refactor(http-clients)!: Remove HttpCrawlingResult left over from HttpClient.crawl

docs/guides/architecture_overview.mdx

@@ -120,8 +120,6 @@ class BasicCrawlingContext
 
 class HttpCrawlingContext
 
-class HttpCrawlingResult
-
 class ParsedHttpCrawlingContext
 
 class ParselCrawlingContext
@@ -152,8 +150,6 @@ class StagehandCrawlingContext
 
 BasicCrawlingContext --|> HttpCrawlingContext
 
-HttpCrawlingResult --|> HttpCrawlingContext
-
 HttpCrawlingContext --|> ParsedHttpCrawlingContext
 
 ParsedHttpCrawlingContext --|> ParselCrawlingContext

docs/upgrading/upgrading_to_v2.md

@@ -326,7 +326,7 @@ The crawler now reads a stall from the status, so it also sees a `ThrottlingRequ
 
 ### Responses are read lazily
 
-`HttpClient.crawl` and `HttpClient.stream` are removed. `send_request` returns the response as soon as its headers arrive and reads the body only on `read` or `read_stream`. A response whose body you don't read keeps its connection until you call `aclose`. Use the response as an async context manager to close it:
+`HttpClient.crawl` and `HttpClient.stream` are removed, and so is `HttpCrawlingResult`, which `crawl` returned. `HttpCrawlingContext` still has `http_response`. `http_response` now comes after the fields of `BasicCrawlingContext` instead of before them, so if you build a crawling context yourself, pass the fields by keyword. `send_request` returns the response as soon as its headers arrive and reads the body only on `read` or `read_stream`. A response whose body you don't read keeps its connection until you call `aclose`. Use the response as an async context manager to close it:
 
 ```python
 # v1

src/crawlee/crawlers/__init__.py

@@ -4,7 +4,7 @@
 from ._abstract_http import AbstractHttpCrawler, AbstractHttpParser, HttpCrawlerOptions, ParsedHttpCrawlingContext
 from ._basic import BasicCrawler, BasicCrawlerOptions, BasicCrawlingContext, ContextPipeline
 from ._file_download import FileDownloadCrawler, FileDownloadCrawlingContext
-from ._http import HttpCrawler, HttpCrawlingContext, HttpCrawlingResult
+from ._http import HttpCrawler, HttpCrawlingContext
 
 _install_import_hook(__name__)
 
@@ -129,7 +129,6 @@
     'HttpCrawler',
     'HttpCrawlerOptions',
     'HttpCrawlingContext',
-    'HttpCrawlingResult',
     'ParsedHttpCrawlingContext',
     'ParselCrawler',
     'ParselCrawlingContext',

src/crawlee/crawlers/_abstract_http/_http_crawling_context.py

@@ -1,21 +1,26 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, fields
-from typing import Generic, Self, TypeVar
+from typing import TYPE_CHECKING, Generic, Self, TypeVar
 
 from crawlee._types import BasicCrawlingContext, EnqueueLinksFunction, ExtractLinksFunction, PageSnapshot
 from crawlee._utils.docs import docs_group
-from crawlee.http_clients import HttpCrawlingResult, HttpResponse
+
+if TYPE_CHECKING:
+    from crawlee.http_clients import HttpResponse
 
 TParseResult = TypeVar('TParseResult')
 TSelectResult = TypeVar('TSelectResult')
 
 
 @dataclass(frozen=True)
 @docs_group('Crawling contexts')
-class HttpCrawlingContext(BasicCrawlingContext, HttpCrawlingResult):
+class HttpCrawlingContext(BasicCrawlingContext):
     """The crawling context used by the `AbstractHttpCrawler`."""
 
+    http_response: HttpResponse
+    """The HTTP response received from the server."""
+
     @classmethod
     def from_basic_crawling_context(cls, context: BasicCrawlingContext, http_response: HttpResponse) -> Self:
         """Initialize a new instance from an existing `BasicCrawlingContext`."""

src/crawlee/crawlers/_http/__init__.py

@@ -1,10 +1,8 @@
 from crawlee.crawlers._abstract_http._http_crawling_context import HttpCrawlingContext
-from crawlee.http_clients import HttpCrawlingResult
 
 from ._http_crawler import HttpCrawler
 
 __all__ = [
     'HttpCrawler',
     'HttpCrawlingContext',
-    'HttpCrawlingResult',
 ]

src/crawlee/http_clients/__init__.py

@@ -2,7 +2,7 @@
 from crawlee._utils.try_import import try_import as _try_import
 
 # These imports have only mandatory dependencies, so they are imported directly.
-from ._base import HttpClient, HttpCrawlingResult, HttpResponse
+from ._base import HttpClient, HttpResponse
 from ._impit import ImpitHttpClient
 
 _install_import_hook(__name__)
@@ -19,7 +19,6 @@
 __all__ = [
     'CurlImpersonateHttpClient',
     'HttpClient',
-    'HttpCrawlingResult',
     'HttpResponse',
     'HttpxHttpClient',
     'ImpitHttpClient',

src/crawlee/http_clients/_base.py

@@ -2,7 +2,6 @@
 
 import asyncio
 from abc import ABC, abstractmethod
-from dataclasses import dataclass
 from datetime import timedelta
 from http import HTTPStatus
 from time import monotonic
@@ -168,19 +167,6 @@ async def __aexit__(
         await self.aclose()
 
 
-@dataclass(frozen=True)
-@docs_group('Crawling contexts')
-class HttpCrawlingResult:
-    """Result of an HTTP-only crawl.
-
-    Mainly for the purpose of composing specific crawling contexts (e.g. `BeautifulSoupCrawlingContext`,
-    `ParselCrawlingContext`, ...).
-    """
-
-    http_response: HttpResponse
-    """The HTTP response received from the server."""
-
-
 @docs_group('HTTP clients')
 class HttpClient(ABC):
     """An abstract base class for HTTP clients used in crawlers (`BasicCrawler` subclasses).