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

feat: adding the retries argument for all methods of Fetcher class

Browse Source
This commit is contained in:
Karim shoair
2024-12-15 15:59:15 +02:00
parent 838dd62ee4
commit 299793af3f
3 changed files with 29 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -236,7 +236,7 @@ Also, the `Response` object returned from all fetchers is the same as the `Adapt
### Fetcher
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.
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 also set the number of retries with the argument `retries` for all methods and this will make httpx retry requests if it failed for any reason. The default number of retries for all `Fetcher` methods is 3.
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
scrapling/engines/static.py
+6 -5
View File
@@ -8,7 +8,7 @@ from .toolbelt import Response, generate_convincing_referer, generate_headers
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, retries: Optional[int] = 3, 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.
@@ -17,6 +17,7 @@ class StaticEngine:
"""
self.timeout = timeout
self.follow_redirects = bool(follow_redirects)
self.retries = retries
self._extra_headers = generate_headers(browser_mode=False)
self.adaptor_arguments = adaptor_arguments if adaptor_arguments else {}
@@ -75,7 +76,7 @@ class StaticEngine:
: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)
with httpx.Client(proxy=proxy) as client:
with httpx.Client(proxy=proxy, transport=httpx.HTTPTransport(retries=self.retries)) as client:
request = client.get(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)
@@ -91,7 +92,7 @@ class StaticEngine:
: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)
with httpx.Client(proxy=proxy) as client:
with httpx.Client(proxy=proxy, transport=httpx.HTTPTransport(retries=self.retries)) as client:
request = client.post(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)
@@ -107,7 +108,7 @@ class StaticEngine:
: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)
with httpx.Client(proxy=proxy) as client:
with httpx.Client(proxy=proxy, transport=httpx.HTTPTransport(retries=self.retries)) as client:
request = client.delete(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)
@@ -123,7 +124,7 @@ class StaticEngine:
: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)
with httpx.Client(proxy=proxy) as client:
with httpx.Client(proxy=proxy, transport=httpx.HTTPTransport(retries=self.retries)) as client:
request = client.put(url=url, headers=headers, follow_redirects=self.follow_redirects, timeout=self.timeout, **kwargs)
return self._prepare_response(request)
scrapling/fetchers.py
+22 -8
View File
@@ -10,7 +10,9 @@ 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, proxy: Optional[str] = None, **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, retries: Optional[int] = 3, **kwargs: Dict) -> Response:
"""Make basic HTTP GET request for you but with some added flavors.
:param url: Target url.
@@ -19,13 +21,16 @@ class Fetcher(BaseFetcher):
: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 retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
: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, proxy, stealthy_headers, **kwargs)
response_object = StaticEngine(follow_redirects, timeout, retries, 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, proxy: Optional[str] = None, **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, retries: Optional[int] = 3, **kwargs: Dict) -> Response:
"""Make basic HTTP POST request for you but with some added flavors.
:param url: Target url.
@@ -34,13 +39,16 @@ class Fetcher(BaseFetcher):
: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 retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
: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, proxy, stealthy_headers, **kwargs)
response_object = StaticEngine(follow_redirects, timeout, retries, 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, proxy: Optional[str] = None, **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, retries: Optional[int] = 3, **kwargs: Dict) -> Response:
"""Make basic HTTP PUT request for you but with some added flavors.
:param url: Target url
@@ -49,14 +57,17 @@ class Fetcher(BaseFetcher):
: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 retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
: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, proxy, stealthy_headers, **kwargs)
response_object = StaticEngine(follow_redirects, timeout, retries, 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, proxy: Optional[str] = None, **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, retries: Optional[int] = 3, **kwargs: Dict) -> Response:
"""Make basic HTTP DELETE request for you but with some added flavors.
:param url: Target url
@@ -65,10 +76,13 @@ class Fetcher(BaseFetcher):
: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 retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
: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, proxy, stealthy_headers, **kwargs)
response_object = StaticEngine(follow_redirects, timeout, retries, adaptor_arguments=self.adaptor_arguments).delete(url, proxy, stealthy_headers, **kwargs)
return response_object
return response_object