commit: fafc564874c63e2c8fb5082c944779c1572e2f15
parent: 357fc47811a1de5a273622881574dbde23c7cb59
Author: Adam Tauber <asciimoo@gmail.com>
Date: Sat, 31 Oct 2015 15:27:23 +0100
[enh] yandex engine added
Diffstat:
2 files changed, 60 insertions(+), 0 deletions(-)
diff --git a/searx/engines/yandex.py b/searx/engines/yandex.py
@@ -0,0 +1,55 @@
+"""
+ Yahoo (Web)
+
+ @website https://yandex.ru/
+ @provide-api ?
+ @using-api no
+ @results HTML (using search portal)
+ @stable no (HTML can change)
+ @parse url, title, content
+"""
+
+from urllib import urlencode
+from lxml import html
+from searx.search import logger
+
+logger = logger.getChild('yandex engine')
+
+# engine dependent config
+categories = ['general']
+paging = True
+language_support = True # TODO
+
+# search-url
+base_url = 'https://yandex.ru/'
+search_url = 'search/?{query}&p={page}'
+
+results_xpath = '//div[@class="serp-item serp-item_plain_yes clearfix i-bem"]'
+url_xpath = './/h2/a/@href'
+title_xpath = './/h2/a//text()'
+content_xpath = './/div[@class="serp-item__text"]//text()'
+
+
+def request(query, params):
+ params['url'] = base_url + search_url.format(page=params['pageno']-1,
+ query=urlencode({'text': query}))
+ return params
+
+
+# get response from search-request
+def response(resp):
+ dom = html.fromstring(resp.text)
+ results = []
+
+ for result in dom.xpath(results_xpath):
+ try:
+ res = {'url': result.xpath(url_xpath)[0],
+ 'title': ''.join(result.xpath(title_xpath)),
+ 'content': ''.join(result.xpath(content_xpath))}
+ except:
+ logger.exception('yandex parse crash')
+ continue
+
+ results.append(res)
+
+ return results
diff --git a/searx/settings.yml b/searx/settings.yml
@@ -274,6 +274,11 @@ engines:
engine : yahoo
shortcut : yh
+ - name : yandex
+ engine : yandex
+ shortcut : ya
+ disabled : True
+
- name : yahoo news
engine : yahoo_news
shortcut : yhn