Merge pull request #219 from pointhi/new_engines

New engines: gigablast and blekko_images

2 files changed, 119 insertions, 0 deletions

diff --git a/searx/engines/blekko_images.py b/searx/engines/blekko_images.py
new file mode 100644
index 000000000..2bae9c35e
--- /dev/null
+++ b/searx/engines/blekko_images.py
@@ -0,0 +1,56 @@
+## Blekko (Images)
+#
+# @website     https://blekko.com
+# @provide-api yes (inofficial)
+#
+# @using-api   yes
+# @results     JSON
+# @stable      yes
+# @parse       url, title, img_src
+
+from json import loads
+from urllib import urlencode
+
+# engine dependent config
+categories = ['images']
+paging = True
+
+# search-url
+base_url = 'https://blekko.com'
+search_url = '/api/images?{query}&c={c}'
+
+
+# do search-request
+def request(query, params):
+    c = (params['pageno'] - 1) * 48
+
+    params['url'] = base_url +\
+        search_url.format(query=urlencode({'q': query}),
+                          c=c)
+
+    if params['pageno'] != 1:
+        params['url'] += '&page={pageno}'.format(pageno=(params['pageno']-1))
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    search_results = loads(resp.text)
+
+    # return empty array if there are no results
+    if not search_results:
+        return []
+
+    for result in search_results:
+        # append result
+        results.append({'url': result['page_url'],
+                        'title': result['title'],
+                        'content': '',
+                        'img_src': result['url'],
+                        'template': 'images.html'})
+
+    # return results
+    return results
diff --git a/searx/engines/gigablast.py b/searx/engines/gigablast.py
new file mode 100644
index 000000000..8749c3256
--- /dev/null
+++ b/searx/engines/gigablast.py
@@ -0,0 +1,63 @@
+## Gigablast (Web)
+#
+# @website     http://gigablast.com
+# @provide-api yes (http://gigablast.com/api.html)
+#
+# @using-api   yes
+# @results     XML
+# @stable      yes
+# @parse       url, title, content
+
+from urllib import urlencode
+from cgi import escape
+from lxml import etree
+
+# engine dependent config
+categories = ['general']
+paging = True
+number_of_results = 5
+
+# search-url
+base_url = 'http://gigablast.com/'
+search_string = 'search?{query}&n={number_of_results}&s={offset}&xml=1&qh=0'
+
+# specific xpath variables
+results_xpath = '//response//result'
+url_xpath = './/url'
+title_xpath = './/title'
+content_xpath = './/sum'
+
+
+# do search-request
+def request(query, params):
+    offset = (params['pageno'] - 1) * number_of_results
+
+    search_path = search_string.format(
+        query=urlencode({'q': query}),
+        offset=offset,
+        number_of_results=number_of_results)
+
+    params['url'] = base_url + search_path
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    dom = etree.fromstring(resp.content)
+
+    # parse results
+    for result in dom.xpath(results_xpath):
+        url = result.xpath(url_xpath)[0].text
+        title = result.xpath(title_xpath)[0].text
+        content = escape(result.xpath(content_xpath)[0].text)
+
+        # append result
+        results.append({'url': url,
+                        'title': title,
+                        'content': content})
+
+    # return results
+    return results