From 930f724ec639c167d870d716240ac5d4512beba2 Mon Sep 17 00:00:00 2001 From: Cqoicebordel Date: Tue, 16 Dec 2014 20:40:03 +0100 Subject: [PATCH] Add an No Api Flickr Engine It uses the webpage json infos to build the results Let the user choose the engine in setting.yml. Noapi active by default + little corrections on Flickr engine --- searx/engines/flickr-noapi.py | 102 ++++++++++++++++++++++++++++++++++ searx/engines/flickr.py | 5 +- searx/settings.yml | 11 ++-- 3 files changed, 110 insertions(+), 8 deletions(-) create mode 100644 searx/engines/flickr-noapi.py diff --git a/searx/engines/flickr-noapi.py b/searx/engines/flickr-noapi.py new file mode 100644 index 00000000..b44affec --- /dev/null +++ b/searx/engines/flickr-noapi.py @@ -0,0 +1,102 @@ +#!/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 +from urlparse import urljoin +from lxml import html +import re + +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) + +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 == None: + return results + + match = matches.group(1) + search_results = loads(match) + + if not '_data' 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 == None: + continue + + # From the biggest to the lowest format + if 'o' in photo['sizes']: + img_src = photo['sizes']['o']['displayUrl'] + elif 'k' in photo['sizes']: + img_src = photo['sizes']['k']['displayUrl'] + elif 'h' in photo['sizes']: + img_src = photo['sizes']['h']['displayUrl'] + elif 'b' in photo['sizes']: + img_src = photo['sizes']['b']['displayUrl'] + elif 'c' in photo['sizes']: + img_src = photo['sizes']['c']['displayUrl'] + elif 'z' in photo['sizes']: + img_src = photo['sizes']['z']['displayUrl'] + elif 'n' in photo['sizes']: + img_src = photo['sizes']['n']['displayUrl'] + elif 'm' in photo['sizes']: + img_src = photo['sizes']['m']['displayUrl'] + elif 't' in photo['sizes']: + img_src = photo['sizes']['to']['displayUrl'] + elif 'q' in photo['sizes']: + img_src = photo['sizes']['q']['displayUrl'] + elif 's' in photo['sizes']: + img_src = photo['sizes']['s']['displayUrl'] + else: + continue + + url = build_flickr_url(photo['owner']['id'], photo['id']) + + title = photo['title'] + + content = ''+ photo['owner']['username'] +'
' + + if 'description' in photo: + content = content + '' + photo['description'] + '' + + # append result + results.append({'url': url, + 'title': title, + 'img_src': img_src, + 'content': content, + 'template': 'images.html'}) + + return results diff --git a/searx/engines/flickr.py b/searx/engines/flickr.py index 8b60aed1..2fa5ed7e 100644 --- a/searx/engines/flickr.py +++ b/searx/engines/flickr.py @@ -13,9 +13,6 @@ from urllib import urlencode from json import loads -from urlparse import urljoin -from lxml import html -from time import time categories = ['images'] @@ -70,7 +67,7 @@ def response(resp): content = ''+ photo['ownername'] +'
' - content = content + ' ' + photo['description']['_content'] + '' + content = content + '' + photo['description']['_content'] + '' # append result results.append({'url': url, diff --git a/searx/settings.yml b/searx/settings.yml index d2c7a32c..07cd2ac3 100644 --- a/searx/settings.yml +++ b/searx/settings.yml @@ -65,12 +65,15 @@ engines: # categories : files # shortcut : fc -# api-key required: https://www.flickr.com/services/apps/create/ -# - name : flickr + - name : flickr + categories : images + shortcut : fl +# You can use the engine using the official stable API, but you need an API key +# See : https://www.flickr.com/services/apps/create/ # engine : flickr -# categories : images -# shortcut : fl # api_key: 'apikey' # required! +# Or you can use the html non-stable engine, activated by default + engine : flickr-noapi - name : general-file engine : generalfile