get-checklist script updated and now uses click.

1. Moved the script from bin to ebird.pages.scripts to reduce the risk of conflict with other ebird libraries. 2. Changed the library used for command line arguments from pyCLI to the rather excellent click. 3. Removed support for passing multiple identifiers to the get-checklists script. 4. Added simple tests for the command line script that can be called manually to make sure everything works with the ebird site. 5. Removed TODOs that were completed or no longer needed.
ProjectBabbler · Aug 21, 2017 · 2c23088 · 2c23088
1 parent e425e80
commit 2c23088
Showing 12 changed files with 78 additions and 63 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,6 +5,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/).
 This project adheres to [PEP440](https://www.python.org/dev/peps/pep-0440/)
 and by implication, [Semantic Versioning](http://semver.org/).
 
-## [unreleased]
+## [0.1] - 2017-08-21
 ### Added
-- Function for scraping the data from the view checklist page.
+- Added get_checklist for scraping the data from the view checklist page.
+- Added script so get_checklist can be called from the command line.
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -1,4 +1,3 @@
 include *.md *.txt *.py *.cfg
-recursive-include bin *.py
 recursive-include ebird *.py
-recursive-include tests *.py
+recursive-include tests *.py *.sh
diff --git a/README.md b/README.md
@@ -36,7 +36,7 @@ Each of the functions has a corresponding script that can be used on the
 command-line:
 
 ```sh
-$ ebird-get-checklists S38429565
+$ get-checklist --id S38429565 --out checklist.json
 ```
 The script allows data for one or more checklists to be downloaded and written 
 to a file in JSON format.
@@ -47,7 +47,7 @@ ebird-pages works with Python 3.3+.
 
 ## Dependencies
 
-eBird Pages makes use of the following packages: Requests, BeautifulSoup4, lxml and pyCLI.
+eBird Pages makes use of the following packages: Requests, BeautifulSoup4, lxml and Click.
 See requirements.txt for the version numbers of each of the libraries.
 
 ## License

diff --git a/bin/ebird-get-checklists b/bin/ebird-get-checklists
diff --git a/ebird/pages/__init__.py b/ebird/pages/__init__.py
@@ -2,9 +2,6 @@
 
 """A set of functions for scraping data from eBird web pages."""
 
-# TODO Configure logging and add NullHandler
-# See https://docs.python.org/3/howto/logging.html#configuring-logging-for-a-library
-
 from .version import __version__
 
 # Import all the functions that make up the public API.

diff --git a/ebird/pages/scripts/__init__.py b/ebird/pages/scripts/__init__.py
diff --git a/ebird/pages/scripts/base.py b/ebird/pages/scripts/base.py
@@ -0,0 +1,28 @@
+import datetime
+import json
+
+
+class JSONDateEncoder(json.JSONEncoder):
+
+    def default(self, o):
+        if isinstance(o, datetime.date):
+            return o.isoformat()
+        if isinstance(o, datetime.time):
+            return o.isoformat()
+        if isinstance(o, datetime.timedelta):
+            return str(o)
+        else:
+            super().default(o)
+
+
+def save(fp, values, indent):
+    """Save the JSON data to a file or stdout.
+
+    :param fp: the writer.
+    :param values: the python data to be saved.
+    :param indent: the level of indentation when prettyprinting the output.
+
+    """
+    fp.write(json.dumps(values, indent=indent, cls=JSONDateEncoder).encode('utf-8'))
+    if fp.name == '<stdout>':
+        fp.write(b'\n')
diff --git a/ebird/pages/scripts/get_checklist.py b/ebird/pages/scripts/get_checklist.py
@@ -0,0 +1,28 @@
+"""
+Command-line script to scape the web page(s) for a checklists and
+save the data in JSON format to a file or to stdout.
+
+"""
+
+import click
+
+from ebird.pages import get_checklist
+
+from .base import save
+
+
+# noinspection PyShadowingBuiltins
+@click.command()
+@click.option('--id', prompt=True,
+              help="The unique identifier for the checklist.")
+@click.option('--out', prompt=True, type=click.File('wb'),
+              help='The name of a file to write the results to. To print'
+                   ' the results to the screen use -.')
+@click.option('--indent', type=int, default=None,
+              help='Pretty-print the results with this level of indentation.')
+def cli(id, out, indent):
+    """Get the data for a checklist from its eBird web page."""
+    save(out, get_checklist(id), indent)
+
+if __name__ == '__main__':
+    cli()
diff --git a/ebird/pages/version.py b/ebird/pages/version.py
@@ -1 +1 @@
-__version__ = '0.1.dev1'
+__version__ = '0.1'
diff --git a/requirements.txt b/requirements.txt
@@ -5,7 +5,7 @@ idna==2.5
 lxml==3.8.0
 pluggy==0.4.0
 py==1.4.34
-pyCLI==2.0.3
+click==6.7
 requests==2.18.2
 tox==2.7.0
 urllib3==1.22

diff --git a/setup.py b/setup.py
@@ -32,7 +32,10 @@ def test_suite():
     keywords='eBird web scraper',
     packages=['ebird.pages'],
     test_suite='setup.test_suite',
-    scripts=['bin/ebird-get-checklists'],
+    entry_points="""
+        [console_scripts]
+        get-checklist=ebird.pages.scripts.get_checklist:cli
+    """,
     classifiers=[
         'Development Status :: 3 - Alpha',
         'Environment :: Console',
@@ -54,6 +57,6 @@ def test_suite():
         'requests',
         'beautifulsoup4',
         'lxml',
-        'pyCLI'
+        'Click'
     ],
 )
diff --git a/tests/checklists/scripts/get-checklist.sh b/tests/checklists/scripts/get-checklist.sh
@@ -0,0 +1,9 @@
+#!/bin/sh
+
+# Tests for the get-checklists script.
+
+# Get the data for a checklist.
+get-checklist --id S38645981 --out -
+
+# Missing values should be prompted for.
+get-checklist --out -