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

style: moving repeated arguments from inside the functions to __init__

Browse Source 
Might give a slight performance increase too
This commit is contained in:
Karim shoair
2024-12-15 16:49:48 +02:00
parent 445af3c702
commit faf728a794
3 changed files with 59 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.flake8
+1
View File
@@ -1,3 +1,4 @@
[flake8]
ignore = E501, F401
extend-ignore = E999
exclude = .git,.venv,__pycache__,docs,.github,build,dist,tests,benchmarks.py
scrapling/engines/static.py
+54 -31
View File
@@ -9,13 +9,23 @@ from .toolbelt import Response, generate_convincing_referer, generate_headers
@lru_cache(typed=True)
class StaticEngine:
def __init__(self, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = None, retries: Optional[int] = 3, adaptor_arguments: Tuple = None):
def __init__(
self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, follow_redirects: bool = True,
timeout: Optional[Union[int, float]] = None, retries: Optional[int] = 3, adaptor_arguments: Tuple = None
):
"""An engine that utilizes httpx library, check the `Fetcher` class for more documentation.
: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 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. The default is 10 seconds.
:param adaptor_arguments: The arguments that will be passed in the end while creating the final Adaptor's class.
"""
self.url = url
self.proxy = proxy
self.stealth = stealthy_headers
self.timeout = timeout
self.follow_redirects = bool(follow_redirects)
self.retries = retries
@@ -24,14 +34,11 @@ class StaticEngine:
# So my solution here was to convert it to tuple then convert it back to dictionary again here as tuples are hashable, ofc `tuple().__hash__()`
self.adaptor_arguments = dict(adaptor_arguments) if adaptor_arguments else {}
@staticmethod
def _headers_job(headers: Optional[Dict], url: str, stealth: bool) -> Dict:
def _headers_job(self, headers: Optional[Dict]) -> 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 {}
@@ -41,10 +48,10 @@ class StaticEngine:
headers['User-Agent'] = generate_headers(browser_mode=False).get('User-Agent')
log.debug(f"Can't find useragent in headers so '{headers['User-Agent']}' was used.")
if stealth:
if self.stealth:
extra_headers = generate_headers(browser_mode=False)
headers.update(extra_headers)
headers.update({'referer': generate_convincing_referer(url)})
headers.update({'referer': generate_convincing_referer(self.url)})
return headers
@@ -68,14 +75,18 @@ class StaticEngine:
**self.adaptor_arguments
)
def get(self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
def get(self, **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.
:param kwargs: Any 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', {}))
with httpx.Client(proxy=self.proxy, transport=httpx.HTTPTransport(retries=self.retries)) as client:
request = client.get(url=self.url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)
: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)
@@ -84,14 +95,18 @@ class StaticEngine:
return self._prepare_response(request)
def post(self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
def post(self, **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.
:param kwargs: Any 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', {}))
with httpx.Client(proxy=self.proxy, transport=httpx.HTTPTransport(retries=self.retries)) as client:
request = client.post(url=self.url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)
: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)
@@ -100,14 +115,18 @@ class StaticEngine:
return self._prepare_response(request)
def delete(self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
def delete(self, **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.
:param kwargs: Any 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', {}))
with httpx.Client(proxy=self.proxy, transport=httpx.HTTPTransport(retries=self.retries)) as client:
request = client.delete(url=self.url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)
: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)
@@ -116,14 +135,18 @@ class StaticEngine:
return self._prepare_response(request)
def put(self, url: str, proxy: Optional[str] = None, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
def put(self, **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.
:param kwargs: Any 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', {}))
with httpx.Client(proxy=self.proxy, transport=httpx.HTTPTransport(retries=self.retries)) as client:
request = client.put(url=self.url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)
: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)
scrapling/fetchers.py
+4 -4
View File
@@ -26,7 +26,7 @@ class Fetcher(BaseFetcher):
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
"""
adaptor_arguments = tuple(self.adaptor_arguments.items())
response_object = StaticEngine(follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).get(url, proxy, stealthy_headers, **kwargs)
response_object = StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).get(**kwargs)
return response_object
def post(
@@ -45,7 +45,7 @@ class Fetcher(BaseFetcher):
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
"""
adaptor_arguments = tuple(self.adaptor_arguments.items())
response_object = StaticEngine(follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).post(url, proxy, stealthy_headers, **kwargs)
response_object = StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).post(**kwargs)
return response_object
def put(
@@ -65,7 +65,7 @@ class Fetcher(BaseFetcher):
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
"""
adaptor_arguments = tuple(self.adaptor_arguments.items())
response_object = StaticEngine(follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).put(url, proxy, stealthy_headers, **kwargs)
response_object = StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).put(**kwargs)
return response_object
def delete(
@@ -84,7 +84,7 @@ class Fetcher(BaseFetcher):
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
"""
adaptor_arguments = tuple(self.adaptor_arguments.items())
response_object = StaticEngine(follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).delete(url, proxy, stealthy_headers, **kwargs)
response_object = StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).delete(**kwargs)
return response_object
return response_object