diff --git a/README.md b/README.md index 3669b3a..08e43b1 100644 --- a/README.md +++ b/README.md @@ -44,10 +44,11 @@ Scrapling is a high-performance, intelligent web scraping library for Python tha * [Text Extraction Speed Test (5000 nested elements).](#text-extraction-speed-test-5000-nested-elements) * [Extraction By Text Speed Test](#extraction-by-text-speed-test) * [Installation](#installation) - * [Fetching Websites Features](#fetching-websites-features) - * [Fetcher](#fetcher) - * [StealthyFetcher](#stealthyfetcher) - * [PlayWrightFetcher](#playwrightfetcher) + * [Fetching Websites](#fetching-websites) + * [Features](#features) + * [Fetcher class](#fetcher) + * [StealthyFetcher class](#stealthyfetcher) + * [PlayWrightFetcher class](#playwrightfetcher) * [Advanced Parsing Features](#advanced-parsing-features) * [Smart Navigation](#smart-navigation) * [Content-based Selection & Finding Similar Elements](#content-based-selection--finding-similar-elements) @@ -210,7 +211,10 @@ playwright install chromium python -m browserforge update ``` -## Fetching Websites Features +## Fetching Websites +Fetchers are basically interfaces that do requests or fetch pages for you in a single request fashion then return an `Adaptor` object for you. This feature was introduced because the only option we had before was to fetch the page as you want then pass it manually to the `Adaptor` class to create an `Adaptor` instance and start playing around with the page. + +### Features You might be a little bit confused by now so let me clear things up. All fetcher-type classes are imported in the same way ```python from scrapling import Fetcher, StealthyFetcher, PlayWrightFetcher @@ -233,9 +237,11 @@ Also, the `Response` object returned from all fetchers is the same as `Adaptor` This class is built on top of [httpx](https://www.python-httpx.org/) with additional configuration options, here you can do `GET`, `POST`, `PUT`, and `DELETE` requests. For all methods, you have `stealth_headers` which makes `Fetcher` create and use real browser's headers then create a referer header as if this request came from Google's search of this URL's domain. It's enabled by default. + +You can route all traffic (HTTP and HTTPS) to a proxy for any of these methods in this format `http://username:password@localhost:8030` ```python >> page = Fetcher().get('https://httpbin.org/get', stealth_headers=True, follow_redirects=True) ->> page = Fetcher().post('https://httpbin.org/post', data={'key': 'value'}) +>> page = Fetcher().post('https://httpbin.org/post', data={'key': 'value'}, proxy='http://username:password@localhost:8030') >> page = Fetcher().put('https://httpbin.org/put', data={'key': 'value'}) >> page = Fetcher().delete('https://httpbin.org/delete') ``` @@ -263,6 +269,7 @@ True | addons | List of Firefox addons to use. **Must be paths to extracted addons.** | ✔️ | | 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 | Whether to allow WebGL. To prevent leaks, only use this for special cases. | ✔️ | +| disable_ads | Enabled 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. | ✔️ | @@ -317,6 +324,7 @@ Add that to a lot of controlling/hiding options as you will see in the arguments | disable_webgl | Disables WebGL and WebGL 2.0 support entirely. | ✔️ | | stealth | Enables stealth mode, always check the documentation to see what stealth mode does currently. | ✔️ | | real_chrome | If you have chrome browser installed on your device, enable this and the Fetcher will launch an instance of your browser and use it. | ✔️ | +| locale | Set the locale for the browser if wanted. The default value is `en-US`. | ✔️ | | cdp_url | Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP. | ✔️ | | nstbrowser_mode | Enables NSTBrowser mode, **it have to be used with `cdp_url` argument or it will get completely ignored.** | ✔️ | | nstbrowser_config | The config you want to send with requests to the NSTBrowser. _If left empty, Scrapling defaults to an optimized NSTBrowser's docker browserless config._ | ✔️ | diff --git a/scrapling/__init__.py b/scrapling/__init__.py index 33342f4..26d815d 100644 --- a/scrapling/__init__.py +++ b/scrapling/__init__.py @@ -4,7 +4,7 @@ from scrapling.parser import Adaptor, Adaptors from scrapling.core.custom_types import TextHandler, AttributesHandler __author__ = "Karim Shoair (karim.shoair@pm.me)" -__version__ = "0.2.6" +__version__ = "0.2.7" __copyright__ = "Copyright (c) 2024 Karim Shoair" diff --git a/scrapling/engines/camo.py b/scrapling/engines/camo.py index 0807a97..90d3378 100644 --- a/scrapling/engines/camo.py +++ b/scrapling/engines/camo.py @@ -12,6 +12,7 @@ from scrapling.engines.toolbelt import ( generate_convincing_referer, ) +from camoufox import DefaultAddons from camoufox.sync_api import Camoufox @@ -21,7 +22,8 @@ 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, os_randomize: Optional[bool] = None, adaptor_arguments: Dict = None + proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True, + adaptor_arguments: Dict = None, ): """An engine that utilizes Camoufox library, check the `StealthyFetcher` class for more documentation. @@ -36,6 +38,7 @@ 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 disable_ads: Enabled 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. @@ -54,6 +57,7 @@ class CamoufoxEngine: self.network_idle = bool(network_idle) self.google_search = bool(google_search) self.os_randomize = bool(os_randomize) + self.disable_ads = bool(disable_ads) self.extra_headers = extra_headers or {} self.proxy = construct_proxy_dict(proxy) self.addons = addons or [] @@ -75,9 +79,11 @@ class CamoufoxEngine: :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] with Camoufox( 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 @@ -105,6 +111,11 @@ class CamoufoxEngine: if self.wait_selector and type(self.wait_selector) is str: waiter = page.locator(self.wait_selector) waiter.first.wait_for(state=self.wait_selector_state) + # Wait again after waiting for the selector, helpful with protections like Cloudflare + page.wait_for_load_state(state="load") + page.wait_for_load_state(state="domcontentloaded") + if self.network_idle: + page.wait_for_load_state('networkidle') # This will be parsed inside `Response` encoding = res.headers.get('content-type', '') or 'utf-8' # default encoding diff --git a/scrapling/engines/constants.py b/scrapling/engines/constants.py index 245e5c0..926e238 100644 --- a/scrapling/engines/constants.py +++ b/scrapling/engines/constants.py @@ -44,7 +44,7 @@ DEFAULT_STEALTH_FLAGS = [ '--disable-default-apps', '--disable-print-preview', '--disable-dev-shm-usage', - '--disable-popup-blocking', + # '--disable-popup-blocking', '--metrics-recording-only', '--disable-crash-reporter', '--disable-partial-raster', diff --git a/scrapling/engines/pw.py b/scrapling/engines/pw.py index 80ff55b..818720b 100644 --- a/scrapling/engines/pw.py +++ b/scrapling/engines/pw.py @@ -26,6 +26,7 @@ class PlaywrightEngine: timeout: Optional[float] = 30000, page_action: Callable = do_nothing, wait_selector: Optional[str] = None, + locale: Optional[str] = 'en-US', wait_selector_state: Optional[str] = 'attached', stealth: Optional[bool] = False, real_chrome: Optional[bool] = False, @@ -50,6 +51,7 @@ class PlaywrightEngine: :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 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`. Default state is `attached`. :param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently. :param real_chrome: If you have chrome browser installed on your device, enable this and the Fetcher will launch an instance of your browser and use it. @@ -64,6 +66,7 @@ class PlaywrightEngine: :param adaptor_arguments: The arguments that will be passed in the end while creating the final Adaptor's class. """ self.headless = headless + self.locale = check_type_validity(locale, [str], 'en-US', param_name='locale') self.disable_resources = disable_resources self.network_idle = bool(network_idle) self.stealth = bool(stealth) @@ -87,6 +90,14 @@ class PlaywrightEngine: self.nstbrowser_mode = bool(nstbrowser_mode) self.nstbrowser_config = nstbrowser_config self.adaptor_arguments = adaptor_arguments if adaptor_arguments else {} + self.harmful_default_args = [ + # This will be ignored to avoid detection more and possibly avoid the popup crashing bug abuse: https://issues.chromium.org/issues/340836884 + '--enable-automation', + '--disable-popup-blocking', + # '--disable-component-update', + # '--disable-default-apps', + # '--disable-extensions', + ] def _cdp_url_logic(self, flags: Optional[List] = None) -> str: """Constructs new CDP URL if NSTBrowser is enabled otherwise return CDP URL as it is @@ -151,15 +162,15 @@ class PlaywrightEngine: else: if self.stealth: browser = p.chromium.launch( - headless=self.headless, args=flags, ignore_default_args=['--enable-automation'], chromium_sandbox=True, channel='chrome' if self.real_chrome else 'chromium' + headless=self.headless, args=flags, ignore_default_args=self.harmful_default_args, chromium_sandbox=True, channel='chrome' if self.real_chrome else 'chromium' ) else: - browser = p.chromium.launch(headless=self.headless, ignore_default_args=['--enable-automation'], channel='chrome' if self.real_chrome else 'chromium') + browser = p.chromium.launch(headless=self.headless, ignore_default_args=self.harmful_default_args, channel='chrome' if self.real_chrome else 'chromium') # Creating the context if self.stealth: context = browser.new_context( - locale='en-US', + locale=self.locale, is_mobile=False, has_touch=False, proxy=self.proxy, @@ -176,6 +187,8 @@ class PlaywrightEngine: ) else: context = browser.new_context( + locale=self.locale, + proxy=self.proxy, color_scheme='dark', user_agent=useragent, device_scale_factor=2, @@ -221,6 +234,11 @@ class PlaywrightEngine: if self.wait_selector and type(self.wait_selector) is str: waiter = page.locator(self.wait_selector) waiter.first.wait_for(state=self.wait_selector_state) + # Wait again after waiting for the selector, helpful with protections like Cloudflare + page.wait_for_load_state(state="load") + page.wait_for_load_state(state="domcontentloaded") + if self.network_idle: + page.wait_for_load_state('networkidle') # This will be parsed inside `Response` encoding = res.headers.get('content-type', '') or 'utf-8' # default encoding diff --git a/scrapling/engines/static.py b/scrapling/engines/static.py index 16e5350..d6b5a6c 100644 --- a/scrapling/engines/static.py +++ b/scrapling/engines/static.py @@ -63,54 +63,66 @@ class StaticEngine: **self.adaptor_arguments ) - def get(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: + def get(self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: """Make basic HTTP GET request for you but with some added flavors. :param url: Target url. :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and create a referer header as if this request had came from Google's search of this URL's domain. + :param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030` :param kwargs: Any additional keyword arguments are passed directly to `httpx.get()` function so check httpx documentation for details. :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers` """ headers = self._headers_job(kwargs.pop('headers', {}), url, stealthy_headers) - request = httpx.get(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs) + with httpx.Client(proxy=proxy) as client: + request = client.get(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs) + return self._prepare_response(request) - def post(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: + def post(self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: """Make basic HTTP POST request for you but with some added flavors. :param url: Target url. :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and create a referer header as if this request had came from Google's search of this URL's domain. + :param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030` :param kwargs: Any additional keyword arguments are passed directly to `httpx.post()` function so check httpx documentation for details. :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers` """ headers = self._headers_job(kwargs.pop('headers', {}), url, stealthy_headers) - request = httpx.post(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs) + with httpx.Client(proxy=proxy) as client: + request = client.post(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs) + return self._prepare_response(request) - def delete(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: + def delete(self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: """Make basic HTTP DELETE request for you but with some added flavors. :param url: Target url. :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and create a referer header as if this request had came from Google's search of this URL's domain. + :param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030` :param kwargs: Any additional keyword arguments are passed directly to `httpx.delete()` function so check httpx documentation for details. :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers` """ headers = self._headers_job(kwargs.pop('headers', {}), url, stealthy_headers) - request = httpx.delete(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs) + with httpx.Client(proxy=proxy) as client: + request = client.delete(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs) + return self._prepare_response(request) - def put(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: + def put(self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: """Make basic HTTP PUT request for you but with some added flavors. :param url: Target url. :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and create a referer header as if this request had came from Google's search of this URL's domain. + :param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030` :param kwargs: Any additional keyword arguments are passed directly to `httpx.put()` function so check httpx documentation for details. :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers` """ headers = self._headers_job(kwargs.pop('headers', {}), url, stealthy_headers) - request = httpx.put(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs) + with httpx.Client(proxy=proxy) as client: + request = client.put(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs) + return self._prepare_response(request) diff --git a/scrapling/engines/toolbelt/custom.py b/scrapling/engines/toolbelt/custom.py index f0053d7..2c7cd94 100644 --- a/scrapling/engines/toolbelt/custom.py +++ b/scrapling/engines/toolbelt/custom.py @@ -39,7 +39,7 @@ class ResponseEncoding: @classmethod @cache(maxsize=None) - def get_value(cls, content_type: Optional[str]) -> str: + def get_value(cls, content_type: Optional[str], text: Optional[str] = 'test') -> str: """Determine the appropriate character encoding from a content-type header. The encoding is determined by these rules in order: @@ -50,26 +50,30 @@ class ResponseEncoding: 5. Default to UTF-8 if nothing else matches :param content_type: Content-Type header value or None + :param text: A text to test the encoding on it :return: String naming the character encoding """ if not content_type: return cls.__DEFAULT_ENCODING try: + encoding = None content_type, params = cls.__parse_content_type(content_type) # First check for explicit charset parameter if "charset" in params: encoding = params["charset"].strip("'\"") - "test".encode(encoding) # Validate encoding - return encoding # Apply content-type specific rules - if content_type in cls.__ISO_8859_1_CONTENT_TYPES: - return "ISO-8859-1" + elif content_type in cls.__ISO_8859_1_CONTENT_TYPES: + encoding = "ISO-8859-1" - if content_type == "application/json": - return cls.__DEFAULT_ENCODING + elif content_type == "application/json": + encoding = cls.__DEFAULT_ENCODING + + if encoding: + _ = text.encode(encoding) # Validate encoding and validate it can encode the given text + return encoding return cls.__DEFAULT_ENCODING @@ -87,7 +91,7 @@ class Response(Adaptor): self.cookies = cookies self.headers = headers self.request_headers = request_headers - encoding = ResponseEncoding.get_value(encoding) + encoding = ResponseEncoding.get_value(encoding, text) super().__init__(text=text, body=body, url=automatch_domain or url, encoding=encoding, **adaptor_arguments) # For back-ward compatibility self.adaptor = self diff --git a/scrapling/fetchers.py b/scrapling/fetchers.py index bc47c8e..552f924 100644 --- a/scrapling/fetchers.py +++ b/scrapling/fetchers.py @@ -9,7 +9,7 @@ class Fetcher(BaseFetcher): Any additional keyword arguments passed to the methods below are passed to the respective httpx's method directly. """ - def get(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: + def get(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, proxy: Optional[str] = None, **kwargs: Dict) -> Response: """Make basic HTTP GET request for you but with some added flavors. :param url: Target url. @@ -17,13 +17,14 @@ class Fetcher(BaseFetcher): :param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds. :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and create a referer header as if this request had came from Google's search of this URL's domain. + :param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030` :param kwargs: Any additional keyword arguments are passed directly to `httpx.get()` function so check httpx documentation for details. :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers` """ - response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).get(url, stealthy_headers, **kwargs) + response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).get(url, proxy, stealthy_headers, **kwargs) return response_object - def post(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: + def post(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, proxy: Optional[str] = None, **kwargs: Dict) -> Response: """Make basic HTTP POST request for you but with some added flavors. :param url: Target url. @@ -31,13 +32,14 @@ class Fetcher(BaseFetcher): :param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds. :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and create a referer header as if this request came from Google's search of this URL's domain. + :param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030` :param kwargs: Any additional keyword arguments are passed directly to `httpx.post()` function so check httpx documentation for details. :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers` """ - response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).post(url, stealthy_headers, **kwargs) + response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).post(url, proxy, stealthy_headers, **kwargs) return response_object - def put(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: + def put(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, proxy: Optional[str] = None, **kwargs: Dict) -> Response: """Make basic HTTP PUT request for you but with some added flavors. :param url: Target url @@ -45,14 +47,15 @@ class Fetcher(BaseFetcher): :param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds. :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and create a referer header as if this request came from Google's search of this URL's domain. + :param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030` :param kwargs: Any additional keyword arguments are passed directly to `httpx.put()` function so check httpx documentation for details. :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers` """ - response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).put(url, stealthy_headers, **kwargs) + response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).put(url, proxy, stealthy_headers, **kwargs) return response_object - def delete(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response: + def delete(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, proxy: Optional[str] = None, **kwargs: Dict) -> Response: """Make basic HTTP DELETE request for you but with some added flavors. :param url: Target url @@ -60,10 +63,11 @@ class Fetcher(BaseFetcher): :param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds. :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and create a referer header as if this request came from Google's search of this URL's domain. + :param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030` :param kwargs: Any additional keyword arguments are passed directly to `httpx.delete()` function so check httpx documentation for details. :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers` """ - response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).delete(url, stealthy_headers, **kwargs) + response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).delete(url, proxy, stealthy_headers, **kwargs) return response_object @@ -78,7 +82,7 @@ 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 + os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True, ) -> Response: """ Opens up a browser and do your request based on your chosen options below. @@ -92,6 +96,7 @@ 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 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. @@ -111,6 +116,7 @@ class StealthyFetcher(BaseFetcher): timeout=timeout, headless=headless, humanize=humanize, + disable_ads=disable_ads, allow_webgl=allow_webgl, page_action=page_action, network_idle=network_idle, @@ -148,7 +154,7 @@ class PlayWrightFetcher(BaseFetcher): useragent: Optional[str] = None, network_idle: Optional[bool] = False, timeout: Optional[float] = 30000, page_action: Optional[Callable] = do_nothing, wait_selector: Optional[str] = None, wait_selector_state: Optional[str] = 'attached', hide_canvas: Optional[bool] = False, disable_webgl: Optional[bool] = False, extra_headers: Optional[Dict[str, str]] = None, google_search: Optional[bool] = True, - proxy: Optional[Union[str, Dict[str, str]]] = None, + proxy: Optional[Union[str, Dict[str, str]]] = None, locale: Optional[str] = 'en-US', stealth: Optional[bool] = False, real_chrome: Optional[bool] = False, cdp_url: Optional[str] = None, nstbrowser_mode: Optional[bool] = False, nstbrowser_config: Optional[Dict] = None, @@ -163,6 +169,7 @@ class PlayWrightFetcher(BaseFetcher): :param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it. :param network_idle: Wait for the page until there are no network connections for at least 500 ms. :param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30000 + :param locale: Set the locale for the browser if wanted. The default value is `en-US`. :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`. @@ -180,6 +187,7 @@ class PlayWrightFetcher(BaseFetcher): """ engine = PlaywrightEngine( proxy=proxy, + locale=locale, timeout=timeout, stealth=stealth, cdp_url=cdp_url, diff --git a/setup.cfg b/setup.cfg index be5aa12..1aa408a 100644 --- a/setup.cfg +++ b/setup.cfg @@ -1,6 +1,6 @@ [metadata] name = scrapling -version = 0.2.6 +version = 0.2.7 author = Karim Shoair author_email = karim.shoair@pm.me description = Scrapling is an undetectable, powerful, flexible, adaptive, and high-performance web scraping library for Python. diff --git a/setup.py b/setup.py index 281f567..91aa89c 100644 --- a/setup.py +++ b/setup.py @@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh: setup( name="scrapling", - version="0.2.6", + version="0.2.7", description="""Scrapling is a powerful, flexible, and high-performance web scraping library for Python. It simplifies the process of extracting data from websites, even when they undergo structural changes, and offers impressive speed improvements over many popular scraping tools.""",