Merge pull request #251 from Cqoicebordel/moar-engines

Moar engines

searx/engines/spotify.py

@@ -0,0 +1,60 @@
+## Spotify (Music)
+#
+# @website     https://spotify.com
+# @provide-api yes (https://developer.spotify.com/web-api/search-item/)
+#
+# @using-api   yes
+# @results     JSON
+# @stable      yes
+# @parse       url, title, content, embedded
+
+from json import loads
+from urllib import urlencode
+
+# engine dependent config
+categories = ['music']
+paging = True
+
+# search-url
+url = 'https://api.spotify.com/'
+search_url = url + 'v1/search?{query}&type=track&offset={offset}'
+
+embedded_url = '<iframe data-src="https://embed.spotify.com/?uri=spotify:track:{audioid}"\
+     width="300" height="80" frameborder="0" allowtransparency="true"></iframe>'
+
+
+# do search-request
+def request(query, params):
+    offset = (params['pageno'] - 1) * 20
+
+    params['url'] = search_url.format(query=urlencode({'q': query}),
+                                      offset=offset)
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    search_res = loads(resp.text)
+
+    # parse results
+    for result in search_res.get('tracks', {}).get('items', {}):
+        if result['type'] == 'track':
+            title = result['name']
+            url = result['external_urls']['spotify']
+            content = result['artists'][0]['name'] +\
+                " &bull; " +\
+                result['album']['name'] +\
+                " &bull; " + result['name']
+            embedded = embedded_url.format(audioid=result['id'])
+
+            # append result
+            results.append({'url': url,
+                            'title': title,
+                            'embedded': embedded,
+                            'content': content})
+
+    # return results
+    return results

searx/settings.yml

@@ -84,12 +84,6 @@ engines:
 #    shortcut : fa
 #    api_key : 'apikey' # required!
 
-# down - website is under criminal investigation by the UK
-#  - name : filecrop
-#    engine : filecrop
-#    categories : files
-#    shortcut : fc
-
   - name : 500px
     engine : www500px
     shortcut : px
@@ -109,11 +103,6 @@ engines:
 # Or you can use the html non-stable engine, activated by default
     engine : flickr_noapi
 
-  - name : general-file
-    engine : generalfile
-    shortcut : gf
-    disabled : True
-
   - name : gigablast
     engine : gigablast
     shortcut : gb
@@ -201,6 +190,10 @@ engines:
     shortcut : scc
     disabled : True
 
+  - name : spotify
+    engine : spotify
+    shortcut : stf
+
   - name : subtitleseeker
     engine : subtitleseeker
     shortcut : ss

searx/tests/engines/test_blekko_images.py

@@ -12,9 +12,14 @@ class TestBlekkoImagesEngine(SearxTestCase):
         dicto['pageno'] = 0
         dicto['safesearch'] = 1
         params = blekko_images.request(query, dicto)
-        self.assertTrue('url' in params)
-        self.assertTrue(query in params['url'])
-        self.assertTrue('blekko.com' in params['url'])
+        self.assertIn('url', params)
+        self.assertIn(query, params['url'])
+        self.assertIn('blekko.com', params['url'])
+        self.assertIn('page', params['url'])
+
+        dicto['pageno'] = 1
+        params = blekko_images.request(query, dicto)
+        self.assertNotIn('page', params['url'])
 
     def test_response(self):
         self.assertRaises(AttributeError, blekko_images.response, None)

searx/tests/engines/test_google_images.py

@@ -11,9 +11,14 @@ class TestGoogleImagesEngine(SearxTestCase):
         dicto = defaultdict(dict)
         dicto['pageno'] = 1
         params = google_images.request(query, dicto)
-        self.assertTrue('url' in params)
-        self.assertTrue(query in params['url'])
-        self.assertTrue('googleapis.com' in params['url'])
+        self.assertIn('url', params)
+        self.assertIn(query, params['url'])
+        self.assertIn('googleapis.com', params['url'])
+        self.assertIn('safe=on', params['url'])
+
+        dicto['safesearch'] = 0
+        params = google_images.request(query, dicto)
+        self.assertIn('safe=off', params['url'])
 
     def test_response(self):
         self.assertRaises(AttributeError, google_images.response, None)

searx/tests/engines/test_spotify.py

@@ -0,0 +1,124 @@
+from collections import defaultdict
+import mock
+from searx.engines import spotify
+from searx.testing import SearxTestCase
+
+
+class TestSpotifyEngine(SearxTestCase):
+
+    def test_request(self):
+        query = 'test_query'
+        dicto = defaultdict(dict)
+        dicto['pageno'] = 0
+        params = spotify.request(query, dicto)
+        self.assertIn('url', params)
+        self.assertIn(query, params['url'])
+        self.assertIn('spotify.com', params['url'])
+
+    def test_response(self):
+        self.assertRaises(AttributeError, spotify.response, None)
+        self.assertRaises(AttributeError, spotify.response, [])
+        self.assertRaises(AttributeError, spotify.response, '')
+        self.assertRaises(AttributeError, spotify.response, '[]')
+
+        response = mock.Mock(text='{}')
+        self.assertEqual(spotify.response(response), [])
+
+        response = mock.Mock(text='{"data": []}')
+        self.assertEqual(spotify.response(response), [])
+
+        json = """
+        {
+          "tracks": {
+            "href": "https://api.spotify.com/v1/search?query=nosfell&offset=0&limit=20&type=track",
+            "items": [
+              {
+                "album": {
+                  "album_type": "album",
+                  "external_urls": {
+                    "spotify": "https://open.spotify.com/album/5c9ap1PBkSGLxT3J73toxA"
+                  },
+                  "href": "https://api.spotify.com/v1/albums/5c9ap1PBkSGLxT3J73toxA",
+                  "id": "5c9ap1PBkSGLxT3J73toxA",
+                  "name": "Album Title",
+                  "type": "album",
+                  "uri": "spotify:album:5c9ap1PBkSGLxT3J73toxA"
+                },
+                "artists": [
+                  {
+                    "external_urls": {
+                      "spotify": "https://open.spotify.com/artist/0bMc6b75FfZEpQHG1jifKu"
+                    },
+                    "href": "https://api.spotify.com/v1/artists/0bMc6b75FfZEpQHG1jifKu",
+                    "id": "0bMc6b75FfZEpQHG1jifKu",
+                    "name": "Artist Name",
+                    "type": "artist",
+                    "uri": "spotify:artist:0bMc6b75FfZEpQHG1jifKu"
+                  }
+                ],
+                "disc_number": 1,
+                "duration_ms": 202386,
+                "explicit": false,
+                "external_ids": {
+                  "isrc": "FRV640600067"
+                },
+                "external_urls": {
+                  "spotify": "https://open.spotify.com/track/2GzvFiedqW8hgqUpWcASZa"
+                },
+                "href": "https://api.spotify.com/v1/tracks/2GzvFiedqW8hgqUpWcASZa",
+                "id": "1000",
+                "is_playable": true,
+                "name": "Title of track",
+                "popularity": 6,
+                "preview_url": "https://p.scdn.co/mp3-preview/7b8ecda580965a066b768c2647f877e43f7b1a0a",
+                "track_number": 3,
+                "type": "track",
+                "uri": "spotify:track:2GzvFiedqW8hgqUpWcASZa"
+              }
+            ],
+            "limit": 20,
+            "next": "https://api.spotify.com/v1/search?query=nosfell&offset=20&limit=20&type=track",
+            "offset": 0,
+            "previous": null,
+            "total": 107
+          }
+        }
+        """
+        response = mock.Mock(text=json)
+        results = spotify.response(response)
+        self.assertEqual(type(results), list)
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0]['title'], 'Title of track')
+        self.assertEqual(results[0]['url'], 'https://open.spotify.com/track/2GzvFiedqW8hgqUpWcASZa')
+        self.assertEqual(results[0]['content'], 'Artist Name • Album Title • Title of track')
+        self.assertIn('1000', results[0]['embedded'])
+
+        json = """
+        {
+          "tracks": {
+            "href": "https://api.spotify.com/v1/search?query=nosfell&offset=0&limit=20&type=track",
+            "items": [
+              {
+                "href": "https://api.spotify.com/v1/tracks/2GzvFiedqW8hgqUpWcASZa",
+                "id": "1000",
+                "is_playable": true,
+                "name": "Title of track",
+                "popularity": 6,
+                "preview_url": "https://p.scdn.co/mp3-preview/7b8ecda580965a066b768c2647f877e43f7b1a0a",
+                "track_number": 3,
+                "type": "album",
+                "uri": "spotify:track:2GzvFiedqW8hgqUpWcASZa"
+              }
+            ],
+            "limit": 20,
+            "next": "https://api.spotify.com/v1/search?query=nosfell&offset=20&limit=20&type=track",
+            "offset": 0,
+            "previous": null,
+            "total": 107
+          }
+        }
+        """
+        response = mock.Mock(text=json)
+        results = spotify.response(response)
+        self.assertEqual(type(results), list)
+        self.assertEqual(len(results), 0)

searx/tests/engines/test_yahoo.py

@@ -75,12 +75,6 @@ class TestYahooEngine(SearxTestCase):
     <li>
         <div class="dd algo lst Sr">
             <div class="compTitle">
-                <h3 class="title"><a class=" td-u" href="http://r.search.yahoo.com/_ylt=AwrBT7zgEudUW.wAe2ZXNyoA;
-                     _ylu=X3oDMTBybGY3bmpvBGNvbG8DYmYxBHBvcwMyBHZ0aWQDBHNlYwNzcg--/RV=2\/RE=1424458593/RO=10
-                     /RU=https%3a%2f%2fthis.is.the.second.url%2f/RK=0/RS=jIctjj_cBH1Efj88GCgHKp3__Qk-"
-                     target="_blank" data-bid="54e712e136926">
-                     This is the second <b><b>title</b></b></a>
-                </h3>
             </div>
             <div class="compText aAbs">
                 <p class="lh-18">This is the second content</p>
@@ -102,16 +96,12 @@ class TestYahooEngine(SearxTestCase):
         """
         response = mock.Mock(text=html)
         results = yahoo.response(response)
-        print results
         self.assertEqual(type(results), list)
-        self.assertEqual(len(results), 3)
+        self.assertEqual(len(results), 2)
         self.assertEqual(results[0]['title'], 'This is the title')
         self.assertEqual(results[0]['url'], 'https://this.is.the.url/')
         self.assertEqual(results[0]['content'], 'This is the content')
-        self.assertEqual(results[1]['title'], 'This is the second title')
-        self.assertEqual(results[1]['url'], 'https://this.is.the.second.url/')
-        self.assertEqual(results[1]['content'], 'This is the second content')
-        self.assertEqual(results[2]['suggestion'], 'This is the suggestion')
+        self.assertEqual(results[1]['suggestion'], 'This is the suggestion')
 
         html = """
 <ol class="reg mb-15 searchCenterMiddle">

searx/tests/test_engines.py

@@ -28,6 +28,7 @@ from searx.tests.engines.test_piratebay import *  # noqa
 from searx.tests.engines.test_searchcode_code import *  # noqa
 from searx.tests.engines.test_searchcode_doc import *  # noqa
 from searx.tests.engines.test_soundcloud import *  # noqa
+from searx.tests.engines.test_spotify import *  # noqa
 from searx.tests.engines.test_stackoverflow import *  # noqa
 from searx.tests.engines.test_startpage import *  # noqa
 from searx.tests.engines.test_subtitleseeker import *  # noqa