pythonExtension and python runtime improvements (#1734)

* pythonExtension and python runtime improvements * Adding streaming support * Use writeFileSync * Restructure extension docs and add python extension docs * Fix broken link * Update docs/config/extensions/overview.mdx Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * Update docs/config/extensions/aptGet.mdx Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * Update docs/config/extensions/custom.mdx Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * Add environment variable support --------- Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-03-04 12:30:26 +00:00
parent bbd82adbda
commit 8f3a28effb
52 changed files with 2064 additions and 1081 deletions
@@ -0,0 +1,37 @@
+import html2text
+import requests
+import argparse
+import sys
+
+def fetch_html(url):
+    """Fetch HTML content from a URL."""
+    try:
+        response = requests.get(url)
+        response.raise_for_status()  # Raise an exception for HTTP errors
+        return response.text
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching URL: {e}", file=sys.stderr)
+        sys.exit(1)
+
+def main():
+    # Set up command line argument parsing
+    parser = argparse.ArgumentParser(description='Convert HTML from a URL to plain text.')
+    parser.add_argument('url', help='The URL to fetch HTML from')
+    parser.add_argument('--ignore-links', action='store_true', 
+                        help='Ignore converting links from HTML')
+    
+    args = parser.parse_args()
+    
+    # Fetch HTML from the URL
+    html_content = fetch_html(args.url)
+    
+    # Configure html2text
+    h = html2text.HTML2Text()
+    h.ignore_links = args.ignore_links
+    
+    # Convert HTML to text and print
+    text_content = h.handle(html_content)
+    print(text_content)
+
+if __name__ == "__main__":
+    main()