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

feat(Fetcher): Add the redirections history to Fetcher

Karim shoair3d2418b67a5d
diff --git a/scrapling/engines/static.py b/scrapling/engines/static.py
index 9d5bed7..a939c46 100644
--- a/scrapling/engines/static.py
+++ b/scrapling/engines/static.py
@@ -72,6 +72,7 @@ class StaticEngine:
headers=dict(response.headers),
request_headers=dict(response.request.headers),
method=response.request.method,
+ history=[self._prepare_response(redirection) for redirection in response.history],
**self.adaptor_arguments
)
diff --git a/scrapling/engines/toolbelt/custom.py b/scrapling/engines/toolbelt/custom.py
index 9705eb3..dd31f4f 100644
--- a/scrapling/engines/toolbelt/custom.py
+++ b/scrapling/engines/toolbelt/custom.py
@@ -85,13 +85,14 @@ class Response(Adaptor):
"""This class is returned by all engines as a way to unify response type between different libraries."""
def __init__(self, url: str, text: str, body: bytes, status: int, reason: str, cookies: Dict, headers: Dict, request_headers: Dict,
- encoding: str = 'utf-8', method: str = 'GET', **adaptor_arguments: Dict):
+ encoding: str = 'utf-8', method: str = 'GET', history: List = None, **adaptor_arguments: Dict):
automatch_domain = adaptor_arguments.pop('automatch_domain', None)
self.status = status
self.reason = reason
self.cookies = cookies
self.headers = headers
self.request_headers = request_headers
+ self.history = history or []
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
diff --git a/scrapling/parser.py b/scrapling/parser.py
index e6b138a..b83d867 100644
--- a/scrapling/parser.py
+++ b/scrapling/parser.py
@@ -132,7 +132,7 @@ class Adaptor(SelectorsGeneration):
self.__tag = None
# No need to check if all response attributes exist or not because if `status` exist, then the rest exist (Save some CPU cycles for speed)
self.__response_data = {
- key: getattr(self, key) for key in ('status', 'reason', 'cookies', 'headers', 'request_headers',)
+ key: getattr(self, key) for key in ('status', 'reason', 'cookies', 'history', 'headers', 'request_headers',)
} if hasattr(self, 'status') else {}
# Node functionalities, I wanted to move to separate Mixin class but it had slight impact on performance