crawlee 1.0.5b16__tar.gz → 1.2.1b5__tar.gz

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/.github/workflows/build_and_deploy_docs.yaml

@@ -24,7 +24,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
         with:
           token: ${{ secrets.APIFY_SERVICE_ACCOUNT_GITHUB_TOKEN }}
           ref: ${{ github.event_name == 'workflow_call' && inputs.ref || github.ref }}
@@ -67,6 +67,10 @@ jobs:
         uses: actions/deploy-pages@v4
 
       - name: Invalidate CloudFront cache
-        run: gh workflow run invalidate.yaml --repo apify/apify-docs-private
+        run: |
+          gh workflow run invalidate-cloudfront.yml \
+            --repo apify/apify-docs-private \
+            --field deployment=crawlee-web
+          echo "✅ CloudFront cache invalidation workflow triggered successfully"
         env:
           GITHUB_TOKEN: ${{ secrets.APIFY_SERVICE_ACCOUNT_GITHUB_TOKEN }}

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/.github/workflows/run_code_checks.yaml

@@ -36,6 +36,7 @@ jobs:
       httpbin_url: ${{ secrets.APIFY_HTTPBIN_TOKEN && format('https://httpbin.apify.actor?token={0}', secrets.APIFY_HTTPBIN_TOKEN) || 'https://httpbin.org'}}
     with:
       python-versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
+      os: '["ubuntu-latest", "windows-latest", "macos-latest"]'
 
   docs_check:
     name: Docs check

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/.github/workflows/templates_e2e_tests.yaml

@@ -24,7 +24,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Setup node
         uses: actions/setup-node@v6

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/.gitignore

@@ -3,6 +3,7 @@ __pycache__
 .mypy_cache
 .pytest_cache
 .ruff_cache
+.uv-cache
 
 # Virtual envs
 .venv

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/CHANGELOG.md

@@ -3,22 +3,57 @@
 All notable changes to this project will be documented in this file.
 
 <!-- git-cliff-unreleased-start -->
-## 1.0.5 - **not yet released**
+## 1.2.1 - **not yet released**
+
+### 🐛 Bug Fixes
+
+- Fix short error summary ([#1605](https://github.com/apify/crawlee-python/pull/1605)) ([b751208](https://github.com/apify/crawlee-python/commit/b751208d9a56e9d923e4559baeba35e2eede0450)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1602](https://github.com/apify/crawlee-python/issues/1602)
+- Freeze core `Request` fields ([#1603](https://github.com/apify/crawlee-python/pull/1603)) ([ae6d86b](https://github.com/apify/crawlee-python/commit/ae6d86b8c82900116032596201d94cd7875aaadc)) by [@Mantisus](https://github.com/Mantisus)
+
+
+<!-- git-cliff-unreleased-end -->
+## [1.2.0](https://github.com/apify/crawlee-python/releases/tag/v1.2.0) (2025-12-08)
+
+### 🚀 Features
+
+- Add additional kwargs to Crawler&#x27;s export_data ([#1597](https://github.com/apify/crawlee-python/pull/1597)) ([5977f37](https://github.com/apify/crawlee-python/commit/5977f376b93a7c0d4dd53f0d331a4b04fedba2c6)) by [@vdusek](https://github.com/vdusek), closes [#526](https://github.com/apify/crawlee-python/issues/526)
+- Add `goto_options` for `PlaywrightCrawler` ([#1599](https://github.com/apify/crawlee-python/pull/1599)) ([0b82f3b](https://github.com/apify/crawlee-python/commit/0b82f3b6fb175223ea2aa5b348afcd5fdb767972)) by [@Mantisus](https://github.com/Mantisus), closes [#1576](https://github.com/apify/crawlee-python/issues/1576)
+
+### 🐛 Bug Fixes
+
+- Only apply requestHandlerTimeout to request handler ([#1474](https://github.com/apify/crawlee-python/pull/1474)) ([0dfb6c2](https://github.com/apify/crawlee-python/commit/0dfb6c2a13b6650736245fa39b3fbff397644df7)) by [@janbuchar](https://github.com/janbuchar)
+- Handle the case when `error_handler` returns `Request` ([#1595](https://github.com/apify/crawlee-python/pull/1595)) ([8a961a2](https://github.com/apify/crawlee-python/commit/8a961a2b07d0d33a7302dbb13c17f3d90999d390)) by [@Mantisus](https://github.com/Mantisus)
+- Align `Request.state` transitions with `Request` lifecycle ([#1601](https://github.com/apify/crawlee-python/pull/1601)) ([383225f](https://github.com/apify/crawlee-python/commit/383225f9f055d95ffb1302b8cf96f42ec264f1fc)) by [@Mantisus](https://github.com/Mantisus)
+
+
+## [1.1.1](https://github.com/apify/crawlee-python/releases/tag/v1.1.1) (2025-12-02)
+
+### 🐛 Bug Fixes
+
+- Unify separators in `unique_key` construction ([#1569](https://github.com/apify/crawlee-python/pull/1569)) ([af46a37](https://github.com/apify/crawlee-python/commit/af46a3733b059a8052489296e172f005def953f7)) by [@vdusek](https://github.com/vdusek), closes [#1512](https://github.com/apify/crawlee-python/issues/1512)
+- Fix `same-domain` strategy ignoring public suffix  ([#1572](https://github.com/apify/crawlee-python/pull/1572)) ([3d018b2](https://github.com/apify/crawlee-python/commit/3d018b21a28a4bee493829783057188d6106a69b)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1571](https://github.com/apify/crawlee-python/issues/1571)
+- Make context helpers work in `FailedRequestHandler` and `ErrorHandler` ([#1570](https://github.com/apify/crawlee-python/pull/1570)) ([b830019](https://github.com/apify/crawlee-python/commit/b830019350830ac33075316061659e2854f7f4a5)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1532](https://github.com/apify/crawlee-python/issues/1532)
+- Fix non-ASCII character corruption in `FileSystemStorageClient` on systems without UTF-8 default encoding ([#1580](https://github.com/apify/crawlee-python/pull/1580)) ([f179f86](https://github.com/apify/crawlee-python/commit/f179f8671b0b6af9264450e4fef7e49d1cecd2bd)) by [@Mantisus](https://github.com/Mantisus), closes [#1579](https://github.com/apify/crawlee-python/issues/1579)
+- Respect `&lt;base&gt;` when enqueuing ([#1590](https://github.com/apify/crawlee-python/pull/1590)) ([de517a1](https://github.com/apify/crawlee-python/commit/de517a1629cc29b20568143eb64018f216d4ba33)) by [@Mantisus](https://github.com/Mantisus), closes [#1589](https://github.com/apify/crawlee-python/issues/1589)
+
+
+## [1.1.0](https://github.com/apify/crawlee-python/releases/tag/v1.1.0) (2025-11-18)
 
 ### 🚀 Features
 
 - Add `chrome` `BrowserType` for `PlaywrightCrawler` to use the Chrome browser ([#1487](https://github.com/apify/crawlee-python/pull/1487)) ([b06937b](https://github.com/apify/crawlee-python/commit/b06937bbc3afe3c936b554bfc503365c1b2c526b)) by [@Mantisus](https://github.com/Mantisus), closes [#1071](https://github.com/apify/crawlee-python/issues/1071)
 - Add `RedisStorageClient` based on Redis v8.0+ ([#1406](https://github.com/apify/crawlee-python/pull/1406)) ([d08d13d](https://github.com/apify/crawlee-python/commit/d08d13d39203c24ab61fe254b0956d6744db3b5f)) by [@Mantisus](https://github.com/Mantisus)
 - Add support for Python 3.14 ([#1553](https://github.com/apify/crawlee-python/pull/1553)) ([89e9130](https://github.com/apify/crawlee-python/commit/89e9130cabee0fbc974b29c26483b7fa0edf627c)) by [@Mantisus](https://github.com/Mantisus)
+- Add `transform_request_function` parameter for `SitemapRequestLoader` ([#1525](https://github.com/apify/crawlee-python/pull/1525)) ([dc90127](https://github.com/apify/crawlee-python/commit/dc901271849b239ba2a947e8ebff8e1815e8c4fb)) by [@Mantisus](https://github.com/Mantisus)
 
 ### 🐛 Bug Fixes
 
 - Improve indexing of the `request_queue_records` table for `SqlRequestQueueClient` ([#1527](https://github.com/apify/crawlee-python/pull/1527)) ([6509534](https://github.com/apify/crawlee-python/commit/65095346a9d8b703b10c91e0510154c3c48a4176)) by [@Mantisus](https://github.com/Mantisus), closes [#1526](https://github.com/apify/crawlee-python/issues/1526)
 - Improve error handling for `RobotsTxtFile.load` ([#1524](https://github.com/apify/crawlee-python/pull/1524)) ([596a311](https://github.com/apify/crawlee-python/commit/596a31184914a254b3e7a81fd2f48ea8eda7db49)) by [@Mantisus](https://github.com/Mantisus)
 - Fix `crawler_runtime` not being updated during run and only in the end ([#1540](https://github.com/apify/crawlee-python/pull/1540)) ([0d6c3f6](https://github.com/apify/crawlee-python/commit/0d6c3f6d3337ddb6cab4873747c28cf95605d550)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1541](https://github.com/apify/crawlee-python/issues/1541)
+- Ensure persist state event emission when exiting `EventManager` context ([#1562](https://github.com/apify/crawlee-python/pull/1562)) ([6a44f17](https://github.com/apify/crawlee-python/commit/6a44f172600cbcacebab899082d6efc9105c4e03)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1560](https://github.com/apify/crawlee-python/issues/1560)
 
 
-<!-- git-cliff-unreleased-end -->
 ## [1.0.4](https://github.com/apify/crawlee-python/releases/tag/v1.0.4) (2025-10-24)
 
 ### 🐛 Bug Fixes

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crawlee
-Version: 1.0.5b16
+Version: 1.2.1b5
 Summary: Crawlee for Python
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://crawlee.dev/python/docs/changelog
@@ -226,6 +226,7 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Software Development :: Libraries
 Requires-Python: >=3.10
+Requires-Dist: async-timeout>=5.0.1
 Requires-Dist: cachetools>=5.5.0
 Requires-Dist: colorama>=0.4.0
 Requires-Dist: impit>=0.8.0
@@ -247,7 +248,7 @@ Requires-Dist: scikit-learn>=1.6.0; extra == 'adaptive-crawler'
 Provides-Extra: all
 Requires-Dist: aiosqlite>=0.21.0; extra == 'all'
 Requires-Dist: apify-fingerprint-datapoints>=0.0.2; extra == 'all'
-Requires-Dist: asyncpg>=0.24.0; (python_version < '3.14') and extra == 'all'
+Requires-Dist: asyncpg>=0.24.0; extra == 'all'
 Requires-Dist: beautifulsoup4[lxml]>=4.12.0; extra == 'all'
 Requires-Dist: browserforge>=1.2.3; extra == 'all'
 Requires-Dist: cookiecutter>=2.6.0; extra == 'all'
@@ -301,7 +302,7 @@ Requires-Dist: playwright>=1.27.0; extra == 'playwright'
 Provides-Extra: redis
 Requires-Dist: redis[hiredis]>=7.0.0; extra == 'redis'
 Provides-Extra: sql-postgres
-Requires-Dist: asyncpg>=0.24.0; (python_version < '3.14') and extra == 'sql-postgres'
+Requires-Dist: asyncpg>=0.24.0; extra == 'sql-postgres'
 Requires-Dist: sqlalchemy[asyncio]<3.0.0,>=2.0.0; extra == 'sql-postgres'
 Provides-Extra: sql-sqlite
 Requires-Dist: aiosqlite>=0.21.0; extra == 'sql-sqlite'

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/docs/deployment/code_examples/google/cloud_run_example.py

@@ -9,7 +9,7 @@ from crawlee.crawlers import PlaywrightCrawler, PlaywrightCrawlingContext
 from crawlee.storage_clients import MemoryStorageClient
 
 
-@get('/')
+@get('/')  # type: ignore[untyped-decorator]
 async def main() -> str:
     """The crawler entry point that will be called when the HTTP endpoint is accessed."""
     # highlight-start

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/docs/deployment/code_examples/google/google_example.py

@@ -6,10 +6,7 @@ from datetime import timedelta
 import functions_framework
 from flask import Request, Response
 
-from crawlee.crawlers import (
-    BeautifulSoupCrawler,
-    BeautifulSoupCrawlingContext,
-)
+from crawlee.crawlers import BeautifulSoupCrawler, BeautifulSoupCrawlingContext
 from crawlee.storage_clients import MemoryStorageClient
 
 
@@ -51,7 +48,7 @@ async def main() -> str:
     # highlight-end
 
 
-@functions_framework.http
+@functions_framework.http  # type: ignore[untyped-decorator]
 def crawlee_run(request: Request) -> Response:
     # You can pass data to your crawler using `request`
     function_id = request.headers['Function-Execution-Id']

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/docs/examples/code_examples/export_entire_dataset_to_file_csv.py

@@ -30,7 +30,8 @@ async def main() -> None:
     await crawler.run(['https://crawlee.dev'])
 
     # Export the entire dataset to a CSV file.
-    await crawler.export_data(path='results.csv')
+    # Use semicolon as delimiter and always quote strings.
+    await crawler.export_data(path='results.csv', delimiter=';', quoting='all')
 
 
 if __name__ == '__main__':

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/docs/examples/code_examples/export_entire_dataset_to_file_json.py

@@ -30,7 +30,8 @@ async def main() -> None:
     await crawler.run(['https://crawlee.dev'])
 
     # Export the entire dataset to a JSON file.
-    await crawler.export_data(path='results.json')
+    # Set ensure_ascii=False to allow Unicode characters in the output.
+    await crawler.export_data(path='results.json', ensure_ascii=False)
 
 
 if __name__ == '__main__':

crawlee-1.2.1b5/docs/examples/code_examples/using_sitemap_request_loader.py

@@ -0,0 +1,101 @@
+import asyncio
+from collections.abc import Callable
+
+from yarl import URL
+
+from crawlee import RequestOptions, RequestTransformAction
+from crawlee.crawlers import BeautifulSoupCrawler, BeautifulSoupCrawlingContext
+from crawlee.http_clients import ImpitHttpClient
+from crawlee.request_loaders import SitemapRequestLoader
+
+
+# Create a transform_request_function that maps request options based on the host in
+# the URL
+def create_transform_request(
+    data_mapper: dict[str, dict],
+) -> Callable[[RequestOptions], RequestOptions | RequestTransformAction]:
+    def transform_request(
+        request_options: RequestOptions,
+    ) -> RequestOptions | RequestTransformAction:
+        # According to the Sitemap protocol, all URLs in a Sitemap must be from a single
+        # host.
+        request_host = URL(request_options['url']).host
+
+        if request_host and (mapping_data := data_mapper.get(request_host)):
+            # Set properties from the mapping data
+            if 'label' in mapping_data:
+                request_options['label'] = mapping_data['label']
+            if 'user_data' in mapping_data:
+                request_options['user_data'] = mapping_data['user_data']
+
+            return request_options
+
+        return 'unchanged'
+
+    return transform_request
+
+
+async def main() -> None:
+    # Prepare data mapping for hosts
+    apify_host = URL('https://apify.com/sitemap.xml').host
+    crawlee_host = URL('https://crawlee.dev/sitemap.xml').host
+
+    if not apify_host or not crawlee_host:
+        raise ValueError('Unable to extract host from URLs')
+
+    data_map = {
+        apify_host: {
+            'label': 'apify',
+            'user_data': {'source': 'apify'},
+        },
+        crawlee_host: {
+            'label': 'crawlee',
+            'user_data': {'source': 'crawlee'},
+        },
+    }
+
+    # Initialize the SitemapRequestLoader with the transform function
+    async with SitemapRequestLoader(
+        # Set the sitemap URLs and the HTTP client
+        sitemap_urls=['https://crawlee.dev/sitemap.xml', 'https://apify.com/sitemap.xml'],
+        http_client=ImpitHttpClient(),
+        transform_request_function=create_transform_request(data_map),
+    ) as sitemap_loader:
+        # Convert the sitemap loader to a request manager
+        request_manager = await sitemap_loader.to_tandem()
+
+        # Create and configure the crawler
+        crawler = BeautifulSoupCrawler(
+            request_manager=request_manager,
+            max_requests_per_crawl=10,
+        )
+
+        # Create default handler for requests without a specific label
+        @crawler.router.default_handler
+        async def handler(context: BeautifulSoupCrawlingContext) -> None:
+            source = context.request.user_data.get('source', 'unknown')
+            context.log.info(
+                f'Processing request: {context.request.url} from source: {source}'
+            )
+
+        # Create handler for requests labeled 'apify'
+        @crawler.router.handler('apify')
+        async def apify_handler(context: BeautifulSoupCrawlingContext) -> None:
+            source = context.request.user_data.get('source', 'unknown')
+            context.log.info(
+                f'Apify handler processing: {context.request.url} from source: {source}'
+            )
+
+        # Create handler for requests labeled 'crawlee'
+        @crawler.router.handler('crawlee')
+        async def crawlee_handler(context: BeautifulSoupCrawlingContext) -> None:
+            source = context.request.user_data.get('source', 'unknown')
+            context.log.info(
+                f'Crawlee handler processing: {context.request.url} from source: {source}'
+            )
+
+        await crawler.run()
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/docs/examples/export_entire_dataset_to_file.mdx

@@ -11,7 +11,7 @@ import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock';
 import JsonExample from '!!raw-loader!roa-loader!./code_examples/export_entire_dataset_to_file_json.py';
 import CsvExample from '!!raw-loader!roa-loader!./code_examples/export_entire_dataset_to_file_csv.py';
 
-This example demonstrates how to use the <ApiLink to="class/BasicCrawler#export_data">`BasicCrawler.export_data`</ApiLink> method of the crawler to export the entire default dataset to a single file. This method supports exporting data in either CSV or JSON format.
+This example demonstrates how to use the <ApiLink to="class/BasicCrawler#export_data">`BasicCrawler.export_data`</ApiLink> method of the crawler to export the entire default dataset to a single file. This method supports exporting data in either CSV or JSON format and also accepts additional keyword arguments so you can fine-tune the underlying `json.dump` or `csv.writer` behavior.
 
 :::note
 

crawlee-1.2.1b5/docs/examples/using_sitemap_request_loader.mdx

@@ -0,0 +1,22 @@
+---
+id: using-sitemap-request-loader
+title: Using sitemap request loader
+---
+
+import ApiLink from '@site/src/components/ApiLink';
+
+import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock';
+
+import SitemapRequestLoaderExample from '!!raw-loader!roa-loader!./code_examples/using_sitemap_request_loader.py';
+
+This example demonstrates how to use <ApiLink to="class/SitemapRequestLoader">`SitemapRequestLoader`</ApiLink> to crawl websites that provide `sitemap.xml` files following the [Sitemaps protocol](https://www.sitemaps.org/protocol.html). The <ApiLink to="class/SitemapRequestLoader">`SitemapRequestLoader`</ApiLink> processes sitemaps in a streaming fashion without loading them entirely into memory, making it suitable for large sitemaps.
+
+The example shows how to use the `transform_request_function` parameter to configure request options based on URL patterns. This allows you to modify request properties such as labels and user data based on the source URL, enabling different handling logic for different websites or sections.
+
+The following code example implements processing of sitemaps from two different domains (Apify and Crawlee), with different labels assigned to requests based on their host. The `create_transform_request` function maps each host to the corresponding request configuration, while the crawler uses different handlers based on the assigned labels.
+
+<RunnableCodeBlock className="language-python" language="python">
+    {SitemapRequestLoaderExample}
+</RunnableCodeBlock>
+
+For more information about request loaders, see the [Request loaders guide](../guides/request-loaders).

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/docs/guides/code_examples/running_in_web_server/server.py

@@ -14,7 +14,7 @@ from .crawler import lifespan
 app = FastAPI(lifespan=lifespan, title='Crawler app')
 
 
-@app.get('/', response_class=HTMLResponse)
+@app.get('/', response_class=HTMLResponse)  # type: ignore[untyped-decorator]
 def index() -> str:
     return """
 <!DOCTYPE html>
@@ -32,7 +32,7 @@ def index() -> str:
 """
 
 
-@app.get('/scrape')
+@app.get('/scrape')  # type: ignore[untyped-decorator]
 async def scrape_url(request: Request, url: str | None = None) -> dict:
     if not url:
         return {'url': 'missing', 'scrape result': 'no results'}

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "crawlee"
-version = "1.0.5b16"
+version = "1.2.1b5"
 description = "Crawlee for Python"
 authors = [{ name = "Apify Technologies s.r.o.", email = "support@apify.com" }]
 license = { file = "LICENSE" }
@@ -34,6 +34,7 @@ keywords = [
     "scraping",
 ]
 dependencies = [
+    "async-timeout>=5.0.1",
     "cachetools>=5.5.0",
     "colorama>=0.4.0",
     "impit>=0.8.0",
@@ -74,7 +75,7 @@ otel = [
 ]
 sql_postgres = [
     "sqlalchemy[asyncio]>=2.0.0,<3.0.0",
-    "asyncpg>=0.24.0; python_version < '3.14'" # TODO: https://github.com/apify/crawlee-python/issues/1555
+    "asyncpg>=0.24.0"
 ]
 sql_sqlite = [
     "sqlalchemy[asyncio]>=2.0.0,<3.0.0",
@@ -101,7 +102,7 @@ dev = [
     "build<2.0.0", # For e2e tests.
     "dycw-pytest-only<3.0.0",
     "fakeredis[probabilistic,json,lua]<3.0.0",
-    "mypy~=1.18.0",
+    "mypy~=1.19.0",
     "pre-commit<5.0.0",
     "proxy-py<3.0.0",
     "pydoc-markdown<5.0.0",
@@ -117,7 +118,7 @@ dev = [
     "types-colorama<1.0.0",
     "types-psutil<8.0.0",
     "types-python-dateutil<3.0.0",
-    "uvicorn[standard]~=0.35.0", # https://github.com/apify/crawlee-python/issues/1441
+    "uvicorn[standard]<1.0.0",
 ]
 
 [tool.hatch.build.targets.wheel]
@@ -221,6 +222,13 @@ timeout = 300
 markers = [
     "run_alone: marks tests that must run in isolation",
 ]
+# Ignore DeprecationWarnings coming from Uvicorn's internal imports. Uvicorn relies on deprecated
+# modules from `websockets`, which triggers warnings during tests. These are safe to ignore until
+# Uvicorn updates its internals.
+filterwarnings = [
+    "ignore:websockets.legacy is deprecated:DeprecationWarning",
+    "ignore:websockets.server.WebSocketServerProtocol is deprecated:DeprecationWarning",
+]
 
 [tool.mypy]
 python_version = "3.10"

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/src/crawlee/__init__.py

@@ -1,6 +1,6 @@
 from importlib import metadata
 
-from ._request import Request, RequestOptions
+from ._request import Request, RequestOptions, RequestState
 from ._service_locator import service_locator
 from ._types import ConcurrencySettings, EnqueueStrategy, HttpHeaders, RequestTransformAction, SkippedReason
 from ._utils.globs import Glob
@@ -14,6 +14,7 @@ __all__ = [
     'HttpHeaders',
     'Request',
     'RequestOptions',
+    'RequestState',
     'RequestTransformAction',
     'SkippedReason',
     'service_locator',

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/src/crawlee/_request.py

@@ -34,14 +34,14 @@ class RequestState(IntEnum):
 class CrawleeRequestData(BaseModel):
     """Crawlee-specific configuration stored in the `user_data`."""
 
-    max_retries: Annotated[int | None, Field(alias='maxRetries')] = None
+    max_retries: Annotated[int | None, Field(alias='maxRetries', frozen=True)] = None
     """Maximum number of retries for this request. Allows to override the global `max_request_retries` option of
     `BasicCrawler`."""
 
     enqueue_strategy: Annotated[EnqueueStrategy | None, Field(alias='enqueueStrategy')] = None
     """The strategy that was used for enqueuing the request."""
 
-    state: RequestState | None = None
+    state: RequestState = RequestState.UNPROCESSED
     """Describes the request's current lifecycle state."""
 
     session_rotation_count: Annotated[int | None, Field(alias='sessionRotationCount')] = None
@@ -137,6 +137,8 @@ class RequestOptions(TypedDict):
     always_enqueue: NotRequired[bool]
     user_data: NotRequired[dict[str, JsonSerializable]]
     no_retry: NotRequired[bool]
+    enqueue_strategy: NotRequired[EnqueueStrategy]
+    max_retries: NotRequired[int | None]
 
 
 @docs_group('Storage data')
@@ -166,7 +168,7 @@ class Request(BaseModel):
 
     model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
-    unique_key: Annotated[str, Field(alias='uniqueKey')]
+    unique_key: Annotated[str, Field(alias='uniqueKey', frozen=True)]
     """A unique key identifying the request. Two requests with the same `unique_key` are considered as pointing
     to the same URL.
 
@@ -178,17 +180,18 @@ class Request(BaseModel):
     and specify which URLs shall be considered equal.
     """
 
-    url: Annotated[str, BeforeValidator(validate_http_url), Field()]
+    url: Annotated[str, BeforeValidator(validate_http_url), Field(frozen=True)]
     """The URL of the web page to crawl. Must be a valid HTTP or HTTPS URL, and may include query parameters
     and fragments."""
 
-    method: HttpMethod = 'GET'
+    method: Annotated[HttpMethod, Field(frozen=True)] = 'GET'
     """HTTP request method."""
 
     payload: Annotated[
         HttpPayload | None,
         BeforeValidator(lambda v: v.encode() if isinstance(v, str) else v),
         PlainSerializer(lambda v: v.decode() if isinstance(v, bytes) else v),
+        Field(frozen=True),
     ] = None
     """HTTP request payload."""
 
@@ -250,6 +253,8 @@ class Request(BaseModel):
         keep_url_fragment: bool = False,
         use_extended_unique_key: bool = False,
         always_enqueue: bool = False,
+        enqueue_strategy: EnqueueStrategy | None = None,
+        max_retries: int | None = None,
         **kwargs: Any,
     ) -> Self:
         """Create a new `Request` instance from a URL.
@@ -277,6 +282,9 @@ class Request(BaseModel):
                 `unique_key` computation. This is only relevant when `unique_key` is not provided.
             always_enqueue: If set to `True`, the request will be enqueued even if it is already present in the queue.
                 Using this is not allowed when a custom `unique_key` is also provided and will result in a `ValueError`.
+            enqueue_strategy: The strategy that will be used for enqueuing the request.
+            max_retries: Maximum number of retries for this request. Allows to override the global `max_request_retries`
+                option of `BasicCrawler`.
             **kwargs: Additional request properties.
         """
         if unique_key is not None and always_enqueue:
@@ -299,7 +307,21 @@ class Request(BaseModel):
         )
 
         if always_enqueue:
-            unique_key = f'{unique_key}_{crypto_random_object_id()}'
+            unique_key = f'{crypto_random_object_id()}|{unique_key}'
+
+        user_data_dict = kwargs.pop('user_data', {}) or {}
+        crawlee_data_dict = user_data_dict.get('__crawlee', {})
+
+        if max_retries is not None:
+            crawlee_data_dict['maxRetries'] = max_retries
+
+        if enqueue_strategy is not None:
+            crawlee_data_dict['enqueueStrategy'] = enqueue_strategy
+
+        crawlee_data = CrawleeRequestData(**crawlee_data_dict)
+
+        if crawlee_data:
+            user_data_dict['__crawlee'] = crawlee_data
 
         request = cls(
             url=url,
@@ -307,6 +329,7 @@ class Request(BaseModel):
             method=method,
             headers=headers,
             payload=payload,
+            user_data=user_data_dict,
             **kwargs,
         )
 
@@ -352,7 +375,7 @@ class Request(BaseModel):
         self.crawlee_data.crawl_depth = new_value
 
     @property
-    def state(self) -> RequestState | None:
+    def state(self) -> RequestState:
         """Crawlee-specific request handling state."""
         return self.crawlee_data.state
 
@@ -365,10 +388,6 @@ class Request(BaseModel):
         """Crawlee-specific limit on the number of retries of the request."""
         return self.crawlee_data.max_retries
 
-    @max_retries.setter
-    def max_retries(self, new_max_retries: int) -> None:
-        self.crawlee_data.max_retries = new_max_retries
-
     @property
     def session_rotation_count(self) -> int | None:
         """Crawlee-specific number of finished session rotations for the request."""

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/src/crawlee/_types.py

@@ -15,7 +15,7 @@ if TYPE_CHECKING:
     import re
     from collections.abc import Callable, Coroutine, Sequence
 
-    from typing_extensions import NotRequired, Required, Unpack
+    from typing_extensions import NotRequired, Required, Self, Unpack
 
     from crawlee import Glob, Request
     from crawlee._request import RequestOptions
@@ -643,6 +643,25 @@ class BasicCrawlingContext:
         """Return hash of the context. Each context is considered unique."""
         return id(self)
 
+    def create_modified_copy(
+        self,
+        push_data: PushDataFunction | None = None,
+        add_requests: AddRequestsFunction | None = None,
+        get_key_value_store: GetKeyValueStoreFromRequestHandlerFunction | None = None,
+    ) -> Self:
+        """Create a modified copy of the crawling context with specified changes."""
+        original_fields = {field.name: getattr(self, field.name) for field in dataclasses.fields(self)}
+        modified_fields = {
+            key: value
+            for key, value in {
+                'push_data': push_data,
+                'add_requests': add_requests,
+                'get_key_value_store': get_key_value_store,
+            }.items()
+            if value
+        }
+        return self.__class__(**{**original_fields, **modified_fields})
+
 
 class GetDataKwargs(TypedDict):
     """Keyword arguments for dataset's `get_data` method."""

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/src/crawlee/_utils/context.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-import asyncio
+import inspect
 from collections.abc import Callable
 from functools import wraps
 from typing import Any, TypeVar
@@ -44,4 +44,4 @@ def ensure_context(method: T) -> T:
 
         return await method(self, *args, **kwargs)
 
-    return async_wrapper if asyncio.iscoroutinefunction(method) else sync_wrapper  # type: ignore[return-value]
+    return async_wrapper if inspect.iscoroutinefunction(method) else sync_wrapper  # type: ignore[return-value]

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/src/crawlee/_utils/file.py

@@ -163,6 +163,13 @@ async def export_csv_to_stream(
     dst: TextIO,
     **kwargs: Unpack[ExportDataCsvKwargs],
 ) -> None:
+    # Set lineterminator to '\n' if not explicitly provided. This prevents double line endings on Windows.
+    # The csv.writer default is '\r\n', which when written to a file in text mode on Windows gets converted
+    # to '\r\r\n' due to newline translation. By using '\n', we let the platform handle the line ending
+    # conversion: '\n' stays as '\n' on Unix, and becomes '\r\n' on Windows.
+    if 'lineterminator' not in kwargs:
+        kwargs['lineterminator'] = '\n'
+
     writer = csv.writer(dst, **kwargs)  # type: ignore[arg-type]
     write_header = True
 

{crawlee-1.0.5b16 → crawlee-1.2.1b5}/src/crawlee/_utils/recurring_task.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import inspect
 from logging import getLogger
 from typing import TYPE_CHECKING
 
@@ -49,7 +50,7 @@ class RecurringTask:
         """
         sleep_time_secs = self.delay.total_seconds()
         while True:
-            await self.func() if asyncio.iscoroutinefunction(self.func) else self.func()
+            await self.func() if inspect.iscoroutinefunction(self.func) else self.func()
             await asyncio.sleep(sleep_time_secs)
 
     def start(self) -> None: