searx

commit: 3386e21cdf30bf0accb84e2dcc4dea0076af1b90
parent: 8d40445ab81d63cdd0e9ea012ffa792edf849e30
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Tue, 20 May 2014 16:57:03 +0200

[fix] flickr.com mods

Diffstat:
M
searx/engines/flickr.py
62
++++++++++++++++++++++++++++++++++----------------------------

1 file changed, 34 insertions(+), 28 deletions(-)
diff --git a/searx/engines/flickr.py b/searx/engines/flickr.py
@@ -1,48 +1,54 @@
 #!/usr/bin/env python
 
 from urllib import urlencode
-from json import loads
-#from urlparse import urljoin
+#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[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]'  # noqa
+url = 'https://secure.flickr.com/'
+search_url = url+'search/?{query}&page={page}'
+results_xpath = '//div[@class="view display-item-tile"]/figure/div'
 
 paging = True
 
-# text=[query]
-# TODO clean "extras"
-search_url = 'https://api.flickr.com/services/rest?extras=can_addmeta%2Ccan_comment%2Ccan_download%2Ccan_share%2Ccontact%2Ccount_comments%2Ccount_faves%2Ccount_notes%2Cdate_taken%2Cdate_upload%2Cdescription%2Cicon_urls_deep%2Cisfavorite%2Cispro%2Clicense%2Cmedia%2Cneeds_interstitial%2Cowner_name%2Cowner_datecreate%2Cpath_alias%2Crealname%2Csafety_level%2Csecret_k%2Csecret_h%2Curl_c%2Curl_h%2Curl_k%2Curl_l%2Curl_m%2Curl_n%2Curl_o%2Curl_q%2Curl_s%2Curl_sq%2Curl_t%2Curl_z%2Cvisibility&per_page=50&page={page}&{query}&sort=relevance&method=flickr.photos.search&api_key=ad11b34c341305471e3c410a02e671d0&format=json'  # noqa
-
 
 def request(query, params):
     params['url'] = search_url.format(query=urlencode({'text': query}),
                                       page=params['pageno'])
-    #params['url'] = search_url.format(query=urlencode({'q': 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'
     return params
 
 
 def response(resp):
     results = []
-    images = loads(resp.text[14:-1])["photos"]["photo"]
-    for i in images:
-        results.append({'url': i['url_s'],
-                        'title': i['title'],
-                        'img_src': i['url_s'],
+    dom = html.fromstring(resp.text)
+    for result in dom.xpath(results_xpath):
+        img = result.xpath('.//img')
+
+        if not img:
+            continue
+
+        img = img[0]
+        img_src = 'https:'+img.attrib.get('src')
+
+        if not img_src:
+            continue
+
+        href = urljoin(url, result.xpath('.//a')[0].attrib.get('href'))
+        title = img.attrib.get('alt', '')
+        results.append({'url': href,
+                        'title': title,
+                        'img_src': img_src,
                         'template': 'images.html'})
-    #dom = html.fromstring(resp.text)
-    #for result in dom.xpath(results_xpath):
-    #    href = urljoin(url, result.attrib.get('href'))
-    #    img = result.xpath('.//img')[0]
-    #    title = img.attrib.get('alt', '')
-    #    img_src = img.attrib.get('data-defer-src')
-    #    if not img_src:
-    #        continue
-    #    results.append({'url': href,
-    #                    'title': title,
-    #                    'img_src': img_src,
-    #                    'template': 'images.html'})
     return results