ZaclysIndustries/searxngRebrandZaclys
2
0
Fork 0
forked from zaclys/searxng
Code Issues Pull requests Activity

Few fixes on Vimeo

Browse source 
Change URL from https to http
Change way of handling text xpath
This commit is contained in:
Cqoicebordel 2015-01-03 23:55:50 +01:00
parent 4450ed5503
commit 3aa3a4633f
1 changed files with 8 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
searx/engines/vimeo.py
View file

@ -13,24 +13,23 @@
# @todo set content-parameter with correct data # @todo set content-parameter with correct data
from urllib import urlencode from urllib import urlencode
from HTMLParser import HTMLParser
from lxml import html from lxml import html
from searx.engines.xpath import extract_text
from dateutil import parser from dateutil import parser
from cgi import escape
# engine dependent config # engine dependent config
categories = ['videos'] categories = ['videos']
paging = True paging = True
# search-url # search-url
base_url = 'https://vimeo.com' base_url = 'http://vimeo.com'
search_url = base_url + '/search/page:{pageno}?{query}' search_url = base_url + '/search/page:{pageno}?{query}'
# specific xpath variables # specific xpath variables
url_xpath = './a/@href'
content_xpath = './a/img/@src'
title_xpath = './a/div[@class="data"]/p[@class="title"]/text()'
results_xpath = '//div[@id="browse_content"]/ol/li' results_xpath = '//div[@id="browse_content"]/ol/li'
url_xpath = './a/@href'
title_xpath = './a/div[@class="data"]/p[@class="title"]'
content_xpath = './a/img/@src'
publishedDate_xpath = './/p[@class="meta"]//attribute::datetime' publishedDate_xpath = './/p[@class="meta"]//attribute::datetime'
@ -39,10 +38,6 @@ def request(query, params):
params['url'] = search_url.format(pageno=params['pageno'], params['url'] = search_url.format(pageno=params['pageno'],
query=urlencode({'q': query})) query=urlencode({'q': query}))
# TODO required?
params['cookies']['__utma'] =\
'00000000.000#0000000.0000000000.0000000000.0000000000.0'
return params return params
@ -52,15 +47,12 @@ def response(resp):
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
p = HTMLParser()
# parse results # parse results
for result in dom.xpath(results_xpath): for result in dom.xpath(results_xpath):
url = base_url + result.xpath(url_xpath)[0] url = base_url + result.xpath(url_xpath)[0]
title = p.unescape(extract_text(result.xpath(title_xpath))) title = escape(html.tostring(result.xpath(title_xpath)[0], method='text', encoding='UTF-8').decode("utf-8"))
thumbnail = extract_text(result.xpath(content_xpath)[0]) thumbnail = result.xpath(content_xpath)[0]
publishedDate = parser.parse(extract_text( publishedDate = parser.parse(result.xpath(publishedDate_xpath)[0])
result.xpath(publishedDate_xpath)[0]))
# append result # append result
results.append({'url': url, results.append({'url': url,