searx

commit: ff0bbd3566ea126b0cd0cb8b9c60d30c8105e765
parent: 141b04c6dde9df0e6b7f2e2b30ec8131429c8932
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Mon, 30 Dec 2013 14:04:37 -0800

Merge pull request #10 from dalf/master

bug fixes and dailymotion engine
Diffstat:
M
engines.cfg_sample
5
+++++
A
searx/engines/dailymotion.py
32
++++++++++++++++++++++++++++++++
M
searx/engines/flickr.py
2
+-
M
searx/engines/xpath.py
2
+-

4 files changed, 39 insertions(+), 2 deletions(-)
diff --git a/engines.cfg_sample b/engines.cfg_sample
@@ -79,3 +79,8 @@ suggestion_xpath = //div[@id="satat"]//a
 [youtube]
 engine = youtube
 categories = videos
+
+[dailymotion]
+engine = dailymotion
+categories = videos
+
diff --git a/searx/engines/dailymotion.py b/searx/engines/dailymotion.py
@@ -0,0 +1,32 @@
+from urllib import urlencode
+from json import loads
+from cgi import escape
+
+categories = ['videos']
+localization = 'en'
+
+# see http://www.dailymotion.com/doc/api/obj-video.html
+search_url = 'https://api.dailymotion.com/videos?fields=title,description,duration,url,thumbnail_360_url&sort=relevance&limit=25&page=1&{query}'
+
+def request(query, params):
+    global search_url
+    params['url'] = search_url.format(query=urlencode({'search': query, 'localization': localization }))
+    return params
+
+
+def response(resp):
+    results = []
+    search_res = loads(resp.text)
+    if not 'list' in search_res:
+        return results
+    for res in search_res['list']:
+        title = res['title']
+        url = res['url']
+        if res['thumbnail_360_url']:
+            content = '<a href="{0}" title="{0}" ><img src="{1}" /></a><br />'.format(url, res['thumbnail_360_url'])
+        else:
+            content = ''
+        if res['description']:
+            content += escape(res['description'][:500])
+        results.append({'url': url, 'title': title, 'content': content})
+    return results
diff --git a/searx/engines/flickr.py b/searx/engines/flickr.py
@@ -7,7 +7,7 @@ from urlparse import urljoin
 categories = ['images']
 
 url = 'https://secure.flickr.com/'
-search_url = url+'search/?q={query}'
+search_url = url+'search/?{query}'
 
 def request(query, params):
     params['url'] = search_url.format(query=urlencode({'q': query}))
diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py
@@ -28,7 +28,7 @@ def extract_url(xpath_results):
             url = xpath_results[0].attrib.get('href')
     else:
         url = xpath_results.attrib.get('href')
-    if not url.startswith('http://') or not url.startswith('https://'):
+    if not url.startswith('http://') and not url.startswith('https://'):
         url = 'http://'+url
     parsed_url = urlparse(url)
     if not parsed_url.netloc: