Update main.py

main.py

@@ -1,6 +1,7 @@
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException, Query
 from pydantic import BaseModel
 import hrequests
+import trafilatura
 from fastapi.middleware.cors import CORSMiddleware
 
 app = FastAPI()
@@ -18,6 +19,46 @@ async def scrape(url_request: URLRequest):
     except Exception as e: 
         raise e
 
+@app.get("/extract-article")
+def extract_article(
+    url: str,
+    record_id: Optional[str] = Query(None, description="Add an ID to the metadata."),
+    no_fallback: Optional[bool] = Query(False, description="Skip the backup extraction with readability-lxml and justext."),
+    favor_precision: Optional[bool] = Query(False, description="Prefer less text but correct extraction."),
+    favor_recall: Optional[bool] = Query(False, description="When unsure, prefer more text."),
+    include_comments: Optional[bool] = Query(True, description="Extract comments along with the main text."),
+    output_format: Optional[str] = Query('txt', description="Define an output format: 'csv', 'json', 'markdown', 'txt', 'xml', 'xmltei'.", enum=["csv", "json", "markdown", "txt", "xml", "xmltei"]),
+    target_language: Optional[str] = Query(None, description="Define a language to discard invalid documents (ISO 639-1 format)."),
+    include_tables: Optional[bool] = Query(True, description="Take into account information within the HTML <table> element."),
+    include_images: Optional[bool] = Query(False, description="Take images into account (experimental)."),
+    include_links: Optional[bool] = Query(False, description="Keep links along with their targets (experimental)."),
+    deduplicate: Optional[bool] = Query(False, description="Remove duplicate segments and documents."),
+    max_tree_size: Optional[int] = Query(None, description="Discard documents with too many elements.")
+):
+    response = hrequests.get(url)
+    filecontent = response.text
+    extracted = trafilatura.extract(
+        filecontent,
+        url=url,
+        record_id=record_id,
+        no_fallback=no_fallback,
+        favor_precision=favor_precision,
+        favor_recall=favor_recall,
+        include_comments=include_comments,
+        output_format=output_format,
+        target_language=target_language,
+        include_tables=include_tables,
+        include_images=include_images,
+        include_links=include_links,
+        deduplicate=deduplicate,
+        max_tree_size=max_tree_size
+    )
+    
+    if extracted:
+        return {"article": extracted}
+    else:
+        return {"error": "Could not extract the article"}
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],