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

feat(StealthyFetcher): Add async fetch support

Browse Source
This commit is contained in:
Karim shoair
2024-12-16 00:59:19 +02:00
parent efb3270c67
commit 79a911e24e
2 changed files with 128 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/engines/camo.py
+70 -4
View File
@@ -1,10 +1,12 @@
from camoufox import DefaultAddons
from camoufox.async_api import AsyncCamoufox
from camoufox.sync_api import Camoufox
from scrapling.core._types import (Callable, Dict, List, Literal, Optional,
Union)
from scrapling.core.utils import log
from scrapling.engines.toolbelt import (Response, StatusText,
async_intercept_route,
check_type_validity,
construct_proxy_dict,
generate_convincing_referer,
@@ -120,11 +122,8 @@ class CamoufoxEngine:
# This will be parsed inside `Response`
encoding = res.headers.get('content-type', '') or 'utf-8' # default encoding
status_text = res.status_text
# PlayWright API sometimes give empty status text for some reason!
if not status_text:
status_text = StatusText.get(res.status)
status_text = res.status_text or StatusText.get(res.status)
response = Response(
url=res.url,
@@ -141,3 +140,70 @@ class CamoufoxEngine:
page.close()
return response
async def async_fetch(self, url: str) -> Response:
"""Opens up the browser and do your request based on your chosen options.
:param url: Target url.
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
"""
addons = [] if self.disable_ads else [DefaultAddons.UBO]
async with AsyncCamoufox(
geoip=self.geoip,
proxy=self.proxy,
addons=self.addons,
exclude_addons=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 = await browser.new_page()
page.set_default_navigation_timeout(self.timeout)
page.set_default_timeout(self.timeout)
if self.disable_resources:
await page.route("**/*", async_intercept_route)
if self.extra_headers:
await page.set_extra_http_headers(self.extra_headers)
res = await page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
await page.wait_for_load_state(state="domcontentloaded")
if self.network_idle:
await page.wait_for_load_state('networkidle')
if self.page_action is not None:
page = await self.page_action(page)
if self.wait_selector and type(self.wait_selector) is str:
waiter = page.locator(self.wait_selector)
await waiter.first.wait_for(state=self.wait_selector_state)
# Wait again after waiting for the selector, helpful with protections like Cloudflare
await page.wait_for_load_state(state="load")
await page.wait_for_load_state(state="domcontentloaded")
if self.network_idle:
await page.wait_for_load_state('networkidle')
# This will be parsed inside `Response`
encoding = res.headers.get('content-type', '') or 'utf-8' # default encoding
# PlayWright API sometimes give empty status text for some reason!
status_text = res.status_text or StatusText.get(res.status)
response = Response(
url=res.url,
text=await page.content(),
body=(await page.content()).encode('utf-8'),
status=res.status,
reason=status_text,
encoding=encoding,
cookies={cookie['name']: cookie['value'] for cookie in await page.context.cookies()},
headers=await res.all_headers(),
request_headers=await res.request.all_headers(),
**self.adaptor_arguments
)
await page.close()
return response
scrapling/fetchers.py
+58
View File
@@ -230,6 +230,64 @@ class StealthyFetcher(BaseFetcher):
)
return engine.fetch(url)
async def async_fetch(
self, url: str, headless: Optional[Union[bool, Literal['virtual']]] = True, block_images: Optional[bool] = False, disable_resources: Optional[bool] = False,
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: 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, disable_ads: Optional[bool] = True, geoip: Optional[bool] = False,
) -> Response:
"""
Opens up a browser and do your request based on your chosen options below.
:param url: Target url.
:param headless: Run the browser in headless/hidden (default), 'virtual' screen mode, or headful/visible mode.
:param block_images: Prevent the loading of images through Firefox preferences.
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends but it made requests ~25% faster in my tests for some websites.
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
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 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.
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region.
: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.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. Default state is `attached`.
:param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search for this website's domain name.
:param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
"""
engine = CamoufoxEngine(
proxy=proxy,
geoip=geoip,
addons=addons,
timeout=timeout,
headless=headless,
humanize=humanize,
disable_ads=disable_ads,
allow_webgl=allow_webgl,
page_action=page_action,
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,
disable_resources=disable_resources,
wait_selector_state=wait_selector_state,
adaptor_arguments=self.adaptor_arguments,
)
return await engine.async_fetch(url)
class PlayWrightFetcher(BaseFetcher):
"""A `Fetcher` class type that provide many options, all of them are based on PlayWright.