alihan/model-context-protocol-servers
1
0
Fork 0
mirror of https://github.com/modelcontextprotocol/servers.git synced 2024-12-01 18:58:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

add handling of non-html pages

Browse Source
This commit is contained in:
Jack Adamson
2024-11-29 11:51:41 +00:00
parent 467330de6e
commit 37622d3872
1 changed files with 9 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
src/fetch/src/mcp_server_fetch/server.py
View File

@@ -23,11 +23,11 @@ DEFAULT_USER_AGENT_AUTONOMOUS = "ModelContextProtocol/1.0 (Autonomous; +https://
DEFAULT_USER_AGENT_MANUAL = "ModelContextProtocol/1.0 (User-Specified; +https://github.com/modelcontextprotocol/servers)" DEFAULT_USER_AGENT_MANUAL = "ModelContextProtocol/1.0 (User-Specified; +https://github.com/modelcontextprotocol/servers)"
def extract_content(html: str) -> str: def extract_content_from_html(html: str) -> str:
ret = readabilipy.simple_json.simple_json_from_html_string( ret = readabilipy.simple_json.simple_json_from_html_string(
html, use_readability=True html, use_readability=True
) )
if not ret["plain_content"]: if not ret["content"]:
return "<error>Page failed to be simplified from HTML</error>" return "<error>Page failed to be simplified from HTML</error>"
content = markdownify.markdownify( content = markdownify.markdownify(
ret["content"], ret["content"],
@@ -105,13 +105,18 @@ async def fetch_url(url: str, user_agent: str) -> str:
f"Failed to fetch {url} - status code {response.status_code}", f"Failed to fetch {url} - status code {response.status_code}",
) )
page_html = response.text page_raw = response.text
return extract_content(page_html) content_type = response.headers.get("content-type", "")
if "<html" in page_raw[:100] or "text/html" in content_type or not content_type:
return extract_content_from_html(page_raw)
return f"Content type {content_type} cannot be simplified to markdown, but here is the raw content:\n{page_raw}"
class Fetch(BaseModel): class Fetch(BaseModel):
url: str = Field(..., description="URL to fetch") url: str = Field(..., description="URL to fetch")
start_index: int = Field(0, description="On return output starting at this character index, useful if a previous fetch was truncated and more context is required.")
async def serve( async def serve(