diff options
author | Venca24 <Venca24@users.noreply.github.com> | 2019-07-25 07:46:41 +0200 |
---|---|---|
committer | Alexandre Flament <alex@al-f.net> | 2019-07-25 07:46:41 +0200 |
commit | 87baa74a863ac74ae4c86bbfcb04148ba7f70696 (patch) | |
tree | 8a24ac0c78f4b3e5e5f02fecf327d613fb928d62 /searx/engines | |
parent | d0dd296424d306049582a5a1b2fa01cbe7d7ce20 (diff) | |
download | searxng-87baa74a863ac74ae4c86bbfcb04148ba7f70696.tar.gz searxng-87baa74a863ac74ae4c86bbfcb04148ba7f70696.zip |
[fix] fixes google play engines and adds thumbnails to their results (#1612)
fix google play apps, google play apps, google play music engines
xpath engine: thumbnail_xpath can define an optional thumbnail
Diffstat (limited to 'searx/engines')
-rw-r--r-- | searx/engines/xpath.py | 18 |
1 files changed, 16 insertions, 2 deletions
diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py index 50f98d935..a5f30d86d 100644 --- a/searx/engines/xpath.py +++ b/searx/engines/xpath.py @@ -7,6 +7,7 @@ search_url = None url_xpath = None content_xpath = None title_xpath = None +thumbnail_xpath = False paging = False suggestion_xpath = '' results_xpath = '' @@ -40,7 +41,9 @@ def extract_text(xpath_results): return ''.join(xpath_results) else: # it's a element - text = html.tostring(xpath_results, encoding='unicode', method='text', with_tail=False) + text = html.tostring( + xpath_results, encoding='unicode', method='text', with_tail=False + ) text = text.strip().replace('\n', ' ') return ' '.join(text.split()) @@ -105,7 +108,18 @@ def response(resp): url = extract_url(result.xpath(url_xpath), search_url) title = extract_text(result.xpath(title_xpath)) content = extract_text(result.xpath(content_xpath)) - results.append({'url': url, 'title': title, 'content': content}) + tmp_result = {'url': url, 'title': title, 'content': content} + + # add thumbnail if available + thumbnail = None + if thumbnail_xpath: + thumbnail = extract_url( + result.xpath(thumbnail_xpath), search_url + ) + if thumbnail: + tmp_result['img_src'] = thumbnail + + results.append(tmp_result) else: for url, title, content in zip( (extract_url(x, search_url) for |