crawlee 0.6.13b41__tar.gz → 1.1.0__tar.gz

{crawlee-0.6.13b41 → crawlee-1.1.0}/.github/workflows/build_and_deploy_docs.yaml

@@ -10,7 +10,7 @@ on:
 
 env:
   NODE_VERSION: 20
-  PYTHON_VERSION: 3.13
+  PYTHON_VERSION: 3.14
 
 jobs:
   build_and_deploy_docs:
@@ -30,7 +30,7 @@ jobs:
           ref: ${{ github.event_name == 'workflow_call' && inputs.ref || github.ref }}
 
       - name: Set up Node
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v6
         with:
           node-version: ${{ env.NODE_VERSION }}
 
@@ -40,7 +40,7 @@ jobs:
           python-version: ${{ env.PYTHON_VERSION }}
 
       - name: Set up uv package manager
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 

{crawlee-0.6.13b41 → crawlee-1.1.0}/.github/workflows/pre_release.yaml

@@ -37,7 +37,7 @@ jobs:
     name: Wait for code checks to pass
     runs-on: ubuntu-latest
     steps:
-      - uses: lewagon/wait-on-check-action@v1.4.0
+      - uses: lewagon/wait-on-check-action@v1.4.1
         with:
           ref: ${{ github.ref }}
           repo-token: ${{ secrets.GITHUB_TOKEN }}

{crawlee-0.6.13b41 → crawlee-1.1.0}/.github/workflows/release.yaml

@@ -47,13 +47,13 @@ jobs:
     name: Lint check
     uses: apify/workflows/.github/workflows/python_lint_check.yaml@main
     with:
-      python-versions: '["3.10", "3.11", "3.12", "3.13"]'
+      python-versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
 
   type_check:
     name: Type check
     uses: apify/workflows/.github/workflows/python_type_check.yaml@main
     with:
-      python-versions: '["3.10", "3.11", "3.12", "3.13"]'
+      python-versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
 
   unit_tests:
     name: Unit tests
@@ -61,7 +61,7 @@ jobs:
     secrets:
       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"]'
+      python-versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
 
   update_changelog:
     name: Update changelog

{crawlee-0.6.13b41 → crawlee-1.1.0}/.github/workflows/run_code_checks.yaml

@@ -21,13 +21,13 @@ jobs:
     name: Lint check
     uses: apify/workflows/.github/workflows/python_lint_check.yaml@main
     with:
-      python-versions: '["3.10", "3.11", "3.12", "3.13"]'
+      python-versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
 
   type_check:
     name: Type check
     uses: apify/workflows/.github/workflows/python_type_check.yaml@main
     with:
-      python-versions: '["3.10", "3.11", "3.12", "3.13"]'
+      python-versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
 
   unit_tests:
     name: Unit tests
@@ -35,8 +35,9 @@ jobs:
     secrets:
       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"]'
+      python-versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
 
   docs_check:
     name: Docs check
     uses: apify/workflows/.github/workflows/python_docs_check.yaml@main
+    secrets: inherit

{crawlee-0.6.13b41 → crawlee-1.1.0}/.github/workflows/templates_e2e_tests.yaml

@@ -7,7 +7,7 @@ on:
 
 env:
   NODE_VERSION: 22
-  PYTHON_VERSION: 3.13
+  PYTHON_VERSION: 3.14
 
 jobs:
   end_to_end_tests:
@@ -27,7 +27,7 @@ jobs:
         uses: actions/checkout@v5
 
       - name: Setup node
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v6
         with:
           node-version: ${{ env.NODE_VERSION }}
 
@@ -44,7 +44,7 @@ jobs:
         run: pipx install poetry
 
       - name: Set up uv package manager
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 

{crawlee-0.6.13b41 → crawlee-1.1.0}/.gitignore

@@ -30,6 +30,7 @@ htmlcov
 # IDE, editors
 .vscode
 .idea
+*~
 .DS_Store
 .nvim.lua
 Session.vim

{crawlee-0.6.13b41 → crawlee-1.1.0}/CHANGELOG.md

@@ -2,8 +2,65 @@
 
 All notable changes to this project will be documented in this file.
 
-<!-- git-cliff-unreleased-start -->
-## 0.6.13 - **not yet released**
+## [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)
+
+
+## [1.0.4](https://github.com/apify/crawlee-python/releases/tag/v1.0.4) (2025-10-24)
+
+### 🐛 Bug Fixes
+
+- Respect `enqueue_strategy` in `enqueue_links` ([#1505](https://github.com/apify/crawlee-python/pull/1505)) ([6ee04bc](https://github.com/apify/crawlee-python/commit/6ee04bc08c50a70f2e956a79d4ce5072a726c3a8)) by [@Mantisus](https://github.com/Mantisus), closes [#1504](https://github.com/apify/crawlee-python/issues/1504)
+- Exclude incorrect links before checking `robots.txt` ([#1502](https://github.com/apify/crawlee-python/pull/1502)) ([3273da5](https://github.com/apify/crawlee-python/commit/3273da5fee62ec9254666b376f382474c3532a56)) by [@Mantisus](https://github.com/Mantisus), closes [#1499](https://github.com/apify/crawlee-python/issues/1499)
+- Resolve compatibility issue between `SqlStorageClient` and `AdaptivePlaywrightCrawler` ([#1496](https://github.com/apify/crawlee-python/pull/1496)) ([ce172c4](https://github.com/apify/crawlee-python/commit/ce172c425a8643a1d4c919db4f5e5a6e47e91deb)) by [@Mantisus](https://github.com/Mantisus), closes [#1495](https://github.com/apify/crawlee-python/issues/1495)
+- Fix `BasicCrawler` statistics persistence ([#1490](https://github.com/apify/crawlee-python/pull/1490)) ([1eb1c19](https://github.com/apify/crawlee-python/commit/1eb1c19aa6f9dda4a0e3f7eda23f77a554f95076)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1501](https://github.com/apify/crawlee-python/issues/1501)
+- Save context state in result for `AdaptivePlaywrightCrawler` after isolated processing in `SubCrawler` ([#1488](https://github.com/apify/crawlee-python/pull/1488)) ([62b7c70](https://github.com/apify/crawlee-python/commit/62b7c70b54085fc65a660062028014f4502beba9)) by [@Mantisus](https://github.com/Mantisus), closes [#1483](https://github.com/apify/crawlee-python/issues/1483)
+
+
+## [1.0.3](https://github.com/apify/crawlee-python/releases/tag/v1.0.3) (2025-10-17)
+
+### 🐛 Bug Fixes
+
+- Add support for Pydantic v2.12 ([#1471](https://github.com/apify/crawlee-python/pull/1471)) ([35c1108](https://github.com/apify/crawlee-python/commit/35c110878c2f445a2866be2522ea8703e9b371dd)) by [@Mantisus](https://github.com/Mantisus), closes [#1464](https://github.com/apify/crawlee-python/issues/1464)
+- Fix database version warning message ([#1485](https://github.com/apify/crawlee-python/pull/1485)) ([18a545e](https://github.com/apify/crawlee-python/commit/18a545ee8add92e844acd0068f9cb8580a82e1c9)) by [@Mantisus](https://github.com/Mantisus)
+- Fix `reclaim_request` in `SqlRequestQueueClient` to correctly update the request state ([#1486](https://github.com/apify/crawlee-python/pull/1486)) ([1502469](https://github.com/apify/crawlee-python/commit/150246957f8f7f1ceb77bb77e3a02a903c50cae1)) by [@Mantisus](https://github.com/Mantisus), closes [#1484](https://github.com/apify/crawlee-python/issues/1484)
+- Fix `KeyValueStore.auto_saved_value` failing in some scenarios ([#1438](https://github.com/apify/crawlee-python/pull/1438)) ([b35dee7](https://github.com/apify/crawlee-python/commit/b35dee78180e57161b826641d45a61b8d8f6ef51)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1354](https://github.com/apify/crawlee-python/issues/1354)
+
+
+## [1.0.2](https://github.com/apify/crawlee-python/releases/tag/v1.0.2) (2025-10-08)
+
+### 🐛 Bug Fixes
+
+- Use Self type in the open() method of storage clients ([#1462](https://github.com/apify/crawlee-python/pull/1462)) ([4ec6f6c](https://github.com/apify/crawlee-python/commit/4ec6f6c08f81632197f602ff99151338b3eba6e7)) by [@janbuchar](https://github.com/janbuchar)
+- Add storages name validation ([#1457](https://github.com/apify/crawlee-python/pull/1457)) ([84de11a](https://github.com/apify/crawlee-python/commit/84de11a3a603503076f5b7df487c9abab68a9015)) by [@Mantisus](https://github.com/Mantisus), closes [#1434](https://github.com/apify/crawlee-python/issues/1434)
+- Pin pydantic version to &lt;2.12.0 to avoid compatibility issues ([#1467](https://github.com/apify/crawlee-python/pull/1467)) ([f11b86f](https://github.com/apify/crawlee-python/commit/f11b86f7ed57f98e83dc1b52f15f2017a919bf59)) by [@vdusek](https://github.com/vdusek)
+
+
+## [1.0.1](https://github.com/apify/crawlee-python/releases/tag/v1.0.1) (2025-10-06)
+
+### 🐛 Bug Fixes
+
+- Fix memory leak in `PlaywrightCrawler` on browser context creation ([#1446](https://github.com/apify/crawlee-python/pull/1446)) ([bb181e5](https://github.com/apify/crawlee-python/commit/bb181e58d8070fba38e62d6e57fe981a00e5f035)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1443](https://github.com/apify/crawlee-python/issues/1443)
+- Update templates to handle optional httpx client ([#1440](https://github.com/apify/crawlee-python/pull/1440)) ([c087efd](https://github.com/apify/crawlee-python/commit/c087efd39baedf46ca3e5cae1ddc1acd6396e6c1)) by [@Pijukatel](https://github.com/Pijukatel)
+
+
+## [1.0.0](https://github.com/apify/crawlee-python/releases/tag/v1.0.0) (2025-09-29)
+
+- Check out the [Release blog post](https://crawlee.dev/blog/crawlee-for-python-v1) for more details.
+- Check out the [Upgrading guide](https://crawlee.dev/python/docs/upgrading/upgrading-to-v1) to ensure a smooth update.
 
 ### 🚀 Features
 
@@ -20,6 +77,8 @@ All notable changes to this project will be documented in this file.
 - Persist `DefaultRenderingTypePredictor` state ([#1340](https://github.com/apify/crawlee-python/pull/1340)) ([fad4c25](https://github.com/apify/crawlee-python/commit/fad4c25fc712915c4a45b24e3290b6f5dbd8a683)) by [@Mantisus](https://github.com/Mantisus), closes [#1272](https://github.com/apify/crawlee-python/issues/1272)
 - Persist the `SitemapRequestLoader` state ([#1347](https://github.com/apify/crawlee-python/pull/1347)) ([27ef9ad](https://github.com/apify/crawlee-python/commit/27ef9ad194552ea9f1321d91a7a52054be9a8a51)) by [@Mantisus](https://github.com/Mantisus), closes [#1269](https://github.com/apify/crawlee-python/issues/1269)
 - Add support for NDU storages ([#1401](https://github.com/apify/crawlee-python/pull/1401)) ([5dbd212](https://github.com/apify/crawlee-python/commit/5dbd212663e7abc37535713f4c6e3a5bbf30a12e)) by [@vdusek](https://github.com/vdusek), closes [#1175](https://github.com/apify/crawlee-python/issues/1175)
+- Add RQ id, name, alias args to `add_requests` and `enqueue_links` methods ([#1413](https://github.com/apify/crawlee-python/pull/1413)) ([1cae2bc](https://github.com/apify/crawlee-python/commit/1cae2bca0b1508fcb3cb419dc239caf33e20a7ef)) by [@Mantisus](https://github.com/Mantisus), closes [#1402](https://github.com/apify/crawlee-python/issues/1402)
+- Add `SqlStorageClient` based on `sqlalchemy` v2+ ([#1339](https://github.com/apify/crawlee-python/pull/1339)) ([07c75a0](https://github.com/apify/crawlee-python/commit/07c75a078b443b58bfaaeb72eb2aa1439458dc47)) by [@Mantisus](https://github.com/Mantisus), closes [#307](https://github.com/apify/crawlee-python/issues/307)
 
 ### 🐛 Bug Fixes
 
@@ -31,6 +90,8 @@ All notable changes to this project will be documented in this file.
 - Include reason in the session rotation warning logs ([#1363](https://github.com/apify/crawlee-python/pull/1363)) ([d6d7a45](https://github.com/apify/crawlee-python/commit/d6d7a45dd64a906419d9552c45062d726cbb1a0f)) by [@vdusek](https://github.com/vdusek), closes [#1318](https://github.com/apify/crawlee-python/issues/1318)
 - Improve crawler statistics logging ([#1364](https://github.com/apify/crawlee-python/pull/1364)) ([1eb6da5](https://github.com/apify/crawlee-python/commit/1eb6da5dd85870124593dcad877284ccaed9c0ce)) by [@vdusek](https://github.com/vdusek), closes [#1317](https://github.com/apify/crawlee-python/issues/1317)
 - Do not add a request that is already in progress to `MemoryRequestQueueClient` ([#1384](https://github.com/apify/crawlee-python/pull/1384)) ([3af326c](https://github.com/apify/crawlee-python/commit/3af326c9dfa8fffd56a42ca42981374613739e39)) by [@Mantisus](https://github.com/Mantisus), closes [#1383](https://github.com/apify/crawlee-python/issues/1383)
+- Save `RequestQueueState` for `FileSystemRequestQueueClient` in default KVS ([#1411](https://github.com/apify/crawlee-python/pull/1411)) ([6ee60a0](https://github.com/apify/crawlee-python/commit/6ee60a08ac1f9414e1b792f4935cc3799cb5089a)) by [@Mantisus](https://github.com/Mantisus), closes [#1410](https://github.com/apify/crawlee-python/issues/1410)
+- Set default desired concurrency for non-browser crawlers to 10 ([#1419](https://github.com/apify/crawlee-python/pull/1419)) ([1cc9401](https://github.com/apify/crawlee-python/commit/1cc940197600d2539bda967880d7f9d241eb8c3e)) by [@vdusek](https://github.com/vdusek)
 
 ### Refactor
 
@@ -43,7 +104,6 @@ All notable changes to this project will be documented in this file.
 - [**breaking**] Refactor storage creation and caching, configuration and services ([#1386](https://github.com/apify/crawlee-python/pull/1386)) ([04649bd](https://github.com/apify/crawlee-python/commit/04649bde60d46b2bc18ae4f6e3fd9667d02a9cef)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1379](https://github.com/apify/crawlee-python/issues/1379)
 
 
-<!-- git-cliff-unreleased-end -->
 
 ## [0.6.12](https://github.com/apify/crawlee-python/releases/tag/v0.6.12) (2025-07-30)
 
@@ -184,6 +244,9 @@ All notable changes to this project will be documented in this file.
 
 ## [0.6.0](https://github.com/apify/crawlee-python/releases/tag/v0.6.0) (2025-03-03)
 
+- Check out the [Release blog post](https://crawlee.dev/blog/crawlee-for-python-v06) for more details.
+- Check out the [Upgrading guide](https://crawlee.dev/python/docs/upgrading/upgrading-to-v0x#upgrading-to-v06) to ensure a smooth update.
+
 ### 🚀 Features
 
 - Integrate browserforge fingerprints ([#829](https://github.com/apify/crawlee-python/pull/829)) ([2b156b4](https://github.com/apify/crawlee-python/commit/2b156b4ba688f9111195422e6058dff30eb1f782)) by [@Pijukatel](https://github.com/Pijukatel), closes [#549](https://github.com/apify/crawlee-python/issues/549)
@@ -222,7 +285,7 @@ All notable changes to this project will be documented in this file.
 
 ### 🐛 Bug Fixes
 
-- Fix session managment with retire ([#947](https://github.com/apify/crawlee-python/pull/947)) ([caee03f](https://github.com/apify/crawlee-python/commit/caee03fe3a43cc1d7a8d3f9e19b42df1bdb1c0aa)) by [@Mantisus](https://github.com/Mantisus)
+- Fix session management with retire ([#947](https://github.com/apify/crawlee-python/pull/947)) ([caee03f](https://github.com/apify/crawlee-python/commit/caee03fe3a43cc1d7a8d3f9e19b42df1bdb1c0aa)) by [@Mantisus](https://github.com/Mantisus)
 - Fix templates - poetry-plugin-export version and camoufox template name ([#952](https://github.com/apify/crawlee-python/pull/952)) ([7addea6](https://github.com/apify/crawlee-python/commit/7addea6605359cceba208e16ec9131724bdb3e9b)) by [@Pijukatel](https://github.com/Pijukatel), closes [#951](https://github.com/apify/crawlee-python/issues/951)
 - Fix convert relative link to absolute in `enqueue_links` for response with redirect ([#956](https://github.com/apify/crawlee-python/pull/956)) ([694102e](https://github.com/apify/crawlee-python/commit/694102e163bb9021a4830d2545d153f6f8f3de90)) by [@Mantisus](https://github.com/Mantisus), closes [#955](https://github.com/apify/crawlee-python/issues/955)
 - Fix `CurlImpersonateHttpClient` cookies handler ([#946](https://github.com/apify/crawlee-python/pull/946)) ([ed415c4](https://github.com/apify/crawlee-python/commit/ed415c433da2a40b0ee62534f0730d0737e991b8)) by [@Mantisus](https://github.com/Mantisus)
@@ -264,6 +327,9 @@ All notable changes to this project will be documented in this file.
 
 ## [0.5.0](https://github.com/apify/crawlee-python/releases/tag/v0.5.0) (2025-01-02)
 
+- Check out the [Release blog post](https://crawlee.dev/blog/crawlee-for-python-v05) for more details.
+- Check out the [Upgrading guide](https://crawlee.dev/python/docs/upgrading/upgrading-to-v0x#upgrading-to-v05) to ensure a smooth update.
+
 ### 🚀 Features
 
 - Add possibility to use None as no proxy in tiered proxies ([#760](https://github.com/apify/crawlee-python/pull/760)) ([0fbd017](https://github.com/apify/crawlee-python/commit/0fbd01723b9fe2e3410e0f358cab2f22848b08d0)) by [@Pijukatel](https://github.com/Pijukatel), closes [#687](https://github.com/apify/crawlee-python/issues/687)
@@ -355,6 +421,8 @@ All notable changes to this project will be documented in this file.
 
 ## [0.4.0](https://github.com/apify/crawlee-python/releases/tag/v0.4.0) (2024-11-01)
 
+- Check out the [Upgrading guide](https://crawlee.dev/python/docs/upgrading/upgrading-to-v0x#upgrading-to-v04) to ensure a smooth update.
+
 ### 🚀 Features
 
 - [**breaking**] Add headers in unique key computation ([#609](https://github.com/apify/crawlee-python/pull/609)) ([6c4746f](https://github.com/apify/crawlee-python/commit/6c4746fa8ff86952a812b32a1d70dc910e76b43e)) by [@Prathamesh010](https://github.com/Prathamesh010), closes [#548](https://github.com/apify/crawlee-python/issues/548)
@@ -464,6 +532,8 @@ All notable changes to this project will be documented in this file.
 
 ## [0.3.0](https://github.com/apify/crawlee-python/releases/tag/v0.3.0) (2024-08-27)
 
+- Check out the [Upgrading guide](https://crawlee.dev/python/docs/upgrading/upgrading-to-v0x#upgrading-to-v03) to ensure a smooth update.
+
 ### 🚀 Features
 
 - Implement ParselCrawler that adds support for Parsel ([#348](https://github.com/apify/crawlee-python/pull/348)) ([a3832e5](https://github.com/apify/crawlee-python/commit/a3832e527f022f32cce4a80055da3b7967b74522)) by [@asymness](https://github.com/asymness), closes [#335](https://github.com/apify/crawlee-python/issues/335)

{crawlee-0.6.13b41 → crawlee-1.1.0}/CONTRIBUTING.md

@@ -103,7 +103,7 @@ make run-docs
 Publishing new versions to [PyPI](https://pypi.org/project/crawlee) is automated through GitHub Actions.
 
 - **Beta releases**: On each commit to the master branch, a new beta release is automatically published. The version number is determined based on the latest release and conventional commits. The beta version suffix is incremented by 1 from the last beta release on PyPI.
-- **Stable releases**: A stable version release may be created by triggering the `release` GitHub Actions workflow. The version number is determined based on the latest release and conventional commits (`auto` release type), or it may be overriden using the `custom` release type.
+- **Stable releases**: A stable version release may be created by triggering the `release` GitHub Actions workflow. The version number is determined based on the latest release and conventional commits (`auto` release type), or it may be overridden using the `custom` release type.
 
 ### Publishing to PyPI manually
 

{crawlee-0.6.13b41 → crawlee-1.1.0}/Makefile

@@ -38,7 +38,7 @@ unit-tests-cov:
 	uv run pytest --numprocesses=auto -vv --cov=src/crawlee --cov-append --cov-report=html tests/unit -m "not run_alone"
 
 e2e-templates-tests $(args):
-	uv run pytest --numprocesses=$(E2E_TESTS_CONCURRENCY) -vv tests/e2e/project_template "$(args)"
+	uv run pytest --numprocesses=$(E2E_TESTS_CONCURRENCY) -vv tests/e2e/project_template "$(args)" --timeout=600
 
 format:
 	uv run ruff check --fix

{crawlee-0.6.13b41 → crawlee-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crawlee
-Version: 0.6.13b41
+Version: 1.1.0
 Summary: Crawlee for Python
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://crawlee.dev/python/docs/changelog
@@ -223,15 +223,16 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Software Development :: Libraries
 Requires-Python: >=3.10
 Requires-Dist: cachetools>=5.5.0
 Requires-Dist: colorama>=0.4.0
-Requires-Dist: impit>=0.6.1
+Requires-Dist: impit>=0.8.0
 Requires-Dist: more-itertools>=10.2.0
 Requires-Dist: protego>=0.5.0
 Requires-Dist: psutil>=6.0.0
-Requires-Dist: pydantic-settings!=2.7.0,!=2.7.1,!=2.8.0,>=2.2.0
+Requires-Dist: pydantic-settings>=2.12.0
 Requires-Dist: pydantic>=2.11.0
 Requires-Dist: pyee>=9.0.0
 Requires-Dist: tldextract>=5.1.0
@@ -244,7 +245,9 @@ Requires-Dist: jaro-winkler>=2.0.3; extra == 'adaptive-crawler'
 Requires-Dist: playwright>=1.27.0; extra == 'adaptive-crawler'
 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: beautifulsoup4[lxml]>=4.12.0; extra == 'all'
 Requires-Dist: browserforge>=1.2.3; extra == 'all'
 Requires-Dist: cookiecutter>=2.6.0; extra == 'all'
@@ -261,8 +264,10 @@ Requires-Dist: opentelemetry-sdk>=1.34.1; extra == 'all'
 Requires-Dist: opentelemetry-semantic-conventions>=0.54; extra == 'all'
 Requires-Dist: parsel>=1.10.0; extra == 'all'
 Requires-Dist: playwright>=1.27.0; extra == 'all'
+Requires-Dist: redis[hiredis]>=7.0.0; extra == 'all'
 Requires-Dist: rich>=13.9.0; extra == 'all'
 Requires-Dist: scikit-learn>=1.6.0; extra == 'all'
+Requires-Dist: sqlalchemy[asyncio]<3.0.0,>=2.0.0; extra == 'all'
 Requires-Dist: typer>=0.12.0; extra == 'all'
 Requires-Dist: wrapt>=1.17.0; extra == 'all'
 Provides-Extra: beautifulsoup
@@ -293,6 +298,14 @@ Provides-Extra: playwright
 Requires-Dist: apify-fingerprint-datapoints>=0.0.2; extra == 'playwright'
 Requires-Dist: browserforge>=1.2.3; extra == 'playwright'
 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: sqlalchemy[asyncio]<3.0.0,>=2.0.0; extra == 'sql-postgres'
+Provides-Extra: sql-sqlite
+Requires-Dist: aiosqlite>=0.21.0; extra == 'sql-sqlite'
+Requires-Dist: sqlalchemy[asyncio]<3.0.0,>=2.0.0; extra == 'sql-sqlite'
 Description-Content-Type: text/markdown
 
 <h1 align="center">
@@ -327,8 +340,6 @@ Description-Content-Type: text/markdown
 
 Crawlee covers your crawling and scraping end-to-end and **helps you build reliable scrapers. Fast.**
 
-> 🚀 Crawlee for Python is open to early adopters!
-
 Your crawlers will appear almost human-like and fly under the radar of modern bot protections even with the default configuration. Crawlee gives you the tools to crawl the web for links, scrape data and persistently store it in machine-readable formats, without having to worry about the technical details. And thanks to rich configuration options, you can tweak almost any aspect of Crawlee to suit your project's needs if the default settings don't cut it.
 
 > 👉 **View full documentation, guides and examples on the [Crawlee project website](https://crawlee.dev/python/)** 👈

{crawlee-0.6.13b41 → crawlee-1.1.0}/README.md

@@ -30,8 +30,6 @@
 
 Crawlee covers your crawling and scraping end-to-end and **helps you build reliable scrapers. Fast.**
 
-> 🚀 Crawlee for Python is open to early adopters!
-
 Your crawlers will appear almost human-like and fly under the radar of modern bot protections even with the default configuration. Crawlee gives you the tools to crawl the web for links, scrape data and persistently store it in machine-readable formats, without having to worry about the technical details. And thanks to rich configuration options, you can tweak almost any aspect of Crawlee to suit your project's needs if the default settings don't cut it.
 
 > 👉 **View full documentation, guides and examples on the [Crawlee project website](https://crawlee.dev/python/)** 👈

{crawlee-0.6.13b41 → crawlee-1.1.0}/docs/deployment/apify_platform.mdx

@@ -99,7 +99,7 @@ apify run
 For running Crawlee code as an Actor on [Apify platform](https://apify.com/actors) you need to wrap the body of the main function of your crawler with `async with Actor`.
 
 :::info NOTE
-Adding `async with Actor` is the only important thing needed to run it on Apify platform as an Actor. It is needed to initialize your Actor (e.g. to set the correct storage implementation) and to correctly handle exitting the process.
+Adding `async with Actor` is the only important thing needed to run it on Apify platform as an Actor. It is needed to initialize your Actor (e.g. to set the correct storage implementation) and to correctly handle exiting the process.
 :::
 
 Let's look at the `BeautifulSoupCrawler` example from the [Quick start](../quick-start) guide:

crawlee-1.1.0/docs/examples/code_examples/using_browser_profiles_chrome.py

@@ -0,0 +1,54 @@
+import asyncio
+import shutil
+from pathlib import Path
+from tempfile import TemporaryDirectory
+
+from crawlee.crawlers import PlaywrightCrawler, PlaywrightCrawlingContext
+
+# Profile name to use (usually 'Default' for single profile setups)
+PROFILE_NAME = 'Default'
+
+# Paths to Chrome profiles in your system (example for Windows)
+# Use `chrome://version/` to find your profile path
+PROFILE_PATH = Path(Path.home(), 'AppData', 'Local', 'Google', 'Chrome', 'User Data')
+
+
+async def main() -> None:
+    # Create a temporary folder to copy the profile to
+    with TemporaryDirectory(prefix='crawlee-') as tmpdirname:
+        tmp_profile_dir = Path(tmpdirname)
+
+        # Copy the profile to a temporary folder
+        shutil.copytree(
+            PROFILE_PATH / PROFILE_NAME,
+            tmp_profile_dir / PROFILE_NAME,
+            dirs_exist_ok=True,
+        )
+
+        crawler = PlaywrightCrawler(
+            headless=False,
+            # Use the installed Chrome browser
+            browser_type='chrome',
+            # Disable fingerprints to preserve profile identity
+            fingerprint_generator=None,
+            # Set user data directory to temp folder
+            user_data_dir=tmp_profile_dir,
+            browser_launch_options={
+                # Slow down actions to mimic human behavior
+                'slow_mo': 200,
+                'args': [
+                    # Use the specified profile
+                    f'--profile-directory={PROFILE_NAME}',
+                ],
+            },
+        )
+
+        @crawler.router.default_handler
+        async def default_handler(context: PlaywrightCrawlingContext) -> None:
+            context.log.info(f'Visiting {context.request.url}')
+
+        await crawler.run(['https://crawlee.dev/'])
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

crawlee-1.1.0/docs/examples/code_examples/using_browser_profiles_firefox.py

@@ -0,0 +1,42 @@
+import asyncio
+from pathlib import Path
+
+from crawlee.crawlers import PlaywrightCrawler, PlaywrightCrawlingContext
+
+# Replace this with your actual Firefox profile name
+# Find it at about:profiles in Firefox
+PROFILE_NAME = 'your-profile-name-here'
+
+# Paths to Firefox profiles in your system (example for Windows)
+# Use `about:profiles` to find your profile path
+PROFILE_PATH = Path(
+    Path.home(), 'AppData', 'Roaming', 'Mozilla', 'Firefox', 'Profiles', PROFILE_NAME
+)
+
+
+async def main() -> None:
+    crawler = PlaywrightCrawler(
+        # Use Firefox browser type
+        browser_type='firefox',
+        # Disable fingerprints to use the profile as is
+        fingerprint_generator=None,
+        headless=False,
+        # Path to your Firefox profile
+        user_data_dir=PROFILE_PATH,
+        browser_launch_options={
+            'args': [
+                # Required to avoid version conflicts
+                '--allow-downgrade'
+            ]
+        },
+    )
+
+    @crawler.router.default_handler
+    async def default_handler(context: PlaywrightCrawlingContext) -> None:
+        context.log.info(f'Visiting {context.request.url}')
+
+    await crawler.run(['https://crawlee.dev/'])
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

crawlee-1.1.0/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-0.6.13b41 → crawlee-1.1.0}/docs/examples/playwright_crawler_with_fingerprint_generator.mdx

@@ -1,5 +1,5 @@
 ---
-id: playwright-crawler-with-fingeprint-generator
+id: playwright-crawler-with-fingerprint-generator
 title: Playwright crawler with fingerprint generator
 ---
 

crawlee-1.1.0/docs/examples/using_browser_profile.mdx

@@ -0,0 +1,39 @@
+---
+id: using_browser_profile
+title: Using browser profile
+---
+
+import ApiLink from '@site/src/components/ApiLink';
+
+import CodeBlock from '@theme/CodeBlock';
+
+import ChromeProfileExample from '!!raw-loader!./code_examples/using_browser_profiles_chrome.py';
+import FirefoxProfileExample from '!!raw-loader!./code_examples/using_browser_profiles_firefox.py';
+
+This example demonstrates how to run <ApiLink to="class/PlaywrightCrawler">`PlaywrightCrawler`</ApiLink> using your local browser profile from [Chrome](https://www.google.com/intl/us/chrome/) or [Firefox](https://www.firefox.com/).
+
+Using browser profiles allows you to leverage existing login sessions, saved passwords, bookmarks, and other personalized browser data during crawling. This can be particularly useful for testing scenarios or when you need to access content that requires authentication.
+
+## Chrome browser
+
+To run <ApiLink to="class/PlaywrightCrawler">`PlaywrightCrawler`</ApiLink> with your Chrome profile, you need to know the path to your profile files. You can find this information by entering `chrome://version/` as a URL in your Chrome browser. If you have multiple profiles, pay attention to the profile name - if you only have one profile, it's always `Default`.
+
+:::warning Profile access limitation
+Due to [Chrome's security policies](https://developer.chrome.com/blog/remote-debugging-port), automation cannot use your main browsing profile directly. The example copies your profile to a temporary location as a workaround.
+:::
+
+Make sure you don't have any running Chrome browser processes before running this code:
+
+<CodeBlock className="language-python" language="python">
+    {ChromeProfileExample}
+</CodeBlock>
+
+## Firefox browser
+
+To find the path to your Firefox profile, enter `about:profiles` as a URL in your Firefox browser. Unlike Chrome, you can use your standard profile path directly without copying it first.
+
+Make sure you don't have any running Firefox browser processes before running this code:
+
+<CodeBlock className="language-python" language="python">
+    {FirefoxProfileExample}
+</CodeBlock>