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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
|
import asyncio, ipaddress, re, signal, socket, traceback, typing
import urllib.error, urllib.parse
import json as _json
import bs4, netifaces, requests
import tornado.httpclient
from src import utils
REGEX_URL = re.compile("https?://\S+", re.I)
PAIRED_CHARACTERS = ["<>", "()"]
# best-effort tidying up of URLs
def url_sanitise(url: str):
if not urllib.parse.urlparse(url).scheme:
url = "http://%s" % url
for pair_start, pair_end in PAIRED_CHARACTERS:
# 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 url.endswith(pair_end):
if pair_start in url:
open_index = url.rfind("(")
other_index = url.rfind(")", 0, len(url)-1)
if not other_index == -1 and other_index < open_index:
url = url[:-1]
else:
url = 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, data: 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 _meta_content(s: str) -> typing.Dict[str, str]:
out = {}
for keyvalue in str.split(";"):
key, _, value = keyvalue.strip().partition("=")
out[key] = value
return out
def _find_encoding(soup: bs4.BeautifulSoup) -> typing.Optional[str]:
meta_charset = soup.meta.get("charset")
if not meta_charset == None:
return meta_charset
else:
meta_content_type = soup.findAll("meta",
{"http-equiv": lambda v: (v or "").lower() == "content-type"})
if meta_content_type:
return _meta_content(meta_content_type[0].get("content"))["charset"]
else:
doctype = [item for item in soup.contents if isinstance(item,
bs4.Doctype)] or None
if doctype and doctype[0] == "html":
return "utf8"
return None
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, check_content_type: 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
with utils.deadline(seconds=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)
if not response_content or not response.raw.read(1) == b"":
# response too large!
pass
except utils.DeadlineExceededException:
raise HTTPTimeoutException()
response_headers = utils.CaseInsensitiveDict(dict(response.headers))
content_type = response.headers.get("Content-Type", "").split(";", 1)[0]
souped = None
encoding = response.encoding
if content_type and content_type in SOUP_CONTENT_TYPES:
souped = bs4.BeautifulSoup(response_content, parser)
encoding = _find_encoding(souped) or encoding
def _decode_data():
return response_content.decode(encoding)
if soup:
if not check_content_type or 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 (%s)" % content_type)
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), data)
return Response(response.status_code, data, response_headers)
def request_many(urls: typing.List[str]) -> typing.Dict[str, Response]:
responses = {}
async def _request(url):
client = tornado.httpclient.AsyncHTTPClient()
request = tornado.httpclient.HTTPRequest(url, method="GET",
connect_timeout=2, request_timeout=2)
response = await client.fetch(request)
headers = utils.CaseInsensitiveDict(dict(response.headers))
data = response.body.decode("utf8")
responses[url] = Response(response.code, data, headers)
loop = asyncio.new_event_loop()
awaits = []
for url in urls:
awaits.append(_request(url))
task = asyncio.wait(awaits, loop=loop, timeout=5)
loop.run_until_complete(task)
loop.close()
return responses
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
|
