diff --git a/CHANGELOG.md b/CHANGELOG.md index 3e8942ceed84..31b27e64d302 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,26 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Bug Fixes + +* **adaptive-crawler:** log only once for the committed request handler execution ([#2524](https://github.com/apify/crawlee/issues/2524)) ([533bd3f](https://github.com/apify/crawlee/commit/533bd3f04671d54273f0861664d316269d08fbfb)) +* increase timeout for retiring inactive browsers ([#2523](https://github.com/apify/crawlee/issues/2523)) ([195f176](https://github.com/apify/crawlee/commit/195f1766a03293db19caa33f9fc3d4ab08081f71)) +* respect implicit router when no `requestHandler` is provided in `AdaptiveCrawler` ([#2518](https://github.com/apify/crawlee/issues/2518)) ([31083aa](https://github.com/apify/crawlee/commit/31083aa27ddd51827f73c7ac4290379ec7a81283)) +* revert the scaling steps back to 5% ([5bf32f8](https://github.com/apify/crawlee/commit/5bf32f855ad84037e68dd9053930fa7be4267cac)) + + +### Features + +* add `waitForSelector` context helper + `parseWithCheerio` in adaptive crawler ([#2522](https://github.com/apify/crawlee/issues/2522)) ([6f88e73](https://github.com/apify/crawlee/commit/6f88e738d43ab4774dc4ef3f78775a5d88728e0d)) +* log desired concurrency in the default status message ([9f0b796](https://github.com/apify/crawlee/commit/9f0b79684d9e27e6ba29634e7da2e9a095367eda)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) diff --git a/lerna.json b/lerna.json index b8e1efcbbcb6..23a7a52d5dd5 100644 --- a/lerna.json +++ b/lerna.json @@ -1,17 +1,22 @@ { - "packages": ["packages/*"], - "version": "3.10.2", - "command": { - "version": { - "conventionalCommits": true, - "createRelease": "github", - "message": "chore(release): %s" - }, - "publish": { - "assets": [] - } - }, - "npmClient": "yarn", - "useNx": false, - "ignoreChanges": ["**/test/**", "**/*.md"] -} + "packages": [ + "packages/*" + ], + "version": "3.10.3", + "command": { + "version": { + "conventionalCommits": true, + "createRelease": "github", + "message": "chore(release): %s" + }, + "publish": { + "assets": [] + } + }, + "npmClient": "yarn", + "useNx": false, + "ignoreChanges": [ + "**/test/**", + "**/*.md" + ] +} \ No newline at end of file diff --git a/packages/basic-crawler/CHANGELOG.md b/packages/basic-crawler/CHANGELOG.md index d1e832b15ee6..6bb3fc86af25 100644 --- a/packages/basic-crawler/CHANGELOG.md +++ b/packages/basic-crawler/CHANGELOG.md @@ -3,6 +3,17 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Features + +* log desired concurrency in the default status message ([9f0b796](https://github.com/apify/crawlee/commit/9f0b79684d9e27e6ba29634e7da2e9a095367eda)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/basic diff --git a/packages/basic-crawler/package.json b/packages/basic-crawler/package.json index 18ed080bb330..f800f143c7d2 100644 --- a/packages/basic-crawler/package.json +++ b/packages/basic-crawler/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/basic", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -48,9 +48,9 @@ "@apify/log": "^2.4.0", "@apify/timeout": "^0.3.0", "@apify/utilities": "^2.7.10", - "@crawlee/core": "3.10.2", - "@crawlee/types": "3.10.2", - "@crawlee/utils": "3.10.2", + "@crawlee/core": "^3.10.3", + "@crawlee/types": "^3.10.3", + "@crawlee/utils": "^3.10.3", "csv-stringify": "^6.2.0", "fs-extra": "^11.0.0", "got-scraping": "^4.0.0", diff --git a/packages/browser-crawler/CHANGELOG.md b/packages/browser-crawler/CHANGELOG.md index 38081ee08b06..a6241e0b847a 100644 --- a/packages/browser-crawler/CHANGELOG.md +++ b/packages/browser-crawler/CHANGELOG.md @@ -3,6 +3,14 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + +**Note:** Version bump only for package @crawlee/browser + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/browser diff --git a/packages/browser-crawler/package.json b/packages/browser-crawler/package.json index 9e6aa3c30b6f..1c86e66fb332 100644 --- a/packages/browser-crawler/package.json +++ b/packages/browser-crawler/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/browser", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -54,10 +54,10 @@ }, "dependencies": { "@apify/timeout": "^0.3.0", - "@crawlee/basic": "3.10.2", - "@crawlee/browser-pool": "3.10.2", - "@crawlee/types": "3.10.2", - "@crawlee/utils": "3.10.2", + "@crawlee/basic": "^3.10.3", + "@crawlee/browser-pool": "^3.10.3", + "@crawlee/types": "^3.10.3", + "@crawlee/utils": "^3.10.3", "ow": "^0.28.1", "tslib": "^2.4.0", "type-fest": "^4.0.0" diff --git a/packages/browser-pool/CHANGELOG.md b/packages/browser-pool/CHANGELOG.md index 3701e68eb762..dad7e085a5b6 100644 --- a/packages/browser-pool/CHANGELOG.md +++ b/packages/browser-pool/CHANGELOG.md @@ -3,6 +3,17 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Bug Fixes + +* increase timeout for retiring inactive browsers ([#2523](https://github.com/apify/crawlee/issues/2523)) ([195f176](https://github.com/apify/crawlee/commit/195f1766a03293db19caa33f9fc3d4ab08081f71)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/browser-pool diff --git a/packages/browser-pool/package.json b/packages/browser-pool/package.json index ec46a566c911..0672bf03e4c7 100644 --- a/packages/browser-pool/package.json +++ b/packages/browser-pool/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/browser-pool", - "version": "3.10.2", + "version": "3.10.3", "description": "Rotate multiple browsers using popular automation libraries such as Playwright or Puppeteer.", "engines": { "node": ">=16.0.0" @@ -38,8 +38,8 @@ "dependencies": { "@apify/log": "^2.4.0", "@apify/timeout": "^0.3.0", - "@crawlee/core": "3.10.2", - "@crawlee/types": "3.10.2", + "@crawlee/core": "^3.10.3", + "@crawlee/types": "^3.10.3", "fingerprint-generator": "^2.0.6", "fingerprint-injector": "^2.0.5", "lodash.merge": "^4.6.2", diff --git a/packages/cheerio-crawler/CHANGELOG.md b/packages/cheerio-crawler/CHANGELOG.md index 09b32128d957..6ba81c8de7a7 100644 --- a/packages/cheerio-crawler/CHANGELOG.md +++ b/packages/cheerio-crawler/CHANGELOG.md @@ -3,6 +3,17 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Features + +* add `waitForSelector` context helper + `parseWithCheerio` in adaptive crawler ([#2522](https://github.com/apify/crawlee/issues/2522)) ([6f88e73](https://github.com/apify/crawlee/commit/6f88e738d43ab4774dc4ef3f78775a5d88728e0d)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/cheerio diff --git a/packages/cheerio-crawler/package.json b/packages/cheerio-crawler/package.json index b106f00b537e..a6e65094855c 100644 --- a/packages/cheerio-crawler/package.json +++ b/packages/cheerio-crawler/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/cheerio", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -53,9 +53,9 @@ "access": "public" }, "dependencies": { - "@crawlee/http": "3.10.2", - "@crawlee/types": "3.10.2", - "@crawlee/utils": "3.10.2", + "@crawlee/http": "^3.10.3", + "@crawlee/types": "^3.10.3", + "@crawlee/utils": "^3.10.3", "cheerio": "^1.0.0-rc.12", "htmlparser2": "^9.0.0", "tslib": "^2.4.0" diff --git a/packages/cli/CHANGELOG.md b/packages/cli/CHANGELOG.md index 249b3b1e2e46..bf63b6e652d1 100644 --- a/packages/cli/CHANGELOG.md +++ b/packages/cli/CHANGELOG.md @@ -3,6 +3,14 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + +**Note:** Version bump only for package @crawlee/cli + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/cli diff --git a/packages/cli/package.json b/packages/cli/package.json index 23b8b32c7f2c..bc3ca0e40e9a 100644 --- a/packages/cli/package.json +++ b/packages/cli/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/cli", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -51,7 +51,7 @@ "access": "public" }, "dependencies": { - "@crawlee/templates": "3.10.2", + "@crawlee/templates": "^3.10.3", "ansi-colors": "^4.1.3", "fs-extra": "^11.0.0", "inquirer": "^8.2.4", diff --git a/packages/core/CHANGELOG.md b/packages/core/CHANGELOG.md index 0d9c10a6a7cb..65955f22722d 100644 --- a/packages/core/CHANGELOG.md +++ b/packages/core/CHANGELOG.md @@ -3,6 +3,23 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Bug Fixes + +* respect implicit router when no `requestHandler` is provided in `AdaptiveCrawler` ([#2518](https://github.com/apify/crawlee/issues/2518)) ([31083aa](https://github.com/apify/crawlee/commit/31083aa27ddd51827f73c7ac4290379ec7a81283)) +* revert the scaling steps back to 5% ([5bf32f8](https://github.com/apify/crawlee/commit/5bf32f855ad84037e68dd9053930fa7be4267cac)) + + +### Features + +* add `waitForSelector` context helper + `parseWithCheerio` in adaptive crawler ([#2522](https://github.com/apify/crawlee/issues/2522)) ([6f88e73](https://github.com/apify/crawlee/commit/6f88e738d43ab4774dc4ef3f78775a5d88728e0d)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/core diff --git a/packages/core/package.json b/packages/core/package.json index 4cd5639893bd..a270192113f5 100644 --- a/packages/core/package.json +++ b/packages/core/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/core", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -59,9 +59,9 @@ "@apify/pseudo_url": "^2.0.30", "@apify/timeout": "^0.3.0", "@apify/utilities": "^2.7.10", - "@crawlee/memory-storage": "3.10.2", - "@crawlee/types": "3.10.2", - "@crawlee/utils": "3.10.2", + "@crawlee/memory-storage": "^3.10.3", + "@crawlee/types": "^3.10.3", + "@crawlee/utils": "^3.10.3", "@sapphire/async-queue": "^1.5.1", "@types/tough-cookie": "^4.0.2", "@vladfrangu/async_event_emitter": "^2.2.2", diff --git a/packages/crawlee/CHANGELOG.md b/packages/crawlee/CHANGELOG.md index e32f420c25c7..bd50e53370e1 100644 --- a/packages/crawlee/CHANGELOG.md +++ b/packages/crawlee/CHANGELOG.md @@ -3,6 +3,14 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + +**Note:** Version bump only for package crawlee + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package crawlee diff --git a/packages/crawlee/package.json b/packages/crawlee/package.json index 8516befe5415..eba030ff730e 100644 --- a/packages/crawlee/package.json +++ b/packages/crawlee/package.json @@ -1,6 +1,6 @@ { "name": "crawlee", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -54,18 +54,18 @@ "access": "public" }, "dependencies": { - "@crawlee/basic": "3.10.2", - "@crawlee/browser": "3.10.2", - "@crawlee/browser-pool": "3.10.2", - "@crawlee/cheerio": "3.10.2", - "@crawlee/cli": "3.10.2", - "@crawlee/core": "3.10.2", - "@crawlee/http": "3.10.2", - "@crawlee/jsdom": "3.10.2", - "@crawlee/linkedom": "3.10.2", - "@crawlee/playwright": "3.10.2", - "@crawlee/puppeteer": "3.10.2", - "@crawlee/utils": "3.10.2", + "@crawlee/basic": "^3.10.3", + "@crawlee/browser": "^3.10.3", + "@crawlee/browser-pool": "^3.10.3", + "@crawlee/cheerio": "^3.10.3", + "@crawlee/cli": "^3.10.3", + "@crawlee/core": "^3.10.3", + "@crawlee/http": "^3.10.3", + "@crawlee/jsdom": "^3.10.3", + "@crawlee/linkedom": "^3.10.3", + "@crawlee/playwright": "^3.10.3", + "@crawlee/puppeteer": "^3.10.3", + "@crawlee/utils": "^3.10.3", "import-local": "^3.1.0", "tslib": "^2.4.0" }, diff --git a/packages/http-crawler/CHANGELOG.md b/packages/http-crawler/CHANGELOG.md index 61c30980216a..58e8ccd24132 100644 --- a/packages/http-crawler/CHANGELOG.md +++ b/packages/http-crawler/CHANGELOG.md @@ -3,6 +3,17 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Features + +* add `waitForSelector` context helper + `parseWithCheerio` in adaptive crawler ([#2522](https://github.com/apify/crawlee/issues/2522)) ([6f88e73](https://github.com/apify/crawlee/commit/6f88e738d43ab4774dc4ef3f78775a5d88728e0d)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/http diff --git a/packages/http-crawler/package.json b/packages/http-crawler/package.json index c42afc96daaa..613fc5d8478f 100644 --- a/packages/http-crawler/package.json +++ b/packages/http-crawler/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/http", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -55,9 +55,9 @@ "dependencies": { "@apify/timeout": "^0.3.0", "@apify/utilities": "^2.7.10", - "@crawlee/basic": "3.10.2", - "@crawlee/types": "3.10.2", - "@crawlee/utils": "3.10.2", + "@crawlee/basic": "^3.10.3", + "@crawlee/types": "^3.10.3", + "@crawlee/utils": "^3.10.3", "@types/content-type": "^1.1.5", "cheerio": "^1.0.0-rc.12", "content-type": "^1.0.4", diff --git a/packages/jsdom-crawler/CHANGELOG.md b/packages/jsdom-crawler/CHANGELOG.md index 30e3d93aae66..4750f97ee992 100644 --- a/packages/jsdom-crawler/CHANGELOG.md +++ b/packages/jsdom-crawler/CHANGELOG.md @@ -3,6 +3,17 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Features + +* add `waitForSelector` context helper + `parseWithCheerio` in adaptive crawler ([#2522](https://github.com/apify/crawlee/issues/2522)) ([6f88e73](https://github.com/apify/crawlee/commit/6f88e738d43ab4774dc4ef3f78775a5d88728e0d)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/jsdom diff --git a/packages/jsdom-crawler/package.json b/packages/jsdom-crawler/package.json index 58c9a7923cd6..19566b7407c7 100644 --- a/packages/jsdom-crawler/package.json +++ b/packages/jsdom-crawler/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/jsdom", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -55,8 +55,8 @@ "dependencies": { "@apify/timeout": "^0.3.0", "@apify/utilities": "^2.7.10", - "@crawlee/http": "3.10.2", - "@crawlee/types": "3.10.2", + "@crawlee/http": "^3.10.3", + "@crawlee/types": "^3.10.3", "@types/jsdom": "^21.0.0", "cheerio": "^1.0.0-rc.12", "jsdom": "^24.0.0", diff --git a/packages/linkedom-crawler/CHANGELOG.md b/packages/linkedom-crawler/CHANGELOG.md index ca4b220b78a7..b185fd68e127 100644 --- a/packages/linkedom-crawler/CHANGELOG.md +++ b/packages/linkedom-crawler/CHANGELOG.md @@ -3,6 +3,17 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Features + +* add `waitForSelector` context helper + `parseWithCheerio` in adaptive crawler ([#2522](https://github.com/apify/crawlee/issues/2522)) ([6f88e73](https://github.com/apify/crawlee/commit/6f88e738d43ab4774dc4ef3f78775a5d88728e0d)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/linkedom diff --git a/packages/linkedom-crawler/package.json b/packages/linkedom-crawler/package.json index d6e68df1f60e..aa8341d1df9a 100644 --- a/packages/linkedom-crawler/package.json +++ b/packages/linkedom-crawler/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/linkedom", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -55,8 +55,8 @@ "dependencies": { "@apify/timeout": "^0.3.0", "@apify/utilities": "^2.7.10", - "@crawlee/http": "3.10.2", - "@crawlee/types": "3.10.2", + "@crawlee/http": "^3.10.3", + "@crawlee/types": "^3.10.3", "linkedom": "^0.18.0", "ow": "^0.28.2", "tslib": "^2.4.0" diff --git a/packages/memory-storage/CHANGELOG.md b/packages/memory-storage/CHANGELOG.md index 4fffeeab5036..9d189d6018df 100644 --- a/packages/memory-storage/CHANGELOG.md +++ b/packages/memory-storage/CHANGELOG.md @@ -3,6 +3,14 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + +**Note:** Version bump only for package @crawlee/memory-storage + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) diff --git a/packages/memory-storage/package.json b/packages/memory-storage/package.json index 74351b184778..4336759c346d 100644 --- a/packages/memory-storage/package.json +++ b/packages/memory-storage/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/memory-storage", - "version": "3.10.2", + "version": "3.10.3", "description": "A simple in-memory storage implementation of the Apify API", "engines": { "node": ">= 16" @@ -49,7 +49,7 @@ }, "dependencies": { "@apify/log": "^2.4.0", - "@crawlee/types": "3.10.2", + "@crawlee/types": "^3.10.3", "@sapphire/async-queue": "^1.5.0", "@sapphire/shapeshift": "^3.0.0", "content-type": "^1.0.4", diff --git a/packages/playwright-crawler/CHANGELOG.md b/packages/playwright-crawler/CHANGELOG.md index 096efb25daa8..24743eb6a6fe 100644 --- a/packages/playwright-crawler/CHANGELOG.md +++ b/packages/playwright-crawler/CHANGELOG.md @@ -3,6 +3,23 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Bug Fixes + +* **adaptive-crawler:** log only once for the committed request handler execution ([#2524](https://github.com/apify/crawlee/issues/2524)) ([533bd3f](https://github.com/apify/crawlee/commit/533bd3f04671d54273f0861664d316269d08fbfb)) +* respect implicit router when no `requestHandler` is provided in `AdaptiveCrawler` ([#2518](https://github.com/apify/crawlee/issues/2518)) ([31083aa](https://github.com/apify/crawlee/commit/31083aa27ddd51827f73c7ac4290379ec7a81283)) + + +### Features + +* add `waitForSelector` context helper + `parseWithCheerio` in adaptive crawler ([#2522](https://github.com/apify/crawlee/issues/2522)) ([6f88e73](https://github.com/apify/crawlee/commit/6f88e738d43ab4774dc4ef3f78775a5d88728e0d)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/playwright diff --git a/packages/playwright-crawler/package.json b/packages/playwright-crawler/package.json index 9a34767688fa..ae38ac1e53f0 100644 --- a/packages/playwright-crawler/package.json +++ b/packages/playwright-crawler/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/playwright", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -56,11 +56,11 @@ "@apify/datastructures": "^2.0.0", "@apify/log": "^2.4.0", "@apify/timeout": "^0.3.1", - "@crawlee/browser": "3.10.2", - "@crawlee/browser-pool": "3.10.2", - "@crawlee/core": "3.10.2", - "@crawlee/types": "3.10.2", - "@crawlee/utils": "3.10.2", + "@crawlee/browser": "^3.10.3", + "@crawlee/browser-pool": "^3.10.3", + "@crawlee/core": "^3.10.3", + "@crawlee/types": "^3.10.3", + "@crawlee/utils": "^3.10.3", "cheerio": "^1.0.0-rc.12", "idcac-playwright": "^0.1.2", "jquery": "^3.6.0", diff --git a/packages/puppeteer-crawler/CHANGELOG.md b/packages/puppeteer-crawler/CHANGELOG.md index 88d9d840a6bb..d514d7d82f33 100644 --- a/packages/puppeteer-crawler/CHANGELOG.md +++ b/packages/puppeteer-crawler/CHANGELOG.md @@ -3,6 +3,17 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Features + +* add `waitForSelector` context helper + `parseWithCheerio` in adaptive crawler ([#2522](https://github.com/apify/crawlee/issues/2522)) ([6f88e73](https://github.com/apify/crawlee/commit/6f88e738d43ab4774dc4ef3f78775a5d88728e0d)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/puppeteer diff --git a/packages/puppeteer-crawler/package.json b/packages/puppeteer-crawler/package.json index bd0ccc46eaa2..eaa94c137880 100644 --- a/packages/puppeteer-crawler/package.json +++ b/packages/puppeteer-crawler/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/puppeteer", - "version": "3.10.2", + "version": "3.10.3", "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.", "engines": { "node": ">=16.0.0" @@ -55,10 +55,10 @@ "dependencies": { "@apify/datastructures": "^2.0.0", "@apify/log": "^2.4.0", - "@crawlee/browser": "3.10.2", - "@crawlee/browser-pool": "3.10.2", - "@crawlee/types": "3.10.2", - "@crawlee/utils": "3.10.2", + "@crawlee/browser": "^3.10.3", + "@crawlee/browser-pool": "^3.10.3", + "@crawlee/types": "^3.10.3", + "@crawlee/utils": "^3.10.3", "cheerio": "^1.0.0-rc.12", "devtools-protocol": "*", "idcac-playwright": "^0.1.2", diff --git a/packages/templates/CHANGELOG.md b/packages/templates/CHANGELOG.md index 36785316b478..c60938610792 100644 --- a/packages/templates/CHANGELOG.md +++ b/packages/templates/CHANGELOG.md @@ -3,6 +3,14 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + +**Note:** Version bump only for package @crawlee/templates + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/templates diff --git a/packages/templates/package.json b/packages/templates/package.json index f5808170e0ca..f40dcc028f04 100644 --- a/packages/templates/package.json +++ b/packages/templates/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/templates", - "version": "3.10.2", + "version": "3.10.3", "description": "Templates for the crawlee projects", "engines": { "node": ">=16.0.0" diff --git a/packages/types/CHANGELOG.md b/packages/types/CHANGELOG.md index 220ecdf52d62..abd1e3a0017f 100644 --- a/packages/types/CHANGELOG.md +++ b/packages/types/CHANGELOG.md @@ -3,6 +3,14 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + +**Note:** Version bump only for package @crawlee/types + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) **Note:** Version bump only for package @crawlee/types diff --git a/packages/types/package.json b/packages/types/package.json index 811512a01be7..bcdc3d256d07 100644 --- a/packages/types/package.json +++ b/packages/types/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/types", - "version": "3.10.2", + "version": "3.10.3", "description": "Shared types for the crawlee projects", "engines": { "node": ">=16.0.0" diff --git a/packages/utils/CHANGELOG.md b/packages/utils/CHANGELOG.md index 6b993fb33262..4c89fe2b9d95 100644 --- a/packages/utils/CHANGELOG.md +++ b/packages/utils/CHANGELOG.md @@ -3,6 +3,17 @@ All notable changes to this project will be documented in this file. See [Conventional Commits](https://conventionalcommits.org) for commit guidelines. +## [3.10.3](https://github.com/apify/crawlee/compare/v3.10.2...v3.10.3) (2024-06-07) + + +### Bug Fixes + +* respect implicit router when no `requestHandler` is provided in `AdaptiveCrawler` ([#2518](https://github.com/apify/crawlee/issues/2518)) ([31083aa](https://github.com/apify/crawlee/commit/31083aa27ddd51827f73c7ac4290379ec7a81283)) + + + + + ## [3.10.2](https://github.com/apify/crawlee/compare/v3.10.1...v3.10.2) (2024-06-03) diff --git a/packages/utils/package.json b/packages/utils/package.json index 27c1fa6ff4e0..1717f0a93a2b 100644 --- a/packages/utils/package.json +++ b/packages/utils/package.json @@ -1,6 +1,6 @@ { "name": "@crawlee/utils", - "version": "3.10.2", + "version": "3.10.3", "description": "A set of shared utilities that can be used by crawlers", "engines": { "node": ">=16.0.0" @@ -49,7 +49,7 @@ "dependencies": { "@apify/log": "^2.4.0", "@apify/ps-tree": "^1.2.0", - "@crawlee/types": "3.10.2", + "@crawlee/types": "^3.10.3", "@types/sax": "^1.2.7", "cheerio": "^1.0.0-rc.12", "file-type": "^19.0.0", diff --git a/yarn.lock b/yarn.lock index 16467ae2fbff..83543a6e08ab 100644 --- a/yarn.lock +++ b/yarn.lock @@ -486,16 +486,16 @@ __metadata: languageName: node linkType: hard -"@crawlee/basic@npm:3.10.2, @crawlee/basic@workspace:packages/basic-crawler": +"@crawlee/basic@npm:^3.10.3, @crawlee/basic@workspace:packages/basic-crawler": version: 0.0.0-use.local resolution: "@crawlee/basic@workspace:packages/basic-crawler" dependencies: "@apify/log": "npm:^2.4.0" "@apify/timeout": "npm:^0.3.0" "@apify/utilities": "npm:^2.7.10" - "@crawlee/core": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" - "@crawlee/utils": "npm:3.10.2" + "@crawlee/core": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" + "@crawlee/utils": "npm:^3.10.3" csv-stringify: "npm:^6.2.0" fs-extra: "npm:^11.0.0" got-scraping: "npm:^4.0.0" @@ -506,14 +506,14 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/browser-pool@npm:3.10.2, @crawlee/browser-pool@workspace:packages/browser-pool": +"@crawlee/browser-pool@npm:^3.10.3, @crawlee/browser-pool@workspace:packages/browser-pool": version: 0.0.0-use.local resolution: "@crawlee/browser-pool@workspace:packages/browser-pool" dependencies: "@apify/log": "npm:^2.4.0" "@apify/timeout": "npm:^0.3.0" - "@crawlee/core": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" + "@crawlee/core": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" fingerprint-generator: "npm:^2.0.6" fingerprint-injector: "npm:^2.0.5" lodash.merge: "npm:^4.6.2" @@ -535,39 +535,39 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/browser@npm:3.10.2, @crawlee/browser@workspace:packages/browser-crawler": +"@crawlee/browser@npm:^3.10.3, @crawlee/browser@workspace:packages/browser-crawler": version: 0.0.0-use.local resolution: "@crawlee/browser@workspace:packages/browser-crawler" dependencies: "@apify/timeout": "npm:^0.3.0" - "@crawlee/basic": "npm:3.10.2" - "@crawlee/browser-pool": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" - "@crawlee/utils": "npm:3.10.2" + "@crawlee/basic": "npm:^3.10.3" + "@crawlee/browser-pool": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" + "@crawlee/utils": "npm:^3.10.3" ow: "npm:^0.28.1" tslib: "npm:^2.4.0" type-fest: "npm:^4.0.0" languageName: unknown linkType: soft -"@crawlee/cheerio@npm:3.10.2, @crawlee/cheerio@workspace:packages/cheerio-crawler": +"@crawlee/cheerio@npm:^3.10.3, @crawlee/cheerio@workspace:packages/cheerio-crawler": version: 0.0.0-use.local resolution: "@crawlee/cheerio@workspace:packages/cheerio-crawler" dependencies: - "@crawlee/http": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" - "@crawlee/utils": "npm:3.10.2" + "@crawlee/http": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" + "@crawlee/utils": "npm:^3.10.3" cheerio: "npm:^1.0.0-rc.12" htmlparser2: "npm:^9.0.0" tslib: "npm:^2.4.0" languageName: unknown linkType: soft -"@crawlee/cli@npm:3.10.2, @crawlee/cli@workspace:packages/cli": +"@crawlee/cli@npm:^3.10.3, @crawlee/cli@workspace:packages/cli": version: 0.0.0-use.local resolution: "@crawlee/cli@workspace:packages/cli" dependencies: - "@crawlee/templates": "npm:3.10.2" + "@crawlee/templates": "npm:^3.10.3" ansi-colors: "npm:^4.1.3" fs-extra: "npm:^11.0.0" inquirer: "npm:^8.2.4" @@ -579,7 +579,7 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/core@npm:3.10.2, @crawlee/core@npm:^3.9.0, @crawlee/core@workspace:packages/core": +"@crawlee/core@npm:^3.10.3, @crawlee/core@npm:^3.9.0, @crawlee/core@workspace:packages/core": version: 0.0.0-use.local resolution: "@crawlee/core@workspace:packages/core" dependencies: @@ -589,9 +589,9 @@ __metadata: "@apify/pseudo_url": "npm:^2.0.30" "@apify/timeout": "npm:^0.3.0" "@apify/utilities": "npm:^2.7.10" - "@crawlee/memory-storage": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" - "@crawlee/utils": "npm:3.10.2" + "@crawlee/memory-storage": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" + "@crawlee/utils": "npm:^3.10.3" "@sapphire/async-queue": "npm:^1.5.1" "@types/tough-cookie": "npm:^4.0.2" "@vladfrangu/async_event_emitter": "npm:^2.2.2" @@ -610,15 +610,15 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/http@npm:3.10.2, @crawlee/http@workspace:packages/http-crawler": +"@crawlee/http@npm:^3.10.3, @crawlee/http@workspace:packages/http-crawler": version: 0.0.0-use.local resolution: "@crawlee/http@workspace:packages/http-crawler" dependencies: "@apify/timeout": "npm:^0.3.0" "@apify/utilities": "npm:^2.7.10" - "@crawlee/basic": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" - "@crawlee/utils": "npm:3.10.2" + "@crawlee/basic": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" + "@crawlee/utils": "npm:^3.10.3" "@types/content-type": "npm:^1.1.5" cheerio: "npm:^1.0.0-rc.12" content-type: "npm:^1.0.4" @@ -631,14 +631,14 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/jsdom@npm:3.10.2, @crawlee/jsdom@workspace:packages/jsdom-crawler": +"@crawlee/jsdom@npm:^3.10.3, @crawlee/jsdom@workspace:packages/jsdom-crawler": version: 0.0.0-use.local resolution: "@crawlee/jsdom@workspace:packages/jsdom-crawler" dependencies: "@apify/timeout": "npm:^0.3.0" "@apify/utilities": "npm:^2.7.10" - "@crawlee/http": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" + "@crawlee/http": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" "@types/jsdom": "npm:^21.0.0" cheerio: "npm:^1.0.0-rc.12" jsdom: "npm:^24.0.0" @@ -647,26 +647,26 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/linkedom@npm:3.10.2, @crawlee/linkedom@workspace:packages/linkedom-crawler": +"@crawlee/linkedom@npm:^3.10.3, @crawlee/linkedom@workspace:packages/linkedom-crawler": version: 0.0.0-use.local resolution: "@crawlee/linkedom@workspace:packages/linkedom-crawler" dependencies: "@apify/timeout": "npm:^0.3.0" "@apify/utilities": "npm:^2.7.10" - "@crawlee/http": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" + "@crawlee/http": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" linkedom: "npm:^0.18.0" ow: "npm:^0.28.2" tslib: "npm:^2.4.0" languageName: unknown linkType: soft -"@crawlee/memory-storage@npm:3.10.2, @crawlee/memory-storage@workspace:packages/memory-storage": +"@crawlee/memory-storage@npm:^3.10.3, @crawlee/memory-storage@workspace:packages/memory-storage": version: 0.0.0-use.local resolution: "@crawlee/memory-storage@workspace:packages/memory-storage" dependencies: "@apify/log": "npm:^2.4.0" - "@crawlee/types": "npm:3.10.2" + "@crawlee/types": "npm:^3.10.3" "@sapphire/async-queue": "npm:^1.5.0" "@sapphire/shapeshift": "npm:^3.0.0" content-type: "npm:^1.0.4" @@ -678,18 +678,18 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/playwright@npm:3.10.2, @crawlee/playwright@workspace:packages/playwright-crawler": +"@crawlee/playwright@npm:^3.10.3, @crawlee/playwright@workspace:packages/playwright-crawler": version: 0.0.0-use.local resolution: "@crawlee/playwright@workspace:packages/playwright-crawler" dependencies: "@apify/datastructures": "npm:^2.0.0" "@apify/log": "npm:^2.4.0" "@apify/timeout": "npm:^0.3.1" - "@crawlee/browser": "npm:3.10.2" - "@crawlee/browser-pool": "npm:3.10.2" - "@crawlee/core": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" - "@crawlee/utils": "npm:3.10.2" + "@crawlee/browser": "npm:^3.10.3" + "@crawlee/browser-pool": "npm:^3.10.3" + "@crawlee/core": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" + "@crawlee/utils": "npm:^3.10.3" cheerio: "npm:^1.0.0-rc.12" idcac-playwright: "npm:^0.1.2" jquery: "npm:^3.6.0" @@ -707,16 +707,16 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/puppeteer@npm:3.10.2, @crawlee/puppeteer@workspace:packages/puppeteer-crawler": +"@crawlee/puppeteer@npm:^3.10.3, @crawlee/puppeteer@workspace:packages/puppeteer-crawler": version: 0.0.0-use.local resolution: "@crawlee/puppeteer@workspace:packages/puppeteer-crawler" dependencies: "@apify/datastructures": "npm:^2.0.0" "@apify/log": "npm:^2.4.0" - "@crawlee/browser": "npm:3.10.2" - "@crawlee/browser-pool": "npm:3.10.2" - "@crawlee/types": "npm:3.10.2" - "@crawlee/utils": "npm:3.10.2" + "@crawlee/browser": "npm:^3.10.3" + "@crawlee/browser-pool": "npm:^3.10.3" + "@crawlee/types": "npm:^3.10.3" + "@crawlee/utils": "npm:^3.10.3" cheerio: "npm:^1.0.0-rc.12" devtools-protocol: "npm:*" idcac-playwright: "npm:^0.1.2" @@ -797,7 +797,7 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/templates@npm:3.10.2, @crawlee/templates@workspace:packages/templates": +"@crawlee/templates@npm:^3.10.3, @crawlee/templates@workspace:packages/templates": version: 0.0.0-use.local resolution: "@crawlee/templates@workspace:packages/templates" dependencies: @@ -809,7 +809,7 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/types@npm:3.10.2, @crawlee/types@npm:^3.3.0, @crawlee/types@npm:^3.9.0, @crawlee/types@workspace:packages/types": +"@crawlee/types@npm:^3.10.3, @crawlee/types@npm:^3.3.0, @crawlee/types@npm:^3.9.0, @crawlee/types@workspace:packages/types": version: 0.0.0-use.local resolution: "@crawlee/types@workspace:packages/types" dependencies: @@ -817,13 +817,13 @@ __metadata: languageName: unknown linkType: soft -"@crawlee/utils@npm:3.10.2, @crawlee/utils@npm:^3.9.0, @crawlee/utils@workspace:packages/utils": +"@crawlee/utils@npm:^3.10.3, @crawlee/utils@npm:^3.9.0, @crawlee/utils@workspace:packages/utils": version: 0.0.0-use.local resolution: "@crawlee/utils@workspace:packages/utils" dependencies: "@apify/log": "npm:^2.4.0" "@apify/ps-tree": "npm:^1.2.0" - "@crawlee/types": "npm:3.10.2" + "@crawlee/types": "npm:^3.10.3" "@types/sax": "npm:^1.2.7" "@types/whatwg-mimetype": "npm:^3.0.2" cheerio: "npm:^1.0.0-rc.12" @@ -4165,18 +4165,18 @@ __metadata: version: 0.0.0-use.local resolution: "crawlee@workspace:packages/crawlee" dependencies: - "@crawlee/basic": "npm:3.10.2" - "@crawlee/browser": "npm:3.10.2" - "@crawlee/browser-pool": "npm:3.10.2" - "@crawlee/cheerio": "npm:3.10.2" - "@crawlee/cli": "npm:3.10.2" - "@crawlee/core": "npm:3.10.2" - "@crawlee/http": "npm:3.10.2" - "@crawlee/jsdom": "npm:3.10.2" - "@crawlee/linkedom": "npm:3.10.2" - "@crawlee/playwright": "npm:3.10.2" - "@crawlee/puppeteer": "npm:3.10.2" - "@crawlee/utils": "npm:3.10.2" + "@crawlee/basic": "npm:^3.10.3" + "@crawlee/browser": "npm:^3.10.3" + "@crawlee/browser-pool": "npm:^3.10.3" + "@crawlee/cheerio": "npm:^3.10.3" + "@crawlee/cli": "npm:^3.10.3" + "@crawlee/core": "npm:^3.10.3" + "@crawlee/http": "npm:^3.10.3" + "@crawlee/jsdom": "npm:^3.10.3" + "@crawlee/linkedom": "npm:^3.10.3" + "@crawlee/playwright": "npm:^3.10.3" + "@crawlee/puppeteer": "npm:^3.10.3" + "@crawlee/utils": "npm:^3.10.3" import-local: "npm:^3.1.0" tslib: "npm:^2.4.0" peerDependencies: