Spaces:
Sleeping
Sleeping
Fix search_patents route not respecting number of results per query
Browse files
app.py
CHANGED
|
@@ -73,15 +73,18 @@ async def query_google_patents(browser: Browser, q: str, n_results: int = 10):
|
|
| 73 |
PATENT_ID_REGEX = r"\b[A-Z]{2}\d{6,}(?:[A-Z]\d?)?\b"
|
| 74 |
|
| 75 |
items = await page.locator("search-result-item").all()
|
| 76 |
-
|
| 77 |
for item in items:
|
| 78 |
all_text = " ".join(await item.locator("span").all_inner_texts())
|
| 79 |
found = re.findall(PATENT_ID_REGEX, all_text)
|
| 80 |
if found:
|
| 81 |
-
|
| 82 |
|
| 83 |
await context.close()
|
| 84 |
-
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
|
| 87 |
async def query_brave_search(browser: Browser, q: str, n_results: int = 10):
|
|
@@ -102,6 +105,10 @@ async def query_brave_search(browser: Browser, q: str, n_results: int = 10):
|
|
| 102 |
|
| 103 |
results_cards = await page.locator('.snippet').all()
|
| 104 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
results = []
|
| 106 |
|
| 107 |
for result in results_cards:
|
|
@@ -141,11 +148,12 @@ async def search_patents(params: APISearchParams) -> APIPatentResults:
|
|
| 141 |
except Exception as e:
|
| 142 |
logging.error(
|
| 143 |
f"Failed to query Google Patents with query `{q}`: {e}")
|
| 144 |
-
return APIPatentResults(results=
|
| 145 |
|
| 146 |
|
| 147 |
@app.post("/search_brave")
|
| 148 |
async def search_brave(params: APISearchParams) -> APIBraveResults:
|
|
|
|
| 149 |
results = []
|
| 150 |
for q in params.queries:
|
| 151 |
logging.info(f"Searching Brave search with query `{q}`")
|
|
|
|
| 73 |
PATENT_ID_REGEX = r"\b[A-Z]{2}\d{6,}(?:[A-Z]\d?)?\b"
|
| 74 |
|
| 75 |
items = await page.locator("search-result-item").all()
|
| 76 |
+
id_matches = []
|
| 77 |
for item in items:
|
| 78 |
all_text = " ".join(await item.locator("span").all_inner_texts())
|
| 79 |
found = re.findall(PATENT_ID_REGEX, all_text)
|
| 80 |
if found:
|
| 81 |
+
id_matches.append(found[0])
|
| 82 |
|
| 83 |
await context.close()
|
| 84 |
+
|
| 85 |
+
patents = [{"href": f"https://patents.google.com/patent/{id}/en", "id": id}
|
| 86 |
+
for id in id_matches]
|
| 87 |
+
return patents[:n_results]
|
| 88 |
|
| 89 |
|
| 90 |
async def query_brave_search(browser: Browser, q: str, n_results: int = 10):
|
|
|
|
| 105 |
|
| 106 |
results_cards = await page.locator('.snippet').all()
|
| 107 |
|
| 108 |
+
if len(results_cards) == 0:
|
| 109 |
+
logging.warning(f"No results for query: {q}")
|
| 110 |
+
logging.warning(await page.content())
|
| 111 |
+
|
| 112 |
results = []
|
| 113 |
|
| 114 |
for result in results_cards:
|
|
|
|
| 148 |
except Exception as e:
|
| 149 |
logging.error(
|
| 150 |
f"Failed to query Google Patents with query `{q}`: {e}")
|
| 151 |
+
return APIPatentResults(results=results, error=None)
|
| 152 |
|
| 153 |
|
| 154 |
@app.post("/search_brave")
|
| 155 |
async def search_brave(params: APISearchParams) -> APIBraveResults:
|
| 156 |
+
"""Searches brave search for the specified queries and returns the found documents."""
|
| 157 |
results = []
|
| 158 |
for q in params.queries:
|
| 159 |
logging.info(f"Searching Brave search with query `{q}`")
|