Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

Static Engine - Doc strings and type annotations stuff

Karim shoair282b130864d0
diff --git a/scrapling/engines/static.py b/scrapling/engines/static.py
index 35b575a..6c6bf84 100644
--- a/scrapling/engines/static.py
+++ b/scrapling/engines/static.py
@@ -8,19 +8,28 @@ from httpx._models import Response as httpxResponse
class StaticEngine:
- def __init__(
- self,
- follow_redirects: bool = True,
- timeout: Optional[Union[int, float]] = None,
- adaptor_arguments: Dict = None
- ):
+ def __init__(self, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = None, adaptor_arguments: Dict = None):
+ """An engine that utilizes httpx library, check the `Fetcher` class for more documentation.
+
+ :param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
+ :param timeout: The time to wait for the request to finish in seconds. Default is 10 seconds.
+ :param adaptor_arguments: The arguments that will be passed in the end while creating the final Adaptor's class.
+ """
self.timeout = timeout
self.follow_redirects = bool(follow_redirects)
self._extra_headers = generate_headers(browser_mode=False)
self.adaptor_arguments = adaptor_arguments if adaptor_arguments else {}
@staticmethod
- def _headers_job(headers, url, stealth):
+ def _headers_job(headers: Optional[Dict], url: str, stealth: bool) -> Dict:
+ """Adds useragent to headers if it doesn't exist, generates real headers and append it to current headers, and
+ finally generates a referer header that looks like if this request came from Google's search of the current URL's domain.
+
+ :param headers: Current headers in the request if the user passed any
+ :param url: The Target URL.
+ :param stealth: Whether stealth mode is enabled or not.
+ :return: A dictionary of the new headers.
+ """
headers = headers or {}
# Validate headers
@@ -35,7 +44,12 @@ class StaticEngine:
return headers
- def _prepare_response(self, response: httpxResponse):
+ def _prepare_response(self, response: httpxResponse) -> Response:
+ """Takes httpx response and generates `Response` object from it.
+
+ :param response: httpx response object
+ :return: A Response object with `url`, `text`, `content`, `status`, `reason`, `encoding`, `cookies`, `headers`, `request_headers`, and the `adaptor` class for parsing, of course.
+ """
return Response(
url=str(response.url),
text=response.text,
@@ -49,22 +63,50 @@ class StaticEngine:
adaptor_arguments=self.adaptor_arguments
)
- def get(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict):
+ def get(self, url: str, 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 kwargs: Any additional keyword arguments are passed directly to `httpx.get()` function so check httpx documentation for details.
+ :return: A Response object with `url`, `text`, `content`, `status`, `reason`, `encoding`, `cookies`, `headers`, `request_headers`, and the `adaptor` class for parsing, of course.
+ """
headers = self._headers_job(kwargs.get('headers'), url, stealthy_headers)
request = httpx.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):
+ def post(self, url: str, 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 kwargs: Any additional keyword arguments are passed directly to `httpx.post()` function so check httpx documentation for details.
+ :return: A Response object with `url`, `text`, `content`, `status`, `reason`, `encoding`, `cookies`, `headers`, `request_headers`, and the `adaptor` class for parsing, of course.
+ """
headers = self._headers_job(kwargs.get('headers'), url, stealthy_headers)
request = httpx.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):
+ def delete(self, url: str, 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 kwargs: Any additional keyword arguments are passed directly to `httpx.delete()` function so check httpx documentation for details.
+ :return: A Response object with `url`, `text`, `content`, `status`, `reason`, `encoding`, `cookies`, `headers`, `request_headers`, and the `adaptor` class for parsing, of course.
+ """
headers = self._headers_job(kwargs.get('headers'), url, stealthy_headers)
request = httpx.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):
+ def put(self, url: str, 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 kwargs: Any additional keyword arguments are passed directly to `httpx.put()` function so check httpx documentation for details.
+ :return: A Response object with `url`, `text`, `content`, `status`, `reason`, `encoding`, `cookies`, `headers`, `request_headers`, and the `adaptor` class for parsing, of course.
+ """
headers = self._headers_job(kwargs.get('headers'), url, stealthy_headers)
request = httpx.put(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)