crawlee 1.0.1b12__tar.gz → 1.0.2b1__tar.gz

{crawlee-1.0.1b12 → crawlee-1.0.2b1}/CHANGELOG.md

@@ -3,7 +3,11 @@
 All notable changes to this project will be documented in this file.
 
 <!-- git-cliff-unreleased-start -->
-## 1.0.1 - **not yet released**
+## 1.0.2 - **not yet released**
+
+
+<!-- git-cliff-unreleased-end -->
+## [1.0.1](https://github.com/apify/crawlee-python/releases/tag/v1.0.1) (2025-10-06)
 
 ### 🐛 Bug Fixes
 
@@ -11,7 +15,6 @@ All notable changes to this project will be documented in this file.
 - 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)
 
 
-<!-- git-cliff-unreleased-end -->
 ## [1.0.0](https://github.com/apify/crawlee-python/releases/tag/v1.0.0) (2025-09-29)
 
 ### 🚀 Features

{crawlee-1.0.1b12 → crawlee-1.0.2b1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crawlee
-Version: 1.0.1b12
+Version: 1.0.2b1
 Summary: Crawlee for Python
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://crawlee.dev/python/docs/changelog

crawlee-1.0.2b1/docs/examples/code_examples/using_browser_profiles_chrome.py

@@ -0,0 +1,56 @@
+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 chromium for Chrome compatibility
+            browser_type='chromium',
+            # 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={
+                # Use installed Chrome browser
+                'channel': 'chrome',
+                # 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-1.0.2b1/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-1.0.2b1/docs/examples/using_browser_profile.mdx

@@ -0,0 +1,41 @@
+---
+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`.
+
+You also need to use the [`channel`](https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-option-channel) parameter in `browser_launch_options` to use the Chrome browser installed on your system instead of Playwright's Chromium.
+
+:::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>

{crawlee-1.0.1b12 → crawlee-1.0.2b1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "crawlee"
-version = "1.0.1b12"
+version = "1.0.2b1"
 description = "Crawlee for Python"
 authors = [{ name = "Apify Technologies s.r.o.", email = "support@apify.com" }]
 license = { file = "LICENSE" }

{crawlee-1.0.1b12 → crawlee-1.0.2b1}/uv.lock

@@ -680,7 +680,7 @@ toml = [
 
 [[package]]
 name = "crawlee"
-version = "1.0.1b12"
+version = "1.0.2b1"
 source = { editable = "." }
 dependencies = [
     { name = "cachetools" },

{crawlee-1.0.1b12 → crawlee-1.0.2b1}/website/package.json

@@ -21,8 +21,8 @@
         "@docusaurus/module-type-aliases": "3.9.1",
         "@docusaurus/types": "3.9.1",
         "@types/react": "^19.0.0",
-        "@typescript-eslint/eslint-plugin": "8.45.0",
-        "@typescript-eslint/parser": "8.45.0",
+        "@typescript-eslint/eslint-plugin": "8.46.0",
+        "@typescript-eslint/parser": "8.46.0",
         "eslint": "8.57.0",
         "eslint-plugin-react": "7.37.5",
         "eslint-plugin-react-hooks": "6.1.0",

{crawlee-1.0.1b12 → crawlee-1.0.2b1}/website/yarn.lock

@@ -4982,106 +4982,106 @@ __metadata:
   languageName: node
   linkType: hard
 
-"@typescript-eslint/eslint-plugin@npm:8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/eslint-plugin@npm:8.45.0"
+"@typescript-eslint/eslint-plugin@npm:8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/eslint-plugin@npm:8.46.0"
   dependencies:
     "@eslint-community/regexpp": "npm:^4.10.0"
-    "@typescript-eslint/scope-manager": "npm:8.45.0"
-    "@typescript-eslint/type-utils": "npm:8.45.0"
-    "@typescript-eslint/utils": "npm:8.45.0"
-    "@typescript-eslint/visitor-keys": "npm:8.45.0"
+    "@typescript-eslint/scope-manager": "npm:8.46.0"
+    "@typescript-eslint/type-utils": "npm:8.46.0"
+    "@typescript-eslint/utils": "npm:8.46.0"
+    "@typescript-eslint/visitor-keys": "npm:8.46.0"
     graphemer: "npm:^1.4.0"
     ignore: "npm:^7.0.0"
     natural-compare: "npm:^1.4.0"
     ts-api-utils: "npm:^2.1.0"
   peerDependencies:
-    "@typescript-eslint/parser": ^8.45.0
+    "@typescript-eslint/parser": ^8.46.0
     eslint: ^8.57.0 || ^9.0.0
     typescript: ">=4.8.4 <6.0.0"
-  checksum: 10c0/0c60a0e5d07fa8618348db38b5a81e66143d528e1b3cdb5678bbc6c60590cd559b27c98c36f5663230fc4cf6920dff2cd604de30b58df26a37fcfcc5dc1dbd45
+  checksum: 10c0/9de2b2127b977b0d73733042602a744e5b69bfe906c6dac424123ff9726816dcc4bb3d4ba470bc1fc5c741421f53274a3a896c09fbb50e298352d4a72011b2c2
   languageName: node
   linkType: hard
 
-"@typescript-eslint/parser@npm:8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/parser@npm:8.45.0"
+"@typescript-eslint/parser@npm:8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/parser@npm:8.46.0"
   dependencies:
-    "@typescript-eslint/scope-manager": "npm:8.45.0"
-    "@typescript-eslint/types": "npm:8.45.0"
-    "@typescript-eslint/typescript-estree": "npm:8.45.0"
-    "@typescript-eslint/visitor-keys": "npm:8.45.0"
+    "@typescript-eslint/scope-manager": "npm:8.46.0"
+    "@typescript-eslint/types": "npm:8.46.0"
+    "@typescript-eslint/typescript-estree": "npm:8.46.0"
+    "@typescript-eslint/visitor-keys": "npm:8.46.0"
     debug: "npm:^4.3.4"
   peerDependencies:
     eslint: ^8.57.0 || ^9.0.0
     typescript: ">=4.8.4 <6.0.0"
-  checksum: 10c0/8b419bcf795b112a39fcac05dcf147835059345b6399035ffa3f76a9d8e320f3fac79cae2fe4320dcda83fa059b017ca7626a7b4e3da08a614415c8867d169b8
+  checksum: 10c0/2e8c75b72c7cf170aca554014dbe30e85478d96799a2eb782c4fb61423c0c9e4416e98d6e7903601b1738ea1d0936417dbf61ac0293a0500f56e0eaeefbb2ecd
   languageName: node
   linkType: hard
 
-"@typescript-eslint/project-service@npm:8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/project-service@npm:8.45.0"
+"@typescript-eslint/project-service@npm:8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/project-service@npm:8.46.0"
   dependencies:
-    "@typescript-eslint/tsconfig-utils": "npm:^8.45.0"
-    "@typescript-eslint/types": "npm:^8.45.0"
+    "@typescript-eslint/tsconfig-utils": "npm:^8.46.0"
+    "@typescript-eslint/types": "npm:^8.46.0"
     debug: "npm:^4.3.4"
   peerDependencies:
     typescript: ">=4.8.4 <6.0.0"
-  checksum: 10c0/98af065a1a3ed9d3d1eb265e09d3e9c2ae676d500a8c1d764f5609fe2c1b86749516b709804eb814fae688be7809d11748b9ae691d43c28da51dac390ca81fa9
+  checksum: 10c0/c3164c795570edfa141917f3099724eca70383b016be1b08f656a491b459d68cf8e2547ac416d75048d3511ca5feaea0586aabad339e3dfe2ae6fddb650d7bc8
   languageName: node
   linkType: hard
 
-"@typescript-eslint/scope-manager@npm:8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/scope-manager@npm:8.45.0"
+"@typescript-eslint/scope-manager@npm:8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/scope-manager@npm:8.46.0"
   dependencies:
-    "@typescript-eslint/types": "npm:8.45.0"
-    "@typescript-eslint/visitor-keys": "npm:8.45.0"
-  checksum: 10c0/54cd36206f6b4fc8e1e48576ed01e0d6ab20c2a9c4c7d90d5cc3a2d317dd8a13abe148ffecf471b16f1224aba5749e0905472745626bef9ae5bed771776f4abe
+    "@typescript-eslint/types": "npm:8.46.0"
+    "@typescript-eslint/visitor-keys": "npm:8.46.0"
+  checksum: 10c0/9c242d1edd51247559f99dd8986bdb571db0a2a583a2d02ee8f5f346d265e956f413b442c27e1b02d55ce3944609f6593050ec657be672d9b24b7ed0a359a6ad
   languageName: node
   linkType: hard
 
-"@typescript-eslint/tsconfig-utils@npm:8.45.0, @typescript-eslint/tsconfig-utils@npm:^8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/tsconfig-utils@npm:8.45.0"
+"@typescript-eslint/tsconfig-utils@npm:8.46.0, @typescript-eslint/tsconfig-utils@npm:^8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/tsconfig-utils@npm:8.46.0"
   peerDependencies:
     typescript: ">=4.8.4 <6.0.0"
-  checksum: 10c0/227a9b7a5baaf35466fd369992cb933192515df1156ddf22f438deb344c2523695208e1036f5590b20603f31724de75a47fe0ee84e2fd4c8e9f3606f23f68112
+  checksum: 10c0/306b27c741709f2435dd1c7eabdf552775dff1b3ced01d791c5b9755394ceb3f37c9bcceec92adb6fe60c622523f9d47d9b0d9e515071f47d50527705a4706f7
   languageName: node
   linkType: hard
 
-"@typescript-eslint/type-utils@npm:8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/type-utils@npm:8.45.0"
+"@typescript-eslint/type-utils@npm:8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/type-utils@npm:8.46.0"
   dependencies:
-    "@typescript-eslint/types": "npm:8.45.0"
-    "@typescript-eslint/typescript-estree": "npm:8.45.0"
-    "@typescript-eslint/utils": "npm:8.45.0"
+    "@typescript-eslint/types": "npm:8.46.0"
+    "@typescript-eslint/typescript-estree": "npm:8.46.0"
+    "@typescript-eslint/utils": "npm:8.46.0"
     debug: "npm:^4.3.4"
     ts-api-utils: "npm:^2.1.0"
   peerDependencies:
     eslint: ^8.57.0 || ^9.0.0
     typescript: ">=4.8.4 <6.0.0"
-  checksum: 10c0/ce0f4c209c2418ebeb65e7de053499fb68bf6000bdd71068594fdb8c8ac3dbbd62935a3cea233989491f7da3ef5db87e7efd2910133c6abf6d0cbf57248f6442
+  checksum: 10c0/a0fa4617a998094bc217be1989b76a3e45c058117cda027a723ff6f98f15e5237abfa123284afbdea7f320b4da65e1053ed47c8a211dd012591908a9daa46f02
   languageName: node
   linkType: hard
 
-"@typescript-eslint/types@npm:8.45.0, @typescript-eslint/types@npm:^8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/types@npm:8.45.0"
-  checksum: 10c0/0213a0573c671d13bc91961a2b2e814ec7f6381ff093bce6704017bd96b2fc7fee25906c815cedb32a0601cf5071ca6c7c5f940d087c3b0d3dd7d4bc03478278
+"@typescript-eslint/types@npm:8.46.0, @typescript-eslint/types@npm:^8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/types@npm:8.46.0"
+  checksum: 10c0/2f986852139bcbe940b4aafe79bbd28dcca7176e95ba4e3880984ef58c81ad077ca9d9191aad56d2b1df6d16060f5744a96ab3118ddbc9766e5035ed470445c1
   languageName: node
   linkType: hard
 
-"@typescript-eslint/typescript-estree@npm:8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/typescript-estree@npm:8.45.0"
+"@typescript-eslint/typescript-estree@npm:8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/typescript-estree@npm:8.46.0"
   dependencies:
-    "@typescript-eslint/project-service": "npm:8.45.0"
-    "@typescript-eslint/tsconfig-utils": "npm:8.45.0"
-    "@typescript-eslint/types": "npm:8.45.0"
-    "@typescript-eslint/visitor-keys": "npm:8.45.0"
+    "@typescript-eslint/project-service": "npm:8.46.0"
+    "@typescript-eslint/tsconfig-utils": "npm:8.46.0"
+    "@typescript-eslint/types": "npm:8.46.0"
+    "@typescript-eslint/visitor-keys": "npm:8.46.0"
     debug: "npm:^4.3.4"
     fast-glob: "npm:^3.3.2"
     is-glob: "npm:^4.0.3"
@@ -5090,32 +5090,32 @@ __metadata:
     ts-api-utils: "npm:^2.1.0"
   peerDependencies:
     typescript: ">=4.8.4 <6.0.0"
-  checksum: 10c0/8c2f44a00fe859a6cd4b50157c484c5b6a1c7af5d48e89ae79c5f4924947964962fc8f478ad4c2ade788907fceee9b72d4e376508ea79b51392f91082a37d239
+  checksum: 10c0/39aed033dc23c3356e39891c9eba6dde0dc618406f0e13e9adc5967fb81790ec199b1d6eb1144e35ad13a0daaf72157f5f3fc7ac1b7c58d152ade68fe27ad221
   languageName: node
   linkType: hard
 
-"@typescript-eslint/utils@npm:8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/utils@npm:8.45.0"
+"@typescript-eslint/utils@npm:8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/utils@npm:8.46.0"
   dependencies:
     "@eslint-community/eslint-utils": "npm:^4.7.0"
-    "@typescript-eslint/scope-manager": "npm:8.45.0"
-    "@typescript-eslint/types": "npm:8.45.0"
-    "@typescript-eslint/typescript-estree": "npm:8.45.0"
+    "@typescript-eslint/scope-manager": "npm:8.46.0"
+    "@typescript-eslint/types": "npm:8.46.0"
+    "@typescript-eslint/typescript-estree": "npm:8.46.0"
   peerDependencies:
     eslint: ^8.57.0 || ^9.0.0
     typescript: ">=4.8.4 <6.0.0"
-  checksum: 10c0/b3c83a23813b15e20e303d7153789508c01e06dec355b1a80547c59aa36998d498102f45fcd13f111031fac57270608abb04d20560248d4448fd00b1cf4dc4ab
+  checksum: 10c0/77cc7dff9132d9f02e8766d128edbeb7c2f2b56f9ebdac7308e75a04924e2369857da27b23f0054476c9640609a9707b8dd8ca8b1c59a067e45f65bf5ef4cc1b
   languageName: node
   linkType: hard
 
-"@typescript-eslint/visitor-keys@npm:8.45.0":
-  version: 8.45.0
-  resolution: "@typescript-eslint/visitor-keys@npm:8.45.0"
+"@typescript-eslint/visitor-keys@npm:8.46.0":
+  version: 8.46.0
+  resolution: "@typescript-eslint/visitor-keys@npm:8.46.0"
   dependencies:
-    "@typescript-eslint/types": "npm:8.45.0"
+    "@typescript-eslint/types": "npm:8.46.0"
     eslint-visitor-keys: "npm:^4.2.1"
-  checksum: 10c0/119adcf50c902dad7f7757bcdd88fad0a23a171d309d9b7cefe78af12e451cf84c04ae611f4c31f7e23f16c2b47665ad92e6e5648fc77d542ef306f465bf1f29
+  checksum: 10c0/473dd4861b81238c1df10008b3b6d4684b2fa5ec4f3a8eeb544ea1278a5e2119f839447d16653ea3070164d7e742e3516fe9b0faf16e12a457fa26d5e14a7498
   languageName: node
   linkType: hard
 
@@ -6994,8 +6994,8 @@ __metadata:
     "@mermaid-js/layout-elk": "npm:^0.2.0"
     "@signalwire/docusaurus-plugin-llms-txt": "npm:^1.2.1"
     "@types/react": "npm:^19.0.0"
-    "@typescript-eslint/eslint-plugin": "npm:8.45.0"
-    "@typescript-eslint/parser": "npm:8.45.0"
+    "@typescript-eslint/eslint-plugin": "npm:8.46.0"
+    "@typescript-eslint/parser": "npm:8.46.0"
     axios: "npm:^1.5.0"
     buffer: "npm:^6.0.3"
     clsx: "npm:^2.0.0"