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
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
#!/usr/bin/env python
"""Sniffs different file types in a given URL."""
import argparse
import re
import typing
import contextlib
import requests # type:ignore
import bs4 # type:ignore
def log_error(error):
"""A logger wrapper."""
print(error)
def simple_get(url) -> typing.Optional[typing.ByteString]:
"""A simple get wrapper."""
try:
with contextlib.closing(
requests.get(url, stream=True, timeout=10)
) as resp:
if is_good_response(resp):
return resp.content
return None
except requests.exceptions.RequestException as error:
log_error(
f"Error during requests to {0} : {1}".format(url, str(error))
)
return None
def is_good_response(resp):
"""Checks if the response we get is a good response."""
content_type = resp.headers["Content-Type"].lower()
return (
resp.status_code == 200
and content_type is not None
and content_type.find("html") > -1
)
# pylint: disable=too-few-public-methods
class Argparser:
"""Argparser"""
def __init__(self):
parser = argparse.ArgumentParser()
parser.add_argument("--src", type=str, help="url")
parser.add_argument("--str", type=str, help="what string to look for")
parser.add_argument(
"--vid", action="store_true", help="video", default=False
)
parser.add_argument(
"--img", action="store_true", help="sniff images", default=False
)
parser.add_argument(
"--url", action="store_true", help="url", default=False
)
self.args = parser.parse_args()
VID_FMTS = [
"webm",
"mpg",
"mp2",
"mpeg",
"mpe",
"mpv",
"ogg",
"mp4",
"m4p",
"m4v",
"flv",
"avi",
"wmv",
"mkv",
"svi",
]
def image_finder(url: str) -> None:
"""Sniffs images."""
# raw_url_content = simple_get(url)
response = requests.get(url, timeout=10, allow_redirects=True)
# print(response.content)
if response.content is None:
return None
soup = bs4.BeautifulSoup(response.content, "lxml")
search_results = soup.findAll("img")
for result in search_results:
print(result["src"])
# img_response = requests.get(
# result["src"], timeout=10, allow_redirects=True
# )
return None
def main() -> None:
"""Entry point."""
argparser = Argparser()
if argparser.args.img:
image_finder(argparser.args.src)
raw_ml = simple_get(argparser.args.src)
ml_str = repr(bs4.BeautifulSoup(raw_ml, "lxml"))
tmp = open("/tmp/riecher", "w", encoding="utf-8")
tmp.write(ml_str)
tmp.close()
tmp = open("/tmp/riecher", "r", encoding="utf-8")
if argparser.args.src:
if argparser.args.vid:
for line in tmp:
for elem in VID_FMTS:
if line.find("." + elem) > -1:
print(line)
if argparser.args.url:
dump_list = []
for line in tmp:
dummy = re.findall(
"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|"
r"(?:%[0-9a-fA-F][0-9a-fA-F]))+",
line,
)
dump_list += dummy
for elem in dump_list:
print(elem)
tmp.close()
if __name__ == "__main__":
main()
|
