query 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: e414f7561d351c15835fb94956919de3d9d6ac62
+  data.tar.gz: 1e75cc2eb2d552b779d7cc33865248cb73d00d64
+SHA512:
+  metadata.gz: e07b5ab0f23e5775945fa66cd55ae0e822888da4d5aa65968ee5a0cf91d219a3126b2af7836e23cde660b43fccca4570cc33be142d08b83092388de975a84339
+  data.tar.gz: baa4d81223b5911ca159735bdff34ba6b4646ebeefe83112463c733373697ee0823b3de5e57513e97105c55f663bce58d87e8530f48c5d2a8718e50f80785974

data/.gitignore

@@ -0,0 +1,23 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+coverage
+InstalledFiles
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+# YARD artifacts
+.yardoc
+_yardoc
+doc/

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in query.gemspec
+gemspec

data/LICENSE

@@ -0,0 +1,20 @@
+The MIT License (MIT)
+
+Copyright (c) 2013 seoaqua
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 刘明
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,24 @@
+Query
+==========
+
+
+#to get the result list by querying "abc"
+Query::Engine::Baidu.new.query("abc").ranks().each do |id,value|
+    puts id,value
+end
+
+#to get the result list with host "www.abc.com.cn" by querying "abc"
+Query::Engine::Baidu.new.query("abc").ranks("www.abc.com.cn").each do |id,value|
+    puts id,value
+end
+
+#to get the result list with host which fit the regex /com.cn/ by querying "abc"
+Query::Engine::Baidu.new.query("abc").ranks(/com.cn/).each do |id,value|
+    puts id,value
+end
+
+# to get the top rank of host "www.abc.com.cn" by querying "abc"
+Query::Engine::Baidu.new.query("abc").rank("www.abc.com.cn")
+
+TODO:
+查询结果不多,翻页不存在时的处理,及rspec

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/lib/query/engine/baidu.rb

@@ -0,0 +1,87 @@
+module Query
+    module Engine
+        class Baidu < Base
+            BaseUri = 'http://www.baidu.com/s?'
+            def self.suggestions(wd)
+                require 'json'
+                json = HTTParty.get("http://suggestion.baidu.com/su?wd=#{URI.encode(wd)}&cb=callback").force_encoding('GBK').encode("UTF-8")
+                m = /\[([^\]]*)\]/.match json
+                return JSON.parse m[0]
+            end
+            #to find out the real url for something lik 'www.baidu.com/link?url=7yoYGJqjJ4zBBpC8yDF8xDhctimd_UkfF8AVaJRPKduy2ypxVG18aRB5L6D558y3MjT_Ko0nqFgkMoS'
+            # def url(id)
+            #   a = Mechanize.new
+            #   a.redirect_ok=false
+            #   return a.head("http://www.baidu.com/link?url=#{id}").header['location']
+            # end
+
+=begin
+            def extend(words,level=3,sleeptime=1)
+                level = level.to_i - 1
+                words = [words] unless words.respond_to? 'each'
+
+                extensions = Array.new
+                words.each do |word|
+                    self.query(word)
+                    extensions += related_keywords
+                    extensions += suggestions(word)
+                    sleep sleeptime
+                end
+                extensions.uniq!
+                return extensions if level < 1
+                return extensions + extend(extensions,level)
+            end
+=end
+
+            def self.popular?(wd)
+                return HTTParty.get("http://index.baidu.com/main/word.php?word=#{URI.encode(wd.encode("GBK"))}").include?"boxFlash"
+            end
+
+            def query(wd)
+                q = Array.new
+                q << "wd=#{wd}"
+                q << "rn=#{@perpage.to_i}" if @perpage
+                queryStr = q.join("&")
+                #uri = URI.encode((BaseUri + queryStr).encode('GBK'))
+                uri = URI.encode((BaseUri + queryStr))
+                begin
+                    # @page = @a.get uri
+                    @page = HTTParty.get uri
+                    r = Query::Result::Baidu.new(@page)
+                    r.baseuri = uri
+                    r.pagenumber = 1
+                    r.perpage = @perpage
+                    r
+                rescue Exception => e
+                    warn e.to_s
+                    return false
+                end
+=begin
+                query = "#{query}"
+                @uri = BaseUri+URI.encode(query.encode('GBK'))
+                @page = @a.get @uri
+                self.clean
+                @number = self.how_many
+                @maxpage = (@number / @perpage.to_f).round
+                @maxpage =10 if @maxpage>10
+                @currpage =0
+=end
+            end
+
+            #site:xxx.yyy.com
+            def pages(host)
+                query("site:#{host}")
+            end
+
+            #domain:xxx.yyy.com/path/file.html
+            def links(uri)
+                query("domain:\"#{uri}\"")
+            end
+
+            #site:xxx.yyy.com inurl:zzz
+            def pages_with(host,string)
+                query("site:#{host} inurl:#{string}")
+            end
+        end
+    end
+end

data/lib/query/engine/baidu_mobile.rb

@@ -0,0 +1,26 @@
+module Query
+    module Engine
+        class BaiduMobile < Base
+            BaseUri = 'http://m.baidu.com/s?'
+            headers = {
+                "User-Agent" => 'Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_2 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8H7 Safari/6533.18.5'
+            }
+            Options = {:headers => headers}
+
+            #基本查询,相当于从搜索框直接输入关键词查询
+            def query(wd)
+                queryStr = "word=#{wd}"
+                uri = URI.encode((BaseUri + queryStr))
+                # begin
+                    res = HTTParty.get(uri,Options)
+                    r = Query::Result::BaiduMobile.new(res)
+                    r.baseuri = uri
+                    r
+                # rescue Exception => e
+                    # warn "#{__FILE__} #{__LINE__} #{uri} fetch error: #{e.to_s}"
+                    # return false
+                # end
+            end
+        end
+    end
+end

data/lib/query/engine/base.rb

@@ -0,0 +1,16 @@
+module Query
+    module Engine
+        class Base
+            attr_accessor :perpage
+           #是否收录
+            # def initialize(perpage = 100)
+            #     @perpage = perpage#只允许10或100
+            # end
+            def indexed?(url)
+                URI(url)
+                result = query(url)
+                return result.has_result?
+            end
+        end
+    end
+end

data/lib/query/engine/qihoo.rb

@@ -0,0 +1,32 @@
+module Query
+    module Engine
+        class Qihoo < Base
+            Host = 'www.so.com'
+            #基本查询, 相当于在搜索框直接数据关键词查询
+            def query(wd)
+                #用原始路径请求
+                uri = URI.join("http://#{Host}/",URI.encode('s?q='+wd)).to_s
+                page = HTTParty.get(uri)
+                #如果请求地址被跳转,重新获取当前页的URI,可避免翻页错误
+                uri = URI.join("http://#{Host}/",page.request.path).to_s
+                r = Query::Result::Qihoo.new(page)
+                r.baseuri = uri
+                r
+            end
+            def self.related_keywords(wd)
+                url = "http://rs.so.com/?callback=Search.relate.render&encodein=utf-8&encodeout=utf-8&q="+URI.encode(wd)
+                # uri = URI.join("http://#{Host}/",URI.encode('s?q='+wd)).to_s
+                page = HTTParty.get(url)
+                json_str = page.body
+                json_str = json_str.split("(")[1]
+                return nil if json_str.nil?
+                json_str = json_str.delete(');').strip
+                parsed_json = JSON.parse(json_str)
+                # each
+                # parsed_json.map { |q| p q['q']}
+                @related_keywords = parsed_json.map { |q| q['q'] }
+                # @related_keywords ||= @page.search("//div[@id=\"rs\"]//tr//a").map{|keyword| keyword.text}
+            end
+        end
+    end
+end

data/lib/query/engine/qihoo_mobile.rb

@@ -0,0 +1,2 @@
+module Query
+end

data/lib/query/engine.rb

@@ -0,0 +1,10 @@
+module Query
+  module Engine
+  end
+end
+
+require 'query/engine/base'
+require 'query/engine/baidu'
+require 'query/engine/baidu_mobile'
+require 'query/engine/qihoo'
+require 'query/engine/qihoo_mobile'

data/lib/query/result/baidu.rb

@@ -0,0 +1,121 @@
+module Query
+    module Result
+        class Baidu < Base
+            def ranks
+                return @ranks unless @ranks.nil?
+                @ranks = Hash.new
+                @page.search("//table[@class=\"result\"]|//table[@class=\"result-op\"]").each do |table|
+                    id = table['id']
+                    # if @perpage == 10
+                    #     id = table['id'][-1,1]
+                    #     id = '10' if id == '0'
+                    # end
+
+                    @ranks[id] = Hash.new
+                    url = table.search("[@class=\"g\"]").first
+                    url = url.text unless url.nil?
+                    a = table.search("h3").first
+                    next if a.nil?
+                    @ranks[id]['text'] = a.text
+                    @ranks[id]['href'] = url #a.first['href'].sub('http://www.baidu.com/link?url=','').strip
+                    unless url.nil?
+                        url = url.strip
+                        @ranks[id]['host'] = Addressable::URI.parse(URI.encode("http://#{url}")).host
+                    else
+                        @ranks[id]['host'] = nil
+                    end
+                end
+                #@page.search("//table[@class=\"result\"]").map{|table|@page.search("//table[@id=\"#{table['id']}\"]//span[@class=\"g\"]").first}.map{|rank|URI(URI.encode('http://'+rank.text.strip)).host unless rank.nil?}
+                @ranks
+            end
+
+            def ads_bottom
+                return {} if @page.search("//table[@bgcolor='f5f5f5']").empty?
+                return ads_top
+                # p @page.search("//table[@bgcolor='f5f5f5']").empty?
+            end
+            def ads_top
+                #灰色底推广,上下都有
+                ads = Hash.new
+                @page.search("//table[@bgcolor='#f5f5f5']").each do |table|
+                    id = table['id']
+                    next if id.nil?
+                    id = id[2,3].to_i.to_s
+                    ads[id]= parse_ad(table)
+                end
+                #白色底推广,只有上部分
+                if ads.empty?
+                    @page.search("//table").each do |table|
+                        id = table['id']
+                        next if id.nil? or id.to_i<3000
+                        id = id[2,3].to_i.to_s
+                        ads[id]= parse_ad(table)
+                    end
+                end
+                ads
+            end
+            def parse_ad(table)
+                href = table.search("font[@color='#008000']").text.split(/\s/).first.strip
+                title = table.search("a").first.text.strip
+                {'title'=>title,'href' => href,'host'=>href}
+            end
+            def ads_right
+                ads = {}
+                @page.search("//div[@id='ec_im_container']").each do |table|
+                    table.search("div[@id]").each do |div|
+                        id = div['id'][-1,1].to_i+1
+                        title = div.search("a").first
+                        next if title.nil?
+                        title = title.text
+                        url = div.search("font[@color='#008000']").first
+                        next if url.nil?
+                        url = url.text
+                        ads[id.to_s] = {'title'=>title,'href'=>url,'host'=>url}
+                    end
+                end
+                ads
+            end
+
+            #return the top rank number from @ranks with the input host
+            # def rank(host)#on base of ranks
+            #     ranks.each do |id,line|
+            #         id = id.to_i
+            #         if host.class == Regexp
+            #             return id if line['host'] =~ host
+            #         elsif host.class == String
+            #             return id if line['host'] == host
+            #         end
+            #     end
+            #     return nil
+            # end
+
+            def count
+                @count ||= @page.search("//span[@class='nums']").map{|num|num.content.gsub(/\D/,'').to_i unless num.nil?}.first
+            end
+
+            def related_keywords
+                @related_keywords ||= @page.search("//div[@id=\"rs\"]//tr//a").map{|keyword| keyword.text}
+            end
+
+            def next
+                url = @page.xpath('//a[text()="下一页>"]').first
+                return if url.nil?
+                url = url['href']
+                url = URI.join(@baseuri,url).to_s
+                page = HTTParty.get(url)
+                r = Query::Result::Baidu.new(page)
+                r.baseuri = url
+                r.pagenumber=@pagenumber+1
+                r.perpage=@perpage
+                r
+
+                # @page = BaiduResult.new(Mechanize.new.click(@page.link_with(:text=>/下一页/))) unless @page.link_with(:text=>/下一页/).nil?
+            end
+            def has_result?
+                submit = @page.search('//a[text()="提交网址"]').first
+                return false if submit and submit['href'].include?'sitesubmit'
+                return true
+            end
+        end
+    end
+end

data/lib/query/result/baidu_mobile.rb

@@ -0,0 +1,114 @@
+module Query
+    module Result
+        class BaiduMobile < Base
+            #返回当前页所有查询结果
+            def ranks
+                #如果已经赋值说明解析过,不需要重新解析,直接返回结果
+                return @ranks unless @ranks.nil?
+                @ranks = Hash.new
+                @page.xpath('//div[@class="result"]').each do |result|
+                    href,text,host,is_mobile = '','','',false
+                    a = result.search("a").first
+                    is_mobile = true unless a.search("img").empty?
+                    host = result.search('[@class="site"]').first
+                    next if host.nil?
+                    host = host.text
+                    href = a['href']
+                    text = a.text
+                    id = href.scan(/&order=(\d+)&/)
+                    if id.empty?
+                        id = nil
+                    else
+                        id = id.first.first.to_i
+                        # id = (@pagenumber-1)*10+id
+                    end
+=begin
+                    result.children.each do |elem|
+                        if elem.name == 'a'
+                            href = elem['href']
+                            id = elem.text.match(/^\d+/).to_s.to_i
+                            text = elem.text.sub(/^\d+/,'')
+                            text.sub!(/^\u00A0/,'')
+                        elsif elem['class'] == 'abs'
+                            elem.children.each do |elem2|
+                                if elem2['class'] == 'site'
+                                    host = elem2.text
+                                    break
+                                end
+                            end
+                        elsif elem['class'] == 'site'
+                            host == elem['href']
+                        end
+                    end
+=end
+
+                    @ranks[id.to_s] = {'href'=>href,'text'=>text,'is_mobile'=>is_mobile,'host'=>host.sub(/\u00A0/,'')}
+                end
+                @ranks
+            end
+            def ads_top
+                id = 0
+                result = []
+                @page.search("div[@class='ec_wise_ad']/div").each do |div|
+                    id += 1
+                    href = div.search("span[@class='ec_site']").first.text
+                    href = "http://#{href}"
+                    title = div.search("a/text()").text.strip
+                    host = Addressable::URI.parse(URI.encode(href)).host
+                    result[id] = {'title'=>title,'href'=>href,'host'=>host}
+                end
+                result
+            end
+            def ads_right
+                []
+            end
+            def ads_bottom
+                []
+            end
+            def related_keywords
+                @related_keywords ||= @page.search("div[@class='relativewords_info']/a").map{|a|a.text}
+            end
+=begin
+            #返回当前页中,符合host条件的结果
+            def ranks_for(specific_host)
+                host_ranks = Hash.new
+                ranks.each do |id,line|
+                    if specific_host.class == Regexp
+                        host_ranks[id] = line if line['host'] =~ specific_host
+                    elsif specific_host.class == String
+                        host_ranks[id] = line if line['host'] == specific_host
+                    end
+                end
+                host_ranks
+            end
+            #return the top rank number from @ranks with the input host
+            def rank(host)#on base of ranks
+                ranks.each do |id,line|
+                    id = id.to_i
+                    if host.class == Regexp
+                        return id if line['host'] =~ host
+                    elsif host.class == String
+                        return id if line['host'] == host
+                    end
+                end
+                return nil
+            end
+=end
+            #下一页
+            def next
+                nextbutton = @page.xpath('//a[text()="下一页"]').first
+                return nil if nextbutton.nil?
+                url = URI.encode nextbutton['href']
+                # puts url
+                # p @baseuri
+                # exit
+                url = URI.join(@baseuri,url).to_s
+                page = HTTParty.get(url)
+                r = Query::Result::BaiduMobile.new(page)
+                r.baseuri=url
+                r.pagenumber=@pagenumber+1
+                r
+            end
+        end
+    end
+end

data/lib/query/result/base.rb

@@ -0,0 +1,50 @@
+module Query
+    module Result
+        class Base
+            attr_accessor :baseuri,:pagenumber,:perpage
+            def initialize(page)
+                @page = Nokogiri::HTML page
+                @pagenumber = 1
+            end
+            # def initialize(page,baseuri,pagenumber=1,perpage=100)
+            #     @page = Nokogiri::HTML page
+            #     @baseuri = baseuri
+            #     # @host = URI(baseuri).host
+            #     @pagenumber = pagenumber
+            #     @perpage = perpage
+            # end
+            def whole
+                {
+                    'ads_top'=>ads_top,
+                    'ads_right'=>ads_right,
+                    'ads_bottom'=>ads_bottom,
+                    'ranks'=>ranks
+                }
+            end
+            #返回当前页中host满足条件的结果
+            def ranks_for(specific_host)
+                host_ranks = Hash.new
+                ranks.each do |id,line|
+                    if specific_host.class == Regexp
+                        host_ranks[id] = line if line['host'] =~ specific_host
+                    elsif specific_host.class == String
+                        host_ranks[id] = line if line['host'] == specific_host
+                    end
+                end
+                host_ranks
+            end
+            #return the top rank number from @ranks with the input host
+            def rank(host)#on base of ranks
+                ranks.each do |id,line|
+                    id = id.to_i
+                    if host.class == Regexp
+                        return id if line['host'] =~ host
+                    elsif host.class == String
+                        return id if line['host'] == host
+                    end
+                end
+                return nil
+            end
+        end
+    end
+end

data/lib/query/result/qihoo.rb

@@ -0,0 +1,75 @@
+module Query
+    module Result
+        class Qihoo < Base
+            # include Query::Result
+            Host = 'www.so.com'
+            #返回所有当前页的排名结果
+            def ranks
+                return @ranks unless @ranks.nil?
+                @ranks = Hash.new
+                # id = (@pagenumber - 1) * 10
+                id = 0
+                @page.search('//li[@class="res-list"]').each do |li|
+                    a = li.search("h3/a").first
+                    url = li.search("cite")
+                    next if a['data-pos'].nil?
+                    id += 1
+                    text = a.text.strip
+                    href = a['href']
+                    url = url.first.text
+                    host = Addressable::URI.parse(URI.encode("http://#{url}")).host
+                    @ranks[id.to_s] = {'href'=>a['href'],'text'=>text,'host'=>host}
+                end
+                @ranks
+            end
+            def ads_top
+                id = 0
+                result = []
+                @page.search("//ul[@id='djbox']/li").each do |li|
+                    id += 1
+                    title = li.search("a").first.text
+                    href = li.search("cite").first.text.downcase
+                    host = Addressable::URI.parse(URI.encode(href)).host
+                    result[id] = {'title'=>title,'href'=>href,'host'=>host}
+                end
+                result
+            end
+            def ads_bottom
+                []
+            end
+            def ads_right
+                id = 0
+                result = []
+                @page.search("//ul[@id='rightbox']/li").each do |li|
+                    id += 1
+                    title = li.search("a").first.text
+                    href = li.search("cite").first.text.downcase
+                    host = Addressable::URI.parse(URI.encode(href)).host
+                    result[id] = {'title'=>title,'href'=>href,'host'=>host}
+                end
+                result
+            end
+            def related_keywords
+                []
+            end
+            #下一页
+            def next
+                next_href = @page.xpath('//a[@id="snext"]')
+                return false if next_href.empty?
+                next_href = next_href.first['href']
+                next_href = URI.join(@baseuri,next_href).to_s
+                # next_href = URI.join("http://#{@host}",next_href).to_s
+                next_page = HTTParty.get(next_href).next
+                r =Query::Result::Qihoo.new(next_page)
+                r.baseuri=next_href
+                r.pagenumber=@pagenumber+1
+                r
+                #@page = MbaiduResult.new(Mechanize.new.click(@page.link_with(:text=>/下一页/))) unless @page.link_with(:text=>/下一页/).nil?
+            end
+            #有结果
+            def has_result?
+                !@page.search('//div[@id="main"]/h3').text().include?'没有找到该URL'
+            end
+        end
+    end
+end

data/lib/query/result/qihoo_mobile.rb

@@ -0,0 +1,6 @@
+module Query
+    module Result
+        class QihooMobile
+        end
+    end
+end

data/lib/query/result.rb

@@ -0,0 +1,10 @@
+module Query
+    module Result
+    end
+end
+require 'nokogiri'
+require 'query/result/base'
+require 'query/result/baidu'
+require 'query/result/baidu_mobile'
+require 'query/result/qihoo'
+require 'query/result/qihoo_mobile'

data/lib/query/version.rb

@@ -0,0 +1,3 @@
+module Query
+  VERSION = "0.0.1"
+end

data/lib/query.rb

@@ -0,0 +1,9 @@
+require "query/version"
+require "query/engine"
+require "query/result"
+require "httparty"
+require 'addressable/uri'
+require 'awesome_print'
+module Query
+  # Your code goes here...
+end

data/query.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'query/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "query"
+  spec.version       = Query::VERSION
+  spec.authors       = ["seoaqua"]
+  spec.email         = ["seoaqua@me.com"]
+  spec.description   = %q{This GEM is designed to work for SEOers who need to fetch query and parse results from all kinds of search engines}
+  spec.summary       = %q{Now its only support Chinese main search engines}
+  spec.homepage      = "https://github.com/seoaqua/query"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_dependency "nokogiri"
+  spec.add_dependency "addressable"
+  spec.add_dependency "httparty"
+
+end

data/spec/baidu_mobile_spec.rb

@@ -0,0 +1,19 @@
+#coding:UTF-8
+require 'spec_helper'
+describe Query::Engine::BaiduMobile do
+    mbaidu = Query::Engine::BaiduMobile.new
+    page = mbaidu.query '百度'
+    it "应返回#{Query::Engine::BaiduMobile}" do
+        page.class.should == Query::Result::BaiduMobile
+    end
+    it "下一页也应是Query::Engine::BaiduMobile" do
+        page.next.class.should == Query::Result::BaiduMobile
+        page.next.next.class.should == Query::Result::BaiduMobile
+    end
+    it "百度百科域名应该大于1" do
+        page.rank('wapbaike.baidu.com').should > 1
+    end
+    it "百度无线域名应该在10以内" do
+        page.rank('m.baidu.com').should < 11
+    end
+end

data/spec/baidu_spec.rb

@@ -0,0 +1,73 @@
+#coding:UTF-8
+require 'spec_helper'
+describe Query::Engine::Baidu do
+    baidu = Query::Engine::Baidu.new
+    page = baidu.query '百度'
+
+    it "should return Query::Result::Baidu" do
+        page.class.should == Query::Result::Baidu
+    end
+
+    it "should return 100,000,000" do
+        page.count.should > 100000
+    end
+    it "should return 1" do
+        page.rank('www.baidu.com').should == 1
+    end
+
+    it "should return Query::Result::Baidu" do
+        page.next.class.should == Query::Result::Baidu
+    end
+
+    it "should return true" do
+        bool = Query::Engine::Baidu.popular?'百度'
+        bool.should == true
+    end
+
+    it "should return false" do
+        bool = Query::Engine::Baidu.popular?'lavataliuming'
+        bool.should == false
+    end
+
+    it "should return over 5 words beginning with the query_word" do
+        query_word = '为'
+        suggestions = Query::Engine::Baidu.suggestions(query_word)
+        suggestions.size.should > 5
+        suggestions.each do |suggestion|
+            suggestion[0].should == query_word
+        end
+    end
+
+    it "should return 100,000,000" do
+        result = baidu.pages('baidu.com')
+        result.class.should == Query::Result::Baidu
+        result.count.should == 100000000
+    end
+
+    it "should return 100,000,000" do
+        result = baidu.links('baidu.com')
+        result.class.should == Query::Result::Baidu
+        result.count.should == 100000000
+    end
+    it "should return 100,000,000" do
+        result = baidu.pages_with('baidu.com','baidu.com')
+        result.class.should == Query::Result::Baidu
+        result.count.should == 100000000
+    end
+    it "查询已经被收录的页面收录情况时,应返回true" do
+        baidu.indexed?('http://www.baidu.com').should == true
+    end
+    it "查询一个不存在的页面收录情况时,应返回true" do
+        baidu.indexed?('http://zxv.not-exists.com').should == false
+    end
+    page1 = baidu.query('seoaqua.com')
+    it "查询结果应该都能拿到title,href,host" do
+        page1.ranks.each do |id,rank|
+            rank['href'].should_not == nil
+            rank['text'].should_not == nil
+            rank['host'].should_not == nil
+        end
+    end
+    # ads_page = baidu.query '减肥药'
+
+end

data/spec/qihoo_spec.rb

@@ -0,0 +1,27 @@
+#coding:UTF-8
+require 'spec_helper'
+describe Query::Engine::Qihoo do
+    qihoo = Query::Engine::Qihoo.new
+    page = qihoo.query '奇虎'
+    page2 = page.next
+    page3 = page2.next
+    it "查询关键词'奇虎'后,应返回正确的实例" do
+        page.class.should == Query::Result::Qihoo
+    end
+    it "查询关键词'奇虎'后,下一页也应是MbaiduResult的实例" do
+        page2.class.should == Query::Result::Qihoo
+    end
+    it "查询关键词'奇虎'后,下一页,再下一页也应是MbaiduResult的实例" do
+        page3.class.should == Query::Result::Qihoo
+    end
+
+    it "查询关键词'奇虎'后,奇虎首页域名应该等于1" do
+        page.rank('www.qihoo.com').should == 1
+    end
+    it "查询已经被收录的页面收录情况时,应返回true" do
+        qihoo.indexed?('http://www.360.cn').should == true
+    end
+    it "查询一个不存在的页面收录情况时,应返回true" do
+        qihoo.indexed?('http://zxv.not-exists.com').should == false
+    end
+end

data/spec/spec_helper.rb

@@ -0,0 +1 @@
+require 'query'

metadata

@@ -0,0 +1,144 @@
+--- !ruby/object:Gem::Specification
+name: query
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- seoaqua
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-10-03 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: httparty
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: This GEM is designed to work for SEOers who need to fetch query and parse
+  results from all kinds of search engines
+email:
+- seoaqua@me.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/query.rb
+- lib/query/engine.rb
+- lib/query/engine/baidu.rb
+- lib/query/engine/baidu_mobile.rb
+- lib/query/engine/base.rb
+- lib/query/engine/qihoo.rb
+- lib/query/engine/qihoo_mobile.rb
+- lib/query/result.rb
+- lib/query/result/baidu.rb
+- lib/query/result/baidu_mobile.rb
+- lib/query/result/base.rb
+- lib/query/result/qihoo.rb
+- lib/query/result/qihoo_mobile.rb
+- lib/query/version.rb
+- query.gemspec
+- spec/baidu_mobile_spec.rb
+- spec/baidu_spec.rb
+- spec/qihoo_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/seoaqua/query
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.1.5
+signing_key: 
+specification_version: 4
+summary: Now its only support Chinese main search engines
+test_files:
+- spec/baidu_mobile_spec.rb
+- spec/baidu_spec.rb
+- spec/qihoo_spec.rb
+- spec/spec_helper.rb