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
134
135
136
137
138
139
140
141
142
143
144
|
import ipaddress, re, signal, socket, traceback, typing
import urllib.error, urllib.parse
import json as _json
import bs4, netifaces, requests
from src import utils
REGEX_URL = re.compile("https?://[A-Z0-9{}]+".format(re.escape("-._~:/%?#[]@!$&'()*+,;=")), re.I)
# best-effort tidying up of URLs
def url_validate(url: str):
if url.endswith(")"):
# trim ")" from the end only if there's not a "(" to match it
# google.com/) -> google.com/
# google.com/() -> google.com/()
# google.com/()) -> google.com/()
if "(" in url:
open_index = url.rfind("(")
other_index = url.rfind(")", 0, len(url)-1)
if other_index == -1 or other_index < open_index:
return url
return url[:-1]
return url
USER_AGENT = ("Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/49.0.2623.87 Safari/537.36")
RESPONSE_MAX = (1024*1024)*100
SOUP_CONTENT_TYPES = ["text/html", "text/xml", "application/xml"]
class HTTPException(Exception):
pass
class HTTPTimeoutException(HTTPException):
def __init__(self):
Exception.__init__(self, "HTTP request timed out")
class HTTPParsingException(HTTPException):
def __init__(self, message: str=None):
Exception.__init__(self, message or "HTTP parsing failed")
class HTTPWrongContentTypeException(HTTPException):
def __init__(self, message: str=None):
Exception.__init__(self,
message or "HTTP request gave wrong content type")
def throw_timeout():
raise HTTPTimeoutException()
class Response(object):
def __init__(self, code: int, data: typing.Any,
headers: typing.Dict[str, str]):
self.code = code
self.data = data
self.headers = headers
def request(url: str, method: str="GET", get_params: dict={},
post_data: typing.Any=None, headers: dict={},
json_data: typing.Any=None, code: bool=False, json: bool=False,
soup: bool=False, parser: str="lxml", fallback_encoding: str="utf8",
allow_redirects: bool=True
) -> Response:
if not urllib.parse.urlparse(url).scheme:
url = "http://%s" % url
if not "Accept-Language" in headers:
headers["Accept-Language"] = "en-GB"
if not "User-Agent" in headers:
headers["User-Agent"] = USER_AGENT
signal.signal(signal.SIGALRM, lambda _1, _2: throw_timeout())
signal.alarm(5)
try:
response = requests.request(
method.upper(),
url,
headers=headers,
params=get_params,
data=post_data,
json=json_data,
allow_redirects=allow_redirects,
stream=True
)
response_content = response.raw.read(RESPONSE_MAX, decode_content=True)
except TimeoutError:
raise HTTPTimeoutException()
finally:
signal.signal(signal.SIGALRM, signal.SIG_IGN)
response_headers = utils.CaseInsensitiveDict(dict(response.headers))
content_type = response.headers["Content-Type"].split(";", 1)[0]
def _decode_data():
return response_content.decode(response.encoding or fallback_encoding)
if soup:
if content_type in SOUP_CONTENT_TYPES:
soup = bs4.BeautifulSoup(_decode_data(), parser)
return Response(response.status_code, soup, response_headers)
else:
raise HTTPWrongContentTypeException(
"Tried to soup non-html/non-xml data")
data = _decode_data()
if json and data:
try:
return Response(response.status_code, _json.loads(data),
response_headers)
except _json.decoder.JSONDecodeError as e:
raise HTTPParsingException(str(e))
return Response(response.status_code, data, response_headers)
def strip_html(s: str) -> str:
return bs4.BeautifulSoup(s, "lxml").get_text()
def resolve_hostname(hostname: str) -> typing.List[str]:
try:
addresses = socket.getaddrinfo(hostname, None, 0, socket.SOCK_STREAM)
except:
return []
return [address[-1][0] for address in addresses]
def is_ip(addr: str) -> bool:
try:
ipaddress.ip_address(addr)
except ValueError:
return False
return True
def is_localhost(hostname: str) -> bool:
if is_ip(hostname):
ips = [ipaddress.ip_address(hostname)]
else:
ips = [ipaddress.ip_address(ip) for ip in resolve_hostname(hostname)]
for interface in netifaces.interfaces():
links = netifaces.ifaddresses(interface)
for link in links.get(netifaces.AF_INET, []
)+links.get(netifaces.AF_INET6, []):
address = ipaddress.ip_address(link["addr"].split("%", 1)[0])
if address in ips:
return True
return False
|
