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
|
import re
import types
import urllib
import logging
import requests
from hashlib import md5
from flask import request, url_for
import conf
logger = logging.getLogger(__name__)
def default_handler(obj, role='admin'):
"""JSON handler for default query formatting"""
if hasattr(obj, 'isoformat'):
return obj.isoformat()
if hasattr(obj, 'dump'):
return obj.dump(role=role)
if isinstance(obj, (set, frozenset, types.GeneratorType)):
return list(obj)
if isinstance(obj, BaseException):
return str(obj)
raise TypeError("Object of type %s with value of %r "
"is not JSON serializable" % (type(obj), obj))
def try_keys(dico, *keys):
for key in keys:
if key in dico:
return dico[key]
return
def rebuild_url(url, base_split):
split = urllib.parse.urlsplit(url)
if split.scheme and split.netloc:
return url # url is fine
new_split = urllib.parse.SplitResult(
scheme=split.scheme or base_split.scheme,
netloc=split.netloc or base_split.netloc,
path=split.path, query='', fragment='')
return urllib.parse.urlunsplit(new_split)
def try_get_icon_url(url, *splits):
for split in splits:
if split is None:
continue
rb_url = rebuild_url(url, split)
response = None
# if html in content-type, we assume it's a fancy 404 page
try:
response = jarr_get(rb_url)
content_type = response.headers.get('content-type', '')
except Exception:
pass
else:
if response is not None and response.ok \
and 'html' not in content_type and response.content:
return response.url
return None
def to_hash(text):
return md5(text.encode('utf8') if hasattr(text, 'encode') else text)\
.hexdigest()
def clear_string(data):
"""
Clear a string by removing HTML tags, HTML special caracters
and consecutive white spaces (more that one).
"""
p = re.compile('<[^>]+>') # HTML tags
q = re.compile('\s') # consecutive white spaces
return p.sub('', q.sub(' ', data))
def redirect_url(default='home'):
return request.args.get('next') or request.referrer or url_for(default)
async def jarr_get(url, **kwargs):
request_kwargs = {'verify': False, 'allow_redirects': True,
'timeout': conf.CRAWLER_TIMEOUT,
'headers': {'User-Agent': conf.CRAWLER_USER_AGENT}}
request_kwargs.update(kwargs)
return requests.get(url, **request_kwargs)
|
