baidu 1.2.10 → 2.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 973532d0e6e0bc141eb17dcd034daccbefe2210a
-  data.tar.gz: abdd019318edf7956ca07a7dd1bca44c02faaa1b
+  metadata.gz: f3ab3b16d4f810561f78ee164b2882eaf8f2bae8
+  data.tar.gz: 706fc2deeb2af8c5606eb685f1c85aef45f85127
 SHA512:
-  metadata.gz: b74a336d56fd97b365db05d095991d49fa7cbf8098c180635afe2b8e16683db51ffa876a1fd855491b7f331574f25a91c3fe80dbdd6f2685517d1b45b9807034
-  data.tar.gz: a430a916135a289b1577f3468d43188b3b8c6dc84db7460cd00d3af6f993f913f358d7e8e5d1a87d5a7557db30a1ec85cedec9eb949d3698d17fcd068438c791
+  metadata.gz: be21dae1919c0f313870b2b0a508304becc13117072bc0c93d7992f9cb992aaba344b30c9af36eee6fea2ec75d96c79a8a94af72430c36468998363987408811
+  data.tar.gz: a3f515b1a9ed7be68eb66437c1038e78ee068304fe1c13f0492c66f23a5bd3bef159f10eb1d2e3c867d946fe921e59375cd4589b6d56ce38d29cf3757e0635c7

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'http://ruby.taobao.org'
+
+# Specify your gem's dependencies in baidu.gemspec
+gemspec

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 +1,82 @@
+# Baidu
+
+Baidu SEM Services
+Baidu Ranking Services
+Baidu Map Services
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'baidu'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install baidu
+
+## Knowledge
+camel命名法，用于request数据格式
+snake命名法，用于response数据格式
+
+## Rspec
+先修改spec/spec_helper.rb
+
+```ruby
+BAIDU_MAP_KEY = ''
+$username = ''
+$password = ''
+$token = ''
+
+```
+
+## Usage
+
+SEM
+
+```ruby
+require 'baidu'
+
+$auth = Baidu::Auth.new
+$auth.username = 'username'
+$auth.password = 'password'
+$auth.token = 'token'
+
+ss = Baidu::SEM::SearchService.new
+res = ss.getKeywordBySearch({:searchWord=>'word',:searchType=>0})
+res = ss.getKeywordBySearch({:searchWord=>'word',:searchType=>0},true) #debug=true
+```
+
+MAP
+
+```ruby
+#返回码 定义 英文返回描述
+#0 正常 ok
+#2 请求参数非法 Parameter Invalid
+#3 权限校验失败 Verify Failure
+#4 配额校验失败 Quota Failure
+#5 ak不存在或者非法 AK Failure
+#2xx 无权限
+#3xx 配额错误
+puts map.get_xy_by_poiname('滨海公园','上海')
+map = Baidumap.new('key')
+require 'awesome_print'
+lat = 40.3377039331399
+lng = 116.647588831718
+ap map.bus.around(lat,lng).info
+puts map.get(39.911031821584,116.44931548023).for(1000).bus
+puts map.geo('22.53','113.38')
+Baidumap.get_baike('北京站')
+Baidumap.get_cityid('北京') #=>131
+```
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

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

data/baidu.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'baidu/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "baidu"
+  spec.version       = Baidu::VERSION
+  spec.authors       = ["seoaqua"]
+  spec.email         = ["seoaqua@me.com"]
+  spec.description   = %q{Baidu Services Pack,including SEM, Map, Ranking and the others}
+  spec.summary       = %q{a gem summary}
+  spec.homepage      = "http://github.com/seoaqua/baidu"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  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 "httparty"
+  spec.add_dependency "awesome_print"
+  spec.add_dependency "savon","~> 3.0"
+end

data/lib/baidu.rb

@@ -1,483 +1,61 @@
-# encoding: utf-8
-require 'nokogiri'
-require 'json'
-require 'addressable/uri'
-require 'httparty'
-class SearchEngine
-   #是否收录
-    def initialize(pagesize = 100)
-        @pagesize = pagesize#只允许10或100
-    end
-    def indexed?(url)
-        URI(url)
-        result = query(url)
-        return result.has_result?
-    end
-end
-class SearchResult
-    def initialize(page,baseuri,pagenumber=1,pagesize=100)
-        @page = Nokogiri::HTML page
-        @baseuri = baseuri
-        # @host = URI(baseuri).host
-        @pagenumber = pagenumber
-        @pagesize = pagesize
-    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
+module Baidu
+  module Rank
+  end
+  module SEM
+  end
 end
 
-class Qihoo < SearchEngine
-    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
-        QihooResult.new(page,uri)
-    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.split("(")[1].gsub(/\s\);/) {""}
-        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
+class String
+  def snake_case
+    self.gsub(/::/, '/').
+    gsub(/([A-Z]+)([A-Z][a-z])/,'\1_\2').
+    gsub(/([a-z\d])([A-Z])/,'\1_\2').
+    tr("-", "_").
+    downcase
+  end
 end
-
-class QihooResult < SearchResult
-    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
+class Savon
+  class Response
+    def header
+      hash[:envelope][:header]
     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
+    def res_header
+      header[:res_header]
     end
-    def ads_bottom
-        []
+    def desc
+      res_header[:desc]
     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
+    def quota
+      res_header[:quota]
     end
-    def related_keywords
-        []
+    def rquota
+      res_header[:rquota]
     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
-        return QihooResult.new(next_page,next_href,@pagenumber+1)
-        #@page = MbaiduResult.new(Mechanize.new.click(@page.link_with(:text=>/下一页/))) unless @page.link_with(:text=>/下一页/).nil?
+    def oprs
+      res_header[:oprs]
     end
-    #有结果
-    def has_result?
-        !@page.search('//div[@id="main"]/h3').text().include?'没有找到该URL'
+    def oprtime
+      res_header[:oprtime]
     end
-end
-
-class Mbaidu < SearchEngine
-    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)
-            MbaiduResult.new(res,uri)
-        rescue Exception => e
-            warn "#{uri} fetch error: #{e.to_s}"
-            return false
-        end
+    def failures
+      res_header[:failures]
     end
-end
-class MbaiduResult < SearchResult
-    # def initialize(page,baseuri,pagenumber=nil)
-    #     @page= Nokogiri::HTML page
-    #     @baseuri = baseuri
-    #     if pagenumber.nil?
-    #         @pagenumber = 1
-    #     else
-    #         @pagenumber = pagenumber
-    #     end
-    # end
-
-    #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
+    def code
+      failures[:code] if failures
     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
+    def message
+      failures[:message] if failures
     end
-=end
-    #下一页
-    def next
-        nextbutton = @page.xpath('//a[text()="下一页"]').first
-        return nil if nextbutton.nil?
-        url = nextbutton['href']
-        url = URI.join(@baseuri,url).to_s
-        page = HTTParty.get(url)
-        return MbaiduResult.new(page,url,@pagenumber+1)
+    def status
+      res_header[:status]
     end
+  end
 end
-class Baidu < SearchEngine
-    BaseUri = 'http://www.baidu.com/s?'
-    def suggestions(wd)
-        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 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}"
-        queryStr = q.join("&")
-        #uri = URI.encode((BaseUri + queryStr).encode('GBK'))
-        uri = URI.encode((BaseUri + queryStr))
-        begin
-            # @page = @a.get uri
-            @page = HTTParty.get uri
-            BaiduResult.new(@page,uri,1,@pagesize)
-        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 how_many_pages(host)
-        query("site:#{host}").how_many
-    end
-
-    #domain:xxx.yyy.com/path/file.html
-    def how_many_links(uri)
-        query("domain:\"#{uri}\"").how_many
-    end
-
-    #site:xxx.yyy.com inurl:zzz
-    def how_many_pages_with(host,string)
-        query("site:#{host} inurl:#{string}").how_many
-    end
-end
-
-class BaiduResult < SearchResult
-    # def initialize(page,baseuri,pagenumber=1,pagesize=100)
-    #     @page = Nokogiri::HTML page
-    #     @baseuri = baseuri
-    #     @pagenumber = pagenumber
-    #     @pagesize = pagesize
-    #     # raise ArgumentError 'should be Mechanize::Page' unless page.class == Mechanize::Page
-    #     # @page = page
-    # end
-    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 @pagesize == 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 how_many
-        @how_many ||= @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)
-        return BaiduResult.new(page,url,@pagenumber+1,@pagesize)
-        # @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
+require "baidu/version"
+require "baidu/map"
+require "baidu/sem"
+require "baidu/rank"
+require "baidu/auth"
+require "baidu/response"
+require "ext"
+require "awesome_print"