dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-24 06:15:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

feat: Add option to return web scrape content instead of printing

Browse source
This commit is contained in:
Paul Gauthier 2024-11-08 14:27:59 -08:00 • committed by Paul Gauthier (aider)
parent 77cb64958e
commit 52c49fc8fd
3 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
aider/coders/base_coder.py
View file

@ -820,7 +820,7 @@ class Coder:
"Add URL to the chat?", subject=url, group=group, allow_never=True "Add URL to the chat?", subject=url, group=group, allow_never=True
): ):
inp += "\n\n" inp += "\n\n"
inp += self.commands.cmd_web(url) inp += self.commands.cmd_web(url, return_content=True)
added_urls.append(url) added_urls.append(url)
else: else:
self.rejected_urls.add(url) self.rejected_urls.add(url)

4
aider/commands.py
View file

@ -139,7 +139,7 @@ class Commands:
else: else:
self.io.tool_output("Please provide a partial model name to search for.") self.io.tool_output("Please provide a partial model name to search for.")
def cmd_web(self, args): def cmd_web(self, args, return_content=False):
"Scrape a webpage, convert to markdown and send in a message" "Scrape a webpage, convert to markdown and send in a message"
url = args.strip() url = args.strip()
@ -159,6 +159,8 @@ class Commands:
content = self.scraper.scrape(url) or "" content = self.scraper.scrape(url) or ""
content = f"Here is the content of {url}:\n\n" + content content = f"Here is the content of {url}:\n\n" + content
if return_content:
return content
self.io.tool_output("... added to chat.") self.io.tool_output("... added to chat.")

2
tests/scrape/test_scrape.py
View file

@ -44,7 +44,7 @@ class TestScrape(unittest.TestCase):
self.commands.io.tool_error = mock_print_error self.commands.io.tool_error = mock_print_error
# Run the cmd_web command # Run the cmd_web command
result = self.commands.cmd_web("https://example.com") result = self.commands.cmd_web("https://example.com", return_content=True)
# Assert that the result contains some content # Assert that the result contains some content
self.assertIsNotNone(result) self.assertIsNotNone(result)