Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

Small speed boost for fetching by some caching

Karim shoair5ad21260305c
diff --git a/scrapling/engines/toolbelt/fingerprints.py b/scrapling/engines/toolbelt/fingerprints.py
index 76f40da..71b8e84 100644
--- a/scrapling/engines/toolbelt/fingerprints.py
+++ b/scrapling/engines/toolbelt/fingerprints.py
@@ -4,6 +4,7 @@ Functions related to generating headers and fingerprints generally
import platform
+from scrapling.core.utils import cache
from scrapling.core._types import Union, Dict
from tldextract import extract
@@ -11,6 +12,7 @@ from browserforge.headers import HeaderGenerator, Browser
from browserforge.fingerprints import FingerprintGenerator, Fingerprint
+@cache(None, typed=True)
def generate_convincing_referer(url: str) -> str:
"""Takes the domain from the URL without the subdomain/suffix and make it look like you were searching google for this website
@@ -24,6 +26,7 @@ def generate_convincing_referer(url: str) -> str:
return f'https://www.google.com/search?q={website_name}'
+@cache(None, typed=True)
def get_os_name() -> Union[str, None]:
"""Get the current OS name in the same format needed for browserforge
diff --git a/scrapling/engines/toolbelt/navigation.py b/scrapling/engines/toolbelt/navigation.py
index e03cfd7..cf73a39 100644
--- a/scrapling/engines/toolbelt/navigation.py
+++ b/scrapling/engines/toolbelt/navigation.py
@@ -6,6 +6,7 @@ import os
import logging
from urllib.parse import urlparse, urlencode
+from scrapling.core.utils import cache
from scrapling.core._types import Union, Dict, Optional
from scrapling.engines.constants import DEFAULT_DISABLED_RESOURCES
@@ -62,6 +63,7 @@ def construct_cdp_url(cdp_url: str, query_params: Optional[Dict] = None) -> str:
raise ValueError(f"Invalid CDP URL: {str(e)}")
+@cache(None, typed=True)
def js_bypass_path(filename: str) -> str:
"""Takes the base filename of JS file inside the `bypasses` folder then return the full path of it