searx

commit: 0549fb40d2ab0b14354e680880b0de3d9d770452
parent 9d9a592266ffc4f257be5c0f7519a19436672cf5
Author: jcherqui <joachim.cherqui@viacesi.fr>
Date:   Sun, 15 Jan 2017 14:24:19 +0100

Add 1337x.to engine

Diffstat:
A
searx/engines/1337x.py
29
+++++++++++++++++++++++++++++
M
searx/settings.yml
4
++++

2 files changed, 33 insertions(+), 0 deletions(-)
diff --git a/searx/engines/1337x.py b/searx/engines/1337x.py
@@ -0,0 +1,29 @@
+from urllib import quote
+from lxml import html
+from searx.engines.xpath import extract_text
+from urlparse import urljoin
+
+url = 'https://1337x.to/'
+search_url = url + 'search/{search_term}/{pageno}/'
+categories = ['videos', 'music', 'files']
+paging = True
+
+def request(query, params):
+    params['url'] = search_url.format(search_term=quote(query), pageno=params['pageno'])
+
+    return params
+
+def response(resp):
+    results = []
+
+    dom = html.fromstring(resp.text)
+
+    for result in dom.xpath('//table[contains(@class, "table-list")]/tbody//tr'):
+        href = urljoin(url, result.xpath('./td[contains(@class, "name")]/a[2]/@href')[0])
+        title = extract_text(result.xpath('./td[contains(@class, "name")]/a[2]'))
+
+        results.append({'url': href,
+                        'title': title,
+                        'content': ''})
+
+    return results
diff --git a/searx/settings.yml b/searx/settings.yml
@@ -588,6 +588,10 @@ engines:
     timeout : 10.0
     disabled : True
 
+  - name : 1337x
+    engine : 1337x
+    shortcut : 1337x
+    disabled : False
 
 #The blekko technology and team have joined IBM Watson! -> https://blekko.com/
 #  - name : blekko images