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
This commit is contained in:
Cqoicebordel 2014-12-15 03:21:25 +01:00
parent e047d22046
commit 0059d08f13
2 changed files with 62 additions and 32 deletions

View file

@ -1,54 +1,83 @@
#!/usr/bin/env python #!/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 urllib import urlencode
#from json import loads from json import loads
from urlparse import urljoin from urlparse import urljoin
from lxml import html from lxml import html
from time import time from time import time
categories = ['images'] categories = ['images']
url = 'https://secure.flickr.com/' nb_per_page = 15
search_url = url+'search/?{query}&page={page}' paging = True
results_xpath = '//div[@class="view display-item-tile"]/figure/div' 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 paging = True
def build_flickr_url(user_id, photo_id):
return photo_url.format(userid=user_id,photoid=photo_id)
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode({'text': query}), params['url'] = url.format(text=urlencode({'text': query}),
page=params['pageno']) api_key=api_key,
time_string = str(int(time())-3) nb_per_page=nb_per_page,
params['cookies']['BX'] = '3oqjr6d9nmpgl&b=3&s=dh' page=params['pageno'])
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 return params
def response(resp): def response(resp):
results = [] results = []
dom = html.fromstring(resp.text)
for result in dom.xpath(results_xpath): search_results = loads(resp.text)
img = result.xpath('.//img')
if not img: # return empty array if there are no results
if not 'photos' in search_results:
return []
if not 'photo' in search_results['photos']:
return []
photos = search_results['photos']['photo']
# 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 continue
img = img[0] url = build_flickr_url(photo['owner'], photo['id'])
img_src = 'https:'+img.attrib.get('src')
if not img_src: title = photo['title']
continue
content = '<span class="photo-author">'+ photo['ownername'] +'</span><br />'
href = urljoin(url, result.xpath('.//a')[0].attrib.get('href'))
title = img.attrib.get('alt', '') content = content + ' <span class="description">' + photo['description']['_content'] + '</span>'
results.append({'url': href,
# append result
results.append({'url': url,
'title': title, 'title': title,
'img_src': img_src, 'img_src': img_src,
'content': content,
'template': 'images.html'}) 'template': 'images.html'})
# return results
return results return results

View file

@ -65,11 +65,12 @@ engines:
# categories : files # categories : files
# shortcut : fc # shortcut : fc
- name : flickr # api-key required: https://www.flickr.com/services/apps/create/
engine : flickr # - name : flickr
categories : images # engine : flickr
shortcut : fl # categories : images
timeout: 3.0 # shortcut : fl
# api_key: 'apikey' # required!
- name : general-file - name : general-file
engine : generalfile engine : generalfile