|
1
|
|
|
import html |
|
2
|
|
|
import os |
|
3
|
|
|
import re |
|
4
|
|
|
import unicodedata |
|
5
|
|
|
|
|
6
|
|
|
import click |
|
7
|
|
|
from humanize import naturalsize |
|
8
|
|
|
from requests import Session |
|
9
|
|
|
|
|
10
|
|
|
|
|
11
|
|
|
def download(url, filename, progress_data=None, session=None, silent=False): |
|
12
|
|
|
""" |
|
13
|
|
|
Initiate a file download and display the progress |
|
14
|
|
|
|
|
15
|
|
|
Args: |
|
16
|
|
|
url(str): Download URL |
|
17
|
|
|
filename(str): Path to save the file to |
|
18
|
|
|
progress_data(dict): Static information to display above the progress bar |
|
19
|
|
|
session(Session): An optional download session to use |
|
20
|
|
|
silent(bool): Download the file, but don't print any output |
|
21
|
|
|
|
|
22
|
|
|
Returns: |
|
23
|
|
|
|
|
24
|
|
|
""" |
|
25
|
|
|
# Set up our requests session and make sure the filepath exists |
|
26
|
|
|
session = session or Session() |
|
27
|
|
|
os.makedirs(os.path.dirname(filename), 0o755, True) |
|
28
|
|
|
|
|
29
|
|
|
# Test the connection |
|
30
|
|
|
response = session.head(url, allow_redirects=True) # type: Response |
|
31
|
|
|
response.raise_for_status() |
|
32
|
|
|
|
|
33
|
|
|
# Get some information about the file we are downloading |
|
34
|
|
|
filesize = naturalsize(response.headers.get('content-length', 0)) |
|
35
|
|
|
filetype = response.headers.get('content-type', 'Unknown') |
|
36
|
|
|
|
|
37
|
|
|
# Format the information output |
|
38
|
|
|
info_lines = [ |
|
39
|
|
|
click.style('Saving to: ', bold=True) + filename, |
|
40
|
|
|
click.style('File type: ', bold=True) + filetype, |
|
41
|
|
|
click.style('File size: ', bold=True) + filesize |
|
42
|
|
|
] |
|
43
|
|
|
|
|
44
|
|
|
if progress_data: |
|
45
|
|
|
for key, value in progress_data.items(): |
|
46
|
|
|
info_lines.append('{key} {value}'.format(key=click.style(key + ':', bold=True), value=value)) |
|
47
|
|
|
|
|
48
|
|
|
# Print the static information now |
|
49
|
|
|
click.echo() |
|
50
|
|
|
for line in info_lines: |
|
51
|
|
|
click.echo(line) |
|
52
|
|
|
|
|
53
|
|
|
# Now let's make the real download request |
|
54
|
|
|
response = session.get(url, allow_redirects=True) # type: Response |
|
55
|
|
|
|
|
56
|
|
|
# Process the download |
|
57
|
|
|
with open(filename, 'wb') as file: |
|
58
|
|
|
length = int(response.headers.get('content-length', 0)) |
|
59
|
|
|
|
|
60
|
|
|
with click.progressbar(response.iter_content(1024), (length / 1024)) as progress: |
|
61
|
|
|
for chunk in progress: |
|
62
|
|
|
if chunk: |
|
63
|
|
|
file.write(chunk) |
|
64
|
|
|
file.flush() |
|
65
|
|
|
|
|
66
|
|
|
|
|
67
|
|
|
def sanitize_filename(name): |
|
68
|
|
|
""" |
|
69
|
|
|
Replace reserved characters/names with underscores (windows) |
|
70
|
|
|
|
|
71
|
|
|
Args: |
|
72
|
|
|
name(str) |
|
73
|
|
|
|
|
74
|
|
|
Returns: |
|
75
|
|
|
str |
|
76
|
|
|
""" |
|
77
|
|
|
if isinstance(name, int): |
|
78
|
|
|
return str(name) |
|
79
|
|
|
|
|
80
|
|
|
if os.sep == '/': |
|
81
|
|
|
bad_chars = re.compile(r'^\.|\.$|^ | $|^$|\?|:|<|>|\||\*|\"|/') |
|
82
|
|
|
else: |
|
83
|
|
|
bad_chars = re.compile(r'^\.|\.$|^ | $|^$|\?|:|<|>|/|\||\*|\"|\\') |
|
84
|
|
|
|
|
85
|
|
|
bad_names = re.compile(r'(aux|com[1-9]|con|lpt[1-9]|prn)(\.|$)') |
|
86
|
|
|
|
|
87
|
|
|
# Unescape '&', '<', and '>' |
|
88
|
|
|
name = html.unescape(name) |
|
89
|
|
|
|
|
90
|
|
|
# Replace bad characters with an underscore |
|
91
|
|
|
name = bad_chars.sub('_', name) |
|
92
|
|
|
if bad_names.match(name): |
|
93
|
|
|
name = '_' + name |
|
94
|
|
|
|
|
95
|
|
|
# Replace newlines with spaces |
|
96
|
|
|
name = name.replace("\r", '') |
|
97
|
|
|
name = name.replace("\n", ' ') |
|
98
|
|
|
|
|
99
|
|
|
# Yavos (?) |
|
100
|
|
|
while name.find('.\\') != -1: |
|
101
|
|
|
name = name.replace('.\\', '\\') |
|
102
|
|
|
|
|
103
|
|
|
name = name.replace('\\', os.sep) |
|
104
|
|
|
|
|
105
|
|
|
# Replace tab characters with spaces |
|
106
|
|
|
name = name.replace('\t', ' ') |
|
107
|
|
|
|
|
108
|
|
|
# Cut to 125 characters |
|
109
|
|
|
if len(name) > 125: |
|
110
|
|
|
name = name[:125] |
|
111
|
|
|
|
|
112
|
|
|
# Remove unicode control characters |
|
113
|
|
|
name = ''.join(char for char in name if unicodedata.category(char)[0] != "C") |
|
114
|
|
|
|
|
115
|
|
|
return name.strip() |
|
116
|
|
|
|
FujiMakoto /
tumdlr
