From c3daa08537668c24224fffecbed4347fee936fcf Mon Sep 17 00:00:00 2001
From: a01200356 <a01200356@itesm.mx>
Date: Thu, 19 May 2016 00:38:43 -0500
Subject: [enh] Add onions category with Ahmia, Not Evil and Torch

Xpath engine and results template changed to account for the fact that
archive.org doesn't cache .onions, though some onion engines migth have
their own cache.

Disabled by default. Can be enabled by setting the SOCKS proxies to
wherever Tor is listening and setting using_tor_proxy as True.

Requires Tor and updating packages.

To avoid manually adding the timeout on each engine, you can set
extra_proxy_timeout to account for Tor's (or whatever proxy used) extra
time.
---
 searx/engines/not_evil.py | 64 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)
 create mode 100644 searx/engines/not_evil.py

(limited to 'searx/engines/not_evil.py')

diff --git a/searx/engines/not_evil.py b/searx/engines/not_evil.py
new file mode 100644
index 000000000..e84f153bd
--- /dev/null
+++ b/searx/engines/not_evil.py
@@ -0,0 +1,64 @@
+"""
+ not Evil (Onions)
+
+ @website     http://hss3uro2hsxfogfq.onion
+ @provide-api yes (http://hss3uro2hsxfogfq.onion/api.htm)
+
+ @using-api   no
+ @results     HTML
+ @stable      no
+ @parse       url, title, content
+"""
+
+from urllib.parse import urlencode
+from lxml import html
+from searx.engines.xpath import extract_text
+
+# engine dependent config
+categories = ['onions']
+paging = True
+page_size = 20
+
+# search-url
+base_url = 'http://hss3uro2hsxfogfq.onion/'
+search_url = 'index.php?{query}&hostLimit=20&start={pageno}&numRows={page_size}'
+
+# specific xpath variables
+results_xpath = '//*[@id="content"]/div/p'
+url_xpath = './span[1]'
+title_xpath = './a[1]'
+content_xpath = './text()'
+
+
+# do search-request
+def request(query, params):
+    offset = (params['pageno'] - 1) * page_size
+
+    params['url'] = base_url + search_url.format(pageno=offset,
+                                                 query=urlencode({'q': query}),
+                                                 page_size=page_size)
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    # needed because otherwise requests guesses wrong encoding
+    resp.encoding = 'utf8'
+    dom = html.fromstring(resp.text)
+
+    # parse results
+    for result in dom.xpath(results_xpath):
+        url = extract_text(result.xpath(url_xpath)[0])
+        title = extract_text(result.xpath(title_xpath)[0])
+        content = extract_text(result.xpath(content_xpath))
+
+        # append result
+        results.append({'url': url,
+                        'title': title,
+                        'content': content,
+                        'is_onion': True})
+
+    return results
-- 
cgit v1.2.3