freedak/Scrapling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(fetchers): Add argument to control the user data directory

Browse Source
This commit is contained in:
Karim shoair
2025-10-12 04:48:59 +03:00
parent 8c995c936d
commit c34e10faed
4 changed files with 27 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/engines/_browsers/_base.py
+6 -3
View File
@@ -149,7 +149,8 @@ class DynamicSessionMixin:
self.wait_selector_state = config.wait_selector_state
self.selector_config = config.selector_config
self.page_action = config.page_action
self._headers_keys = set(map(str.lower, self.extra_headers.keys())) if self.extra_headers else set()
self.user_data_dir = config.user_data_dir
self._headers_keys = {header.lower() for header in self.extra_headers.keys()} if self.extra_headers else set()
self.__initiate_browser_options__()
def __initiate_browser_options__(self):
@@ -173,6 +174,7 @@ class DynamicSessionMixin:
)
self.launch_options["extra_http_headers"] = dict(self.launch_options["extra_http_headers"])
self.launch_options["proxy"] = dict(self.launch_options["proxy"]) or None
self.launch_options["user_data_dir"] = self.user_data_dir
self.context_options = dict()
else:
# while `context_options` is left to be used when cdp mode is enabled
@@ -221,7 +223,8 @@ class StealthySessionMixin:
self.selector_config = config.selector_config
self.additional_args = config.additional_args
self.page_action = config.page_action
self._headers_keys = set(map(str.lower, self.extra_headers.keys())) if self.extra_headers else set()
self.user_data_dir = config.user_data_dir
self._headers_keys = {header.lower() for header in self.extra_headers.keys()} if self.extra_headers else set()
self.__initiate_browser_options__()
def __initiate_browser_options__(self):
@@ -239,7 +242,7 @@ class StealthySessionMixin:
"block_webrtc": self.block_webrtc,
"block_images": self.block_images, # Careful! it makes some websites don't finish loading at all like stackoverflow even in headful mode.
"os": None if self.os_randomize else get_os_name(),
"user_data_dir": "",
"user_data_dir": self.user_data_dir,
"ff_version": __ff_version_str__,
"firefox_user_prefs": {
# This is what enabling `enable_cache` does internally, so we do it from here instead