1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
|
# wikiget - CLI tool for downloading files from Wikimedia sites
# Copyright (C) 2023 Cody Logan
# SPDX-License-Identifier: GPL-3.0-or-later
#
# Wikiget is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# Wikiget is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Wikiget. If not, see <https://www.gnu.org/licenses/>.
import logging
from argparse import Namespace
from typing import Dict
from urllib.parse import unquote, urlparse
import wikiget
from wikiget.exceptions import ParseError
from wikiget.file import File
from wikiget.validations import valid_file
logger = logging.getLogger(__name__)
def get_dest(dl: str, args: Namespace) -> File:
url = urlparse(dl)
if url.netloc:
filename = url.path
site_name = url.netloc
if args.site is not wikiget.DEFAULT_SITE:
# this will work even if the user specifies 'commons.wikimedia.org' since
# we're comparing objects instead of values (is not vs. !=)
logger.warning("Target is a URL, ignoring site specified with --site")
else:
filename = dl
site_name = args.site
file_match = valid_file(filename)
# check if this is a valid file
if file_match and file_match.group(1):
# has File:/Image: prefix and extension
filename = file_match.group(2)
else:
# no file extension and/or prefix, probably an article
msg = f"Could not parse input '{filename}' as a file"
raise ParseError(msg)
filename = unquote(filename) # remove URL encoding for special characters
dest = args.output or filename
file = File(filename, dest, site_name)
return file
def read_batch_file(batch_file: str) -> Dict[int, str]:
dl_list = {}
logger.info(f"Using batch file '{batch_file}'.")
with open(batch_file) as fd:
# read the file into memory and process each line as we go
for line_num, line in enumerate(fd, start=1):
line_s = line.strip()
# ignore blank lines and lines starting with "#" (for comments)
if line_s and not line_s.startswith("#"):
dl_list[line_num] = line_s
return dl_list
|
