def __init__(self, service, source = 'Web', resultsPerPage = 10, **args):
"""
Args:
source - should be 'Web', 'Image', 'News', 'RelatedSearch', 'SpellingSuggestions'
"""
SearchEngine.__init__(self, service, **args)
self.source = source
self.resultsPerPage = resultsPerPage
def __init__(self, service, source = 'Web', adult = 'Strict', market = 'en-US', resultsPerPage = 8, filters = None, sortBy = None, newsCategory = None, sites=None, **args):
"""
Arguments for all source types:
(1) source(str) - Should be 'Web', 'Image', 'News', 'RelatedSearch', 'SpellingSuggestions'
(2) adult(str) - Strict is the default, not recommended to change this, can also be 'Moderate' or 'Off'
(3) market(str) - For UK: en-GB, For Netherlands: nl-NL etc
(4) resultsPerPage(int) - How many results per page
Arguments for Image and Video searches only:
(1) filters(str) - Filter options split up by '+' you can only have one of each type see
Bing API documentation for examples of the valid filters.
Example: "Style:Photo+Aspect:Tall'" gets tall photos.
Arguments for Video and News searches only:
(1) sortBy(str) - You can select to sort by either 'Date' or 'Relevance'
Arguments for News searches only:
(1) newsCategory(str) - What sort of news is wanted, see BingAPI for list of options, for example:
'rt_ScienceAndTechnology' to find news under this category. Only available
with the en-US market, 'cause the rest of the world do not like categories.
"""
SearchEngine.__init__(self, service, **args) # This will also handle any unsupported parameters
# The search sources have different limits
sources_to_limits = {"Image" : 50,
"Web" : 50,
"News" : 15,
"RelatedSearch" : 50,
"Video" : 50,
"SpellingSuggestions" : 50}
self.engineName = "Bing V3_json" # Used for error identification
# If there is not entry in the sources dictionary with their limits raise an Error
if source in sources_to_limits:
self.source = source
else:
raise SearchEngineError(self.engineName, "Invalid source type: %s is not supported" % source)
# For some reason Spelling Suggestions (named wrongly in their documentation) is only available as Atom
if self.source != "SpellingSuggestions":
self.format = "json"
else:
self.format = "atom"
# Quick bit of validation, if greater than the sources limit or 0 or less use a default
if resultsPerPage > sources_to_limits[source] or resultsPerPage <= 0:
self.resultsPerPage = 8
else:
self.resultsPerPage = resultsPerPage
self.adult = adult
self.market = market
self.filters = filters
self.sortBy = sortBy
self.newsCategory = newsCategory
self.sites = sites
def __init__(self, service, source = 'web', adult = 'Strict', market = 'en-GB', resultsPerPage = 10, lat = None, lon = None, radius = 5, sites=None, **args): SearchEngine.__init__(self, service, **args) sitesearch.__init__(self, sites) self.sites = sites self.source = source self.adult = adult self.market = market self.resultsPerPage = resultsPerPage self.lat = lat self.lon = lon self.radius = radius
def __init__(self, service, source = 'Web', adult = 'Strict', market = 'en-GB', resultsPerPage = 8, filters = None, sortBy = None, newsCategory = None, sites=None, **args):
SearchEngine.__init__(self, service, **args)
sitesearch.__init__(self, sites)
self.source = source
self.adult = adult
self.market = market
self.resultsPerPage = resultsPerPage
self.filters = filters
self.sortBy = sortBy
self.newsCategory = newsCategory
def __init__(self, service, resultsPerPage = 8, order=None, tags=None, filter=None, genres=None, types=None, bpmFilter=None, durationFilter=None, createdFilter=None, **args):
SearchEngine.__init__(self, service, **args)
self.resultsPerPage = resultsPerPage
self.order = order
self.tags = tags
self.filter = filter
self.genres = genres
self.types = types
self.bpmFilter = bpmFilter
self.durationFilter = durationFilter
self.createdFilter = createdFilter
def __init__(self,
service,
source='web',
adult='Strict',
market='en-GB',
resultsPerPage=10,
lat=None,
lon=None,
radius=5,
sites=None,
**args):
SearchEngine.__init__(self, service, **args)
sitesearch.__init__(self, sites)
self.sites = sites
self.source = source
self.adult = adult
self.market = market
self.resultsPerPage = resultsPerPage
self.lat = lat
self.lon = lon
self.radius = radius
def __init__(self,
service,
source='Web',
adult='Strict',
market='en-GB',
resultsPerPage=8,
filters=None,
sortBy=None,
newsCategory=None,
sites=None,
**args):
SearchEngine.__init__(self, service, **args)
sitesearch.__init__(self, sites)
self.source = source
self.adult = adult
self.market = market
self.resultsPerPage = resultsPerPage
self.filters = filters
self.sortBy = sortBy
self.newsCategory = newsCategory
def __init__(self,
service,
resultsPerPage=8,
order=None,
tags=None,
filter=None,
genres=None,
types=None,
bpmFilter=None,
durationFilter=None,
createdFilter=None,
**args):
SearchEngine.__init__(self, service, **args)
self.resultsPerPage = resultsPerPage
self.order = order
self.tags = tags
self.filter = filter
self.genres = genres
self.types = types
self.bpmFilter = bpmFilter
self.durationFilter = durationFilter
self.createdFilter = createdFilter
def read(self, request):
print "REST service: read"
q = request.GET.get('query')
profile = request.GET.get('profile')
if (q == None):
#none to search
print "Blank search"
xmldata = '<searchresponse><error>Blank search</error></searchresponse>'
responseXML = HttpResponse(xmldata,
mimetype='text/xml',
content_type='text/xml;charset=UTF-8')
return responseXML
if (profile != None):
print "Profile", profile
# at this moment, we only admit a default profile
print q
q = q.strip(' ')
q = q.strip('%20')
#q = django.utils.http.urlquote(q)
print q
# I see 2 alternatives for the future, with profiles
# 1st to move this to several independent python files, for loading it
# dinamicaly (like filters)
# 2nd XML files describing the filters and parameters. It is slower, but
# new filters can be added by a REST interface
service = Service()
# set up services
service.add_query_filter(TermExpansionFilter("--terms=for+kids"))
service.add_query_filter(TermExpansionFilter("--terms=colouring+book"))
service.add_search_suggestion(SuggestionFilter())
#service.add_search_engine(SearchEngine('Pathfinder'))
service.add_search_engine(SearchEngine('Yahoo'))
query = Query(q)
response = service.search(query)
xmldata = responseToXML(response)
responseXML = HttpResponse(xmldata,
mimetype='text/xml',
content_type='text/xml;charset=UTF-8')
return responseXML
def __init__(self, service, source = 'Definitions', resultsPerPage = 8, sourceDictionaries = None, **args):
SearchEngine.__init__(self, service, **args)
self.source = source
self.resultsPerPage = resultsPerPage
self.sourceDictionaries = sourceDictionaries
#!/usr/bin/python
# -*- coding: utf-8 -*-
from puppy.service import Service
from puppy.search import SearchEngine
from puppy.query.filter import TermExpansionFilter
from puppy.query.filter import BlackListFilter
from puppy.query.filter import TestEqualFilter
from puppy.model import Query
service = Service()
black_list_query = "--terms=+book"
service.add_query_filter(TermExpansionFilter("--terms=for+kids"))
service.add_query_filter(TestEqualFilter("--terms=for+kids+elmo"))
service.add_query_filter(TermExpansionFilter("--terms=colouring+book"))
service.add_query_filter(
TestEqualFilter("--terms=for+kids+elmo+colouring+book"))
service.add_query_filter(BlackListFilter("--terms=+book"))
# This line fails, book is not longer in the query list
#service.add_query_filter(TestEqualFilter("--terms=for+kids+elmo+colouring+book"))
service.add_search_engine(SearchEngine('Yahoo'))
query = Query('elmo')
service.search(query)
def __init__(self, service, source='web', resultsPerPage=10, **args):
SearchEngine.__init__(self, service, **args)
self.source = source
self.resultsPerPage = resultsPerPage
#!/usr/bin/python
# -*- coding: utf-8 -*-
from puppy.service import Service
from puppy.search import SearchEngine
from puppy.query.filter import TermExpansionFilter
from puppy.result.filter import BlackListResultFilter
from puppy.result.filter import ExclusionFilter
from puppy.model import Query
service = Service()
black_list_result = "--terms=verybadword"
exclusion_list_result = "--terms=badword"
service.add_search_engine(SearchEngine('EchoSearch'))
service.add_result_filter(ExclusionFilter(exclusion_list_result))
service.add_result_filter(BlackListResultFilter(black_list_result))
query = Query('elmo badword verybadword')
service.search(query)
def __init__(self, service, source = 'web', resultsPerPage = 10, **args):
SearchEngine.__init__(self, service, **args)
self.source = source
self.resultsPerPage = resultsPerPage
def __init__(self,
service,
source='Web',
adult='Strict',
market='en-US',
resultsPerPage=8,
filters=None,
sortBy=None,
newsCategory=None,
sites=None,
**args):
"""
Arguments for all source types:
(1) source(str) - Should be 'Web', 'Image', 'News', 'RelatedSearch', 'SpellingSuggestions'
(2) adult(str) - Strict is the default, not recommended to change this, can also be 'Moderate' or 'Off'
(3) market(str) - For UK: en-GB, For Netherlands: nl-NL etc
(4) resultsPerPage(int) - How many results per page
Arguments for Image and Video searches only:
(1) filters(str) - Filter options split up by '+' you can only have one of each type see
Bing API documentation for examples of the valid filters.
Example: "Style:Photo+Aspect:Tall'" gets tall photos.
Arguments for Video and News searches only:
(1) sortBy(str) - You can select to sort by either 'Date' or 'Relevance'
Arguments for News searches only:
(1) newsCategory(str) - What sort of news is wanted, see BingAPI for list of options, for example:
'rt_ScienceAndTechnology' to find news under this category. Only available
with the en-US market, 'cause the rest of the world do not like categories.
"""
SearchEngine.__init__(
self, service,
**args) # This will also handle any unsupported parameters
# The search sources have different limits
sources_to_limits = {
"Image": 50,
"Web": 50,
"News": 15,
"RelatedSearch": 50,
"Video": 50,
"SpellingSuggestions": 50
}
self.engineName = "Bing V3_json" # Used for error identification
# If there is not entry in the sources dictionary with their limits raise an Error
if source in sources_to_limits:
self.source = source
else:
raise SearchEngineError(
self.engineName,
"Invalid source type: %s is not supported" % source)
# For some reason Spelling Suggestions (named wrongly in their documentation) is only available as Atom
if self.source != "SpellingSuggestions":
self.format = "json"
else:
self.format = "atom"
# Quick bit of validation, if greater than the sources limit or 0 or less use a default
if resultsPerPage > sources_to_limits[source] or resultsPerPage <= 0:
self.resultsPerPage = 8
else:
self.resultsPerPage = resultsPerPage
self.adult = adult
self.market = market
self.filters = filters
self.sortBy = sortBy
self.newsCategory = newsCategory
self.sites = sites
