summaryrefslogtreecommitdiff
path: root/searx/engines/flickr_noapi.py
diff options
context:
space:
mode:
authorAdam Tauber <asciimoo@gmail.com>2015-01-31 22:05:13 +0100
committerAdam Tauber <asciimoo@gmail.com>2015-01-31 22:05:13 +0100
commitbfd321a7a9cfc6d643fdebe5e7a5824fe70b9aa9 (patch)
treebdbe71be7cff27d0176bf22296ae93c045c619ed /searx/engines/flickr_noapi.py
parent8de97dac03fc97a9705c8d3cd3163330a6f08375 (diff)
[mod] python importable engine names
Diffstat (limited to 'searx/engines/flickr_noapi.py')
-rw-r--r--searx/engines/flickr_noapi.py109
1 files changed, 109 insertions, 0 deletions
diff --git a/searx/engines/flickr_noapi.py b/searx/engines/flickr_noapi.py
new file mode 100644
index 000000000..9b28ded13
--- /dev/null
+++ b/searx/engines/flickr_noapi.py
@@ -0,0 +1,109 @@
+#!/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 no
+# @results HTML
+# @stable no
+# @parse url, title, thumbnail, img_src
+
+from urllib import urlencode
+from json import loads
+import re
+from searx.engines import logger
+
+
+logger = logger.getChild('flickr-noapi')
+
+categories = ['images']
+
+url = 'https://secure.flickr.com/'
+search_url = url+'search/?{query}&page={page}'
+photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}'
+regex = re.compile(r"\"search-photos-models\",\"photos\":(.*}),\"totalItems\":", re.DOTALL)
+image_sizes = ('o', 'k', 'h', 'b', 'c', 'z', 'n', 'm', 't', 'q', 's')
+
+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'])
+ return params
+
+
+def response(resp):
+ results = []
+
+ matches = regex.search(resp.text)
+
+ if matches is None:
+ return results
+
+ match = matches.group(1)
+ search_results = loads(match)
+
+ if '_data' not in search_results:
+ return []
+
+ photos = search_results['_data']
+
+ for photo in photos:
+
+ # In paged configuration, the first pages' photos
+ # are represented by a None object
+ if photo is None:
+ continue
+
+ img_src = None
+ # From the biggest to the lowest format
+ for image_size in image_sizes:
+ if image_size in photo['sizes']:
+ img_src = photo['sizes'][image_size]['url']
+ break
+
+ if not img_src:
+ logger.debug('cannot find valid image size: {0}'.format(repr(photo)))
+ continue
+
+ if 'id' not in photo['owner']:
+ continue
+
+# For a bigger thumbnail, keep only the url_z, not the url_n
+ if 'n' in photo['sizes']:
+ thumbnail_src = photo['sizes']['n']['url']
+ elif 'z' in photo['sizes']:
+ thumbnail_src = photo['sizes']['z']['url']
+ else:
+ thumbnail_src = img_src
+
+ url = build_flickr_url(photo['owner']['id'], photo['id'])
+
+ title = photo.get('title', '')
+
+ content = '<span class="photo-author">' +\
+ photo['owner']['username'] +\
+ '</span><br />'
+
+ if 'description' in photo:
+ content = content +\
+ '<span class="description">' +\
+ photo['description'] +\
+ '</span>'
+
+ # append result
+ results.append({'url': url,
+ 'title': title,
+ 'img_src': img_src,
+ 'thumbnail_src': thumbnail_src,
+ 'content': content,
+ 'template': 'images.html'})
+
+ return results