aboutsummaryrefslogtreecommitdiff
path: root/wikiget/wikiget.py
diff options
context:
space:
mode:
Diffstat (limited to 'wikiget/wikiget.py')
-rw-r--r--wikiget/wikiget.py84
1 files changed, 42 insertions, 42 deletions
diff --git a/wikiget/wikiget.py b/wikiget/wikiget.py
index 8bcd3fd..a78056c 100644
--- a/wikiget/wikiget.py
+++ b/wikiget/wikiget.py
@@ -40,9 +40,9 @@ from tqdm import tqdm
from wikiget.version import __version__
BLOCKSIZE = 65536
-DEFAULT_SITE = "en.wikipedia.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():
@@ -62,25 +62,25 @@ def main():
it under certain conditions. There is NO WARRANTY, to the
extent permitted by law.
""")
- parser.add_argument("FILE", help="""
+ 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()
@@ -96,9 +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:
@@ -119,8 +119,8 @@ def download(dl, args):
filename = url.path
site_name = url.netloc
if args.site is not DEFAULT_SITE and not args.quiet:
- # this will work even if the user specifies 'en.wikipedia.org'
- print("Warning: target is a URL, ignoring site specified with --site")
+ # this will work even if the user specifies 'commons.wikimedia.org'
+ print('Warning: target is a URL, ignoring site specified with --site')
else:
filename = dl
site_name = args.site
@@ -130,7 +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
@@ -139,13 +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
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
@@ -153,7 +153,7 @@ 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:
@@ -172,31 +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))
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)
@@ -209,14 +209,14 @@ 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:
@@ -235,7 +235,7 @@ def valid_file(search_string):
"""
# 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)
@@ -248,7 +248,7 @@ def valid_site(search_string):
: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)
@@ -259,7 +259,7 @@ def verify_hash(filename):
: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)
generated by cgit v1.2.3 (git 2.25.1) at 2026-02-12 09:16:01 +0000