grab_epg 0.0.3 → 0.0.4

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    YTNkOGZkMTk5NjFhODc3MmViMTQxODY2MzNjZTA2NzJmNTZjZDAyMA==
+    YmFmODhhZjdhMzkwMjFkMWMxZThiYzViYzA1NjFmMDQwY2YyMjQ3NQ==
   data.tar.gz: !binary |-
-    YTdiYmZmY2JhZDRjNDE4ZWQzZWY1ZWNlM2U2ZjI4MGQ3NGVhOWVhZQ==
+    ZjY0ODlhNjUwYWI4ODJlN2EyMmMzMWU1ZGI5MDNlZWRmMTcyZWE1Mg==
 !binary "U0hBNTEy":
   metadata.gz: !binary |-
-    MmFmZmI2ODQyOTFkZDZiNzA5OTIxZGMzZTNhNzQxODA4MWUzOGRjNDI4OWU4
-    ZGQwYWZmNzBkYTQxYWEyY2Y1NzcxNDNhMzg1MTUwZGE5NWM5OWYxMWI5MmZi
-    NmIwZDE1OTMyYzk2MTgxMGI0OTgyYzAyNDYwZjI3M2M1ZjYwOTg=
+    ZDVlODljMzUxOWYxOTIxNjAxZmViYjZhODAwZjBmOTE5NTVhYmIzNDQwNTgw
+    NzU4ODcwOTExNTFlNGYxMDcwZGJkYzMyZmM0ZTBkNzc2MmY0ODY2MTY1MjM3
+    ODJjZTdlYjcxNWY0Zjk3MmVmYzUxOGUxMTFlOGU4Yzk2Yzk5OTk=
   data.tar.gz: !binary |-
-    ZTFiNjExY2RlYTI3YWU4ZmYzODA2ZjUyMzQwN2MxZjhkN2NkYTdjMmFjYjJi
-    NjU4YzE5MWZjYTMwZDQ1Y2QxMmM3M2YwZjE0MjBmOTQ0YWIzYjgzNjIwODQ3
-    NzlmY2MxMTJkYjkyYzM0MDc4ZmRiYTk1MzY5NmM2ZjIyMTEzZjY=
+    ZGJkNmQ4MTQxZGIyZDI2MmIzMWMyNjgyYjFkNDZiY2NhOWUxZWQ3ZThkNGM5
+    YzkyOTFmNWY0N2ExZTdlMWRmMzk4NDRiZTBhMDc4YWJjY2ViMGJmYzJiMDky
+    MzczMDMyZTNhNWNkYTQyZjMwZTJkNmE2NTNjM2Q1OWUzZTQ0MGE=

data/.grabepg.gemspec

@@ -10,6 +10,6 @@ Gem::Specification.new do |gem|
   gem.files         = `git ls-files`.split($\)
   gem.name          = "grab_epg"
   gem.require_paths = ["lib"]
-  gem.version       = "0.0.3"
+  gem.version       = "0.0.4"
   gem.homepage      = "https://github.com/hahazql/grab_epg"
 end

data/README.md

@@ -4,14 +4,20 @@ eg:
 gem grab_epg
 
 proxy_list=Grabepg.get_topfast_list
+
 Grabepg.getchannels.each do |channel,url|
+
   Grabepg.getschedule(channel,url,proxy_list)
+  
 end
 
 
 Grabepg.getschedule 的返回：
+
 channel_schedule 是日期的时间表
+
 show_schedule 是根据节目的时间表
+
  {"channel_schedule"=>channel_schedule,"show_schedule"=>@show_schedule}
 
 

data/lib/debug.rb

@@ -5,8 +5,7 @@ require 'open-uri'
 require File.expand_path("../grabepg.rb", __FILE__)
 class Debug
   # To change this template use File | Settings | File Templates.
-  proxylist = ["123.125.116.243:6256", "123.125.116.243:28832", "123.125.116.243:29952", "123.125.116.243:9386", "219.234.82.73:7806", "123.125.116.243:38205", "123.125.116.243:11229", "123.125.116.243:12978", "219.234.82.89:8090", "120.197.85.173:20368", "123.125.116.243:8089", "123.125.116.243:8160", "219.234.82.78:31565", "123.125.116.243:21457", "123.125.116.241:17421", "123.125.116.243:14191", "219.234.82.88:29037", "123.125.116.242:13669", "123.125.116.243:19009", "123.125.116.243:6193", "123.125.116.242:15692", "123.125.116.241:20307", "123.125.116.242:18725", "219.234.82.82:29082", "123.125.116.243:5195", "123.125.116.242:21725", "123.125.116.241:32793", "219.234.82.60:8000", "123.125.116.242:17403", "123.125.116.243:6938", "123.125.116.242:16348", "219.234.82.54:8726", "120.197.85.173:20371", "123.125.116.241:9286", "219.234.82.88:19279", "219.234.82.89:13374", "123.125.116.242:5976"]
-
+  proxylist = [""]
 
   def self.test_get_doc_with_proxy(proxylist)
     herf = "http://www.tvmao.com/drama/HS5oLCs="

data/lib/grabepg.rb

@@ -7,10 +7,14 @@ module Grabepg
   # To change this template use File | Settings | File Templates.
 
 
+  #图片的获取： Net::HTTP.get(url)
+  #图片的文件类型获取：
+
   attr_reader :channel  #频道列表
   attr_reader :site #网站地址
   attr_reader :proxyindex #代理的索引
   attr_reader :show_schedule #根据节目的时间表
+  attr_reader :img_down_path #图片下载路径存放
 
   DEFAULT_GrabtvType=["cctv","satellite","digital",]
   DEFAULT_SITE = "http://www.tvmao.com"
@@ -20,19 +24,29 @@ module Grabepg
   def self.start
     @channel = []
     @site = DEFAULT_SITE
-    channel_urls = self.getchannels
+    channel_urls = self.getchannels("/home/zql")
     proxy_list=get_topfast_list
+    img_down_path = self.img_down_path
+    p img_down_path
     channel_urls.each do |channel,url|
       p "****************************************GetSchedule : #{getschedule(channel,url,proxy_list)}"
     end
   end
 
+  def self.img_down_path
+    @img_down_path
+  end
+
 
   #获取网站的频道表
-  def self.getchannels
+  #img_path 图片存放路径
+  def self.getchannels(img_dir_path)
     @channel = []
     @site=DEFAULT_SITE
     @proxyindex = 0
+    @img_down_dir_path = img_dir_path
+    @img_down_file = File.new(File.join(img_dir_path,"channel_img_down_path"),'w+')
+
     channel_urls = {}
 
     get_url =lambda { |type|
@@ -56,10 +70,15 @@ module Grabepg
         herf=a['href']
        end
         channel_id = get_channel_id.call(herf)
+
+       #获取频道图片的地址
+        img_path = "http://static.haotv.me/channel/logo/#{channel_id}.jpg"
+        @img_down_file.puts("#{channel_id}:#{img_path}")
         @channel<<({channel_id=>{name:channel_name,herf:herf,type:type}})
         channel_urls.merge!({channel_id=>herf})
       end
     end
+    @img_down_file.close
     p "Channel: #{@channel}"
     channel_urls
   end
@@ -70,13 +89,14 @@ module Grabepg
       @proxyindex = 0
     end
     @proxyindex=@proxyindex%proxylist.size
-    if(proxylist[@proxyindex]!="123.125.116.243:6256"||proxylist[@proxyindex]!="http://123.125.116.243:28832")
+    if(proxylist[@proxyindex])
       proxy = proxylist[@proxyindex]
     else
       proxy = proxylist[@proxyindex+1]
     end
     begin
-      doc = Nokogiri::HTML(open(url,:proxy=>"http://#{proxy}"))
+      doc = Nokogiri::HTML(open(url,:proxy=>"http://#{proxy}")) unless proxy.nil?||proxy.empty?
+      doc = Nokogiri::HTML(open(url)) if proxy.nil?||proxy.empty?
       @no_firest = false
     rescue => err
       @no_firest = true
@@ -94,7 +114,12 @@ module Grabepg
 
 
   #获取节目表
-  def self.getschedule(channel,herf,proxylist,site="http://www.tvmao.com")
+  def self.getschedule(channel,herf,proxylist,site="http://www.tvmao.com",img_dir_down_path=@img_down_dir_path)
+    unless img_dir_down_path
+      img_dir_down_path = __FILE__
+    end
+    @img_down_file = File.new(File.join(img_dir_down_path,"schedule_img_down_path"),"w+")
+
     if(@site)
       site=@site
     end
@@ -116,14 +141,6 @@ module Grabepg
     channel_schedule = {}
     get_week_url.call(herf).each do |url|
       p "Grab: #{url}"
-      #if(proxylist[proxyidex]!="219.234.82.89:33948")
-      #  proxy = proxylist[@proxyidex]
-      #else
-      #  proxy = proxylist[@proxyidex+1]
-      #end
-      #p "Proxy: http://#{proxy}"
-      #doc = Nokogiri::HTML(open(url,:proxy=>"http://#{proxy}"))
-      #@proxyidex += 1
       doc = get_doc_with_proxy(proxylist,url)
       show_type = []
       img_url = _img_url + channel+".jpg"
@@ -150,19 +167,22 @@ module Grabepg
             show_infomation=get_show_infomation(proxylist,schedule_herf)
             show_type=show_infomation["type"]
             show_name = show_infomation["name"]
+            show_img = show_infomation["img"]
           end
-          p "Time: #{time} schedule: #{schedule} show_infomation_herf: #{schedule_herf}  type: #{show_type} name: #{show_name}"
-          schedule_list << {"time"=>time,"schedule"=>schedule,"show_infomation_herf"=>schedule_herf,"type"=>show_type,"name"=>show_name}
+          p "Time: #{time} schedule: #{schedule} show_infomation_herf: #{schedule_herf}  type: #{show_type} name: #{show_name} img:#{show_img}"
+          schedule_list << {"time"=>time,"schedule"=>schedule,"show_infomation_herf"=>schedule_herf,"type"=>show_type,"name"=>show_name,"img"=>show_img}
         end
       end
       channel_schedule.merge!({"#{week}(#{date})"=>schedule_list})
     end
+    @img_down_file.close
     {"channel_schedule"=>channel_schedule,"show_schedule"=>@show_schedule}
   end
 
 
   #获取节目详细信息
   def self.get_show_infomation(proxy_list,schedule_herf)
+    begin
     @proxyindex = 0
     unless @site
       @site = "http://www.tvmao.com"
@@ -173,6 +193,12 @@ module Grabepg
    # p "title: %s" % title
     type = []
     name = doc.css('span[itemprop="name"]')[0].content
+
+    #获取节目的图片
+    schedule_img_down_path = doc.css('img[class="tvc"]')[0].get_attribute('src') if doc.css('img[class="tvc"]')
+
+
+
     doc.css('span[itemprop="genre"]').each do |_type|
       type << _type.content
     end
@@ -188,8 +214,12 @@ module Grabepg
       type<<_type.content
     end
     type.uniq!
+    @img_down_file.puts("#{name}:#{schedule_img_down_path}")
     @show_schedule.merge!(name=>get_show_schedule(proxy_list,schedule_herf)) unless @show_schedule.has_key?(name)
-    {"type"=>type,"name"=>name}
+    {"type"=>type,"name"=>name,"img"=>schedule_img_down_path}
+    rescue => e
+      p "Error In get_show_infomation msg : #{e.to_s}"
+    end
   end
 
   #获取节目的时间表
@@ -282,4 +312,8 @@ module Grabepg
     list = contxt.scan(regex_list)
   end
 
+  def save_img
+
+  end
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: grab_epg
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors:
 - hahazql
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-04-26 00:00:00.000000000 Z
+date: 2013-04-27 00:00:00.000000000 Z
 dependencies: []
 description: ! '"用于从TVMAO抓取EPG信息"'
 email: