Rework Flickr Engine

Everything was redone to use the API. It needs an API key, but it's worth it.
Everything works. Title, Image, Content, URL
The API allow lots of things. Thumbnails and date will be easy to add when it will be implemented in Searx.

Fix asciimoo/searx#126

2 files changed, 61 insertions, 31 deletions

diff --git a/searx/engines/flickr.py b/searx/engines/flickr.py
index 4ec2841dd..8b60aed1d 100644
--- a/searx/engines/flickr.py
+++ b/searx/engines/flickr.py
@@ -1,54 +1,83 @@
 #!/usr/bin/env python
 
+## Flickr (Images)
+# 
+# @website     https://www.flickr.com
+# @provide-api yes (https://secure.flickr.com/services/api/flickr.photos.search.html) 
+# 
+# @using-api   yes
+# @results     JSON
+# @stable      yes
+# @parse       url, title, thumbnail, img_src
+#More info on api-key : https://www.flickr.com/services/apps/create/
+
 from urllib import urlencode
-#from json import loads
+from json import loads
 from urlparse import urljoin
 from lxml import html
 from time import time
 
 categories = ['images']
 
-url = 'https://secure.flickr.com/'
-search_url = url+'search/?{query}&page={page}'
-results_xpath = '//div[@class="view display-item-tile"]/figure/div'
+nb_per_page = 15
+paging = True
+api_key= None
+
+
+url = 'https://api.flickr.com/services/rest/?method=flickr.photos.search&api_key={api_key}&{text}&sort=relevance&extras=description%2C+owner_name%2C+url_o%2C+url_z&per_page={nb_per_page}&format=json&nojsoncallback=1&page={page}'
+photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}'
 
 paging = True
 
+def build_flickr_url(user_id, photo_id):
+    return photo_url.format(userid=user_id,photoid=photo_id)
+
 
 def request(query, params):
-    params['url'] = search_url.format(query=urlencode({'text': query}),
-                                      page=params['pageno'])
-    time_string = str(int(time())-3)
-    params['cookies']['BX'] = '3oqjr6d9nmpgl&b=3&s=dh'
-    params['cookies']['xb'] = '421409'
-    params['cookies']['localization'] = 'en-us'
-    params['cookies']['flrbp'] = time_string +\
-        '-3a8cdb85a427a33efda421fbda347b2eaf765a54'
-    params['cookies']['flrbs'] = time_string +\
-        '-ed142ae8765ee62c9ec92a9513665e0ee1ba6776'
-    params['cookies']['flrb'] = '9'
+    params['url'] = url.format(text=urlencode({'text': query}),
+                               api_key=api_key,
+                               nb_per_page=nb_per_page,
+                               page=params['pageno'])
     return params
 
 
 def response(resp):
     results = []
-    dom = html.fromstring(resp.text)
-    for result in dom.xpath(results_xpath):
-        img = result.xpath('.//img')
+    
+    search_results = loads(resp.text)
 
-        if not img:
-            continue
+    # return empty array if there are no results
+    if not 'photos' in search_results:
+        return []
+
+    if not 'photo' in search_results['photos']:
+        return []
 
-        img = img[0]
-        img_src = 'https:'+img.attrib.get('src')
+    photos = search_results['photos']['photo']
 
-        if not img_src:
+    # parse results
+    for photo in photos:
+        if 'url_o' in photo:
+            img_src = photo['url_o']
+        elif 'url_z' in photo:
+            img_src = photo['url_z']
+        else:
             continue
 
-        href = urljoin(url, result.xpath('.//a')[0].attrib.get('href'))
-        title = img.attrib.get('alt', '')
-        results.append({'url': href,
+        url = build_flickr_url(photo['owner'], photo['id'])
+
+        title = photo['title']
+        
+        content = '<span class="photo-author">'+ photo['ownername'] +'</span><br />'
+        
+        content = content + ' <span class="description">' + photo['description']['_content'] + '</span>'
+        
+        # append result
+        results.append({'url': url,
                         'title': title,
                         'img_src': img_src,
+                        'content': content,
                         'template': 'images.html'})
+
+    # return results
     return results
diff --git a/searx/settings.yml b/searx/settings.yml
index 5e9f11202..b7359b919 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -65,11 +65,12 @@ engines:
 #    categories : files
 #    shortcut : fc
 
-  - name : flickr
-    engine : flickr
-    categories : images
-    shortcut : fl
-    timeout: 3.0
+# api-key required: https://www.flickr.com/services/apps/create/
+#  - name : flickr
+#    engine : flickr
+#    categories : images
+#    shortcut : fl
+#    api_key: 'apikey' # required!
 
   - name : general-file
     engine : generalfile