From 836b0489919f3680b057fbe4a03e872be1ab441f Mon Sep 17 00:00:00 2001 From: "Ian T." Date: Thu, 24 Sep 2026 18:00:24 -0700 Subject: [PATCH] chore: bump version to 2.7.1 pyproject.toml, uv.lock, CITATION.cff (version 2.7.1), README current-release line, and a CHANGELOG 2.7.1 section. Patch release: live per-page feedback while scraping several URLs, Back that returns to the previous prompt in every menu, the Multiple URLs box finishing on Enter at an empty line, and a new "Pages I scraped earlier" input that builds a dataset from a no-AI scrape folder without fetching the pages again. --- CHANGELOG.md | 5 +++++ CITATION.cff | 2 +- README.md | 15 ++++++++------- pyproject.toml | 2 +- uv.lock | 2 +- 5 files changed, 16 insertions(+), 10 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 7b83a68..4b0e3b2 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,11 @@ Format loosely follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). ## [Unreleased] +## [2.7.1] - 2026-09-24 + +Live feedback while scraping, a Back option that goes back, and a way to +build a dataset from pages you already scraped. + ### Added - **Use a scrape folder as dataset input**: *Build an AI training dataset* now offers **Pages I scraped earlier** next to the URL options. Pick a diff --git a/CITATION.cff b/CITATION.cff index 9d9ca47..e4072de 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -12,7 +12,7 @@ authors: orcid: 'https://orcid.org/0009-0000-4888-1941' affiliation: William Jessup University repository-code: 'https://github.com/ianktoo/data-forge' -version: 2.7.0 +version: 2.7.1 date-released: '2026-09-24' abstract: >- DataForge is an open-source pipeline for building synthetic diff --git a/README.md b/README.md index 9a17506..f175625 100644 --- a/README.md +++ b/README.md @@ -6,13 +6,14 @@ [![Python](https://img.shields.io/badge/python-3.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue)](https://www.python.org/) [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE) -**Current release: 2.7.0.** Easier URL selection: tick pages from the -keyboard (arrows, Space, Left and Right to turn pages, `/` to filter), choose -which language to keep on a multilingual site, and scrape just the page you -gave, its links, or the whole site. A key saved with "Save API key globally" -is now found in every folder. Tested on Linux, Windows and macOS with Python -3.11 to 3.14, with standalone binaries for Windows, Linux and Apple Silicon -Macs. See the [changelog](CHANGELOG.md#270---2026-09-24). +**Current release: 2.7.1.** Scraping several URLs now shows each page as +it is fetched, Back works in every menu, and the Multiple URLs box finishes on +Enter at an empty line. New: build a dataset from pages you already scraped +with no AI, without fetching them again. 2.7.0 added keyboard URL review, a +language choice on multilingual sites, and scraping just the page you gave. +Tested on Linux, Windows and macOS with Python 3.11 to 3.14, with standalone +binaries for Windows, Linux and Apple Silicon Macs. See the +[changelog](CHANGELOG.md#271---2026-09-24). Fine-tuning needs data, and good domain data is trapped in documentation sites, knowledge bases and public archives. Getting it out usually means diff --git a/pyproject.toml b/pyproject.toml index 879ae1d..9636f96 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "llm-web-crawler" -version = "2.7.0" +version = "2.7.1" description = "LLM data collection and synthetic fine-tuning dataset pipeline" readme = "README.md" requires-python = ">=3.11" diff --git a/uv.lock b/uv.lock index e3c6445..3ff76f0 100644 --- a/uv.lock +++ b/uv.lock @@ -1559,7 +1559,7 @@ wheels = [ [[package]] name = "llm-web-crawler" -version = "2.7.0" +version = "2.7.1" source = { editable = "." } dependencies = [ { name = "aiofiles" },