Merge pull request #208 from pointhi/new_engines

add 1x.com engine, improve yacy-engine

2 files changed, 94 insertions, 13 deletions

diff --git a/searx/engines/www1x.py b/searx/engines/www1x.py
new file mode 100644
index 000000000..a68c105ce
--- /dev/null
+++ b/searx/engines/www1x.py
@@ -0,0 +1,82 @@
+## 1x (Images)
+#
+# @website     http://1x.com/
+# @provide-api no
+#
+# @using-api   no
+# @results     HTML
+# @stable      no (HTML can change)
+# @parse       url, title, thumbnail, img_src, content
+
+
+from urllib import urlencode
+from urlparse import urljoin
+from lxml import html
+import string
+import re
+
+# engine dependent config
+categories = ['images']
+paging = False
+
+# search-url
+base_url = 'http://1x.com'
+search_url = base_url+'/backend/search.php?{query}'
+
+
+# do search-request
+def request(query, params):
+    params['url'] = search_url.format(query=urlencode({'q': query}))
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    # get links from result-text
+    regex = re.compile('(</a>|<a)')
+    results_parts = re.split(regex, resp.text)
+
+    cur_element = ''
+
+    # iterate over link parts
+    for result_part in results_parts:
+        # processed start and end of link
+        if result_part == '<a':
+            cur_element = result_part
+            continue
+        elif result_part != '</a>':
+            cur_element += result_part
+            continue
+
+        cur_element += result_part
+
+        # fix xml-error
+        cur_element = string.replace(cur_element, '"></a>', '"/></a>')
+
+        dom = html.fromstring(cur_element)
+        link = dom.xpath('//a')[0]
+
+        url = urljoin(base_url, link.attrib.get('href'))
+        title = link.attrib.get('title', '')
+
+        thumbnail_src = urljoin(base_url, link.xpath('.//img')[0].attrib['src'])
+        # TODO: get image with higher resolution
+        img_src = thumbnail_src
+
+        # check if url is showing to a photo
+        if '/photo/' not in url:
+            continue
+
+        # append result
+        results.append({'url': url,
+                        'title': title,
+                        'img_src': img_src,
+                        'content': '',
+                        'thumbnail_src': thumbnail_src,
+                        'template': 'images.html'})
+
+    # return results
+    return results
diff --git a/searx/engines/yacy.py b/searx/engines/yacy.py
index 4c4fac7df..17e2a7aab 100644
--- a/searx/engines/yacy.py
+++ b/searx/engines/yacy.py
@@ -68,9 +68,18 @@ def response(resp):
 
     search_results = raw_search_results.get('channels', {})[0].get('items', [])
 
-    if resp.search_params['category'] == 'general':
+    for result in search_results:
+        # parse image results
+        if result.get('image'):
+            # append result
+            results.append({'url': result['url'],
+                            'title': result['title'],
+                            'content': '',
+                            'img_src': result['image'],
+                            'template': 'images.html'})
+
         # parse general results
-        for result in search_results:
+        else:
             publishedDate = parser.parse(result['pubDate'])
 
             # append result
@@ -79,17 +88,7 @@ def response(resp):
                             'content': result['description'],
                             'publishedDate': publishedDate})
 
-    elif resp.search_params['category'] == 'images':
-        # parse image results
-        for result in search_results:
-            # append result
-            results.append({'url': result['url'],
-                            'title': result['title'],
-                            'content': '',
-                            'img_src': result['image'],
-                            'template': 'images.html'})
-
-    #TODO parse video, audio and file results
+        #TODO parse video, audio and file results
 
     # return results
     return results