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

Adding proxy support for basic requests

Browse Source
This commit is contained in:
Karim shoair
2024-11-26 21:24:41 +02:00
parent 1cf7cee1a2
commit dbd674aa7c
3 changed files with 35 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -1
View File
@@ -233,9 +233,11 @@ 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')
```
scrapling/engines/static.py
+20 -8
View File
@@ -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)
scrapling/fetchers.py
+12 -8
View File
@@ -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