diff options
| author | pw3t <romain@berthor.fr> | 2014-01-05 17:57:55 +0100 |
|---|---|---|
| committer | pw3t <romain@berthor.fr> | 2014-01-05 17:57:55 +0100 |
| commit | 0d93ad20186937f86ca9101c1c7453e99c282107 (patch) | |
| tree | 1ff55038c8df267d8a3a1d4f33fbd4101546bf5d /searx/engines/startpage.py | |
| parent | 89183ed985157540c42c73c5a303dd574c227c7f (diff) | |
| parent | 5c9f6d51746796ef63cd08d27c31e931272e083f (diff) | |
Merge branch 'master' of https://github.com/asciimoo/searx
Diffstat (limited to 'searx/engines/startpage.py')
| -rw-r--r-- | searx/engines/startpage.py | 11 |
1 files changed, 5 insertions, 6 deletions
diff --git a/searx/engines/startpage.py b/searx/engines/startpage.py index 061c8158d..87c091e2d 100644 --- a/searx/engines/startpage.py +++ b/searx/engines/startpage.py @@ -19,14 +19,13 @@ def response(resp): global base_url results = [] dom = html.fromstring(resp.content) - for result in dom.xpath('//div[@class="result"]'): + # ads xpath //div[@id="results"]/div[@id="sponsored"]//div[@class="result"] + # not ads : div[@class="result"] are the direct childs of div[@id="results"] + for result in dom.xpath('//div[@id="results"]/div[@class="result"]'): link = result.xpath('.//h3/a')[0] url = link.attrib.get('href') parsed_url = urlparse(url) - # TODO better google link detection - if parsed_url.netloc.find('www.google.com') >= 0: - continue - title = ' '.join(link.xpath('.//text()')) - content = escape(' '.join(result.xpath('.//p[@class="desc"]//text()'))) + title = link.text_content() + content = result.xpath('./p[@class="desc"]')[0].text_content() results.append({'url': url, 'title': title, 'content': content}) return results |