blob: 2743dc2a08e13308d5f7ed279df5dc0462f45033 (
plain)
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
|
from lxml import html
from urllib import urlencode
from urlparse import urlparse, urljoin
from cgi import escape
from lxml.etree import _ElementStringResult
search_url = None
url_xpath = None
content_xpath = None
title_xpath = None
results_xpath = ''
def extract_url(xpath_results):
url = ''
parsed_search_url = urlparse(search_url)
if type(xpath_results) == list:
if not len(xpath_results):
raise Exception('Empty url resultset')
if type(xpath_results[0]) == _ElementStringResult:
url = ''.join(xpath_results)
if url.startswith('//'):
url = parsed_search_url.scheme+url
elif url.startswith('/'):
url = urljoin(search_url, url)
#TODO
else:
url = xpath_results[0].attrib.get('href')
else:
url = xpath_results.attrib.get('href')
if not url.startswith('http://') or not url.startswith('https://'):
url = 'http://'+url
parsed_url = urlparse(url)
if not parsed_url.netloc:
raise Exception('Cannot parse url')
if not parsed_url.path:
url += '/'
return url
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 = []
dom = html.fromstring(resp.text)
if results_xpath:
for result in dom.xpath(results_xpath):
url = extract_url(result.xpath(url_xpath))
title = ' '.join(result.xpath(title_xpath))
content = escape(' '.join(result.xpath(content_xpath)))
results.append({'url': url, 'title': title, 'content': content})
else:
for content, url, title in zip(dom.xpath(content_xpath), map(extract_url, dom.xpath(url_xpath)), dom.xpath(title_xpath)):
results.append({'url': url, 'title': title, 'content': content})
return results
|
