blob: 486c76d40981e663aeac70f3bcb8a64f08911d53 (
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
|
from urllib import urlencode
from HTMLParser import HTMLParser
from xpath import extract_text
from lxml import html
base_url = 'http://vimeo.com'
search_url = base_url + '/search?{query}'
# the cookie set by vime contains all the following values, but only __utma seems to be requiered
Cookie = {
#'vuid':'918282893.1027205400'
# 'ab_bs':'%7B%223%22%3A279%7D'
'__utma':'00000000.000#0000000.0000000000.0000000000.0000000000.0'
# '__utmb':'18302654.1.10.1388942090'
#, '__utmc':'18302654'
#, '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)'
#, '__utml':'search'
}
def request(query, params):
params['url'] = search_url.format(query=urlencode({'q' :query}))
print params['url']
params['cookies'] = Cookie
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
p = HTMLParser()
for result in dom.xpath(results_xpath):
url = base_url + result.xpath(url_xpath)[0]
title = p.unescape(extract_text(result.xpath(title_xpath)))
content = '<a href="{0}"> <img src="{2}"/> </a>'.format(url, title, extract_text(result.xpath(content_xpath)[0]))
results.append({'url': url, 'title': title, 'content': content})
return results
|
