diff options
Diffstat (limited to 'searx/engines/www1x.py')
| -rw-r--r-- | searx/engines/www1x.py | 35 |
1 files changed, 6 insertions, 29 deletions
diff --git a/searx/engines/www1x.py b/searx/engines/www1x.py index 508803240..f1154b16d 100644 --- a/searx/engines/www1x.py +++ b/searx/engines/www1x.py @@ -11,8 +11,8 @@ """ from lxml import html -import re from searx.url_utils import urlencode, urljoin +from searx.engines.xpath import extract_text # engine dependent config categories = ['images'] @@ -34,41 +34,18 @@ def request(query, params): def response(resp): results = [] - # get links from result-text - regex = re.compile('(</a>|<a)') - results_parts = re.split(regex, resp.text) - - cur_element = '' - - # iterate over link parts - for result_part in results_parts: + dom = html.fromstring(resp.text) + for res in dom.xpath('//div[@class="List-item MainListing"]'): # processed start and end of link - if result_part == '<a': - cur_element = result_part - continue - elif result_part != '</a>': - cur_element += result_part - continue - - cur_element += result_part - - # fix xml-error - cur_element = cur_element.replace('"></a>', '"/></a>') - - dom = html.fromstring(cur_element) - link = dom.xpath('//a')[0] + link = res.xpath('//a')[0] url = urljoin(base_url, link.attrib.get('href')) - title = link.attrib.get('title', '') + title = extract_text(link) - thumbnail_src = urljoin(base_url, link.xpath('.//img')[0].attrib['src']) + thumbnail_src = urljoin(base_url, res.xpath('.//img')[0].attrib['src']) # TODO: get image with higher resolution img_src = thumbnail_src - # check if url is showing to a photo - if '/photo/' not in url: - continue - # append result results.append({'url': url, 'title': title, |