diff options
| -rw-r--r-- | .travis.yml | 3 | ||||
| -rw-r--r-- | README.md | 4 | ||||
| -rw-r--r-- | setup.py | 56 | ||||
| -rw-r--r-- | wikiget/version.py | 2 | ||||
| -rw-r--r-- | wikiget/wikiget.py | 151 |
5 files changed, 102 insertions, 114 deletions
diff --git a/.travis.yml b/.travis.yml index d373bba..cda16db 100644 --- a/.travis.yml +++ b/.travis.yml @@ -1,6 +1,7 @@ language: python dist: xenial python: +- '2.7' - '3.5' - '3.6' - '3.7' @@ -16,5 +17,5 @@ deploy: secure: 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 on: tags: true - distributions: sdist bdist_wheel + distributions: sdist bdist_wheel --universal skip_existing: true @@ -7,7 +7,7 @@ Something like wget for downloading a file from MediaWiki sites (like Wikipedia or Wikimedia Commons) using only the file name or the URL of its description page. -Requires Python 3.5+. Install with `pip install --user wikiget` or, if you're using +Requires Python 2.7 or 3.5+. Install with `pip install --user wikiget` or, if you're using [Homebrew](https://brew.sh/), `brew tap clpo13/wikiget && brew install wikiget`. ## Usage @@ -85,7 +85,7 @@ executable script. Unit tests can be run with `python setup.py test`. ## License -Copyright (C) 2018, 2019, 2020 Cody Logan +Copyright (C) 2018, 2019 Cody Logan This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -1,5 +1,5 @@ # wikiget - CLI tool for downloading files from Wikimedia sites -# Copyright (C) 2018, 2019, 2020 Cody Logan +# Copyright (C) 2018, 2019 Cody Logan # SPDX-License-Identifier: GPL-3.0-or-later # # Wikiget is free software: you can redistribute it and/or modify @@ -23,47 +23,45 @@ from os import path from setuptools import setup, find_packages here = path.abspath(path.dirname(__file__)) -with open(path.join(here, 'README.md'), 'r') as fr: +with open(path.join(here, "README.md"), "r") as fr: long_description = fr.read() version = {} -with open(path.join(here, 'wikiget', 'version.py'), 'r') as fv: +with open(path.join(here, "wikiget", "version.py"), "r") as fv: exec(fv.read(), version) setup( - name='wikiget', - version=version['__version__'], - author='Cody Logan', - author_email='clpo13@gmail.com', - description='CLI tool for downloading files from MediaWiki sites', + name="wikiget", + version=version["__version__"], + author="Cody Logan", + author_email="clpo13@gmail.com", + description="CLI tool for downloading files from MediaWiki sites", long_description=long_description, - long_description_content_type='text/markdown', - url='https://github.com/clpo13/wikiget', - keywords='download mediawiki wikimedia wikipedia', + long_description_content_type="text/markdown", + url="https://github.com/clpo13/wikiget", + keywords="download mediawiki wikimedia wikipedia", packages=find_packages(), classifiers=[ - 'Development Status :: 4 - Beta', - 'Environment :: Console', - 'Intended Audience :: End Users/Desktop', - 'License :: OSI Approved :: GNU General Public License v3 or later ' - '(GPLv3+)', - 'Operating System :: OS Independent', - 'Programming Language :: Python :: 3', - 'Programming Language :: Python :: 3.5', - 'Programming Language :: Python :: 3.6', - 'Programming Language :: Python :: 3.7', - 'Programming Language :: Python :: 3.8', - 'Topic :: Utilities', + "Development Status :: 4 - Beta", + "Environment :: Console", + "Intended Audience :: End Users/Desktop", + "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)", + "Operating System :: OS Independent", + "Programming Language :: Python :: 2.7", + "Programming Language :: Python :: 3.5", + "Programming Language :: Python :: 3.6", + "Programming Language :: Python :: 3.7", + "Programming Language :: Python :: 3.8", + "Topic :: Utilities", ], - python_requires='>=3.5', - install_requires=['future', 'mwclient>=0.10.0', 'pytest-runner', - 'requests', 'tqdm'], - tests_require=['pytest'], + python_requires='>=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*', + install_requires=["future", "mwclient>=0.10.0", "pytest-runner", "requests", "tqdm"], + tests_require=["pytest"], project_urls={ - 'Bug Reports': 'https://github.com/clpo13/wikiget/issues', + "Bug Reports": "https://github.com/clpo13/wikiget/issues", }, entry_points={ - 'console_scripts': [ + "console_scripts": [ 'wikiget=wikiget.wikiget:main', ], }, diff --git a/wikiget/version.py b/wikiget/version.py index d4bb133..0958641 100644 --- a/wikiget/version.py +++ b/wikiget/version.py @@ -1,3 +1,3 @@ """Sets the program version in setup.py and on the command line.""" -__version__ = "0.3.0" +__version__ = "0.2.1" diff --git a/wikiget/wikiget.py b/wikiget/wikiget.py index bdd05a3..3680fd0 100644 --- a/wikiget/wikiget.py +++ b/wikiget/wikiget.py @@ -1,5 +1,5 @@ # wikiget - CLI tool for downloading files from Wikimedia sites -# Copyright (C) 2018, 2019, 2020 Cody Logan +# Copyright (C) 2018, 2019 Cody Logan # SPDX-License-Identifier: GPL-3.0-or-later # # Wikiget is free software: you can redistribute it and/or modify @@ -17,6 +17,14 @@ """Main wikiget functions.""" +from __future__ import absolute_import, division, print_function, unicode_literals + +from builtins import open + +from future import standard_library + +standard_library.install_aliases() + import argparse import hashlib import logging @@ -32,9 +40,9 @@ from tqdm import tqdm from wikiget.version import __version__ BLOCKSIZE = 65536 -DEFAULT_SITE = 'commons.wikimedia.org' -USER_AGENT = 'wikiget/{} (https://github.com/clpo13/wikiget) ' \ - 'mwclient/{}'.format(__version__, mwclient_version) +DEFAULT_SITE = "commons.wikimedia.org" +USER_AGENT = "wikiget/{} (https://github.com/clpo13/wikiget) " \ + "mwclient/{}".format(__version__, mwclient_version) def main(): @@ -44,43 +52,35 @@ def main(): """ parser = argparse.ArgumentParser(description=""" - A tool for downloading files from - MediaWiki sites using the file name or - description page URL + A tool for downloading files from MediaWiki sites + using the file name or description page URL """, epilog=""" - Copyright (C) 2018, 2019, 2020 Cody Logan. - License GPLv3+: GNU GPL version 3 or later - <http://www.gnu.org/licenses/gpl.html>. - This is free software; you are free to - change and redistribute it under certain - conditions. There is NO WARRANTY, to the + Copyright (C) 2018, 2019 Cody Logan. License GPLv3+: GNU GPL + version 3 or later <http://www.gnu.org/licenses/gpl.html>. + This is free software; you are free to change and redistribute + it under certain conditions. There is NO WARRANTY, to the extent permitted by law. """) - parser.add_argument('FILE', help=""" - name of the file to download with the File: or Image: - prefix, or the URL of its file description page + parser.add_argument("FILE", help=""" + name of the file to download with the File: or Image: prefix, + or the URL of its file description page """) - parser.add_argument('-V', '--version', action='version', - version='%(prog)s {}'.format(__version__)) + parser.add_argument("-V", "--version", action="version", + version="%(prog)s {}".format(__version__)) output_options = parser.add_mutually_exclusive_group() - output_options.add_argument('-q', '--quiet', - help='suppress warning messages', - action='store_true') - output_options.add_argument('-v', '--verbose', - help='print detailed information; use -vv for ' - 'even more detail', action='count', default=0) - parser.add_argument('-f', '--force', - help='force overwriting existing files', - action='store_true') - parser.add_argument('-s', '--site', default=DEFAULT_SITE, - help='MediaWiki site to download from (default: ' - '%(default)s)') - parser.add_argument('-o', '--output', help='write download to OUTPUT') - parser.add_argument('-a', '--batch', - help='treat FILE as a textfile containing multiple ' - 'files to download, one URL or filename per line', - action='store_true') + output_options.add_argument("-q", "--quiet", help="suppress warning messages", + action="store_true") + output_options.add_argument("-v", "--verbose", + help="print detailed information; use -vv for even more detail", + action="count", default=0) + parser.add_argument("-f", "--force", help="force overwriting existing files", + action="store_true") + parser.add_argument("-s", "--site", default=DEFAULT_SITE, + help="MediaWiki site to download from (default: %(default)s)") + parser.add_argument("-o", "--output", help="write download to OUTPUT") + parser.add_argument("-a", "--batch", help="treat FILE as a textfile containing multiple files to download, one URL or filename per line", + action="store_true") args = parser.parse_args() @@ -96,10 +96,9 @@ def main(): if args.verbose >= 1: print("Info: using batch file '{}'".format(input_file)) try: - fd = open(input_file, 'r') + fd = open(input_file, "r") except IOError as e: - print('File could not be read. The following error was ' - 'encountered:') + print("File could not be read. The following error was encountered:") print(e) sys.exit(1) else: @@ -121,8 +120,7 @@ def download(dl, args): site_name = url.netloc if args.site is not DEFAULT_SITE and not args.quiet: # this will work even if the user specifies 'commons.wikimedia.org' - print('Warning: target is a URL, ignoring site specified with ' - '--site') + print("Warning: target is a URL, ignoring site specified with --site") else: filename = dl site_name = args.site @@ -132,8 +130,7 @@ def download(dl, args): # check for valid site parameter if not site_match: - print('Only Wikimedia sites (wikipedia.org and wikimedia.org) are ' - 'currently supported.') + print("Only Wikimedia sites (wikipedia.org and wikimedia.org) are currently supported.") sys.exit(1) # check if this is a valid file @@ -142,15 +139,13 @@ def download(dl, args): filename = file_match.group(2) else: # no file extension and/or prefix, probably an article - print('Downloading Wikipedia articles is not currently supported.', - end='') + print("Downloading Wikipedia articles is not currently supported.", end="") if file_match and not file_match.group(1): # file extension detected, but no prefix - # TODO: no longer possible to get to this point since file_match is - # None with no prefix + # TODO: no longer possible to get to this point since file_match is None with no prefix print(" If this is a file, please add the 'File:' prefix.") else: - print('\n', end='') + print("\n", end="") sys.exit(1) filename = unquote(filename) # remove URL encoding for special characters @@ -158,14 +153,13 @@ def download(dl, args): dest = args.output or filename if args.verbose >= 2: - print('User agent: {}'.format(USER_AGENT)) + print("User agent: {}".format(USER_AGENT)) # connect to site and identify ourselves try: site = Site(site_name, clients_useragent=USER_AGENT) except ConnectionError: - # usually this means there is no such site, or there's no network - # connection + # usually this means there is no such site, or there's no network connection print("Error: couldn't connect to specified site.") sys.exit(1) except InvalidResponse as e: @@ -178,34 +172,31 @@ def download(dl, args): if file.imageinfo != {}: # file exists either locally or at Wikimedia Commons - file_url = file.imageinfo['url'] - file_size = file.imageinfo['size'] - file_sha1 = file.imageinfo['sha1'] + file_url = file.imageinfo["url"] + file_size = file.imageinfo["size"] + file_sha1 = file.imageinfo["sha1"] if args.verbose >= 1: print("Info: downloading '{}' " - '({} bytes) from {}'.format(filename, file_size, site.host), - end='') + "({} bytes) from {}".format(filename, file_size, site.host), end="") if args.output: print(" to '{}'".format(dest)) else: - print('\n', end='') - print('Info: {}'.format(file_url)) + print("\n", end="") + print("Info: {}".format(file_url)) if os.path.isfile(dest) and not args.force: - print("File '{}' already exists, skipping download (use -f to " - "ignore)".format(dest)) + print("File '{}' already exists, skipping download (use -f to ignore)".format(dest)) else: try: - fd = open(dest, 'wb') + fd = open(dest, "wb") except IOError as e: - print('File could not be written. The following error was ' - 'encountered:') + print("File could not be written. The following error was encountered:") print(e) sys.exit(1) else: # download the file - with tqdm(total=file_size, unit='B', + with tqdm(total=file_size, unit="B", unit_scale=True, unit_divisor=1024) as progress_bar: with fd: res = site.connection.get(file_url, stream=True) @@ -218,59 +209,57 @@ def download(dl, args): dl_sha1 = verify_hash(dest) if args.verbose >= 1: - print('Info: downloaded file SHA1 is {}'.format(dl_sha1)) - print('Info: server file SHA1 is {}'.format(file_sha1)) + print("Info: downloaded file SHA1 is {}".format(dl_sha1)) + print("Info: server file SHA1 is {}".format(file_sha1)) if dl_sha1 == file_sha1: if args.verbose >= 1: - print('Info: hashes match!') + print("Info: hashes match!") # at this point, we've successfully downloaded the file else: - print('Error: hash mismatch! Downloaded file may be corrupt.') + print("Error: hash mismatch! Downloaded file may be corrupt.") sys.exit(1) else: # no file information returned - print("Target '{}' does not appear to be a valid file." - .format(filename)) + print("Target '{}' does not appear to be a valid file.".format(filename)) sys.exit(1) def valid_file(search_string): """ - Determines if the given string contains a valid file name, defined as a - string ending with a '.' and at least one character, beginning with 'File:' - or 'Image:', the standard file prefixes in MediaWiki. + Determines if the given string contains a valid file name, defined as a string + ending with a '.' and at least one character, beginning with 'File:' or + 'Image:', the standard file prefixes in MediaWiki. :param search_string: string to validate :returns: a regex Match object if there's a match or None otherwise """ # second group could also restrict to file extensions with three or more # letters with ([^/\r\n\t\f\v]+\.\w{3,}) - file_regex = re.compile(r'(File:|Image:)([^/\r\n\t\f\v]+\.\w+)$', re.I) + file_regex = re.compile(r"(File:|Image:)([^/\r\n\t\f\v]+\.\w+)$", re.I) return file_regex.search(search_string) def valid_site(search_string): """ - Determines if the given string contains a valid site name, defined as a - string ending with 'wikipedia.org' or 'wikimedia.org'. This covers all - subdomains of those domains. Eventually, it should be possible to support - any MediaWiki site, regardless of domain name. + Determines if the given string contains a valid site name, defined as a string + ending with 'wikipedia.org' or 'wikimedia.org'. This covers all subdomains of + those domains. Eventually, it should be possible to support any MediaWiki site, + regardless of domain name. :param search_string: string to validate :returns: a regex Match object if there's a match or None otherwise """ - site_regex = re.compile(r'wiki[mp]edia\.org$', re.I) + site_regex = re.compile(r"wiki[mp]edia\.org$", re.I) return site_regex.search(search_string) def verify_hash(filename): """ - Calculates the SHA1 hash of the given file for comparison with a known - value. + Calculates the SHA1 hash of the given file for comparison with a known value. :param filename: name of the file to calculate a hash for :return: hash digest """ hasher = hashlib.sha1() - with open(filename, 'rb') as dl: + with open(filename, "rb") as dl: buf = dl.read(BLOCKSIZE) while len(buf) > 0: hasher.update(buf) |