Add bing search backend

app.py

@@ -12,7 +12,7 @@ import logging
 import re
 import uvicorn
 
-from backends import APISearchResults, APIPatentResults, query_brave_search, query_ddg_search, query_google_patents
+from backends import APISearchResults, APIPatentResults, query_bing_search, query_brave_search, query_ddg_search, query_google_patents
 
 logging.basicConfig(level=logging.INFO)
 
@@ -89,6 +89,25 @@ async def search_brave(params: APISearchParams) -> APISearchResults:
     return APISearchResults(results=results, error=str(last_exception) if len(results) == 0 and last_exception else None)
 
 
+@app.post("/search_bing")
+async def search_bing(params: APISearchParams) -> APISearchResults:
+    """Searches Bing search for the specified queries and returns the found documents."""
+    results = []
+    last_exception: Optional[Exception] = None
+    for q in params.queries:
+        logging.info(f"Searching Bing search with query `{q}`")
+        try:
+            res = await query_brave_search(pw_browser, q, params.n_results)
+            results.extend(res)
+        except Exception as e:
+            last_exception = e
+            backend_status["bing"] = "rate-limited"
+            logging.error(
+                f"Failed to query Bing search with query `{q}`: {e}")
+
+    return APISearchResults(results=results, error=str(last_exception) if len(results) == 0 and last_exception else None)
+
+
 @app.post("/search_duck")
 async def search_duck(params: APISearchParams) -> APISearchResults:
     """Searches duckduckgo for the specified queries and returns the found documents"""
@@ -131,6 +150,16 @@ async def search(params: APISearchParams):
         except Exception as e:
             logging.error(
                 f"Failed to query Brave Search with query `{q}`: {e}")
+            logging.info("Trying with next browser backend.")
+
+        try:
+            logging.info(f"Querying Bing with query: `{q}`")
+            res = await query_bing_search(pw_browser, q, params.n_results)
+            results.extend(res)
+            continue
+        except Exception as e:
+            logging.error(f"Failed to query Bing search with query `{q}`: {e}")
+            logging.info("Trying with next browser backend.")
 
         if len(results) == 0:
             return APISearchResults(results=[], error="All backends are rate-limited.")

backends.py

@@ -36,6 +36,7 @@ async def playwright_open_page(browser: Browser):
         await context.close()
 
 
+#TODO: update to return same format for results
 async def query_google_patents(browser: Browser, q: str, n_results: int = 10):
     """Queries google patents for the specified query and number of results. Returns relevant patents"""
 
@@ -93,11 +94,9 @@ async def query_brave_search(browser: Browser, q: str, n_results: int = 10):
         results_cards = await page.locator('.snippet').all()
 
         if len(results_cards) == 0:
-            logging.warning(f"No results for query: {q}")
             page_content = await page.content()
 
             if "suspicious" in page_content:
-                logging.warning("Brave search flagged browser as suspicious.")
                 raise BraveSearchBlockedException()
 
         results = []
@@ -128,6 +127,56 @@ async def query_brave_search(browser: Browser, q: str, n_results: int = 10):
         return results
 
 
+async def query_bing_search(browser: Browser, q: str, n_results: int = 10):
+    """Queries bing search for the specified query"""
+    async with playwright_open_page(browser) as page:
+        async def _block_resources(route, request):
+            if request.resource_type in ["stylesheet", "image"]:
+                await route.abort()
+            else:
+                await route.continue_()
+
+        await page.route("**/*", _block_resources)
+
+        url = f"https://www.bing.com/search?q={quote_plus(q)}"
+        await page.goto(url)
+
+        await page.wait_for_selector("li.b_algo")
+
+        results = []
+
+        items = await page.query_selector_all("li.b_algo")
+        for item in items[:n_results]:
+            title_el = await item.query_selector("h2 > a")
+            url = await title_el.get_attribute("href") if title_el else None
+            title = await title_el.inner_text() if title_el else ""
+
+            snippet = ""
+
+            # Try several fallback selectors
+            for selector in [
+                "div.b_caption p",  # typical snippet
+                "div.b_caption",    # sometimes snippet is here
+                "div.b_snippet",    # used in some result types
+                "div.b_text",       # used in some panels
+                "p"                 # fallback to any paragraph
+            ]:
+                snippet_el = await item.query_selector(selector)
+                if snippet_el:
+                    snippet = await snippet_el.inner_text()
+                    if snippet.strip():
+                        break
+
+            if title and url:
+                results.append({
+                    "title": title.strip(),
+                    "href": url.strip(),
+                    "body": snippet.strip()
+                })
+
+        return results
+
+
 async def query_ddg_search(q: str, n_results: int = 10):
     """Queries duckduckgo search for the specified query"""
     ddgs = DDGS()