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

feat(StealthyFetcher): Make ads enabled by default for performance boost

Browse Source
This commit is contained in:
Karim shoair
2025-01-28 23:51:31 +02:00
parent 52b66c98ec
commit 675c0110e6
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -263,7 +263,7 @@ True
| humanize | Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement. The cursor typically takes up to 1.5 seconds to move across the window. | ✔️ |
| allow_webgl | Enabled by default. Disabling it WebGL not recommended as many WAFs now checks if WebGL is enabled. | ✔️ |
| geoip | Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, & spoof the WebRTC IP address. It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region. | ✔️ |
| disable_ads | Enabled by default, this installs `uBlock Origin` addon on the browser if enabled. | ✔️ |
| disable_ads | Disabled by default, this installs `uBlock Origin` addon on the browser if enabled. | ✔️ |
| network_idle | Wait for the page until there are no network connections for at least 500 ms. | ✔️ |
| timeout | The timeout in milliseconds that is used in all operations and waits through the page. The default is 30000. | ✔️ |
| wait_selector | Wait for a specific css selector to be in a specific state. | ✔️ |
scrapling/engines/camo.py
+2 -2
View File
@@ -19,7 +19,7 @@ class CamoufoxEngine:
block_webrtc: Optional[bool] = False, allow_webgl: Optional[bool] = True, network_idle: Optional[bool] = False, humanize: Optional[Union[bool, float]] = True,
timeout: Optional[float] = 30000, page_action: Callable = None, wait_selector: Optional[str] = None, addons: Optional[List[str]] = None,
wait_selector_state: Optional[SelectorWaitStates] = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None,
proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True,
proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = False,
geoip: Optional[bool] = False,
adaptor_arguments: Dict = None,
):
@@ -36,7 +36,7 @@ class CamoufoxEngine:
:param humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement. The cursor typically takes up to 1.5 seconds to move across the window.
:param allow_webgl: Enabled by default. Disabling it WebGL not recommended as many WAFs now checks if WebGL is enabled.
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
:param disable_ads: Enabled by default, this installs `uBlock Origin` addon on the browser if enabled.
:param disable_ads: Disabled by default, this installs `uBlock Origin` addon on the browser if enabled.
:param os_randomize: If enabled, Scrapling will randomize the OS fingerprints used. The default is Scrapling matching the fingerprints with the current OS.
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30000
:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.
scrapling/fetchers.py
+4 -4
View File
@@ -177,7 +177,7 @@ class StealthyFetcher(BaseFetcher):
block_webrtc: Optional[bool] = False, allow_webgl: Optional[bool] = True, network_idle: Optional[bool] = False, addons: Optional[List[str]] = None,
timeout: Optional[float] = 30000, page_action: Callable = None, wait_selector: Optional[str] = None, humanize: Optional[Union[bool, float]] = True,
wait_selector_state: SelectorWaitStates = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None,
proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True, geoip: Optional[bool] = False,
proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = False, geoip: Optional[bool] = False,
) -> Response:
"""
Opens up a browser and do your request based on your chosen options below.
@@ -191,7 +191,7 @@ class StealthyFetcher(BaseFetcher):
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
:param block_webrtc: Blocks WebRTC entirely.
:param addons: List of Firefox addons to use. Must be paths to extracted addons.
:param disable_ads: Enabled by default, this installs `uBlock Origin` addon on the browser if enabled.
:param disable_ads: Disabled by default, this installs `uBlock Origin` addon on the browser if enabled.
:param humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement. The cursor typically takes up to 1.5 seconds to move across the window.
:param allow_webgl: Enabled by default. Disabling it WebGL not recommended as many WAFs now checks if WebGL is enabled.
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, & spoof the WebRTC IP address.
@@ -235,7 +235,7 @@ class StealthyFetcher(BaseFetcher):
block_webrtc: Optional[bool] = False, allow_webgl: Optional[bool] = True, network_idle: Optional[bool] = False, addons: Optional[List[str]] = None,
timeout: Optional[float] = 30000, page_action: Callable = None, wait_selector: Optional[str] = None, humanize: Optional[Union[bool, float]] = True,
wait_selector_state: SelectorWaitStates = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None,
proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True, geoip: Optional[bool] = False,
proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = False, geoip: Optional[bool] = False,
) -> Response:
"""
Opens up a browser and do your request based on your chosen options below.
@@ -249,7 +249,7 @@ class StealthyFetcher(BaseFetcher):
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
:param block_webrtc: Blocks WebRTC entirely.
:param addons: List of Firefox addons to use. Must be paths to extracted addons.
:param disable_ads: Enabled by default, this installs `uBlock Origin` addon on the browser if enabled.
:param disable_ads: Disabled by default, this installs `uBlock Origin` addon on the browser if enabled.
:param humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement. The cursor typically takes up to 1.5 seconds to move across the window.
:param allow_webgl: Enabled by default. Disabling it WebGL not recommended as many WAFs now checks if WebGL is enabled.
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, & spoof the WebRTC IP address.