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

fix(browsers): solve a bug with setting referer on the request level

Karim shoairc5bc82deb813
diff --git a/scrapling/core/_types.py b/scrapling/core/_types.py
index c897954..48a2eec 100644
--- a/scrapling/core/_types.py
+++ b/scrapling/core/_types.py
@@ -19,6 +19,7 @@ from typing import (
Set,
Literal,
Optional,
+ Iterator,
Pattern,
Sequence,
Tuple,
diff --git a/scrapling/engines/_browsers/_controllers.py b/scrapling/engines/_browsers/_controllers.py
index 285bb32..aef197a 100644
--- a/scrapling/engines/_browsers/_controllers.py
+++ b/scrapling/engines/_browsers/_controllers.py
@@ -108,8 +108,11 @@ class DynamicSession(SyncSession, DynamicSessionMixin):
if not self._is_alive: # pragma: no cover
raise RuntimeError("Context manager has been closed")
+ request_headers_keys = {h.lower() for h in params.extra_headers.keys()} if params.extra_headers else set()
referer = (
- generate_convincing_referer(url) if (params.google_search and "referer" not in self._headers_keys) else None
+ generate_convincing_referer(url)
+ if (params.google_search and "referer" not in request_headers_keys)
+ else None
)
page_info = self._get_page(params.timeout, params.extra_headers, params.disable_resources)
@@ -240,8 +243,11 @@ class AsyncDynamicSession(AsyncSession, DynamicSessionMixin):
if not self._is_alive: # pragma: no cover
raise RuntimeError("Context manager has been closed")
+ request_headers_keys = {h.lower() for h in params.extra_headers.keys()} if params.extra_headers else set()
referer = (
- generate_convincing_referer(url) if (params.google_search and "referer" not in self._headers_keys) else None
+ generate_convincing_referer(url)
+ if (params.google_search and "referer" not in request_headers_keys)
+ else None
)
page_info = await self._get_page(params.timeout, params.extra_headers, params.disable_resources)
diff --git a/scrapling/engines/_browsers/_stealth.py b/scrapling/engines/_browsers/_stealth.py
index e191059..6883fdf 100644
--- a/scrapling/engines/_browsers/_stealth.py
+++ b/scrapling/engines/_browsers/_stealth.py
@@ -195,8 +195,11 @@ class StealthySession(SyncSession, StealthySessionMixin):
if not self._is_alive: # pragma: no cover
raise RuntimeError("Context manager has been closed")
+ request_headers_keys = {h.lower() for h in params.extra_headers.keys()} if params.extra_headers else set()
referer = (
- generate_convincing_referer(url) if (params.google_search and "referer" not in self._headers_keys) else None
+ generate_convincing_referer(url)
+ if (params.google_search and "referer" not in request_headers_keys)
+ else None
)
page_info = self._get_page(params.timeout, params.extra_headers, params.disable_resources)
@@ -410,8 +413,11 @@ class AsyncStealthySession(AsyncSession, StealthySessionMixin):
if not self._is_alive: # pragma: no cover
raise RuntimeError("Context manager has been closed")
+ request_headers_keys = {h.lower() for h in params.extra_headers.keys()} if params.extra_headers else set()
referer = (
- generate_convincing_referer(url) if (params.google_search and "referer" not in self._headers_keys) else None
+ generate_convincing_referer(url)
+ if (params.google_search and "referer" not in request_headers_keys)
+ else None
)
page_info = await self._get_page(params.timeout, params.extra_headers, params.disable_resources)