diff --git a/CHANGELOG.md b/CHANGELOG.md new file mode 100644 index 0000000..d8bf0cf --- /dev/null +++ b/CHANGELOG.md @@ -0,0 +1,18 @@ +# Changelog + +All notable changes to this project will be documented in this file. + +The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), +and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). + +## [Unreleased] + +## [1.0.2] - 2020-07-26 + +### Added + +- This CHANGELOG file to keep track of changes in future releases. + +### Fixed + +- Crashes from decoding errors while downloading, contribution from [@Sarunas-Girdenas](https://github.com/Sarunas-Girdenas) diff --git a/comcrawl/__init__.py b/comcrawl/__init__.py index d402cb9..01432ce 100644 --- a/comcrawl/__init__.py +++ b/comcrawl/__init__.py @@ -7,6 +7,6 @@ """ -__version__ = "1.0.1" +__version__ = "1.0.2" from .core import IndexClient diff --git a/comcrawl/utils/download.py b/comcrawl/utils/download.py index 623f20e..9538359 100644 --- a/comcrawl/utils/download.py +++ b/comcrawl/utils/download.py @@ -44,7 +44,7 @@ def download_single_result(result: Result) -> Result: data: str = raw_data.decode("utf-8") except UnicodeDecodeError: print(f"Warning: Could not extract file downloaded from {url}") - data = '' + data = "" result["html"] = "" diff --git a/pyproject.toml b/pyproject.toml index 17f78e8..fca11d7 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "comcrawl" -version = "1.0.1" +version = "1.0.2" description = "A python utility for downloading Common Crawl data." authors = ["Michael Harms "] license = "MIT"