Spaces:
Sleeping
Sleeping
Update scraper.py
Browse files- scraper.py +4 -3
scraper.py
CHANGED
|
@@ -25,6 +25,7 @@ from playwright.sync_api import TimeoutError as PWTimeout
|
|
| 25 |
from playwright.sync_api import sync_playwright
|
| 26 |
|
| 27 |
BASE = "https://www.idealista.pt"
|
|
|
|
| 28 |
DEFAULT_LANG = "es" # "es" o "pt"
|
| 29 |
|
| 30 |
LISTING_COLUMNS = [
|
|
@@ -405,14 +406,14 @@ def sanitize_filename(stem: str) -> str:
|
|
| 405 |
return re.sub(r"[^a-zA-Z0-9_\-\.]+", "_", stem).strip("_") or "consulta"
|
| 406 |
|
| 407 |
|
| 408 |
-
def normalize_input_to_url(s, lang=
|
| 409 |
s = (str(s or "")).strip()
|
| 410 |
if not s:
|
| 411 |
return None
|
| 412 |
|
| 413 |
if s.startswith("http://") or s.startswith("https://"):
|
| 414 |
-
# No modificar URLs completas
|
| 415 |
-
#
|
| 416 |
return s
|
| 417 |
|
| 418 |
s = s.strip("/")
|
|
|
|
| 25 |
from playwright.sync_api import sync_playwright
|
| 26 |
|
| 27 |
BASE = "https://www.idealista.pt"
|
| 28 |
+
|
| 29 |
DEFAULT_LANG = "es" # "es" o "pt"
|
| 30 |
|
| 31 |
LISTING_COLUMNS = [
|
|
|
|
| 406 |
return re.sub(r"[^a-zA-Z0-9_\-\.]+", "_", stem).strip("_") or "consulta"
|
| 407 |
|
| 408 |
|
| 409 |
+
def normalize_input_to_url(s, lang="es"):
|
| 410 |
s = (str(s or "")).strip()
|
| 411 |
if not s:
|
| 412 |
return None
|
| 413 |
|
| 414 |
if s.startswith("http://") or s.startswith("https://"):
|
| 415 |
+
# No modificar URLs completas.
|
| 416 |
+
# Importante: si la URL trae ?shape=..., agregar "/" al final rompe el parámetro.
|
| 417 |
return s
|
| 418 |
|
| 419 |
s = s.strip("/")
|