # Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
 # SPDX-License-Identifier: MIT
 
+import logging
 from readabilipy import simple_json_from_html_string
 
 from .article import Article
 
+logger = logging.getLogger(__name__)
+
 
 class ReadabilityExtractor:
     def extract_article(self, html: str) -> Article:
         article = simple_json_from_html_string(html, use_readability=True)
+        
+        content = article.get("content")
+        if not content or not str(content).strip():
+            logger.warning("Readability extraction returned empty content")
+            content = "<p>No content could be extracted from this page</p>"
+        
+        title = article.get("title")
+        if not title or not str(title).strip():
+            title = "Untitled"
+        
         return Article(
-            title=article.get("title"),
-            html_content=article.get("content"),
+            title=title,
+            html_content=content,
         )