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

build: update deps

Karim shoair3068bb135621
diff --git a/pyproject.toml b/pyproject.toml
index d70a8b0..77e450a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -59,8 +59,8 @@ dependencies = [
"IPython",
"click",
"orjson>=3",
- "tldextract",
- "curl_cffi>=0.11.1",
+ "tldextract>=5.3.0",
+ "curl_cffi>=0.11.3",
"playwright>=1.52.0",
"rebrowser-playwright>=1.52.0",
"camoufox[geoip]>=0.4.11",
diff --git a/scrapling/core/storage_adaptors.py b/scrapling/core/storage_adaptors.py
index d13b549..cabbde5 100644
--- a/scrapling/core/storage_adaptors.py
+++ b/scrapling/core/storage_adaptors.py
@@ -26,7 +26,11 @@ class StorageSystemMixin(ABC):
try:
extracted = tld(self.url)
- return extracted.registered_domain or extracted.domain or default_value
+ return (
+ extracted.top_domain_under_public_suffix
+ or extracted.domain
+ or default_value
+ )
except AttributeError:
return default_value