Adam Tauber
commit
9517f7a6e7
|
|
@ -1,8 +1,9 @@
|
|||
## Bing (Web)
|
||||
#
|
||||
#
|
||||
# @website https://www.bing.com
|
||||
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), max. 5000 query/month
|
||||
#
|
||||
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
|
||||
# max. 5000 query/month
|
||||
#
|
||||
# @using-api no (because of query limit)
|
||||
# @results HTML (using search portal)
|
||||
# @stable no (HTML can change)
|
||||
|
|
@ -58,8 +59,8 @@ def response(resp):
|
|||
content = escape(' '.join(result.xpath('.//p//text()')))
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
'content': content})
|
||||
|
||||
# return results if something is found
|
||||
|
|
@ -74,8 +75,8 @@ def response(resp):
|
|||
content = escape(' '.join(result.xpath('.//p//text()')))
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
'content': content})
|
||||
|
||||
# return results
|
||||
|
|
|
|||
|
|
@ -1,17 +1,19 @@
|
|||
## Bing (Images)
|
||||
#
|
||||
#
|
||||
# @website https://www.bing.com/images
|
||||
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), max. 5000 query/month
|
||||
#
|
||||
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
|
||||
# max. 5000 query/month
|
||||
#
|
||||
# @using-api no (because of query limit)
|
||||
# @results HTML (using search portal)
|
||||
# @stable no (HTML can change)
|
||||
# @parse url, title, img_src
|
||||
#
|
||||
# @todo currently there are up to 35 images receive per page, because bing does not parse count=10. limited response to 10 images
|
||||
# @todo currently there are up to 35 images receive per page,
|
||||
# because bing does not parse count=10.
|
||||
# limited response to 10 images
|
||||
|
||||
from urllib import urlencode
|
||||
from cgi import escape
|
||||
from lxml import html
|
||||
from yaml import load
|
||||
import re
|
||||
|
|
@ -51,15 +53,15 @@ def response(resp):
|
|||
dom = html.fromstring(resp.content)
|
||||
|
||||
# init regex for yaml-parsing
|
||||
p = re.compile( '({|,)([a-z]+):(")')
|
||||
p = re.compile('({|,)([a-z]+):(")')
|
||||
|
||||
# parse results
|
||||
for result in dom.xpath('//div[@class="dg_u"]'):
|
||||
link = result.xpath('./a')[0]
|
||||
|
||||
# parse yaml-data (it is required to add a space, to make it parsable)
|
||||
yaml_data = load(p.sub( r'\1\2: \3', link.attrib.get('m')))
|
||||
|
||||
yaml_data = load(p.sub(r'\1\2: \3', link.attrib.get('m')))
|
||||
|
||||
title = link.attrib.get('t1')
|
||||
#url = 'http://' + link.attrib.get('t3')
|
||||
url = yaml_data.get('surl')
|
||||
|
|
@ -69,7 +71,7 @@ def response(resp):
|
|||
results.append({'template': 'images.html',
|
||||
'url': url,
|
||||
'title': title,
|
||||
'content': '',
|
||||
'content': '',
|
||||
'img_src': img_src})
|
||||
|
||||
# TODO stop parsing if 10 images are found
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
## Bing (News)
|
||||
#
|
||||
#
|
||||
# @website https://www.bing.com/news
|
||||
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), max. 5000 query/month
|
||||
#
|
||||
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
|
||||
# max. 5000 query/month
|
||||
#
|
||||
# @using-api no (because of query limit)
|
||||
# @results HTML (using search portal)
|
||||
# @stable no (HTML can change)
|
||||
|
|
@ -57,12 +58,12 @@ def response(resp):
|
|||
url = link.attrib.get('href')
|
||||
title = ' '.join(link.xpath('.//text()'))
|
||||
contentXPath = result.xpath('.//div[@class="sn_txt"]/div//span[@class="sn_snip"]//text()')
|
||||
if contentXPath != None:
|
||||
if contentXPath is not None:
|
||||
content = escape(' '.join(contentXPath))
|
||||
|
||||
|
||||
# parse publishedDate
|
||||
publishedDateXPath = result.xpath('.//div[@class="sn_txt"]/div//span[contains(@class,"sn_ST")]//span[contains(@class,"sn_tm")]//text()')
|
||||
if publishedDateXPath != None:
|
||||
if publishedDateXPath is not None:
|
||||
publishedDate = escape(' '.join(publishedDateXPath))
|
||||
|
||||
if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
|
||||
|
|
@ -89,10 +90,10 @@ def response(resp):
|
|||
except TypeError:
|
||||
# FIXME
|
||||
publishedDate = datetime.now()
|
||||
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
'publishedDate': publishedDate,
|
||||
'content': content})
|
||||
|
||||
|
|
|
|||
|
|
@ -55,6 +55,6 @@ def response(resp):
|
|||
resp.search_params['to'].lower()
|
||||
)
|
||||
|
||||
results.append({'answer' : answer, 'url': url})
|
||||
results.append({'answer': answer, 'url': url})
|
||||
|
||||
return results
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Dailymotion (Videos)
|
||||
#
|
||||
#
|
||||
# @website https://www.dailymotion.com
|
||||
# @provide-api yes (http://www.dailymotion.com/developer)
|
||||
#
|
||||
#
|
||||
# @using-api yes
|
||||
# @results JSON
|
||||
# @stable yes
|
||||
|
|
@ -12,7 +12,6 @@
|
|||
|
||||
from urllib import urlencode
|
||||
from json import loads
|
||||
from lxml import html
|
||||
|
||||
# engine dependent config
|
||||
categories = ['videos']
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Deviantart (Images)
|
||||
#
|
||||
#
|
||||
# @website https://www.deviantart.com/
|
||||
# @provide-api yes (https://www.deviantart.com/developers/) (RSS)
|
||||
#
|
||||
#
|
||||
# @using-api no (TODO, rewrite to api)
|
||||
# @results HTML
|
||||
# @stable no (HTML can change)
|
||||
|
|
|
|||
|
|
@ -1,15 +1,17 @@
|
|||
## DuckDuckGo (Web)
|
||||
#
|
||||
#
|
||||
# @website https://duckduckgo.com/
|
||||
# @provide-api yes (https://duckduckgo.com/api), but not all results from search-site
|
||||
#
|
||||
# @provide-api yes (https://duckduckgo.com/api),
|
||||
# but not all results from search-site
|
||||
#
|
||||
# @using-api no
|
||||
# @results HTML (using search portal)
|
||||
# @stable no (HTML can change)
|
||||
# @parse url, title, content
|
||||
#
|
||||
# @todo rewrite to api
|
||||
# @todo language support (the current used site does not support language-change)
|
||||
# @todo language support
|
||||
# (the current used site does not support language-change)
|
||||
|
||||
from urllib import urlencode
|
||||
from lxml.html import fromstring
|
||||
|
|
@ -37,7 +39,7 @@ def request(query, params):
|
|||
if params['language'] == 'all':
|
||||
locale = 'en-us'
|
||||
else:
|
||||
locale = params['language'].replace('_','-').lower()
|
||||
locale = params['language'].replace('_', '-').lower()
|
||||
|
||||
params['url'] = url.format(
|
||||
query=urlencode({'q': query, 'kl': locale}),
|
||||
|
|
|
|||
|
|
@ -3,21 +3,25 @@ from urllib import urlencode
|
|||
from lxml import html
|
||||
from searx.engines.xpath import extract_text
|
||||
|
||||
url = 'https://api.duckduckgo.com/?{query}&format=json&pretty=0&no_redirect=1&d=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:
|
||||
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}))
|
||||
|
|
@ -38,16 +42,15 @@ def response(resp):
|
|||
# add answer if there is one
|
||||
answer = search_res.get('Answer', '')
|
||||
if answer != '':
|
||||
results.append({ 'answer' : html_to_text(answer) })
|
||||
results.append({'answer': html_to_text(answer)})
|
||||
|
||||
# add infobox
|
||||
if 'Definition' in search_res:
|
||||
content = content + search_res.get('Definition', '')
|
||||
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
|
||||
|
|
@ -55,29 +58,35 @@ def response(resp):
|
|||
# attributes
|
||||
if 'Infobox' in search_res:
|
||||
infobox = search_res.get('Infobox', None)
|
||||
if 'content' in infobox:
|
||||
if 'content' in infobox:
|
||||
for info in infobox.get('content'):
|
||||
attributes.append({'label': info.get('label'), 'value': info.get('value')})
|
||||
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})
|
||||
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))
|
||||
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 })
|
||||
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))
|
||||
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)
|
||||
|
||||
|
|
@ -86,21 +95,26 @@ def response(resp):
|
|||
if abstractURL != '':
|
||||
# add as result ? problem always in english
|
||||
infobox_id = abstractURL
|
||||
urls.append({'title': search_res.get('AbstractSource'), 'url': 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})
|
||||
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 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 film / actor / television / media franchise :
|
||||
# links to IMDB / rottentomatoes (or scrap result)
|
||||
# TODO music : link tu musicbrainz / last.fm
|
||||
# TODO book : ??
|
||||
# TODO artist / playwright : ??
|
||||
|
|
@ -114,24 +128,25 @@ def response(resp):
|
|||
# TODO programming language : ??
|
||||
# TODO file format : ??
|
||||
|
||||
if len(heading)>0:
|
||||
if len(heading) > 0:
|
||||
# TODO get infobox.meta.value where .label='article_title'
|
||||
if image==None and len(attributes)==0 and len(urls)==1 and len(relatedTopics)==0 and len(content)==0:
|
||||
if image is None and len(attributes) == 0 and len(urls) == 1 and\
|
||||
len(relatedTopics) == 0 and len(content) == 0:
|
||||
results.append({
|
||||
'url': urls[0]['url'],
|
||||
'title': heading,
|
||||
'content': content
|
||||
})
|
||||
'url': urls[0]['url'],
|
||||
'title': heading,
|
||||
'content': content
|
||||
})
|
||||
else:
|
||||
results.append({
|
||||
'infobox': heading,
|
||||
'id': infobox_id,
|
||||
'entity': entity,
|
||||
'content': content,
|
||||
'img_src' : image,
|
||||
'attributes': attributes,
|
||||
'urls': urls,
|
||||
'relatedTopics': relatedTopics
|
||||
})
|
||||
'infobox': heading,
|
||||
'id': infobox_id,
|
||||
'entity': entity,
|
||||
'content': content,
|
||||
'img_src': image,
|
||||
'attributes': attributes,
|
||||
'urls': urls,
|
||||
'relatedTopics': relatedTopics
|
||||
})
|
||||
|
||||
return results
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
## Dummy
|
||||
#
|
||||
#
|
||||
# @results empty array
|
||||
# @stable yes
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Faroo (Web, News)
|
||||
#
|
||||
#
|
||||
# @website http://www.faroo.com
|
||||
# @provide-api yes (http://www.faroo.com/hp/api/api.html), require API-key
|
||||
#
|
||||
#
|
||||
# @using-api yes
|
||||
# @results JSON
|
||||
# @stable yes
|
||||
|
|
@ -24,9 +24,10 @@ api_key = None
|
|||
url = 'http://www.faroo.com/'
|
||||
search_url = url + 'api?{query}&start={offset}&length={number_of_results}&l={language}&src={categorie}&i=false&f=json&key={api_key}'
|
||||
|
||||
search_category = {'general': 'web',
|
||||
search_category = {'general': 'web',
|
||||
'news': 'news'}
|
||||
|
||||
|
||||
# do search-request
|
||||
def request(query, params):
|
||||
offset = (params['pageno']-1) * number_of_results + 1
|
||||
|
|
@ -48,7 +49,7 @@ def request(query, params):
|
|||
query=urlencode({'q': query}),
|
||||
language=language,
|
||||
categorie=categorie,
|
||||
api_key=api_key )
|
||||
api_key=api_key)
|
||||
|
||||
# using searx User-Agent
|
||||
params['headers']['User-Agent'] = searx_useragent()
|
||||
|
|
@ -101,7 +102,7 @@ def response(resp):
|
|||
results.append({'template': 'images.html',
|
||||
'url': result['url'],
|
||||
'title': result['title'],
|
||||
'content': result['kwic'],
|
||||
'content': result['kwic'],
|
||||
'img_src': result['iurl']})
|
||||
|
||||
# return results
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## General Files (Files)
|
||||
#
|
||||
#
|
||||
# @website http://www.general-files.org
|
||||
# @provide-api no (nothing found)
|
||||
#
|
||||
#
|
||||
# @using-api no (because nothing found)
|
||||
# @results HTML (using search portal)
|
||||
# @stable no (HTML can change)
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Github (It)
|
||||
#
|
||||
#
|
||||
# @website https://github.com/
|
||||
# @provide-api yes (https://developer.github.com/v3/)
|
||||
#
|
||||
#
|
||||
# @using-api yes
|
||||
# @results JSON
|
||||
# @stable yes (using api)
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
## Google (Images)
|
||||
#
|
||||
#
|
||||
# @website https://www.google.com
|
||||
# @provide-api yes (https://developers.google.com/web-search/docs/), deprecated!
|
||||
#
|
||||
# @provide-api yes (https://developers.google.com/web-search/docs/),
|
||||
# deprecated!
|
||||
#
|
||||
# @using-api yes
|
||||
# @results JSON
|
||||
# @stable yes (but deprecated)
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
## Google (News)
|
||||
#
|
||||
#
|
||||
# @website https://www.google.com
|
||||
# @provide-api yes (https://developers.google.com/web-search/docs/), deprecated!
|
||||
#
|
||||
# @provide-api yes (https://developers.google.com/web-search/docs/),
|
||||
# deprecated!
|
||||
#
|
||||
# @using-api yes
|
||||
# @results JSON
|
||||
# @stable yes (but deprecated)
|
||||
|
|
|
|||
|
|
@ -39,16 +39,16 @@ def response(resp):
|
|||
url = result_base_url.format(osm_type=osm_type,
|
||||
osm_id=r['osm_id'])
|
||||
|
||||
osm = {'type':osm_type,
|
||||
'id':r['osm_id']}
|
||||
osm = {'type': osm_type,
|
||||
'id': r['osm_id']}
|
||||
|
||||
geojson = r.get('geojson')
|
||||
geojson = r.get('geojson')
|
||||
|
||||
# if no geojson is found and osm_type is a node, add geojson Point
|
||||
if not geojson and\
|
||||
osm_type == 'node':
|
||||
geojson = {u'type':u'Point',
|
||||
u'coordinates':[r['lon'],r['lat']]}
|
||||
geojson = {u'type': u'Point',
|
||||
u'coordinates': [r['lon'], r['lat']]}
|
||||
|
||||
address_raw = r.get('address')
|
||||
address = {}
|
||||
|
|
@ -59,20 +59,20 @@ def response(resp):
|
|||
r['class'] == 'tourism' or\
|
||||
r['class'] == 'leisure':
|
||||
if address_raw.get('address29'):
|
||||
address = {'name':address_raw.get('address29')}
|
||||
address = {'name': address_raw.get('address29')}
|
||||
else:
|
||||
address = {'name':address_raw.get(r['type'])}
|
||||
address = {'name': address_raw.get(r['type'])}
|
||||
|
||||
# add rest of adressdata, if something is already found
|
||||
if address.get('name'):
|
||||
address.update({'house_number':address_raw.get('house_number'),
|
||||
'road':address_raw.get('road'),
|
||||
'locality':address_raw.get('city',
|
||||
address_raw.get('town',
|
||||
address_raw.get('village'))),
|
||||
'postcode':address_raw.get('postcode'),
|
||||
'country':address_raw.get('country'),
|
||||
'country_code':address_raw.get('country_code')})
|
||||
address.update({'house_number': address_raw.get('house_number'),
|
||||
'road': address_raw.get('road'),
|
||||
'locality': address_raw.get('city',
|
||||
address_raw.get('town',
|
||||
address_raw.get('village'))),
|
||||
'postcode': address_raw.get('postcode'),
|
||||
'country': address_raw.get('country'),
|
||||
'country_code': address_raw.get('country_code')})
|
||||
else:
|
||||
address = None
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Piratebay (Videos, Music, Files)
|
||||
#
|
||||
#
|
||||
# @website https://thepiratebay.se
|
||||
# @provide-api no (nothing found)
|
||||
#
|
||||
#
|
||||
# @using-api no
|
||||
# @results HTML (using search portal)
|
||||
# @stable yes (HTML can change)
|
||||
|
|
@ -23,7 +23,7 @@ url = 'https://thepiratebay.se/'
|
|||
search_url = url + 'search/{search_term}/{pageno}/99/{search_type}'
|
||||
|
||||
# piratebay specific type-definitions
|
||||
search_types = {'files': '0',
|
||||
search_types = {'files': '0',
|
||||
'music': '100',
|
||||
'videos': '200'}
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Soundcloud (Music)
|
||||
#
|
||||
#
|
||||
# @website https://soundcloud.com
|
||||
# @provide-api yes (https://developers.soundcloud.com/)
|
||||
#
|
||||
#
|
||||
# @using-api yes
|
||||
# @results JSON
|
||||
# @stable yes
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Stackoverflow (It)
|
||||
#
|
||||
#
|
||||
# @website https://stackoverflow.com/
|
||||
# @provide-api not clear (https://api.stackexchange.com/docs/advanced-search)
|
||||
#
|
||||
#
|
||||
# @using-api no
|
||||
# @results HTML
|
||||
# @stable no (HTML can change)
|
||||
|
|
@ -50,8 +50,8 @@ def response(resp):
|
|||
content = escape(' '.join(result.xpath(content_xpath)))
|
||||
|
||||
# append result
|
||||
results.append({'url': href,
|
||||
'title': title,
|
||||
results.append({'url': href,
|
||||
'title': title,
|
||||
'content': content})
|
||||
|
||||
# return results
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Twitter (Social media)
|
||||
#
|
||||
#
|
||||
# @website https://www.bing.com/news
|
||||
# @provide-api yes (https://dev.twitter.com/docs/using-search)
|
||||
#
|
||||
#
|
||||
# @using-api no
|
||||
# @results HTML (using search portal)
|
||||
# @stable no (HTML can change)
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
## Vimeo (Videos)
|
||||
#
|
||||
#
|
||||
# @website https://vimeo.com/
|
||||
# @provide-api yes (http://developer.vimeo.com/api), they have a maximum count of queries/hour
|
||||
#
|
||||
# @provide-api yes (http://developer.vimeo.com/api),
|
||||
# they have a maximum count of queries/hour
|
||||
#
|
||||
# @using-api no (TODO, rewrite to api)
|
||||
# @results HTML (using search portal)
|
||||
# @stable no (HTML can change)
|
||||
|
|
@ -35,11 +36,12 @@ publishedDate_xpath = './/p[@class="meta"]//attribute::datetime'
|
|||
|
||||
# do search-request
|
||||
def request(query, params):
|
||||
params['url'] = search_url.format(pageno=params['pageno'] ,
|
||||
params['url'] = search_url.format(pageno=params['pageno'],
|
||||
query=urlencode({'q': query}))
|
||||
|
||||
# TODO required?
|
||||
params['cookies']['__utma'] = '00000000.000#0000000.0000000000.0000000000.0000000000.0'
|
||||
params['cookies']['__utma'] =\
|
||||
'00000000.000#0000000.0000000000.0000000000.0000000000.0'
|
||||
|
||||
return params
|
||||
|
||||
|
|
|
|||
|
|
@ -2,13 +2,25 @@ import json
|
|||
from requests import get
|
||||
from urllib import urlencode
|
||||
|
||||
resultCount=1
|
||||
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}'
|
||||
urlMap = 'https://www.openstreetmap.org/?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M'
|
||||
result_count = 1
|
||||
wikidata_host = 'https://www.wikidata.org'
|
||||
wikidata_api = wikidata_host + '/w/api.php'
|
||||
url_search = wikidata_api \
|
||||
+ '?action=query&list=search&format=json'\
|
||||
+ '&srnamespace=0&srprop=sectiontitle&{query}'
|
||||
url_detail = wikidata_api\
|
||||
+ '?action=wbgetentities&format=json'\
|
||||
+ '&props=labels%7Cinfo%7Csitelinks'\
|
||||
+ '%7Csitelinks%2Furls%7Cdescriptions%7Cclaims'\
|
||||
+ '&{query}'
|
||||
url_map = '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}))
|
||||
params['url'] = url_search.format(
|
||||
query=urlencode({'srsearch': query,
|
||||
'srlimit': result_count}))
|
||||
return params
|
||||
|
||||
|
||||
|
|
@ -23,7 +35,8 @@ def response(resp):
|
|||
language = resp.search_params['language'].split('_')[0]
|
||||
if language == 'all':
|
||||
language = 'en'
|
||||
url = urlDetail.format(query=urlencode({'ids': '|'.join(wikidata_ids), 'languages': language + '|en'}))
|
||||
url = url_detail.format(query=urlencode({'ids': '|'.join(wikidata_ids),
|
||||
'languages': language + '|en'}))
|
||||
|
||||
htmlresponse = get(url)
|
||||
jsonresponse = json.loads(htmlresponse.content)
|
||||
|
|
@ -32,6 +45,7 @@ def response(resp):
|
|||
|
||||
return results
|
||||
|
||||
|
||||
def getDetail(jsonresponse, wikidata_id, language):
|
||||
results = []
|
||||
urls = []
|
||||
|
|
@ -40,60 +54,103 @@ 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:
|
||||
if title is None:
|
||||
title = result.get('labels', {}).get('en', {}).get('value', None)
|
||||
if title == None:
|
||||
if title is None:
|
||||
return results
|
||||
|
||||
description = result.get('descriptions', {}).get(language, {}).get('value', None)
|
||||
if description == None:
|
||||
description = result.get('descriptions', {}).get('en', {}).get('value', '')
|
||||
description = result\
|
||||
.get('descriptions', {})\
|
||||
.get(language, {})\
|
||||
.get('value', None)
|
||||
|
||||
if description is None:
|
||||
description = result\
|
||||
.get('descriptions', {})\
|
||||
.get('en', {})\
|
||||
.get('value', '')
|
||||
|
||||
claims = result.get('claims', {})
|
||||
official_website = get_string(claims, 'P856', None)
|
||||
if official_website != None:
|
||||
urls.append({ 'title' : 'Official site', 'url': official_website })
|
||||
results.append({ 'title': title, 'url' : official_website })
|
||||
if official_website is not None:
|
||||
urls.append({'title': 'Official site', 'url': official_website})
|
||||
results.append({'title': title, 'url': official_website})
|
||||
|
||||
wikipedia_link_count = 0
|
||||
if language != 'en':
|
||||
wikipedia_link_count += add_url(urls, 'Wikipedia (' + language + ')', get_wikilink(result, language + 'wiki'))
|
||||
wikipedia_link_count += add_url(urls,
|
||||
'Wikipedia (' + language + ')',
|
||||
get_wikilink(result, language +
|
||||
'wiki'))
|
||||
wikipedia_en_link = get_wikilink(result, 'enwiki')
|
||||
wikipedia_link_count += add_url(urls, 'Wikipedia (en)', wikipedia_en_link)
|
||||
wikipedia_link_count += add_url(urls,
|
||||
'Wikipedia (en)',
|
||||
wikipedia_en_link)
|
||||
if wikipedia_link_count == 0:
|
||||
misc_language = get_wiki_firstlanguage(result, 'wiki')
|
||||
if misc_language != None:
|
||||
add_url(urls, 'Wikipedia (' + misc_language + ')', get_wikilink(result, misc_language + 'wiki'))
|
||||
if misc_language is not None:
|
||||
add_url(urls,
|
||||
'Wikipedia (' + misc_language + ')',
|
||||
get_wikilink(result, misc_language + 'wiki'))
|
||||
|
||||
if language != 'en':
|
||||
add_url(urls, 'Wiki voyage (' + language + ')', get_wikilink(result, language + 'wikivoyage'))
|
||||
add_url(urls, 'Wiki voyage (en)', get_wikilink(result, 'enwikivoyage'))
|
||||
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,
|
||||
'Wikiquote (' + language + ')',
|
||||
get_wikilink(result, language + 'wikiquote'))
|
||||
|
||||
add_url(urls, 'Commons wiki', get_wikilink(result, 'commonswiki'))
|
||||
add_url(urls,
|
||||
'Wikiquote (en)',
|
||||
get_wikilink(result, 'enwikiquote'))
|
||||
|
||||
add_url(urls, 'Location', get_geolink(claims, 'P625', None))
|
||||
add_url(urls,
|
||||
'Commons wiki',
|
||||
get_wikilink(result, 'commonswiki'))
|
||||
|
||||
add_url(urls, 'Wikidata', 'https://www.wikidata.org/wiki/' + wikidata_id + '?uselang='+ language)
|
||||
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)
|
||||
if musicbrainz_work_id is not 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)
|
||||
if musicbrainz_artist_id is not 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)
|
||||
if musicbrainz_release_group_id is not 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)
|
||||
if musicbrainz_label_id is not None:
|
||||
add_url(urls,
|
||||
'MusicBrainz',
|
||||
'http://musicbrainz.org/label/'
|
||||
+ musicbrainz_label_id)
|
||||
|
||||
# musicbrainz_area_id = get_string(claims, 'P982')
|
||||
# P1407 MusicBrainz series ID
|
||||
|
|
@ -102,42 +159,43 @@ def getDetail(jsonresponse, wikidata_id, language):
|
|||
# P1407 MusicBrainz series ID
|
||||
|
||||
postal_code = get_string(claims, 'P281', None)
|
||||
if postal_code != None:
|
||||
attributes.append({'label' : 'Postal code(s)', 'value' : postal_code})
|
||||
if postal_code is not 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})
|
||||
if date_of_birth is not 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})
|
||||
if date_of_death is not None:
|
||||
attributes.append({'label': 'Date of death', 'value': date_of_death})
|
||||
|
||||
if len(attributes)==0 and len(urls)==2 and len(description)==0:
|
||||
if len(attributes) == 0 and len(urls) == 2 and len(description) == 0:
|
||||
results.append({
|
||||
'url': urls[0]['url'],
|
||||
'title': title,
|
||||
'content': description
|
||||
})
|
||||
'url': urls[0]['url'],
|
||||
'title': title,
|
||||
'content': description
|
||||
})
|
||||
else:
|
||||
results.append({
|
||||
'infobox' : title,
|
||||
'id' : wikipedia_en_link,
|
||||
'content' : description,
|
||||
'attributes' : attributes,
|
||||
'urls' : urls
|
||||
})
|
||||
'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})
|
||||
if url is not None:
|
||||
urls.append({'title': title, 'url': url})
|
||||
return 1
|
||||
else:
|
||||
return 0
|
||||
|
||||
|
||||
def get_mainsnak(claims, propertyName):
|
||||
propValue = claims.get(propertyName, {})
|
||||
if len(propValue) == 0:
|
||||
|
|
@ -157,7 +215,7 @@ def get_string(claims, propertyName, defaultValue=None):
|
|||
mainsnak = e.get('mainsnak', {})
|
||||
|
||||
datavalue = mainsnak.get('datavalue', {})
|
||||
if datavalue != None:
|
||||
if datavalue is not None:
|
||||
result.append(datavalue.get('value', ''))
|
||||
|
||||
if len(result) == 0:
|
||||
|
|
@ -177,7 +235,7 @@ def get_time(claims, propertyName, defaultValue=None):
|
|||
mainsnak = e.get('mainsnak', {})
|
||||
|
||||
datavalue = mainsnak.get('datavalue', {})
|
||||
if datavalue != None:
|
||||
if datavalue is not None:
|
||||
value = datavalue.get('value', '')
|
||||
result.append(value.get('time', ''))
|
||||
|
||||
|
|
@ -190,7 +248,7 @@ def get_time(claims, propertyName, defaultValue=None):
|
|||
def get_geolink(claims, propertyName, defaultValue=''):
|
||||
mainsnak = get_mainsnak(claims, propertyName)
|
||||
|
||||
if mainsnak == None:
|
||||
if mainsnak is None:
|
||||
return defaultValue
|
||||
|
||||
datatype = mainsnak.get('datatype', '')
|
||||
|
|
@ -209,21 +267,25 @@ def get_geolink(claims, propertyName, defaultValue=''):
|
|||
# 1 --> 6
|
||||
# 0.016666666666667 --> 9
|
||||
# 0.00027777777777778 --> 19
|
||||
# wolframalpha : quadratic fit { {13, 5}, {1, 6}, {0.0166666, 9}, {0.0002777777,19}}
|
||||
# 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))
|
||||
url = url_map\
|
||||
.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:
|
||||
if url is None:
|
||||
return url
|
||||
elif url.startswith('http://'):
|
||||
url = url.replace('http://', 'https://')
|
||||
|
|
@ -231,8 +293,9 @@ def get_wikilink(result, wikiid):
|
|||
url = 'https:' + url
|
||||
return url
|
||||
|
||||
|
||||
def get_wiki_firstlanguage(result, wikipatternid):
|
||||
for k in result.get('sitelinks', {}).keys():
|
||||
if k.endswith(wikipatternid) and len(k)==(2+len(wikipatternid)):
|
||||
if k.endswith(wikipatternid) and len(k) == (2+len(wikipatternid)):
|
||||
return k[0:2]
|
||||
return None
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
## Yacy (Web, Images, Videos, Music, Files)
|
||||
#
|
||||
#
|
||||
# @website http://yacy.net
|
||||
# @provide-api yes (http://www.yacy-websuche.de/wiki/index.php/Dev:APIyacysearch)
|
||||
#
|
||||
# @provide-api yes
|
||||
# (http://www.yacy-websuche.de/wiki/index.php/Dev:APIyacysearch)
|
||||
#
|
||||
# @using-api yes
|
||||
# @results JSON
|
||||
# @stable yes
|
||||
|
|
@ -16,7 +17,7 @@ from urllib import urlencode
|
|||
from dateutil import parser
|
||||
|
||||
# engine dependent config
|
||||
categories = ['general', 'images'] #TODO , 'music', 'videos', 'files'
|
||||
categories = ['general', 'images'] # TODO , 'music', 'videos', 'files'
|
||||
paging = True
|
||||
language_support = True
|
||||
number_of_results = 5
|
||||
|
|
@ -28,7 +29,7 @@ search_url = '/yacysearch.json?{query}&startRecord={offset}&maximumRecords={limi
|
|||
# yacy specific type-definitions
|
||||
search_types = {'general': 'text',
|
||||
'images': 'image',
|
||||
'files': 'app',
|
||||
'files': 'app',
|
||||
'music': 'audio',
|
||||
'videos': 'video'}
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
## Yahoo (Web)
|
||||
#
|
||||
#
|
||||
# @website https://search.yahoo.com/web
|
||||
# @provide-api yes (https://developer.yahoo.com/boss/search/), $0.80/1000 queries
|
||||
#
|
||||
# @provide-api yes (https://developer.yahoo.com/boss/search/),
|
||||
# $0.80/1000 queries
|
||||
#
|
||||
# @using-api no (because pricing)
|
||||
# @results HTML (using search portal)
|
||||
# @stable no (HTML can change)
|
||||
|
|
@ -40,8 +41,8 @@ def parse_url(url_string):
|
|||
if endpos > -1:
|
||||
endpositions.append(endpos)
|
||||
|
||||
if start==0 or len(endpositions) == 0:
|
||||
return url_string
|
||||
if start == 0 or len(endpositions) == 0:
|
||||
return url_string
|
||||
else:
|
||||
end = min(endpositions)
|
||||
return unquote(url_string[start:end])
|
||||
|
|
@ -84,8 +85,8 @@ def response(resp):
|
|||
content = extract_text(result.xpath(content_xpath)[0])
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
'content': content})
|
||||
|
||||
# if no suggestion found, return results
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
## Youtube (Videos)
|
||||
#
|
||||
#
|
||||
# @website https://www.youtube.com/
|
||||
# @provide-api yes (http://gdata-samples-youtube-search-py.appspot.com/)
|
||||
#
|
||||
#
|
||||
# @using-api yes
|
||||
# @results JSON
|
||||
# @stable yes
|
||||
|
|
|
|||
Loading…
Reference in New Issue