diff options
| author | Kirill Isakov <ukwt@ya.ru> | 2016-03-25 00:38:48 +0600 |
|---|---|---|
| committer | Kirill Isakov <ukwt@ya.ru> | 2016-03-25 00:38:48 +0600 |
| commit | 8b7dc2acb9f670ba65e4b98eb310f04e4c212bd8 (patch) | |
| tree | 7e084da807052c86423804242ef0b0ecd3687028 /searx/engines | |
| parent | d748b8419ad1ef875f34783bbbcf773ebc4cfb5e (diff) | |
| download | searxng-8b7dc2acb9f670ba65e4b98eb310f04e4c212bd8.tar.gz searxng-8b7dc2acb9f670ba65e4b98eb310f04e4c212bd8.zip | |
Remove content field from ArchWiki results; reformat code in archlinux.py
Content field in Arch Wiki search results is of no real use, more often
than not it contains no usable information and includes too many markup
tags which make the text unreadable. It is safe to remove it.
Diffstat (limited to 'searx/engines')
| -rw-r--r-- | searx/engines/archlinux.py | 17 |
1 files changed, 7 insertions, 10 deletions
diff --git a/searx/engines/archlinux.py b/searx/engines/archlinux.py index f12c4328a..84e0d0fba 100644 --- a/searx/engines/archlinux.py +++ b/searx/engines/archlinux.py @@ -3,12 +3,12 @@ """ Arch Linux Wiki - @website https://wiki.archlinux.org - @provide-api no (Mediawiki provides API, but Arch Wiki blocks access to it - @using-api no - @results HTML - @stable no (HTML can change) - @parse url, title, content + @website https://wiki.archlinux.org + @provide-api no (Mediawiki provides API, but Arch Wiki blocks access to it + @using-api no + @results HTML + @stable no (HTML can change) + @parse url, title """ from urlparse import urljoin @@ -26,7 +26,6 @@ base_url = 'https://wiki.archlinux.org' # xpath queries xpath_results = '//ul[@class="mw-search-results"]/li' xpath_link = './/div[@class="mw-search-result-heading"]/a' -xpath_content = './/div[@class="searchresult"]' # cut 'en' from 'en_US', 'de' from 'de_CH', and so on @@ -135,10 +134,8 @@ def response(resp): link = result.xpath(xpath_link)[0] href = urljoin(base_url, link.attrib.get('href')) title = escape(extract_text(link)) - content = escape(extract_text(result.xpath(xpath_content))) results.append({'url': href, - 'title': title, - 'content': content}) + 'title': title}) return results |