Merge branch 'master' into docker/opencontainers

6 files changed, 42 insertions, 16 deletions

diff --git a/searx/engines/bing.py b/searx/engines/bing.py
index ed0b87dbd..b193f7c60 100644
--- a/searx/engines/bing.py
+++ b/searx/engines/bing.py
@@ -89,8 +89,7 @@ def response(resp):
                         'content': content})
 
     try:
-        result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]/text()'))
-        result_len_container = utils.to_string(result_len_container)
+        result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]//text()'))
         if "-" in result_len_container:
             # Remove the part "from-to" for paginated request ...
             result_len_container = result_len_container[result_len_container.find("-") * 2 + 2:]
@@ -102,7 +101,7 @@ def response(resp):
         logger.debug('result error :\n%s', e)
         pass
 
-    if _get_offset_from_pageno(resp.search_params.get("pageno", 0)) > result_len:
+    if result_len and _get_offset_from_pageno(resp.search_params.get("pageno", 0)) > result_len:
         return []
 
     results.append({'number_of_results': result_len})
diff --git a/searx/engines/flickr_noapi.py b/searx/engines/flickr_noapi.py
index 198ac2cff..c8ee34f7a 100644
--- a/searx/engines/flickr_noapi.py
+++ b/searx/engines/flickr_noapi.py
@@ -109,14 +109,22 @@ def response(resp):
         else:
             url = build_flickr_url(photo['ownerNsid'], photo['id'])
 
-        results.append({'url': url,
-                        'title': title,
-                        'img_src': img_src,
-                        'thumbnail_src': thumbnail_src,
-                        'content': content,
-                        'author': author,
-                        'source': source,
-                        'img_format': img_format,
-                        'template': 'images.html'})
+        result = {
+            'url': url,
+            'img_src': img_src,
+            'thumbnail_src': thumbnail_src,
+            'source': source,
+            'img_format': img_format,
+            'template': 'images.html'
+        }
+        try:
+            result['author'] = author
+            result['title'] = title
+            result['content'] = content
+        except:
+            result['author'] = ''
+            result['title'] = ''
+            result['content'] = ''
+        results.append(result)
 
     return results
diff --git a/searx/engines/ina.py b/searx/engines/ina.py
index 37a05f099..ea509649f 100644
--- a/searx/engines/ina.py
+++ b/searx/engines/ina.py
@@ -32,7 +32,7 @@ base_url = 'https://www.ina.fr'
 search_url = base_url + '/layout/set/ajax/recherche/result?autopromote=&hf={ps}&b={start}&type=Video&r=&{query}'
 
 # specific xpath variables
-results_xpath = '//div[contains(@class,"search-results--list")]/div[@class="media"]'
+results_xpath = '//div[contains(@class,"search-results--list")]//div[@class="media-body"]'
 url_xpath = './/a/@href'
 title_xpath = './/h3[@class="h3--title media-heading"]'
 thumbnail_xpath = './/img/@src'
@@ -65,8 +65,11 @@ def response(resp):
         videoid = result.xpath(url_xpath)[0]
         url = base_url + videoid
         title = p.unescape(extract_text(result.xpath(title_xpath)))
-        thumbnail = extract_text(result.xpath(thumbnail_xpath)[0])
-        if thumbnail[0] == '/':
+        try:
+            thumbnail = extract_text(result.xpath(thumbnail_xpath)[0])
+        except:
+            thumbnail = ''
+        if thumbnail and thumbnail[0] == '/':
             thumbnail = base_url + thumbnail
         d = extract_text(result.xpath(publishedDate_xpath)[0])
         d = d.split('/')
diff --git a/searx/engines/microsoft_academic.py b/searx/engines/microsoft_academic.py
index 9387b08d0..9bac0069c 100644
--- a/searx/engines/microsoft_academic.py
+++ b/searx/engines/microsoft_academic.py
@@ -45,6 +45,8 @@ def request(query, params):
 def response(resp):
     results = []
     response_data = loads(resp.text)
+    if not response_data:
+        return results
 
     for result in response_data['results']:
         url = _get_url(result)
diff --git a/searx/engines/scanr_structures.py b/searx/engines/scanr_structures.py
index 72fd2b3c9..7208dcb70 100644
--- a/searx/engines/scanr_structures.py
+++ b/searx/engines/scanr_structures.py
@@ -29,7 +29,7 @@ def request(query, params):
     params['url'] = search_url
     params['method'] = 'POST'
     params['headers']['Content-type'] = "application/json"
-    params['data'] = dumps({"query": query,
+    params['data'] = dumps({"query": query.decode('utf-8'),
                             "searchField": "ALL",
                             "sortDirection": "ASC",
                             "sortOrder": "RELEVANCY",
diff --git a/searx/engines/spotify.py b/searx/engines/spotify.py
index aed756be3..00c395706 100644
--- a/searx/engines/spotify.py
+++ b/searx/engines/spotify.py
@@ -12,10 +12,14 @@
 
 from json import loads
 from searx.url_utils import urlencode
+import requests
+import base64
 
 # engine dependent config
 categories = ['music']
 paging = True
+api_client_id = None
+api_client_secret = None
 
 # search-url
 url = 'https://api.spotify.com/'
@@ -31,6 +35,16 @@ def request(query, params):
 
     params['url'] = search_url.format(query=urlencode({'q': query}), offset=offset)
 
+    r = requests.post(
+        'https://accounts.spotify.com/api/token',
+        data={'grant_type': 'client_credentials'},
+        headers={'Authorization': 'Basic ' + base64.b64encode(
+            "{}:{}".format(api_client_id, api_client_secret).encode('utf-8')
+        ).decode('utf-8')}
+    )
+    j = loads(r.text)
+    params['headers'] = {'Authorization': 'Bearer {}'.format(j.get('access_token'))}
+
     return params