Merge 2c51f2b into 54423cf

.coveragerc

@@ -2,7 +2,7 @@
 # https://coverage.readthedocs.io/en/latest/config.html
 
 [run]
-source = src/example
+source = src/hash_http_content
 omit =
 branch = true
 

.github/lineage.yml

@@ -3,4 +3,4 @@ version: "1"
 
 lineage:
   skeleton:
-    remote-url: https://github.com/cisagov/skeleton-generic.git
+    remote-url: https://github.com/cisagov/skeleton-python-library.git

.github/workflows/build.yml

@@ -64,6 +64,8 @@ jobs:
             ${{ hashFiles('**/requirements.txt') }}"
           restore-keys: |
             ${{ env.BASE_CACHE_KEY }}
+      - name: Download and extract a serverless-chrome binary
+        run: ./get_serverless_chrome_binary.sh
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip

CONTRIBUTING.md

@@ -15,7 +15,7 @@ all of which should be in this repository.
 
 If you want to report a bug or request a new feature, the most direct
 method is to [create an
-issue](https://github.com/cisagov/skeleton-python-library/issues) in
+issue](https://github.com/cisagov/hash-http-content/issues) in
 this repository.  We recommend that you first search through existing
 issues (both open and closed) to check if your particular issue has
 already been reported.  If it has then you might want to add a comment
@@ -25,7 +25,7 @@ one.
 ## Pull requests ##
 
 If you choose to [submit a pull
-request](https://github.com/cisagov/skeleton-python-library/pulls),
+request](https://github.com/cisagov/hash-http-content/pulls),
 you will notice that our continuous integration (CI) system runs a
 fairly extensive set of linters, syntax checkers, system, and unit tests.
 Your pull request may fail these checks, and that's OK.  If you want
@@ -111,9 +111,9 @@ can create and configure the Python virtual environment with these
 commands:
 
 ```console
-cd skeleton-python-library
-pyenv virtualenv <python_version_to_use> skeleton-python-library
-pyenv local skeleton-python-library
+cd hash-http-content
+pyenv virtualenv <python_version_to_use> hash-http-content
+pyenv local hash-http-content
 pip install --requirement requirements-dev.txt
 ```
 

README.md

@@ -1,25 +1,39 @@
-# skeleton-python-library #
-
-[![GitHub Build Status](https://github.com/cisagov/skeleton-python-library/workflows/build/badge.svg)](https://github.com/cisagov/skeleton-python-library/actions)
-[![Coverage Status](https://coveralls.io/repos/github/cisagov/skeleton-python-library/badge.svg?branch=develop)](https://coveralls.io/github/cisagov/skeleton-python-library?branch=develop)
-[![Total alerts](https://img.shields.io/lgtm/alerts/g/cisagov/skeleton-python-library.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/cisagov/skeleton-python-library/alerts/)
-[![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/cisagov/skeleton-python-library.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/cisagov/skeleton-python-library/context:python)
-[![Known Vulnerabilities](https://snyk.io/test/github/cisagov/skeleton-python-library/develop/badge.svg)](https://snyk.io/test/github/cisagov/skeleton-python-library)
-
-This is a generic skeleton project that can be used to quickly get a
-new [cisagov](https://github.com/cisagov) Python library GitHub
-project started.  This skeleton project contains [licensing
-information](LICENSE), as well as
-[pre-commit hooks](https://pre-commit.com) and
-[GitHub Actions](https://github.com/features/actions) configurations
-appropriate for a Python library project.
-
-## New Repositories from a Skeleton ##
-
-Please see our [Project Setup guide](https://github.com/cisagov/development-guide/tree/develop/project_setup)
-for step-by-step instructions on how to start a new repository from
-a skeleton. This will save you time and effort when configuring a
-new repository!
+# hash-http-content #
+
+[![GitHub Build Status](https://github.com/cisagov/hash-http-content/workflows/build/badge.svg)](https://github.com/cisagov/hash-http-content/actions)
+[![Coverage Status](https://coveralls.io/repos/github/cisagov/hash-http-content/badge.svg?branch=develop)](https://coveralls.io/github/cisagov/hash-http-content?branch=develop)
+[![Total alerts](https://img.shields.io/lgtm/alerts/g/cisagov/hash-http-content.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/cisagov/hash-http-content/alerts/)
+[![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/cisagov/hash-http-content.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/cisagov/hash-http-content/context:python)
+[![Known Vulnerabilities](https://snyk.io/test/github/cisagov/hash-http-content/develop/badge.svg)](https://snyk.io/test/github/cisagov/hash-http-content)
+
+This is a Python library to retrieve the contents of a given URL via HTTP (or
+HTTPS) and hash the processed contents.
+
+## Content processing ##
+
+If an encoding is detected, this package will convert content into the UTF-8
+encoding before proceeding.
+
+Additional content processing is currently implemented for the following types
+of content:
+
+* HTML
+* JSON
+
+### HTML ###
+
+HTML content is processed by leveraging the
+[pyppeteer](https://github.com/pyppeteer/pyppeteer) package to execute any
+JavaScript on a retrieved page. The result is then parsed by
+[Beautiful Soup](https://www.crummy.com/software/BeautifulSoup/) to reduce the
+content to the human visible portions of a page.
+
+### JSON ###
+
+JSON content is processed by using the
+[`json` library](https://docs.python.org/3/library/json.html) that is part of
+the Python standard library. It is read in and then output in a deterministic
+manner to adjust for any styling differences between content.
 
 ## Contributing ##
 

bump_version.sh

@@ -6,7 +6,7 @@ set -o nounset
 set -o errexit
 set -o pipefail
 
-VERSION_FILE=src/example/_version.py
+VERSION_FILE=src/hash_http_content/_version.py
 
 HELP_INFORMATION="bump_version.sh (show|major|minor|patch|prerelease|build|finalize)"
 

get_serverless_chrome_binary.sh

@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+
+set -o nounset
+set -o errexit
+set -o pipefail
+
+function usage {
+  echo "Usage:"
+  echo "  ${0##*/} [options]"
+  echo
+  echo "Options:"
+  echo "  -h, --help    Show the help message."
+  echo "  -l, --latest  Pull down the latest release on GitHub."
+  exit "$1"
+}
+
+# Defaults to a specific version for use in GitHub Actions
+DOWNLOAD_URL="https://github.com/adieuadieu/serverless-chrome/releases/download/v1.0.0-57/stable-headless-chromium-amazonlinux-2.zip"
+LOCAL_FILE="serverless-chrome.zip"
+LOCAL_DIR="tests/files/"
+
+
+# Get the URL of the latest stable release available
+function get_latest_stable_url {
+  releases_url="https://api.github.com/repos/adieuadieu/serverless-chrome/releases"
+  # Get the URL for the latest release's assets
+  latest_assets=$(curl -s "$releases_url" | jq -r '.[0].assets_url')
+  # Download the zip for the stable branch
+  DOWNLOAD_URL=$(curl -s "$latest_assets" | jq -r '.[] | select(.browser_download_url | contains("stable")) | .browser_download_url')
+}
+
+while (( "$#" ))
+do
+  case "$1" in
+    -h|--help)
+      usage 0
+      ;;
+    -l|--latest)
+      get_latest_stable_url
+      shift 1
+      ;;
+    -*)
+      usage 1
+      ;;
+  esac
+done
+
+# Follow redirects and output as the specified file name
+curl -L --output "$LOCAL_FILE" "$DOWNLOAD_URL"
+# Extract the specified file to the specified directory and overwrite without
+# prompting
+unzip -o "$LOCAL_FILE" -d "$LOCAL_DIR"

setup.py

@@ -1,5 +1,5 @@
 """
-This is the setup module for the example project.
+This is the setup module for the hash-http-content project.
 
 Based on:
 
@@ -42,16 +42,16 @@ def get_version(version_file):
 
 
 setup(
-    name="example",
+    name="hash-http-content",
     # Versions should comply with PEP440
-    version=get_version("src/example/_version.py"),
-    description="Example python library",
+    version=get_version("src/hash_http_content/_version.py"),
+    description="HTTP content hasher",
     long_description=readme(),
     long_description_content_type="text/markdown",
     # NCATS "homepage"
     url="https://www.us-cert.gov/resources/ncats",
     # The project's main homepage
-    download_url="https://github.com/cisagov/skeleton-python-library",
+    download_url="https://github.com/cisagov/hash-http-content",
     # Author details
     author="Cyber and Infrastructure Security Agency",
     author_email="ncats@hq.dhs.gov",
@@ -77,13 +77,20 @@ def get_version(version_file):
     ],
     python_requires=">=3.6",
     # What does your project relate to?
-    keywords="skeleton",
+    keywords="hash http requests",
     packages=find_packages(where="src"),
     package_dir={"": "src"},
-    package_data={"example": ["data/*.txt"]},
     py_modules=[splitext(basename(path))[0] for path in glob("src/*.py")],
     include_package_data=True,
-    install_requires=["docopt", "schema", "setuptools >= 24.2.0"],
+    install_requires=[
+        "beautifulsoup4",
+        "docopt",
+        "lxml",
+        "pyppeteer",
+        "requests",
+        "schema",
+        "setuptools >= 24.2.0",
+    ],
     extras_require={
         "test": [
             "coverage",
@@ -99,6 +106,6 @@ def get_version(version_file):
             "pytest",
         ]
     },
-    # Conveniently allows one to run the CLI tool as `example`
-    entry_points={"console_scripts": ["example = example.example:main"]},
+    # Conveniently allows one to run the CLI tool as `hash-url`
+    entry_points={"console_scripts": ["hash-url = hash_http_content.cli:main"]},
 )

src/example/__init__.py → src/hash_http_content/__init__.py

@@ -1,9 +1,12 @@
-"""The example library."""
+"""The hash-http-content library."""
+# Standard Python Libraries
+from typing import List
+
 # We disable a Flake8 check for "Module imported but unused (F401)" here because
 # although this import is not directly used, it populates the value
 # package_name.__version__, which is used to get version information about this
 # Python package.
 from ._version import __version__  # noqa: F401
-from .example import example_div
+from .hasher import UrlHasher, UrlResult
 
-__all__ = ["example_div"]
+__all__: List[str] = ["UrlHasher", "UrlResult"]

src/example/__main__.py → src/hash_http_content/__main__.py

@@ -1,5 +1,5 @@
 """Code to run if this package is used as a Python module."""
 
-from .example import main
+from .cli import main
 
 main()