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

Adding the option to randomize the OS fingerprints with the StealthyFetcher

Browse Source
This commit is contained in:
Karim shoair
2024-11-15 16:36:32 +02:00
parent 2abb70218f
commit 5e8275c3eb
3 changed files with 16 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -1
View File
@@ -8,7 +8,7 @@ Scrapling is a high-performance, intelligent web scraping library for Python tha
```python
>> from scrapling import Fetcher, StealthyFetcher, PlayWrightFetcher
# Fetch websites' source under the radar!
>> page = StealthyFetcher().fetch('https://example.com', headless=True, disable_resources=True)
>> page = StealthyFetcher().fetch('https://example.com', headless=True, network_idle=True)
>> print(page.status)
200
>> products = page.css('.product', auto_save=True) # Scrape data that survives website design changes!
@@ -258,6 +258,7 @@ True
| 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. | ✔️ |
| proxy | The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only. | ✔️ |
| os_randomize | If enabled, Scrapling will randomize the OS fingerprints used. The default is Scrapling matching the fingerprints with the current OS. | ✔️ |
| wait_selector_state | The state to wait for the selector given with `wait_selector`. _Default state is `attached`._ | ✔️ |
</details>
scrapling/engines/camo.py
+11 -9
View File
@@ -20,7 +20,7 @@ class CamoufoxEngine:
block_webrtc: Optional[bool] = False, allow_webgl: Optional[bool] = False, network_idle: Optional[bool] = False, humanize: Optional[Union[bool, float]] = True,
timeout: Optional[float] = 30000, page_action: Callable = do_nothing, wait_selector: Optional[str] = None, addons: Optional[List[str]] = None,
wait_selector_state: str = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None,
proxy: Optional[Union[str, Dict[str, str]]] = None, adaptor_arguments: Dict = None
proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, adaptor_arguments: Dict = None
):
"""An engine that utilizes Camoufox library, check the `StealthyFetcher` class for more documentation.
@@ -35,6 +35,7 @@ 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: Whether to allow WebGL. To prevent leaks, only use this for special cases.
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
: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.
:param wait_selector: Wait for a specific css selector to be in a specific state.
@@ -51,6 +52,7 @@ class CamoufoxEngine:
self.allow_webgl = bool(allow_webgl)
self.network_idle = bool(network_idle)
self.google_search = bool(google_search)
self.os_randomize = bool(os_randomize)
self.extra_headers = extra_headers or {}
self.proxy = construct_proxy_dict(proxy)
self.addons = addons or []
@@ -73,15 +75,15 @@ class CamoufoxEngine:
:return: A Response object with `url`, `text`, `content`, `status`, `reason`, `encoding`, `cookies`, `headers`, `request_headers`, and the `adaptor` class for parsing, of course.
"""
with Camoufox(
headless=self.headless,
block_images=self.block_images, # Careful! it makes some websites doesn't finish loading at all like stackoverflow even in headful
os=get_os_name(),
block_webrtc=self.block_webrtc,
allow_webgl=self.allow_webgl,
addons=self.addons,
humanize=self.humanize,
proxy=self.proxy,
i_know_what_im_doing=True, # To turn warnings off with user configurations
addons=self.addons,
headless=self.headless,
humanize=self.humanize,
i_know_what_im_doing=True, # To turn warnings off with the user configurations
allow_webgl=self.allow_webgl,
block_webrtc=self.block_webrtc,
block_images=self.block_images, # Careful! it makes some websites doesn't finish loading at all like stackoverflow even in headful
os=None if self.os_randomize else get_os_name(),
) as browser:
page = browser.new_page()
page.set_default_navigation_timeout(self.timeout)
scrapling/fetchers.py
+3
View File
@@ -73,6 +73,7 @@ class StealthyFetcher(BaseFetcher):
block_webrtc: Optional[bool] = False, allow_webgl: Optional[bool] = False, network_idle: Optional[bool] = False, addons: Optional[List[str]] = None,
timeout: Optional[float] = 30000, page_action: Callable = do_nothing, wait_selector: Optional[str] = None, humanize: Optional[Union[bool, float]] = True,
wait_selector_state: str = '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
) -> Response:
"""
Opens up a browser and do your request based on your chosen options below.
@@ -88,6 +89,7 @@ class StealthyFetcher(BaseFetcher):
: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: Whether to allow WebGL. To prevent leaks, only use this for special cases.
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
: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.
:param wait_selector: Wait for a specific css selector to be in a specific state.
@@ -108,6 +110,7 @@ class StealthyFetcher(BaseFetcher):
network_idle=network_idle,
block_images=block_images,
block_webrtc=block_webrtc,
os_randomize=os_randomize,
wait_selector=wait_selector,
google_search=google_search,
extra_headers=extra_headers,