A couple of changes to RSS tool

Author: jimbrub

README.md

@@ -55,6 +55,7 @@ Strands Agents Tools is a community-driven project that provides a powerful set
 - 🔄 **Multiple tools in Parallel**  - Call multiple other tools at the same time in parallel with Batch Tool
 - 🔍 **Browser Tool** - Tool giving an agent access to perform automated actions on a browser (chromium)
 - 📈 **Diagram** - Create AWS cloud diagrams, basic diagrams, or UML diagrams using python libraries
+- 📰 **RSS Feed Manager** - Subscribe, fetch, and process RSS feeds with content filtering and persistent storage
 
 ## 📦 Installation
 
@@ -67,7 +68,7 @@ pip install strands-agents-tools
 To install the dependencies for optional tools:
 
 ```bash
-pip install strands-agents-tools[mem0_memory, use_browser]
+pip install strands-agents-tools[mem0_memory, use_browser, rss]
 ```
 
 ### Development Install
@@ -130,6 +131,7 @@ Below is a comprehensive table of all available tools, how to use them with an a
 | batch| `agent.tool.batch(invocations=[{"name": "current_time", "arguments": {"timezone": "Europe/London"}}, {"name": "stop", "arguments": {}}])` | Call multiple other tools in parallel. |
 | browser | `browser = LocalChromiumBrowser(); agent = Agent(tools=[browser.browser])` | Web scraping, automated testing, form filling, web automation tasks |
 | diagram | `agent.tool.diagram(diagram_type="cloud", nodes=[{"id": "s3", "type": "S3"}], edges=[])` | Create AWS cloud architecture diagrams, network diagrams, graphs, and UML diagrams (all 14 types) |
+| rss | `agent.tool.rss(action="subscribe", url="https://example.com/feed.xml", feed_id="tech_news")` | Manage RSS feeds: subscribe, fetch, read, search, and update content from various sources |
 
 \* *These tools do not work on windows*
 
@@ -504,6 +506,46 @@ result = agent.tool.diagram(
 )
 ```
 
+### RSS Feed Management
+
+```python
+from strands import Agent
+from strands_tools import rss
+
+agent = Agent(tools=[rss])
+
+# Subscribe to a feed
+result = agent.tool.rss(
+    action="subscribe",
+    url="https://news.example.com/rss/technology"
+)
+
+# List all subscribed feeds
+feeds = agent.tool.rss(action="list")
+
+# Read entries from a specific feed
+entries = agent.tool.rss(
+    action="read",
+    feed_id="news_example_com_technology",
+    max_entries=5,
+    include_content=True
+)
+
+# Search across all feeds
+search_results = agent.tool.rss(
+    action="search",
+    query="machine learning",
+    max_entries=10
+)
+
+# Fetch feed content without subscribing
+latest_news = agent.tool.rss(
+    action="fetch",
+    url="https://blog.example.org/feed",
+    max_entries=3
+)
+```
+
 ## 🌍 Environment Variables Configuration
 
 Agents Tools provides extensive customization through environment variables. This allows you to configure tool behavior without modifying code, making it ideal for different environments (development, testing, production).
@@ -659,6 +701,14 @@ The Mem0 Memory Tool supports three different backend configurations:
 | STRANDS_BROWSER_WIDTH | Default width of the browser | 1280 |
 | STRANDS_BROWSER_HEIGHT | Default height of the browser | 800 |
 
+#### RSS Tool
+
+| Environment Variable | Description | Default |
+|----------------------|-------------|---------|
+| STRANDS_RSS_MAX_ENTRIES | Default setting for maximum number of entries per feed | 100 |
+| STRANDS_RSS_UPDATE_INTERVAL | Default amount of time between updating rss feeds in minutes | 60 |
+| STRANDS_RSS_STORAGE_PATH | Default storage path where rss feeds are stored locally | ~/.strands/rss_feeds |
+
 
 ## Contributing ❤️
 

pyproject.toml

@@ -97,9 +97,10 @@ diagram = [
     "networkx>=2.8.0,<4.0.0",
     "diagrams>=0.23.0,<1.0.0",
 ]
+rss = ["feedparser>=6.0.10,<7.0.0", "html2text>=2020.1.16,<2021.0.0"]
 
 [tool.hatch.envs.hatch-static-analysis]
-features = ["mem0_memory", "local_chromium_browser", "agent_core_browser", "agent_core_code_interpreter", "a2a_client", "diagram"]
+features = ["mem0_memory", "local_chromium_browser", "agent_core_browser", "agent_core_code_interpreter", "a2a_client", "diagram", "rss"]
 dependencies = [
     "strands-agents>=1.0.0",
     "mypy>=0.981,<1.0.0",
@@ -118,7 +119,7 @@ lint-check = [
 lint-fix = ["ruff check --fix"]
 
 [tool.hatch.envs.hatch-test]
-features = ["mem0_memory", "local_chromium_browser",  "agent_core_browser", "agent_core_code_interpreter", "a2a_client", "diagram"]
+features = ["mem0_memory", "local_chromium_browser",  "agent_core_browser", "agent_core_code_interpreter", "a2a_client", "diagram", "rss"]
 extra-dependencies = [
     "moto>=5.1.0,<6.0.0",
     "pytest>=8.0.0,<9.0.0",

src/strands_tools/rss.py

@@ -2,6 +2,7 @@
 import logging
 import os
 import re
+import tempfile
 from datetime import datetime
 from typing import Dict, List, Optional, Set, Union
 from urllib.parse import urlparse
@@ -13,7 +14,8 @@
 
 # Configure logging and defaults
 logger = logging.getLogger(__name__)
-DEFAULT_STORAGE_PATH = os.path.expanduser("~/.strands/rss_feeds")
+# Always use temporary directory for storage
+DEFAULT_STORAGE_PATH = os.path.join(tempfile.gettempdir(), "strands_rss_feeds")
 DEFAULT_MAX_ENTRIES = int(os.environ.get("STRANDS_RSS_MAX_ENTRIES", "100"))
 DEFAULT_UPDATE_INTERVAL = int(os.environ.get("STRANDS_RSS_UPDATE_INTERVAL", "60"))  # minutes
 
@@ -115,11 +117,21 @@ def save_feed_data(self, feed_id: str, data: Dict) -> None:
         with open(self.get_feed_file_path(feed_id), "w") as f:
             json.dump(data, f, indent=2)
 
-    def fetch_feed(self, url: str, auth: Optional[Dict] = None, user_agent: Optional[str] = None) -> Dict:
+    def fetch_feed(self, url: str, auth: Optional[Dict] = None, headers: Optional[Dict] = None) -> Dict:
+        # Initialize headers dictionary if not provided
+        if headers is None:
+            headers = {}
+        # Handle case where headers might be a string (for backward compatibility with tests)
+        elif isinstance(headers, str):
+            headers = {"User-Agent": headers}
+
+        # If using basic auth, make the request with headers and auth
         if auth and auth.get("type") == "basic":
-            headers = {"User-Agent": user_agent} if user_agent else {}
             response = requests.get(url, headers=headers, auth=(auth.get("username", ""), auth.get("password", "")))
             return feedparser.parse(response.content)
+
+        # For non-auth requests, extract User-Agent if present in headers
+        user_agent = headers.get("User-Agent")
         return feedparser.parse(url, agent=user_agent)
 
     def update_feed(self, feed_id: str, subscriptions: Dict[str, Dict]) -> Dict:
@@ -128,7 +140,7 @@ def update_feed(self, feed_id: str, subscriptions: Dict[str, Dict]) -> Dict:
 
         try:
             feed_info = subscriptions[feed_id]
-            feed = self.fetch_feed(feed_info["url"], feed_info.get("auth"), feed_info.get("user_agent"))
+            feed = self.fetch_feed(feed_info["url"], feed_info.get("auth"), feed_info.get("headers"))
 
             if not hasattr(feed, "entries"):
                 return {"error": f"Could not parse feed from {feed_info['url']}"}
@@ -193,7 +205,7 @@ def rss(
     update_interval: Optional[int] = None,
     auth_username: Optional[str] = None,
     auth_password: Optional[str] = None,
-    user_agent: Optional[str] = None,
+    headers: Optional[Dict[str, str]] = None,
 ) -> Union[str, List[Dict], Dict]:
     """
     Interact with RSS feeds - fetch, subscribe, search, and manage feeds.
@@ -219,14 +231,14 @@ def rss(
         update_interval: Update interval in minutes
         auth_username: Username for authenticated feeds
         auth_password: Password for authenticated feeds
-        user_agent: Custom user agent string
+        headers: Dictionary of HTTP headers to send with requests (e.g., {"User-Agent": "MyRSSReader/1.0"})
     """
     try:
         if action == "fetch":
             if not url:
                 return "Error: URL is required for fetch action"
 
-            feed = feedparser.parse(url)
+            feed = rss_manager.fetch_feed(url, headers=headers)
             if not hasattr(feed, "entries"):
                 return f"Error: Could not parse feed from {url}"
 
@@ -252,8 +264,8 @@ def rss(
 
             if auth_username and auth_password:
                 subscription["auth"] = {"type": "basic", "username": auth_username, "password": auth_password}
-            if user_agent:
-                subscription["user_agent"] = user_agent
+            if headers:
+                subscription["headers"] = headers
 
             subscriptions[feed_id] = subscription
             rss_manager.save_subscriptions(subscriptions)