searxngRebrandZaclys/searx/engines/vimeo.py

42 lines
1.3 KiB
Python
Raw Normal View History

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}'
2014-01-11 10:14:46 +00:00
url_xpath = None
content_xpath = None
title_xpath = None
results_xpath = ''
2014-01-11 10:14:46 +00:00
# the cookie set by vimeo 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}))
2014-01-11 10:14:46 +00:00
params['cookies'] = cookie
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
2014-01-11 10:14:46 +00:00
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