From 6b058962e1f87a17ce2d9c2bcb4faa73df285df3 Mon Sep 17 00:00:00 2001
From: Dalf <alex@al-f.net>
Date: Mon, 22 Sep 2014 22:55:51 +0200
Subject: [PATCH 1/6] [fix] when two results are merged, really use the content
with more text
---
searx/search.py | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/searx/search.py b/searx/search.py
index c861a795a..10916cc50 100644
--- a/searx/search.py
+++ b/searx/search.py
@@ -16,6 +16,7 @@ along with searx. If not, see < http://www.gnu.org/licenses/ >.
'''
import grequests
+import re
from itertools import izip_longest, chain
from datetime import datetime
from operator import itemgetter
@@ -76,6 +77,13 @@ def make_callback(engine_name, results, suggestions, callback, params):
return process_callback
+# return the meaningful length of the content for a result
+def content_result_len(result):
+ if isinstance(result.get('content'), basestring):
+ content = re.sub('[,;:!?\./\\\\ ()-_]', '', result.get('content'))
+ return len(content)
+ else:
+ return 0
# score results and remove duplications
def score_results(results):
@@ -110,6 +118,9 @@ def score_results(results):
duplicated = False
# check for duplicates
+ if 'content' in res:
+ res['content'] = re.sub(' +', ' ', res['content'].strip().replace('\n', ''))
+
for new_res in results:
# remove / from the end of the url if required
p1 = res['parsed_url'].path[:-1] if res['parsed_url'].path.endswith('/') else res['parsed_url'].path # noqa
@@ -126,7 +137,7 @@ def score_results(results):
# merge duplicates together
if duplicated:
# using content with more text
- if res.get('content') > duplicated.get('content'):
+ if content_result_len(res) > content_result_len(duplicated):
duplicated['content'] = res['content']
# increase result-score
From e39d9fe5423a0fceed1d15dc63c1f8aa30d72e44 Mon Sep 17 00:00:00 2001
From: Dalf <alex@al-f.net>
Date: Mon, 22 Sep 2014 23:39:21 +0200
Subject: [PATCH 2/6] update comment
---
searx/search.py | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/searx/search.py b/searx/search.py
index 10916cc50..48f8012f1 100644
--- a/searx/search.py
+++ b/searx/search.py
@@ -106,8 +106,13 @@ def score_results(results):
res['host'] = res['host'].replace('www.', '', 1)
res['engines'] = [res['engine']]
+
weight = 1.0
+ # strip multiple spaces and cariage returns from content
+ if 'content' in res:
+ res['content'] = re.sub(' +', ' ', res['content'].strip().replace('\n', ''))
+
# get weight of this engine if possible
if hasattr(engines[res['engine']], 'weight'):
weight = float(engines[res['engine']].weight)
@@ -115,12 +120,8 @@ def score_results(results):
# calculate score for that engine
score = int((flat_len - i) / engines_len) * weight + 1
- duplicated = False
-
# check for duplicates
- if 'content' in res:
- res['content'] = re.sub(' +', ' ', res['content'].strip().replace('\n', ''))
-
+ duplicated = False
for new_res in results:
# remove / from the end of the url if required
p1 = res['parsed_url'].path[:-1] if res['parsed_url'].path.endswith('/') else res['parsed_url'].path # noqa
From 6bfd5663539052a64c984f5bdb7135d0d652c923 Mon Sep 17 00:00:00 2001
From: Dalf <alex@al-f.net>
Date: Sun, 28 Sep 2014 16:51:41 +0200
Subject: [PATCH 3/6] [enh] add infoboxes and answers
---
searx/engines/currency_convert.py | 11 +-
searx/engines/duckduckgo_definitions.py | 121 ++++++++++-
searx/engines/wikidata.py | 193 ++++++++++++++++++
searx/search.py | 104 +++++++++-
searx/settings.yml | 2 +-
searx/static/default/css/style.css | 76 +------
searx/static/default/less/style.less | 124 ++++++++---
.../default/result_templates/default.html | 4 +-
searx/templates/default/results.html | 16 ++
searx/webapp.py | 4 +-
10 files changed, 525 insertions(+), 130 deletions(-)
create mode 100644 searx/engines/wikidata.py
diff --git a/searx/engines/currency_convert.py b/searx/engines/currency_convert.py
index 561527bce..b5f0953d8 100644
--- a/searx/engines/currency_convert.py
+++ b/searx/engines/currency_convert.py
@@ -38,16 +38,14 @@ def response(resp):
except:
return results
- title = '{0} {1} in {2} is {3}'.format(
+ answer = '{0} {1} = {2} {3} (1 {1} = {4} {3})'.format(
resp.search_params['ammount'],
resp.search_params['from'],
+ resp.search_params['ammount'] * conversion_rate,
resp.search_params['to'],
- resp.search_params['ammount'] * conversion_rate
+ conversion_rate
)
- content = '1 {0} is {1} {2}'.format(resp.search_params['from'],
- conversion_rate,
- resp.search_params['to'])
now_date = datetime.now().strftime('%Y%m%d')
url = 'http://finance.yahoo.com/currency/converter-results/{0}/{1}-{2}-to-{3}.html' # noqa
url = url.format(
@@ -56,6 +54,7 @@ def response(resp):
resp.search_params['from'].lower(),
resp.search_params['to'].lower()
)
- results.append({'title': title, 'content': content, 'url': url})
+
+ results.append({'answer' : answer, 'url': url})
return results
diff --git a/searx/engines/duckduckgo_definitions.py b/searx/engines/duckduckgo_definitions.py
index 3037aae53..3da7352a4 100644
--- a/searx/engines/duckduckgo_definitions.py
+++ b/searx/engines/duckduckgo_definitions.py
@@ -1,10 +1,25 @@
import json
from urllib import urlencode
+from lxml import html
+from searx.engines.xpath import extract_text
-url = 'http://api.duckduckgo.com/?{query}&format=json&pretty=0&no_redirect=1'
+url = 'https://api.duckduckgo.com/?{query}&format=json&pretty=0&no_redirect=1&d=1'
+def result_to_text(url, text, htmlResult):
+ # TODO : remove result ending with "Meaning" or "Category"
+ dom = html.fromstring(htmlResult)
+ a = dom.xpath('//a')
+ if len(a)>=1:
+ return extract_text(a[0])
+ else:
+ return text
+
+def html_to_text(htmlFragment):
+ dom = html.fromstring(htmlFragment)
+ return extract_text(dom)
def request(query, params):
+ # TODO add kl={locale}
params['url'] = url.format(query=urlencode({'q': query}))
return params
@@ -12,12 +27,104 @@ def request(query, params):
def response(resp):
search_res = json.loads(resp.text)
results = []
+
+ content = ''
+ heading = search_res.get('Heading', '')
+ attributes = []
+ urls = []
+ infobox_id = None
+ relatedTopics = []
+
+ # add answer if there is one
+ answer = search_res.get('Answer', '')
+ if answer != '':
+ results.append({ 'answer' : html_to_text(answer) })
+
+ # add infobox
if 'Definition' in search_res:
- if search_res.get('AbstractURL'):
- res = {'title': search_res.get('Heading', ''),
- 'content': search_res.get('Definition', ''),
- 'url': search_res.get('AbstractURL', ''),
- 'class': 'definition_result'}
- results.append(res)
+ content = content + search_res.get('Definition', '')
+
+ if 'Abstract' in search_res:
+ content = content + search_res.get('Abstract', '')
+
+
+ # image
+ image = search_res.get('Image', '')
+ image = None if image == '' else image
+
+ # attributes
+ if 'Infobox' in search_res:
+ infobox = search_res.get('Infobox', None)
+ if 'content' in infobox:
+ for info in infobox.get('content'):
+ attributes.append({'label': info.get('label'), 'value': info.get('value')})
+
+ # urls
+ for ddg_result in search_res.get('Results', []):
+ if 'FirstURL' in ddg_result:
+ firstURL = ddg_result.get('FirstURL', '')
+ text = ddg_result.get('Text', '')
+ urls.append({'title':text, 'url':firstURL})
+ results.append({'title':heading, 'url': firstURL})
+
+ # related topics
+ for ddg_result in search_res.get('RelatedTopics', None):
+ if 'FirstURL' in ddg_result:
+ suggestion = result_to_text(ddg_result.get('FirstURL', None), ddg_result.get('Text', None), ddg_result.get('Result', None))
+ if suggestion != heading:
+ results.append({'suggestion': suggestion})
+ elif 'Topics' in ddg_result:
+ suggestions = []
+ relatedTopics.append({ 'name' : ddg_result.get('Name', ''), 'suggestions': suggestions })
+ for topic_result in ddg_result.get('Topics', []):
+ suggestion = result_to_text(topic_result.get('FirstURL', None), topic_result.get('Text', None), topic_result.get('Result', None))
+ if suggestion != heading:
+ suggestions.append(suggestion)
+
+ # abstract
+ abstractURL = search_res.get('AbstractURL', '')
+ if abstractURL != '':
+ # add as result ? problem always in english
+ infobox_id = abstractURL
+ urls.append({'title': search_res.get('AbstractSource'), 'url': abstractURL})
+
+ # definition
+ definitionURL = search_res.get('DefinitionURL', '')
+ if definitionURL != '':
+ # add as result ? as answer ? problem always in english
+ infobox_id = definitionURL
+ urls.append({'title': search_res.get('DefinitionSource'), 'url': definitionURL})
+
+ # entity
+ entity = search_res.get('Entity', None)
+ # TODO continent / country / department / location / waterfall / mountain range : link to map search, get weather, near by locations
+ # TODO musician : link to music search
+ # TODO concert tour : ??
+ # TODO film / actor / television / media franchise : links to IMDB / rottentomatoes (or scrap result)
+ # TODO music : link tu musicbrainz / last.fm
+ # TODO book : ??
+ # TODO artist / playwright : ??
+ # TODO compagny : ??
+ # TODO software / os : ??
+ # TODO software engineer : ??
+ # TODO prepared food : ??
+ # TODO website : ??
+ # TODO performing art : ??
+ # TODO prepared food : ??
+ # TODO programming language : ??
+ # TODO file format : ??
+
+ if len(heading)>0:
+ # TODO get infobox.meta.value where .label='article_title'
+ results.append({
+ 'infobox': heading,
+ 'id': infobox_id,
+ 'entity': entity,
+ 'content': content,
+ 'img_src' : image,
+ 'attributes': attributes,
+ 'urls': urls,
+ 'relatedTopics': relatedTopics
+ })
return results
diff --git a/searx/engines/wikidata.py b/searx/engines/wikidata.py
new file mode 100644
index 000000000..a5ee44246
--- /dev/null
+++ b/searx/engines/wikidata.py
@@ -0,0 +1,193 @@
+import json
+from datetime import datetime
+from requests import get
+from urllib import urlencode
+
+resultCount=2
+urlSearch = 'https://www.wikidata.org/w/api.php?action=query&list=search&format=json&srnamespace=0&srprop=sectionsnippet&{query}'
+urlDetail = 'https://www.wikidata.org/w/api.php?action=wbgetentities&format=json&props=labels%7Cinfo%7Csitelinks%7Csitelinks%2Furls%7Cdescriptions%7Cclaims&{query}'
+# find the right URL for urlMap
+urlMap = 'http://www.openstreetmap.org/?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M'
+
+def request(query, params):
+ params['url'] = urlSearch.format(query=urlencode({'srsearch': query, 'srlimit': resultCount}))
+ print params['url']
+ return params
+
+
+def response(resp):
+ results = []
+ search_res = json.loads(resp.text)
+ # TODO parallel http queries
+ before = datetime.now()
+ for r in search_res.get('query', {}).get('search', {}):
+ wikidata_id = r.get('title', '')
+ results = results + getDetail(wikidata_id)
+ after = datetime.now()
+ print str(after - before) + " second(s)"
+
+ return results
+
+def getDetail(wikidata_id):
+ language = 'fr'
+
+ url = urlDetail.format(query=urlencode({'ids': wikidata_id, 'languages': language + '|en'}))
+ print url
+ response = get(url)
+ result = json.loads(response.content)
+ result = result.get('entities', {}).get(wikidata_id, {})
+
+ title = result.get('labels', {}).get(language, {}).get('value', None)
+ if title == None:
+ title = result.get('labels', {}).get('en', {}).get('value', wikidata_id)
+ results = []
+ urls = []
+ attributes = []
+
+ description = result.get('descriptions', {}).get(language, {}).get('value', '')
+ if description == '':
+ description = result.get('descriptions', {}).get('en', {}).get('value', '')
+
+ claims = result.get('claims', {})
+ official_website = get_string(claims, 'P856', None)
+ print official_website
+ if official_website != None:
+ urls.append({ 'title' : 'Official site', 'url': official_website })
+ results.append({ 'title': title, 'url' : official_website })
+
+ if language != 'en':
+ add_url(urls, 'Wikipedia (' + language + ')', get_wikilink(result, language + 'wiki'))
+ wikipedia_en_link = get_wikilink(result, 'enwiki')
+ add_url(urls, 'Wikipedia (en)', wikipedia_en_link)
+
+ if language != 'en':
+ add_url(urls, 'Wiki voyage (' + language + ')', get_wikilink(result, language + 'wikivoyage'))
+ add_url(urls, 'Wiki voyage (en)', get_wikilink(result, 'enwikivoyage'))
+
+ if language != 'en':
+ add_url(urls, 'Wikiquote (' + language + ')', get_wikilink(result, language + 'wikiquote'))
+ add_url(urls, 'Wikiquote (en)', get_wikilink(result, 'enwikiquote'))
+
+
+ add_url(urls, 'Commons wiki', get_wikilink(result, 'commonswiki'))
+
+ add_url(urls, 'Location', get_geolink(claims, 'P625', None))
+
+ add_url(urls, 'Wikidata', 'https://www.wikidata.org/wiki/' + wikidata_id + '?uselang='+ language)
+
+ postal_code = get_string(claims, 'P281', None)
+ if postal_code != None:
+ attributes.append({'label' : 'Postal code(s)', 'value' : postal_code})
+
+ date_of_birth = get_time(claims, 'P569', None)
+ if date_of_birth != None:
+ attributes.append({'label' : 'Date of birth', 'value' : date_of_birth})
+
+ date_of_death = get_time(claims, 'P570', None)
+ if date_of_death != None:
+ attributes.append({'label' : 'Date of death', 'value' : date_of_death})
+
+
+ results.append({
+ 'infobox' : title,
+ 'id' : wikipedia_en_link,
+ 'content' : description,
+ 'attributes' : attributes,
+ 'urls' : urls
+ })
+
+ return results
+
+def add_url(urls, title, url):
+ if url != None:
+ urls.append({'title' : title, 'url' : url})
+
+def get_mainsnak(claims, propertyName):
+ propValue = claims.get(propertyName, {})
+ if len(propValue) == 0:
+ return None
+
+ propValue = propValue[0].get('mainsnak', None)
+ return propValue
+
+def get_string(claims, propertyName, defaultValue=None):
+ propValue = claims.get(propertyName, {})
+ if len(propValue) == 0:
+ return defaultValue
+
+ result = []
+ for e in propValue:
+ mainsnak = e.get('mainsnak', {})
+
+ datatype = mainsnak.get('datatype', '')
+ datavalue = mainsnak.get('datavalue', {})
+ if datavalue != None:
+ result.append(datavalue.get('value', ''))
+
+ if len(result) == 0:
+ return defaultValue
+ else:
+ return ', '.join(result)
+
+def get_time(claims, propertyName, defaultValue=None):
+ propValue = claims.get(propertyName, {})
+ if len(propValue) == 0:
+ return defaultValue
+
+ result = []
+ for e in propValue:
+ mainsnak = e.get('mainsnak', {})
+
+ datatype = mainsnak.get('datatype', '')
+ datavalue = mainsnak.get('datavalue', {})
+ if datavalue != None:
+ value = datavalue.get('value', '')
+ result.append(value.get('time', ''))
+
+ if len(result) == 0:
+ return defaultValue
+ else:
+ return ', '.join(result)
+
+def get_geolink(claims, propertyName, defaultValue=''):
+ mainsnak = get_mainsnak(claims, propertyName)
+
+ if mainsnak == None:
+ return defaultValue
+
+ datatype = mainsnak.get('datatype', '')
+ datavalue = mainsnak.get('datavalue', {})
+
+ if datatype != 'globe-coordinate':
+ return defaultValue
+
+ value = datavalue.get('value', {})
+
+ precision = value.get('precision', 0.0002)
+
+ # there is no zoom information, deduce from precision (error prone)
+ # samples :
+ # 13 --> 5
+ # 1 --> 6
+ # 0.016666666666667 --> 9
+ # 0.00027777777777778 --> 19
+ # wolframalpha : quadratic fit { {13, 5}, {1, 6}, {0.0166666, 9}, {0.0002777777,19}}
+ # 14.1186-8.8322 x+0.625447 x^2
+ if precision < 0.0003:
+ zoom = 19
+ else:
+ zoom = int(15 - precision*8.8322 + precision*precision*0.625447)
+
+ url = urlMap.replace('{latitude}', str(value.get('latitude',0))).replace('{longitude}', str(value.get('longitude',0))).replace('{zoom}', str(zoom))
+
+ return url
+
+def get_wikilink(result, wikiid):
+ url = result.get('sitelinks', {}).get(wikiid, {}).get('url', None)
+ if url == None:
+ return url
+ elif url.startswith('http://'):
+ url = url.replace('http://', 'https://')
+ elif url.startswith('//'):
+ url = 'https:' + url
+ return url
diff --git a/searx/search.py b/searx/search.py
index 48f8012f1..7eb605e11 100644
--- a/searx/search.py
+++ b/searx/search.py
@@ -38,17 +38,14 @@ def default_request_params():
# create a callback wrapper for the search engine results
-def make_callback(engine_name, results, suggestions, callback, params):
+def make_callback(engine_name, results, suggestions, answers, infoboxes, callback, params):
# creating a callback wrapper for the search engine results
def process_callback(response, **kwargs):
cb_res = []
response.search_params = params
- # update stats with current page-load-time
- engines[engine_name].stats['page_load_time'] += \
- (datetime.now() - params['started']).total_seconds()
-
+ # callback
try:
search_results = callback(response)
except Exception, e:
@@ -61,6 +58,7 @@ def make_callback(engine_name, results, suggestions, callback, params):
engine_name, str(e))
return
+ # add results
for result in search_results:
result['engine'] = engine_name
@@ -70,21 +68,38 @@ def make_callback(engine_name, results, suggestions, callback, params):
suggestions.add(result['suggestion'])
continue
+ # if it is an answer, add it to list of answers
+ if 'answer' in result:
+ answers.add(result['answer'])
+ continue
+
+ # if it is an infobox, add it to list of infoboxes
+ if 'infobox' in result:
+ infoboxes.append(result)
+ print result
+ continue
+
# append result
cb_res.append(result)
results[engine_name] = cb_res
+ # update stats with current page-load-time
+ engines[engine_name].stats['page_load_time'] += \
+ (datetime.now() - params['started']).total_seconds()
+
return process_callback
+
# return the meaningful length of the content for a result
-def content_result_len(result):
- if isinstance(result.get('content'), basestring):
- content = re.sub('[,;:!?\./\\\\ ()-_]', '', result.get('content'))
+def content_result_len(content):
+ if isinstance(content, basestring):
+ content = re.sub('[,;:!?\./\\\\ ()-_]', '', content)
return len(content)
else:
return 0
+
# score results and remove duplications
def score_results(results):
# calculate scoring parameters
@@ -138,7 +153,7 @@ def score_results(results):
# merge duplicates together
if duplicated:
# using content with more text
- if content_result_len(res) > content_result_len(duplicated):
+ if content_result_len(res.get('content', '')) > content_result_len(duplicated.get('content', '')):
duplicated['content'] = res['content']
# increase result-score
@@ -197,6 +212,64 @@ def score_results(results):
return gresults
+def merge_two_infoboxes(infobox1, infobox2):
+ if 'urls' in infobox2:
+ urls1 = infobox1.get('urls', None)
+ if urls1 == None:
+ urls1 = []
+ infobox1.set('urls', urls1)
+
+ urlSet = set()
+ for url in infobox1.get('urls', []):
+ urlSet.add(url.get('url', None))
+
+ for url in infobox2.get('urls', []):
+ if url.get('url', None) not in urlSet:
+ urls1.append(url)
+
+ if 'attributes' in infobox2:
+ attributes1 = infobox1.get('attributes', None)
+ if attributes1 == None:
+ attributes1 = []
+ infobox1.set('attributes', attributes1)
+
+ attributeSet = set()
+ for attribute in infobox1.get('attributes', []):
+ if attribute.get('label', None) not in attributeSet:
+ attributeSet.add(attribute.get('label', None))
+
+ for attribute in infobox2.get('attributes', []):
+ attributes1.append(attribute)
+
+ if 'content' in infobox2:
+ content1 = infobox1.get('content', None)
+ content2 = infobox2.get('content', '')
+ if content1 != None:
+ if content_result_len(content2) > content_result_len(content1):
+ infobox1['content'] = content2
+ else:
+ infobox1.set('content', content2)
+
+
+def merge_infoboxes(infoboxes):
+ results = []
+ infoboxes_id = {}
+ for infobox in infoboxes:
+ add_infobox = True
+ infobox_id = infobox.get('id', None)
+ if infobox_id != None:
+ existingIndex = infoboxes_id.get(infobox_id, None)
+ if existingIndex != None:
+ merge_two_infoboxes(results[existingIndex], infobox)
+ add_infobox=False
+
+ if add_infobox:
+ results.append(infobox)
+ infoboxes_id[infobox_id] = len(results)-1
+
+ return results
+
+
class Search(object):
"""Search information container"""
@@ -219,6 +292,8 @@ class Search(object):
self.results = []
self.suggestions = []
+ self.answers = []
+ self.infoboxes = []
self.request_data = {}
# set specific language if set
@@ -350,6 +425,8 @@ class Search(object):
requests = []
results = {}
suggestions = set()
+ answers = set()
+ infoboxes = []
# increase number of searches
number_of_searches += 1
@@ -394,6 +471,8 @@ class Search(object):
selected_engine['name'],
results,
suggestions,
+ answers,
+ infoboxes,
engine.response,
request_params
)
@@ -431,11 +510,14 @@ class Search(object):
# score results and remove duplications
results = score_results(results)
+ # merge infoboxes according to their ids
+ infoboxes = merge_infoboxes(infoboxes)
+
# update engine stats, using calculated score
for result in results:
for res_engine in result['engines']:
engines[result['engine']]\
.stats['score_count'] += result['score']
- # return results and suggestions
- return results, suggestions
+ # return results, suggestions, answers and infoboxes
+ return results, suggestions, answers, infoboxes
diff --git a/searx/settings.yml b/searx/settings.yml
index da053ce6a..77bcd2aa4 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -1,7 +1,7 @@
server:
port : 8888
secret_key : "ultrasecretkey" # change this!
- debug : False # Debug mode, only for development
+ debug : True # Debug mode, only for development
request_timeout : 2.0 # seconds
base_url : False # Set custom base_url. Possible values: False or "https://your.custom.host/location/"
themes_path : "" # Custom ui themes path
diff --git a/searx/static/default/css/style.css b/searx/static/default/css/style.css
index 9a6faadef..ec476d19a 100644
--- a/searx/static/default/css/style.css
+++ b/searx/static/default/css/style.css
@@ -1,75 +1 @@
-html{font-family:sans-serif;font-size:.9em;-webkit-text-size-adjust:100%;-ms-text-size-adjust:100%;-moz-text-size-adjust:100%;text-size-adjust:100%;color:#444;padding:0;margin:0}
-body,#container{padding:0;margin:0}
-#container{width:100%;position:absolute;top:0}
-.search{padding:0;margin:0}.search .checkbox_container label{font-size:.9em;border-bottom:2px solid #e8e7e6}
-.search .checkbox_container label:hover{border-bottom:2px solid #3498db}
-.search .checkbox_container input[type="checkbox"]:checked+label{border-bottom:2px solid #2980b9}
-#search_wrapper{position:relative;width:50em;padding:10px}
-.center #search_wrapper{margin-left:auto;margin-right:auto}
-.q{background:none repeat scroll 0 0 #fff;border:1px solid #3498db;color:#222;font-size:16px;height:28px;margin:0;outline:medium none;padding:2px;padding-left:8px;padding-right:0 !important;width:100%;z-index:2}
-#search_submit{position:absolute;top:13px;right:1px;padding:0;border:0;background:url('../img/search-icon.png') no-repeat;background-size:24px 24px;opacity:.8;width:24px;height:30px;font-size:0}
-@media screen and (max-width:50em){#search_wrapper{width:90%;clear:both;overflow:hidden}}ul.autocompleter-choices{position:absolute;margin:0;padding:0;list-style:none;border:1px solid #3498db;border-left-color:#3498db;border-right-color:#3498db;border-bottom-color:#3498db;text-align:left;font-family:Verdana,Geneva,Arial,Helvetica,sans-serif;z-index:50;background-color:#fff;color:#444}ul.autocompleter-choices li{position:relative;margin:-2px 0 0 0;padding:.2em 1.5em .2em 1em;display:block;float:none !important;cursor:pointer;font-weight:normal;white-space:nowrap;font-size:1em;line-height:1.5em}ul.autocompleter-choices li.autocompleter-selected{background-color:#444;color:#fff}ul.autocompleter-choices li.autocompleter-selected span.autocompleter-queried{color:#9fcfff}
-ul.autocompleter-choices span.autocompleter-queried{display:inline;float:none;font-weight:bold;margin:0;padding:0}
-.row{max-width:800px;margin:20px auto;text-align:justify}.row h1{font-size:3em;margin-top:50px}
-.row p{padding:0 10px;max-width:700px}
-.row h3,.row ul{margin:4px 8px}
-.hmarg{margin:0 20px;border:1px solid #3498db;padding:4px 10px}
-a:link.hmarg{color:#3498db}
-a:visited.hmarg{color:#3498db}
-a:active.hmarg{color:#3498db}
-a:hover.hmarg{color:#3498db}
-.top_margin{margin-top:60px}
-.center{text-align:center}
-h1{font-size:5em}
-div.title{background:url('../img/searx.png') no-repeat;width:100%;background-position:center}div.title h1{visibility:hidden}
-input[type="submit"]{padding:2px 6px;margin:2px 4px;display:inline-block;background:#3498db;color:#fff;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;border:0;cursor:pointer}
-input[type="checkbox"]{visibility:hidden}
-fieldset{margin:8px;border:1px solid #3498db}
-#categories{margin:0 10px}
-.checkbox_container{display:inline-block;position:relative;margin:0 3px;padding:0}.checkbox_container input{display:none}
-.checkbox_container label,.engine_checkbox label{cursor:pointer;padding:4px 10px;margin:0;display:block;text-transform:capitalize;-webkit-touch-callout:none;-webkit-user-select:none;-khtml-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none}
-.checkbox_container input[type="checkbox"]:checked+label{background:#3498db;color:#fff}
-.engine_checkbox{padding:4px}
-label.allow{background:#e74c3c;padding:4px 8px;color:#fff;display:none}
-label.deny{background:#2ecc71;padding:4px 8px;color:#444;display:inline}
-.engine_checkbox input[type="checkbox"]:checked+label:nth-child(2)+label{display:none}
-.engine_checkbox input[type="checkbox"]:checked+label.allow{display:inline}
-a{text-decoration:none;color:#1a11be}a:visited{color:#8e44ad}
-.result{margin:19px 0 18px 0;padding:0;clear:both}
-.result_title{margin-bottom:0}.result_title a{color:#2980b9;font-weight:normal;font-size:1.1em}.result_title a:hover{text-decoration:underline}
-.result_title a:visited{color:#8e44ad}
-.cache_link{font-size:10px !important}
-.result h3{font-size:1em;word-wrap:break-word;margin:5px 0 1px 0;padding:0}
-.result .content{font-size:.8em;margin:0;padding:0;max-width:54em;word-wrap:break-word;line-height:1.24}
-.result .url{font-size:.8em;margin:0 0 3px 0;padding:0;max-width:54em;word-wrap:break-word;color:#c0392b}
-.result .published_date{font-size:.8em;color:#888;margin:5px 20px}
-.engines{color:#888}
-.small_font{font-size:.8em}
-.small p{margin:2px 0}
-.right{float:right}
-.invisible{display:none}
-.left{float:left}
-.highlight{color:#094089}
-.content .highlight{color:#000}
-.image_result{float:left;margin:10px 10px;position:relative;height:160px}.image_result img{border:0;height:160px}
-.image_result p{margin:0;padding:0}.image_result p span a{display:none;color:#fff}
-.image_result p:hover span a{display:block;position:absolute;bottom:0;right:0;padding:4px;background-color:rgba(0,0,0,0.6);font-size:.7em}
-.torrent_result{border-left:10px solid #d3d3d3;padding-left:3px}.torrent_result p{margin:3px;font-size:.8em}
-.definition_result{border-left:10px solid #808080;padding-left:3px}
-.percentage{position:relative;width:300px}.percentage div{background:#444}
-table{width:100%}
-td{padding:0 4px}
-tr:hover{background:#ddd}
-#results{margin:auto;padding:0;width:50em;margin-bottom:20px}
-#sidebar{position:absolute;top:100px;right:10px;margin:0 2px 5px 5px;padding:0 2px 2px 2px;width:14em}#sidebar input{padding:0;margin:3px;font-size:.8em;display:inline-block;background:transparent;color:#444;cursor:pointer}
-#sidebar input[type="submit"]{text-decoration:underline}
-#suggestions{margin-top:20px}#suggestions span{display:inline;margin:0 2px 2px 2px;padding:0}
-#suggestions input{padding:0;margin:3px;font-size:.8em;display:inline-block;background:transparent;color:#444;cursor:pointer}
-#suggestions input[type="submit"]{text-decoration:underline}
-#suggestions form{display:inline}
-#search_url{margin-top:8px}#search_url input{border:1px solid #888;padding:4px;color:#444;width:14em;display:block;margin:4px;font-size:.8em}
-#preferences{top:10px;padding:0;border:0;background:url('../img/preference-icon.png') no-repeat;background-size:28px 28px;opacity:.8;width:28px;height:30px;display:block}#preferences *{display:none}
-#pagination{clear:both;width:40em}
-#apis{margin-top:8px;clear:both}
-@media screen and (max-width:50em){#categories{font-size:90%;clear:both}#categories .checkbox_container{margin-top:2px;margin:auto} #results{margin:auto;padding:0;width:90%} .github{display:none} .checkbox_container{display:block;width:90%}.checkbox_container label{border-bottom:0}}@media screen and (max-width:70em){.right{display:none;postion:fixed !important;top:100px;right:0} #sidebar{position:static;max-width:50em;margin:0 0 2px 0;padding:0;float:none;border:none;width:auto}#sidebar input{border:0} #apis{display:none} #search_url{display:none} .result{border-top:1px solid #e8e7e6;margin:7px 0 6px 0}.result img{max-width:90%;width:auto;height:auto}}.favicon{float:left;margin-right:4px;margin-top:2px}
-.preferences_back{background:none repeat scroll 0 0 #3498db;border:0 none;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;cursor:pointer;display:inline-block;margin:2px 4px;padding:4px 6px}.preferences_back a{color:#fff}
+html{font-family:sans-serif;font-size:.9em;-webkit-text-size-adjust:100%;-ms-text-size-adjust:100%;-moz-text-size-adjust:100%;text-size-adjust:100%;color:#444;padding:0;margin:0}body,#container{padding:0;margin:0}#container{width:100%;position:absolute;top:0}.search{padding:0;margin:0}.search .checkbox_container label{font-size:.9em;border-bottom:2px solid #e8e7e6}.search .checkbox_container label:hover{border-bottom:2px solid #3498db}.search .checkbox_container input[type="checkbox"]:checked+label{border-bottom:2px solid #2980b9}#search_wrapper{position:relative;width:50em;padding:10px}.center #search_wrapper{margin-left:auto;margin-right:auto}.q{background:none repeat scroll 0 0 #fff;border:1px solid #3498db;color:#222;font-size:16px;height:28px;margin:0;outline:medium none;padding:2px;padding-left:8px;padding-right:0 !important;width:100%;z-index:2}#search_submit{position:absolute;top:13px;right:1px;padding:0;border:0;background:url('../img/search-icon.png') no-repeat;background-size:24px 24px;opacity:.8;width:24px;height:30px;font-size:0}@media screen and (max-width:50em){#search_wrapper{width:90%;clear:both;overflow:hidden}}ul.autocompleter-choices{position:absolute;margin:0;padding:0;list-style:none;border:1px solid #3498db;border-left-color:#3498db;border-right-color:#3498db;border-bottom-color:#3498db;text-align:left;font-family:Verdana,Geneva,Arial,Helvetica,sans-serif;z-index:50;background-color:#fff;color:#444}ul.autocompleter-choices li{position:relative;margin:-2px 0 0 0;padding:.2em 1.5em .2em 1em;display:block;float:none !important;cursor:pointer;font-weight:normal;white-space:nowrap;font-size:1em;line-height:1.5em}ul.autocompleter-choices li.autocompleter-selected{background-color:#444;color:#fff}ul.autocompleter-choices li.autocompleter-selected span.autocompleter-queried{color:#9fcfff}ul.autocompleter-choices span.autocompleter-queried{display:inline;float:none;font-weight:bold;margin:0;padding:0}.row{max-width:800px;margin:20px auto;text-align:justify}.row h1{font-size:3em;margin-top:50px}.row p{padding:0 10px;max-width:700px}.row h3,.row ul{margin:4px 8px}.hmarg{margin:0 20px;border:1px solid #3498db;padding:4px 10px}a:link.hmarg{color:#3498db}a:visited.hmarg{color:#3498db}a:active.hmarg{color:#3498db}a:hover.hmarg{color:#3498db}.top_margin{margin-top:60px}.center{text-align:center}h1{font-size:5em}div.title{background:url('../img/searx.png') no-repeat;width:100%;background-position:center}div.title h1{visibility:hidden}input[type="submit"]{padding:2px 6px;margin:2px 4px;display:inline-block;background:#3498db;color:#fff;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;border:0;cursor:pointer}input[type="checkbox"]{visibility:hidden}fieldset{margin:8px;border:1px solid #3498db}#categories{margin:0 10px}.checkbox_container{display:inline-block;position:relative;margin:0 3px;padding:0}.checkbox_container input{display:none}.checkbox_container label,.engine_checkbox label{cursor:pointer;padding:4px 10px;margin:0;display:block;text-transform:capitalize;-webkit-touch-callout:none;-webkit-user-select:none;-khtml-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none}.checkbox_container input[type="checkbox"]:checked+label{background:#3498db;color:#fff}.engine_checkbox{padding:4px}label.allow{background:#e74c3c;padding:4px 8px;color:#fff;display:none}label.deny{background:#2ecc71;padding:4px 8px;color:#444;display:inline}.engine_checkbox input[type="checkbox"]:checked+label:nth-child(2)+label{display:none}.engine_checkbox input[type="checkbox"]:checked+label.allow{display:inline}a{text-decoration:none;color:#1a11be}a:visited{color:#8e44ad}.result{margin:19px 0 18px 0;padding:0;clear:both}.result_title{margin-bottom:0}.result_title a{color:#2980b9;font-weight:normal;font-size:1.1em}.result_title a:hover{text-decoration:underline}.result_title a:visited{color:#8e44ad}.cache_link{font-size:10px !important}.result h3{font-size:1em;word-wrap:break-word;margin:5px 0 1px 0;padding:0}.result .content{font-size:.8em;margin:0;padding:0;max-width:54em;word-wrap:break-word;line-height:1.24}.result .content img{float:left;margin-right:5px;max-width:200px;max-height:100px}.result .content br.last{clear:both}.result .url{font-size:.8em;margin:0 0 3px 0;padding:0;max-width:54em;word-wrap:break-word;color:#c0392b}.result .published_date{font-size:.8em;color:#888;margin:5px 20px}.engines{color:#888}.small_font{font-size:.8em}.small p{margin:2px 0}.right{float:right}.invisible{display:none}.left{float:left}.highlight{color:#094089}.content .highlight{color:#000}.image_result{float:left;margin:10px 10px;position:relative;height:160px}.image_result img{border:0;height:160px}.image_result p{margin:0;padding:0}.image_result p span a{display:none;color:#fff}.image_result p:hover span a{display:block;position:absolute;bottom:0;right:0;padding:4px;background-color:rgba(0,0,0,0.6);font-size:.7em}.torrent_result{border-left:10px solid #d3d3d3;padding-left:3px}.torrent_result p{margin:3px;font-size:.8em}.definition_result{border-left:10px solid #808080;padding-left:3px}.percentage{position:relative;width:300px}.percentage div{background:#444}table{width:100%}td{padding:0 4px}tr:hover{background:#ddd}#results{margin:auto;padding:0;width:50em;margin-bottom:20px}#sidebar{position:absolute;top:100px;right:10px;margin:0 2px 5px 5px;padding:0 2px 2px 2px;width:14em}#sidebar input{padding:0;margin:3px;font-size:.8em;display:inline-block;background:transparent;color:#444;cursor:pointer}#sidebar input[type="submit"]{text-decoration:underline}#suggestions,#answers{margin-top:20px}#suggestions input,#answers input,#infoboxes input{padding:0;margin:3px;font-size:.8em;display:inline-block;background:transparent;color:#444;cursor:pointer}#suggestions input[type="submit"],#answers input[type="submit"],#infoboxes input[type="submit"]{text-decoration:underline}#suggestions form,#answers form,#infoboxes form{display:inline}#infoboxes{position:absolute;top:220px;right:20px;margin:0 2px 5px 5px;padding:0 2px 2px;max-width:21em}#infoboxes .infobox{margin:10px 0 10px;border:1px solid #ddd;padding:5px;font-size:.8em}#infoboxes .infobox img{max-width:20em;max-heigt:12em;display:block;margin:5px;padding:5px}#infoboxes .infobox h2{margin:0}#infoboxes .infobox table{width:auto}#infoboxes .infobox table td{vertical-align:top}#infoboxes .infobox input{font-size:1em}#infoboxes .infobox br{clear:both}#search_url{margin-top:8px}#search_url input{border:1px solid #888;padding:4px;color:#444;width:14em;display:block;margin:4px;font-size:.8em}#preferences{top:10px;padding:0;border:0;background:url('../img/preference-icon.png') no-repeat;background-size:28px 28px;opacity:.8;width:28px;height:30px;display:block}#preferences *{display:none}#pagination{clear:both;width:40em}#apis{margin-top:8px;clear:both}@media screen and (max-width:50em){#results{margin:auto;padding:0;width:90%}.github{display:none}.checkbox_container{display:block;width:90%}.checkbox_container label{border-bottom:0}}@media screen and (max-width:75em){#infoboxes{position:inherit;max-width:inherit}#infoboxes .infobox{clear:both}#infoboxes .infobox img{float:left;max-width:10em}#categories{font-size:90%;clear:both}#categories .checkbox_container{margin-top:2px;margin:auto}.right{display:none;postion:fixed !important;top:100px;right:0}#sidebar{position:static;max-width:50em;margin:0 0 2px 0;padding:0;float:none;border:none;width:auto}#sidebar input{border:0}#apis{display:none}#search_url{display:none}.result{border-top:1px solid #e8e7e6;margin:7px 0 6px 0}}.favicon{float:left;margin-right:4px;margin-top:2px}.preferences_back{background:none repeat scroll 0 0 #3498db;border:0 none;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;cursor:pointer;display:inline-block;margin:2px 4px;padding:4px 6px}.preferences_back a{color:#fff}
\ No newline at end of file
diff --git a/searx/static/default/less/style.less b/searx/static/default/less/style.less
index e3fac1b10..27da09e35 100644
--- a/searx/static/default/less/style.less
+++ b/searx/static/default/less/style.less
@@ -235,6 +235,17 @@ a {
max-width: 54em;
word-wrap:break-word;
line-height: 1.24;
+
+ img {
+ float: left;
+ margin-right: 5px;
+ max-width: 200px;
+ max-height: 100px;
+ }
+
+ br.last {
+ clear: both;
+ }
}
.url {
@@ -384,33 +395,80 @@ tr {
}
}
-#suggestions {
+#suggestions, #answers {
- margin-top: 20px;
+ margin-top: 20px;
+
+}
+
+#suggestions, #answers, #infoboxes {
- span {
- display: inline;
- margin: 0 2px 2px 2px;
- padding: 0;
- }
input {
padding: 0;
margin: 3px;
font-size: 0.8em;
display: inline-block;
- background: transparent;
- color: @color-result-search-url-font;
+ background: transparent;
+ color: @color-result-search-url-font;
cursor: pointer;
}
- input[type="submit"] {
+
+ input[type="submit"] {
text-decoration: underline;
- }
+ }
form {
display: inline;
}
}
+
+#infoboxes {
+ position: absolute;
+ top: 220px;
+ right: 20px;
+ margin: 0px 2px 5px 5px;
+ padding: 0px 2px 2px;
+ max-width: 21em;
+
+ .infobox {
+ margin: 10px 0 10px;
+ border: 1px solid #ddd;
+ padding: 5px;
+ font-size: 0.8em;
+
+ img {
+ max-width: 20em;
+ max-heigt: 12em;
+ display: block;
+ margin: 5px;
+ padding: 5px;
+ }
+
+ h2 {
+ margin: 0;
+ }
+
+ table {
+ width: auto;
+
+ td {
+ vertical-align: top;
+ }
+
+ }
+
+ input {
+ font-size: 1em;
+ }
+
+ br {
+ clear: both;
+ }
+
+ }
+}
+
#search_url {
margin-top: 8px;
@@ -453,16 +511,6 @@ tr {
@media screen and (max-width: @results-width) {
- #categories {
- font-size: 90%;
- clear: both;
-
- .checkbox_container {
- margin-top: 2px;
- margin: auto;
- }
- }
-
#results {
margin: auto;
padding: 0;
@@ -483,7 +531,33 @@ tr {
}
}
-@media screen and (max-width: 70em) {
+@media screen and (max-width: 75em) {
+
+ #infoboxes {
+ position: inherit;
+ max-width: inherit;
+
+ .infobox {
+ clear:both;
+
+ img {
+ float: left;
+ max-width: 10em;
+ }
+ }
+
+ }
+
+ #categories {
+ font-size: 90%;
+ clear: both;
+
+ .checkbox_container {
+ margin-top: 2px;
+ margin: auto;
+ }
+ }
+
.right {
display: none;
postion: fixed !important;
@@ -515,12 +589,6 @@ tr {
.result {
border-top: 1px solid @color-result-top-border;
margin: 7px 0 6px 0;
-
- img {
- max-width: 90%;
- width: auto;
- height: auto
- }
}
}
diff --git a/searx/templates/default/result_templates/default.html b/searx/templates/default/result_templates/default.html
index ac9b9b979..277946202 100644
--- a/searx/templates/default/result_templates/default.html
+++ b/searx/templates/default/result_templates/default.html
@@ -8,6 +8,8 @@
<h3 class="result_title"><a href="{{ result.url }}">{{ result.title|safe }}</a></h3>
<p class="url">{{ result.pretty_url }} <a class="cache_link" href="https://web.archive.org/web/{{ result.url }}">cached</a></p>
{% if result.publishedDate %}<p class="published_date">{{ result.publishedDate }}</p>{% endif %}
- <p class="content">{% if result.content %}{{ result.content|safe }}<br />{% endif %}</p>
+ <p class="content">
+ {% if result.img_src %}<img src="{{ result.img_src|safe }}" class="image" />{% endif %}
+ {% if result.content %}{{ result.content|safe }}<br class="last"/>{% endif %}</p>
</div>
</div>
diff --git a/searx/templates/default/results.html b/searx/templates/default/results.html
index d0b53b48a..b66d6e2af 100644
--- a/searx/templates/default/results.html
+++ b/searx/templates/default/results.html
@@ -30,6 +30,14 @@
</div>
</div>
+ {% if answers %}
+ <div id="answers"><span>{{ _('Answers') }}</span>
+ {% for answer in answers %}
+ <span>{{ answer }}</span>
+ {% endfor %}
+ </div>
+ {% endif %}
+
{% if suggestions %}
<div id="suggestions"><span>{{ _('Suggestions') }}</span>
{% for suggestion in suggestions %}
@@ -41,6 +49,14 @@
</div>
{% endif %}
+ {% if infoboxes %}
+ <div id="infoboxes">
+ {% for infobox in infoboxes %}
+ {% include 'default/infobox.html' %}
+ {% endfor %}
+ </div>
+ {% endif %}
+
{% for result in results %}
{% if result['template'] %}
{% include 'default/result_templates/'+result['template'] %}
diff --git a/searx/webapp.py b/searx/webapp.py
index 42cb42678..d0212169c 100644
--- a/searx/webapp.py
+++ b/searx/webapp.py
@@ -198,7 +198,7 @@ def index():
'index.html',
)
- search.results, search.suggestions = search.search(request)
+ search.results, search.suggestions, search.answers, search.infoboxes = search.search(request)
for result in search.results:
@@ -291,6 +291,8 @@ def index():
pageno=search.pageno,
base_url=get_base_url(),
suggestions=search.suggestions,
+ answers=search.answers,
+ infoboxes=search.infoboxes,
theme=get_current_theme_name()
)
From 0a71525ab6d4fe4cbc4b33b4653bdb39ae4d55e9 Mon Sep 17 00:00:00 2001
From: Dalf <alex@al-f.net>
Date: Sun, 28 Sep 2014 16:53:30 +0200
Subject: [PATCH 4/6] [enh] add infoboxes and answers (clean up)
---
searx/engines/wikidata.py | 45 ++++++++++++++++------------
searx/search.py | 1 -
searx/settings.yml | 4 +++
searx/templates/default/infobox.html | 44 +++++++++++++++++++++++++++
4 files changed, 74 insertions(+), 20 deletions(-)
create mode 100644 searx/templates/default/infobox.html
diff --git a/searx/engines/wikidata.py b/searx/engines/wikidata.py
index a5ee44246..46f2323c8 100644
--- a/searx/engines/wikidata.py
+++ b/searx/engines/wikidata.py
@@ -1,13 +1,12 @@
import json
-from datetime import datetime
from requests import get
from urllib import urlencode
+from datetime import datetime
resultCount=2
-urlSearch = 'https://www.wikidata.org/w/api.php?action=query&list=search&format=json&srnamespace=0&srprop=sectionsnippet&{query}'
+urlSearch = 'https://www.wikidata.org/w/api.php?action=query&list=search&format=json&srnamespace=0&srprop=sectiontitle&{query}'
urlDetail = 'https://www.wikidata.org/w/api.php?action=wbgetentities&format=json&props=labels%7Cinfo%7Csitelinks%7Csitelinks%2Furls%7Cdescriptions%7Cclaims&{query}'
-# find the right URL for urlMap
-urlMap = 'http://www.openstreetmap.org/?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M'
+urlMap = 'https://www.openstreetmap.org/?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M'
def request(query, params):
params['url'] = urlSearch.format(query=urlencode({'srsearch': query, 'srlimit': resultCount}))
@@ -18,24 +17,27 @@ def request(query, params):
def response(resp):
results = []
search_res = json.loads(resp.text)
- # TODO parallel http queries
- before = datetime.now()
+
+ wikidata_ids = set()
for r in search_res.get('query', {}).get('search', {}):
- wikidata_id = r.get('title', '')
- results = results + getDetail(wikidata_id)
- after = datetime.now()
- print str(after - before) + " second(s)"
+ wikidata_ids.add(r.get('title', ''))
+
+ language = resp.search_params['language'].split('_')[0]
+ if language == 'all':
+ language = 'en'
+ url = urlDetail.format(query=urlencode({'ids': '|'.join(wikidata_ids), 'languages': language + '|en'}))
+
+ before = datetime.now()
+ htmlresponse = get(url)
+ print datetime.now() - before
+ jsonresponse = json.loads(htmlresponse.content)
+ for wikidata_id in wikidata_ids:
+ results = results + getDetail(jsonresponse, wikidata_id, language)
return results
-def getDetail(wikidata_id):
- language = 'fr'
-
- url = urlDetail.format(query=urlencode({'ids': wikidata_id, 'languages': language + '|en'}))
- print url
- response = get(url)
- result = json.loads(response.content)
- result = result.get('entities', {}).get(wikidata_id, {})
+def getDetail(jsonresponse, wikidata_id, language):
+ result = jsonresponse.get('entities', {}).get(wikidata_id, {})
title = result.get('labels', {}).get(language, {}).get('value', None)
if title == None:
@@ -50,7 +52,6 @@ def getDetail(wikidata_id):
claims = result.get('claims', {})
official_website = get_string(claims, 'P856', None)
- print official_website
if official_website != None:
urls.append({ 'title' : 'Official site', 'url': official_website })
results.append({ 'title': title, 'url' : official_website })
@@ -98,10 +99,12 @@ def getDetail(wikidata_id):
return results
+
def add_url(urls, title, url):
if url != None:
urls.append({'title' : title, 'url' : url})
+
def get_mainsnak(claims, propertyName):
propValue = claims.get(propertyName, {})
if len(propValue) == 0:
@@ -110,6 +113,7 @@ def get_mainsnak(claims, propertyName):
propValue = propValue[0].get('mainsnak', None)
return propValue
+
def get_string(claims, propertyName, defaultValue=None):
propValue = claims.get(propertyName, {})
if len(propValue) == 0:
@@ -129,6 +133,7 @@ def get_string(claims, propertyName, defaultValue=None):
else:
return ', '.join(result)
+
def get_time(claims, propertyName, defaultValue=None):
propValue = claims.get(propertyName, {})
if len(propValue) == 0:
@@ -149,6 +154,7 @@ def get_time(claims, propertyName, defaultValue=None):
else:
return ', '.join(result)
+
def get_geolink(claims, propertyName, defaultValue=''):
mainsnak = get_mainsnak(claims, propertyName)
@@ -182,6 +188,7 @@ def get_geolink(claims, propertyName, defaultValue=''):
return url
+
def get_wikilink(result, wikiid):
url = result.get('sitelinks', {}).get(wikiid, {}).get('url', None)
if url == None:
diff --git a/searx/search.py b/searx/search.py
index 7eb605e11..f9157ef7e 100644
--- a/searx/search.py
+++ b/searx/search.py
@@ -76,7 +76,6 @@ def make_callback(engine_name, results, suggestions, answers, infoboxes, callbac
# if it is an infobox, add it to list of infoboxes
if 'infobox' in result:
infoboxes.append(result)
- print result
continue
# append result
diff --git a/searx/settings.yml b/searx/settings.yml
index 77bcd2aa4..02f7caacb 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -44,6 +44,10 @@ engines:
engine : duckduckgo_definitions
shortcut : ddd
+ - name : wikidata
+ engine : wikidata
+ shortcut : wd
+
- name : duckduckgo
engine : duckduckgo
shortcut : ddg
diff --git a/searx/templates/default/infobox.html b/searx/templates/default/infobox.html
new file mode 100644
index 000000000..f963e898c
--- /dev/null
+++ b/searx/templates/default/infobox.html
@@ -0,0 +1,44 @@
+<div class="infobox">
+ <h2>{{ infobox.infobox }}</h2>
+ {% if infobox.img_src %}<img src="{{ infobox.img_src }}" />{% endif %}
+ <p>{{ infobox.entity }}</p>
+ <p>{{ infobox.content }}</p>
+ {% if infobox.attributes %}
+ <div class="attributes">
+ <table>
+ {% for attribute in infobox.attributes %}
+ <tr><td>{{ attribute.label }}</td><td>{{ attribute.value }}</td></tr>
+ {% endfor %}
+ </table>
+ </div>
+ {% endif %}
+
+ {% if infobox.urls %}
+ <div class="urls">
+ <ul>
+ {% for url in infobox.urls %}
+ <li class="url"><a href="{{ url.url }}">{{ url.title }}</a></li>
+ {% endfor %}
+ </ul>
+ </div>
+ {% endif %}
+
+ {% if infobox.relatedTopics %}
+ <div class="relatedTopics">
+ {% for topic in infobox.relatedTopics %}
+ <div>
+ <h3>{{ topic.name }}</h3>
+ {% for suggestion in topic.suggestions %}
+ <form method="{{ method or 'POST' }}" action="{{ url_for('index') }}">
+ <input type="hidden" name="q" value="{{ suggestion }}">
+ <input type="submit" value="{{ suggestion }}" />
+ </form>
+ {% endfor %}
+ </div>
+ {% endfor %}
+ </div>
+ {% endif %}
+
+ <br />
+
+</div>
From 728fc611da126ddb20cb16ccaa214a1f6d8bcdbd Mon Sep 17 00:00:00 2001
From: dalf <alex@al-f.net>
Date: Wed, 1 Oct 2014 22:46:31 +0200
Subject: [PATCH 5/6] [fix] infoboxes and answers : pass all tests
---
searx/templates/default/result_templates/default.html | 4 +---
searx/tests/test_webapp.py | 10 +++++++++-
2 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/searx/templates/default/result_templates/default.html b/searx/templates/default/result_templates/default.html
index 277946202..938d66d04 100644
--- a/searx/templates/default/result_templates/default.html
+++ b/searx/templates/default/result_templates/default.html
@@ -8,8 +8,6 @@
<h3 class="result_title"><a href="{{ result.url }}">{{ result.title|safe }}</a></h3>
<p class="url">{{ result.pretty_url }} <a class="cache_link" href="https://web.archive.org/web/{{ result.url }}">cached</a></p>
{% if result.publishedDate %}<p class="published_date">{{ result.publishedDate }}</p>{% endif %}
- <p class="content">
- {% if result.img_src %}<img src="{{ result.img_src|safe }}" class="image" />{% endif %}
- {% if result.content %}{{ result.content|safe }}<br class="last"/>{% endif %}</p>
+ <p class="content">{% if result.img_src %}<img src="{{ result.img_src|safe }}" class="image" />{% endif %}{% if result.content %}{{ result.content|safe }}<br class="last"/>{% endif %}</p>
</div>
</div>
diff --git a/searx/tests/test_webapp.py b/searx/tests/test_webapp.py
index 9d1722eeb..9cf586180 100644
--- a/searx/tests/test_webapp.py
+++ b/searx/tests/test_webapp.py
@@ -43,6 +43,8 @@ class ViewsTestCase(SearxTestCase):
def test_index_html(self, search):
search.return_value = (
self.test_results,
+ set(),
+ set(),
set()
)
result = self.app.post('/', data={'q': 'test'})
@@ -51,7 +53,7 @@ class ViewsTestCase(SearxTestCase):
result.data
)
self.assertIn(
- '<p class="content">first <span class="highlight">test</span> content<br /></p>', # noqa
+ '<p class="content">first <span class="highlight">test</span> content<br class="last"/></p>', # noqa
result.data
)
@@ -59,6 +61,8 @@ class ViewsTestCase(SearxTestCase):
def test_index_json(self, search):
search.return_value = (
self.test_results,
+ set(),
+ set(),
set()
)
result = self.app.post('/', data={'q': 'test', 'format': 'json'})
@@ -75,6 +79,8 @@ class ViewsTestCase(SearxTestCase):
def test_index_csv(self, search):
search.return_value = (
self.test_results,
+ set(),
+ set(),
set()
)
result = self.app.post('/', data={'q': 'test', 'format': 'csv'})
@@ -90,6 +96,8 @@ class ViewsTestCase(SearxTestCase):
def test_index_rss(self, search):
search.return_value = (
self.test_results,
+ set(),
+ set(),
set()
)
result = self.app.post('/', data={'q': 'test', 'format': 'rss'})
From 63a0328c8b26c5d749ecf83ee73a44902e1d5cef Mon Sep 17 00:00:00 2001
From: dalf <alex@al-f.net>
Date: Thu, 2 Oct 2014 23:36:18 +0200
Subject: [PATCH 6/6] [enh] wikidata engine : add links to musicbrainz
---
searx/engines/wikidata.py | 23 ++++++++++++++++++++++-
1 file changed, 22 insertions(+), 1 deletion(-)
diff --git a/searx/engines/wikidata.py b/searx/engines/wikidata.py
index 46f2323c8..e8af8e204 100644
--- a/searx/engines/wikidata.py
+++ b/searx/engines/wikidata.py
@@ -69,13 +69,34 @@ def getDetail(jsonresponse, wikidata_id, language):
add_url(urls, 'Wikiquote (' + language + ')', get_wikilink(result, language + 'wikiquote'))
add_url(urls, 'Wikiquote (en)', get_wikilink(result, 'enwikiquote'))
-
add_url(urls, 'Commons wiki', get_wikilink(result, 'commonswiki'))
add_url(urls, 'Location', get_geolink(claims, 'P625', None))
add_url(urls, 'Wikidata', 'https://www.wikidata.org/wiki/' + wikidata_id + '?uselang='+ language)
+ musicbrainz_work_id = get_string(claims, 'P435')
+ if musicbrainz_work_id != None:
+ add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/work/' + musicbrainz_work_id)
+
+ musicbrainz_artist_id = get_string(claims, 'P434')
+ if musicbrainz_artist_id != None:
+ add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/artist/' + musicbrainz_artist_id)
+
+ musicbrainz_release_group_id = get_string(claims, 'P436')
+ if musicbrainz_release_group_id != None:
+ add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/release-group/' + musicbrainz_release_group_id)
+
+ musicbrainz_label_id = get_string(claims, 'P966')
+ if musicbrainz_label_id != None:
+ add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/label/' + musicbrainz_label_id)
+
+ # musicbrainz_area_id = get_string(claims, 'P982')
+ # P1407 MusicBrainz series ID
+ # P1004 MusicBrainz place ID
+ # P1330 MusicBrainz instrument ID
+ # P1407 MusicBrainz series ID
+
postal_code = get_string(claims, 'P281', None)
if postal_code != None:
attributes.append({'label' : 'Postal code(s)', 'value' : postal_code})