logo

searx

My custom branche(s) on searx, a meta-search engine
commit: 3b672039aab207d0002eac9d7406f0c5b3239df0
parent: 7b531c6fcefe1c0c5cc19967454cdddb6e1c8fbd
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Tue,  6 Jan 2015 18:38:04 +0100

Merge pull request #167 from Cqoicebordel/minor-fixes

Minor fixes

Diffstat:

Msearx/engines/digg.py3+++
Msearx/engines/vimeo.py22+++++++---------------
2 files changed, 10 insertions(+), 15 deletions(-)

diff --git a/searx/engines/digg.py b/searx/engines/digg.py @@ -44,6 +44,9 @@ def response(resp): search_result = loads(resp.text) + if search_result['html'] == '': + return results + dom = html.fromstring(search_result['html']) # parse results diff --git a/searx/engines/vimeo.py b/searx/engines/vimeo.py @@ -13,24 +13,23 @@ # @todo set content-parameter with correct data from urllib import urlencode -from HTMLParser import HTMLParser from lxml import html -from searx.engines.xpath import extract_text from dateutil import parser +from cgi import escape # engine dependent config categories = ['videos'] paging = True # search-url -base_url = 'https://vimeo.com' +base_url = 'http://vimeo.com' search_url = base_url + '/search/page:{pageno}?{query}' # specific xpath variables +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' -title_xpath = './a/div[@class="data"]/p[@class="title"]/text()' -results_xpath = '//div[@id="browse_content"]/ol/li' publishedDate_xpath = './/p[@class="meta"]//attribute::datetime' @@ -39,10 +38,6 @@ def request(query, params): params['url'] = search_url.format(pageno=params['pageno'], query=urlencode({'q': query})) - # TODO required? - params['cookies']['__utma'] =\ - '00000000.000#0000000.0000000000.0000000000.0000000000.0' - return params @@ -52,15 +47,12 @@ def response(resp): dom = html.fromstring(resp.text) - p = HTMLParser() - # parse results for result in dom.xpath(results_xpath): url = base_url + result.xpath(url_xpath)[0] - title = p.unescape(extract_text(result.xpath(title_xpath))) - thumbnail = extract_text(result.xpath(content_xpath)[0]) - publishedDate = parser.parse(extract_text( - result.xpath(publishedDate_xpath)[0])) + title = escape(html.tostring(result.xpath(title_xpath)[0], method='text', encoding='UTF-8').decode("utf-8")) + thumbnail = result.xpath(content_xpath)[0] + publishedDate = parser.parse(result.xpath(publishedDate_xpath)[0]) # append result results.append({'url': url,