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
|
from urllib import urlencode
from json import loads
from collections import Iterable
search_url = None
url_query = None
content_query = None
title_query = None
#suggestion_xpath = ''
def iterate(iterable):
if type(iterable) == dict:
it = iterable.iteritems()
else:
it = enumerate(iterable)
for index, value in it:
yield str(index), value
def is_iterable(obj):
if type(obj) == str:
return False
if type(obj) == unicode:
return False
return isinstance(obj, Iterable)
def parse(query):
q = []
for part in query.split('/'):
if part == '':
continue
else:
q.append(part)
return q
def do_query(data, q):
ret = []
if not q:
return ret
qkey = q[0]
for key, value in iterate(data):
if len(q) == 1:
if key == qkey:
ret.append(value)
elif is_iterable(value):
ret.extend(do_query(value, q))
else:
if not is_iterable(value):
continue
if key == qkey:
ret.extend(do_query(value, q[1:]))
else:
ret.extend(do_query(value, q))
return ret
def query(data, query_string):
q = parse(query_string)
return do_query(data, q)
def request(query, params):
query = urlencode({'q': query})[2:]
params['url'] = search_url.format(query=query)
params['query'] = query
return params
def response(resp):
results = []
json = loads(resp.text)
urls = query(json, url_query)
contents = query(json, content_query)
titles = query(json, title_query)
for url, title, content in zip(urls, titles, contents):
results.append({'url': url, 'title': title, 'content': content})
return results
|
