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

v0.3.1 (#78)

Browse Source
This commit is contained in:
Karim shoair
2025-09-02 17:20:53 +03:00
committed by GitHub
parent e7482a267a 934d8a1452
commit 23997f2755
10 changed files with 80 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/fetching/dynamic.md
+1
View File
@@ -79,6 +79,7 @@ Scrapling provides many options with this fetcher. To make it as simple as possi
| wait | The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the `Response` object. | ✔️ |
| page_action | Added for automation. Pass a function that takes the `page` object and does the necessary automation, then returns `page` again. | ✔️ |
| wait_selector | Wait for a specific css selector to be in a specific state. | ✔️ |
| init_script | An absolute path to a JavaScript file to be executed on page creation for all pages in this session. | ✔️ |
| wait_selector_state | Scrapling will wait for the given state to be fulfilled for the selector given with `wait_selector`. _Default state is `attached`._ | ✔️ |
| google_search | Enabled by default, Scrapling will set the referer header as if this request came from a Google search of this website's domain name. | ✔️ |
| 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._ | ✔️ |
docs/fetching/stealthy.md
+1
View File
@@ -43,6 +43,7 @@ Before jumping to [examples](#examples), here's the full list of arguments
| timeout | The timeout used in all operations and waits through the page. It's in milliseconds, and the default is 30000. | ✔️ |
| wait | The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the `Response` object. | ✔️ |
| wait_selector | Wait for a specific css selector to be in a specific state. | ✔️ |
| init_script | An absolute path to a JavaScript file to be executed on page creation for all pages in this session. | ✔️ |
| wait_selector_state | Scrapling will wait for the given state to be fulfilled for the selector given with `wait_selector`. _Default state is `attached`._ | ✔️ |
| proxy | The proxy to be used with requests. It can be a string or a dictionary with the keys 'server', 'username', and 'password' only. | ✔️ |
| additional_args | Additional arguments to be passed to Camoufox as additional settings, and they take higher priority than Scrapling's settings. | ✔️ |
scrapling/__init__.py
+1 -1
View File
@@ -1,5 +1,5 @@
__author__ = "Karim Shoair (karim.shoair@pm.me)"
__version__ = "0.3"
__version__ = "0.3.1"
__copyright__ = "Copyright (c) 2024 Karim Shoair"
scrapling/core/shell.py
+3 -3
View File
@@ -20,7 +20,6 @@ from logging import (
getLevelName,
)
from IPython.terminal.embed import InteractiveShellEmbed
from orjson import loads as json_loads, JSONDecodeError
from scrapling import __version__
@@ -394,8 +393,7 @@ class CurlParser:
else: # pragma: no cover
log.error("Input must be a valid curl command string or a Request object.")
return None
return None
def show_page_in_browser(page: Selector): # pragma: no cover
@@ -544,6 +542,8 @@ Type 'exit' or press Ctrl+D to exit.
def start(self): # pragma: no cover
"""Start the interactive shell"""
from IPython.terminal.embed import InteractiveShellEmbed
# Get our namespace with application objects
namespace = self.get_namespace()
ipython_shell = InteractiveShellEmbed(
scrapling/engines/_browsers/_camoufox.py
+14
View File
@@ -60,6 +60,7 @@ class StealthySession:
"timeout",
"page_action",
"wait_selector",
"init_script",
"addons",
"wait_selector_state",
"cookies",
@@ -95,6 +96,7 @@ class StealthySession:
timeout: int | float = 30000,
page_action: Optional[Callable] = None,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
addons: Optional[List[str]] = None,
wait_selector_state: SelectorWaitStates = "attached",
cookies: Optional[List[Dict]] = None,
@@ -128,6 +130,7 @@ class StealthySession:
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
: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 init_script: An absolute path to a JavaScript file to be executed on page creation for all pages in this session.
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and 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 wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
@@ -153,6 +156,7 @@ class StealthySession:
"timeout": timeout,
"page_action": page_action,
"wait_selector": wait_selector,
"init_script": init_script,
"addons": addons,
"wait_selector_state": wait_selector_state,
"cookies": cookies,
@@ -180,6 +184,7 @@ class StealthySession:
self.timeout = config.timeout
self.page_action = config.page_action
self.wait_selector = config.wait_selector
self.init_script = config.init_script
self.addons = config.addons
self.wait_selector_state = config.wait_selector_state
self.cookies = config.cookies
@@ -234,6 +239,9 @@ class StealthySession:
**self.launch_options
)
)
if self.init_script: # pragma: no cover
self.context.add_init_script(path=self.init_script)
if self.cookies: # pragma: no cover
self.context.add_cookies(self.cookies)
@@ -474,6 +482,7 @@ class AsyncStealthySession(StealthySession):
timeout: int | float = 30000,
page_action: Optional[Callable] = None,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
addons: Optional[List[str]] = None,
wait_selector_state: SelectorWaitStates = "attached",
cookies: Optional[List[Dict]] = None,
@@ -507,6 +516,7 @@ class AsyncStealthySession(StealthySession):
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
: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 init_script: An absolute path to a JavaScript file to be executed on page creation for all pages in this session.
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and 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 wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
@@ -531,6 +541,7 @@ class AsyncStealthySession(StealthySession):
timeout,
page_action,
wait_selector,
init_script,
addons,
wait_selector_state,
cookies,
@@ -557,6 +568,9 @@ class AsyncStealthySession(StealthySession):
**self.launch_options
)
)
if self.init_script: # pragma: no cover
await self.context.add_init_script(path=self.init_script)
if self.cookies:
await self.context.add_cookies(self.cookies)
scrapling/engines/_browsers/_controllers.py
+14
View File
@@ -60,6 +60,7 @@ class DynamicSession:
"disable_resources",
"network_idle",
"wait_selector",
"init_script",
"wait_selector_state",
"wait",
"playwright",
@@ -94,6 +95,7 @@ class DynamicSession:
timeout: int | float = 30000,
disable_resources: bool = False,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
cookies: Optional[List[Dict]] = None,
network_idle: bool = False,
wait_selector_state: SelectorWaitStates = "attached",
@@ -112,6 +114,7 @@ class DynamicSession:
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
: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 init_script: An absolute path to a JavaScript file to be executed on page creation for all pages in this session.
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
@@ -143,6 +146,7 @@ class DynamicSession:
"selector_config": selector_config,
"disable_resources": disable_resources,
"wait_selector": wait_selector,
"init_script": init_script,
"cookies": cookies,
"network_idle": network_idle,
"wait_selector_state": wait_selector_state,
@@ -168,6 +172,7 @@ class DynamicSession:
self.cdp_url = config.cdp_url
self.network_idle = config.network_idle
self.wait_selector = config.wait_selector
self.init_script = config.init_script
self.wait_selector_state = config.wait_selector_state
self.playwright: Optional[Playwright] = None
@@ -243,6 +248,9 @@ class DynamicSession:
user_data_dir="", **self.launch_options
)
if self.init_script: # pragma: no cover
self.context.add_init_script(path=self.init_script)
if self.cookies: # pragma: no cover
self.context.add_cookies(self.cookies)
@@ -409,6 +417,7 @@ class AsyncDynamicSession(DynamicSession):
timeout: int | float = 30000,
disable_resources: bool = False,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
cookies: Optional[List[Dict]] = None,
network_idle: bool = False,
wait_selector_state: SelectorWaitStates = "attached",
@@ -427,6 +436,7 @@ class AsyncDynamicSession(DynamicSession):
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
: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 init_script: An absolute path to a JavaScript file to be executed on page creation for all pages in this session.
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
@@ -459,6 +469,7 @@ class AsyncDynamicSession(DynamicSession):
timeout,
disable_resources,
wait_selector,
init_script,
cookies,
network_idle,
wait_selector_state,
@@ -494,6 +505,9 @@ class AsyncDynamicSession(DynamicSession):
)
)
if self.init_script: # pragma: no cover
await self.context.add_init_script(path=self.init_script)
if self.cookies:
await self.context.add_cookies(self.cookies)
scrapling/engines/_browsers/_validators.py
+20
View File
@@ -32,6 +32,7 @@ class PlaywrightConfig(Struct, kw_only=True, frozen=False):
extra_headers: Optional[Dict[str, str]] = None
useragent: Optional[str] = None
timeout: int | float = 30000
init_script: Optional[str] = None
disable_resources: bool = False
wait_selector: Optional[str] = None
cookies: Optional[List[Dict]] = None
@@ -58,6 +59,15 @@ class PlaywrightConfig(Struct, kw_only=True, frozen=False):
if not self.selector_config:
self.selector_config = {}
if self.init_script is not None:
script_path = Path(self.init_script)
if not script_path.exists():
raise ValueError("Init script path not found")
elif not script_path.is_file():
raise ValueError("Init script is not a file")
elif not script_path.is_absolute():
raise ValueError("Init script is not a absolute path")
@staticmethod
def __validate_cdp(cdp_url):
try:
@@ -90,6 +100,7 @@ class CamoufoxConfig(Struct, kw_only=True, frozen=False):
solve_cloudflare: bool = False
wait: int | float = 0
timeout: int | float = 30000
init_script: Optional[str] = None
page_action: Optional[Callable] = None
wait_selector: Optional[str] = None
addons: Optional[List[str]] = None
@@ -131,6 +142,15 @@ class CamoufoxConfig(Struct, kw_only=True, frozen=False):
f"Addon's path is not a folder, you need to pass a folder of the extracted addon: {addon}"
)
if self.init_script is not None:
script_path = Path(self.init_script)
if not script_path.exists():
raise ValueError("Init script path not found")
elif not script_path.is_file():
raise ValueError("Init script is not a file")
elif not script_path.is_absolute():
raise ValueError("Init script is not a absolute path")
if not self.cookies:
self.cookies = []
if self.solve_cloudflare and self.timeout < 60_000:
scrapling/fetchers.py
+12
View File
@@ -62,6 +62,7 @@ class StealthyFetcher(BaseFetcher):
timeout: int | float = 30000,
page_action: Optional[Callable] = None,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
addons: Optional[List[str]] = None,
wait_selector_state: SelectorWaitStates = "attached",
cookies: Optional[List[Dict]] = None,
@@ -97,6 +98,7 @@ class StealthyFetcher(BaseFetcher):
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
: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 init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and 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 wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
@@ -127,6 +129,7 @@ class StealthyFetcher(BaseFetcher):
disable_ads=disable_ads,
allow_webgl=allow_webgl,
page_action=page_action,
init_script=init_script,
network_idle=network_idle,
block_images=block_images,
block_webrtc=block_webrtc,
@@ -158,6 +161,7 @@ class StealthyFetcher(BaseFetcher):
timeout: int | float = 30000,
page_action: Optional[Callable] = None,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
addons: Optional[List[str]] = None,
wait_selector_state: SelectorWaitStates = "attached",
cookies: Optional[List[Dict]] = None,
@@ -193,6 +197,7 @@ class StealthyFetcher(BaseFetcher):
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
: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 init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and 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 wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
@@ -223,6 +228,7 @@ class StealthyFetcher(BaseFetcher):
disable_ads=disable_ads,
allow_webgl=allow_webgl,
page_action=page_action,
init_script=init_script,
network_idle=network_idle,
block_images=block_images,
block_webrtc=block_webrtc,
@@ -276,6 +282,7 @@ class DynamicFetcher(BaseFetcher):
timeout: int | float = 30000,
disable_resources: bool = False,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
cookies: Optional[Iterable[Dict]] = None,
network_idle: bool = False,
wait_selector_state: SelectorWaitStates = "attached",
@@ -295,6 +302,7 @@ class DynamicFetcher(BaseFetcher):
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
: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 init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
@@ -328,6 +336,7 @@ class DynamicFetcher(BaseFetcher):
real_chrome=real_chrome,
page_action=page_action,
hide_canvas=hide_canvas,
init_script=init_script,
network_idle=network_idle,
google_search=google_search,
extra_headers=extra_headers,
@@ -359,6 +368,7 @@ class DynamicFetcher(BaseFetcher):
timeout: int | float = 30000,
disable_resources: bool = False,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
cookies: Optional[Iterable[Dict]] = None,
network_idle: bool = False,
wait_selector_state: SelectorWaitStates = "attached",
@@ -378,6 +388,7 @@ class DynamicFetcher(BaseFetcher):
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
: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 init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
@@ -412,6 +423,7 @@ class DynamicFetcher(BaseFetcher):
real_chrome=real_chrome,
page_action=page_action,
hide_canvas=hide_canvas,
init_script=init_script,
network_idle=network_idle,
google_search=google_search,
extra_headers=extra_headers,
setup.cfg
+1 -1
View File
@@ -1,6 +1,6 @@
[metadata]
name = scrapling
version = 0.3
version = 0.3.1
author = Karim Shoair
author_email = karim.shoair@pm.me
description = Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be!
tests/cli/test_shell_functionality.py
+13 -15
View File
@@ -178,23 +178,21 @@ class TestCustomShell:
def test_shell_initialization(self):
"""Test shell initialization"""
with patch('scrapling.core.shell.InteractiveShellEmbed'):
shell = CustomShell(code="", log_level="debug")
shell = CustomShell(code="", log_level="debug")
assert shell.log_level == 10 # DEBUG level
assert shell.page is None
assert len(shell.pages) == 0
assert shell.log_level == 10 # DEBUG level
assert shell.page is None
assert len(shell.pages) == 0
def test_shell_namespace(self):
"""Test shell namespace creation"""
with patch('scrapling.core.shell.InteractiveShellEmbed'):
shell = CustomShell(code="")
namespace = shell.get_namespace()
shell = CustomShell(code="")
namespace = shell.get_namespace()
# Check all expected functions/classes are available
assert 'get' in namespace
assert 'post' in namespace
assert 'Fetcher' in namespace
assert 'DynamicFetcher' in namespace
assert 'view' in namespace
assert 'uncurl' in namespace
# Check all expected functions/classes are available
assert 'get' in namespace
assert 'post' in namespace
assert 'Fetcher' in namespace
assert 'DynamicFetcher' in namespace
assert 'view' in namespace
assert 'uncurl' in namespace