grab_epg 0.1.5 → 0.1.6

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    NjYwZWJkYTFmZjM2ODEyNTlmNzdhMmRjMDJiMjczYzIzMGE2MTMyMg==
+    NmI0ZDZlY2FkNzVhNTNiNTQwYjU0NDNhOTNhYmUyZWUzY2ViN2U5OA==
   data.tar.gz: !binary |-
-    MjIwNmU3YThlM2E5NTRlMzBiYzNiNTdlOGZkYzFkZmFjMGNhMGY0ZA==
+    NzBkMjAxZmUwNDE1YzAzNWNmMTc1NjEwNjJlM2NhYjlmZmU2N2MzZg==
 !binary "U0hBNTEy":
   metadata.gz: !binary |-
-    MTU0MjBiYzNhZWYxOGY0OTEwMTIwMzkwNmQ5ZWFkNzc4MzA4OGQxNzkzMTIw
-    MzdjZDMxNDNiMzZhOThlODQ0ZDRhZDNiNDkyYzc4N2UwZDFkMGYxYjFhZmJl
-    NjRmMjdiZTBjMzIxNzYyZjdiMGVhMzNjZjdjNWQzZmFkYjU5MWQ=
+    MmZiNGVkM2JjMGUwZDNmMDE5OTc2NzE2NjFmMDJmMzgyODU2Nzg1ZjgxZjBl
+    NmVkMmU0MThhZmY1YjZhOWYxNDBlOWZjZDEwODNlYWI3MWFhNmY2ZDQ1OThl
+    NTFjM2VmMjgxOTc1MmNkY2EzMmU2YzNjN2JkNjA0M2FlNjllZmE=
   data.tar.gz: !binary |-
-    NTRhZTA3YTdlZGIyZDZkZGIxNzViYWI0OTY4N2FhNDAyN2QyM2E3ZjE2Mzkx
-    ZmY5NjlhNjNjNGM3MzMyNzk1YTY2ZWQ0ZWM2MDhkN2Q1OTlkOWE4OGQ3YjUy
-    MGYxNTYxNWY3YmE5NWMyMDcwNDEwYWNkNDJkNWM2NDM5MTk3ZGU=
+    ZTBmMzY2MDkyZDEzZDVhMzQ0MDA4MmVjYTBkMGM2YmJhYTlhYzkzOWYyNjJj
+    ZjAxOTNmZjgwZTljNWI3MWQxMjY3Y2FmZjczODNhYWU4MGQ3YzZhNDRjOWM1
+    NTJlZWYxNDViNDgwZjMxNDMxZWNhYzY1NzA1OTg5ZGIwY2YyYWI=

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       = "0.1.5"
+  gem.version       = "0.1.6"
   gem.homepage      = "https://github.com/hahazql/grab_epg"
 end

data/lib/debug.rb

@@ -5,7 +5,7 @@ require 'open-uri'
 require File.expand_path("../grabepg.rb", __FILE__)
 class Debug
   # To change this template use File | Settings | File Templates.
-  proxylist = [""]
+  proxylist = ["219.234.82.84:24809", "219.234.82.84:17130", "219.234.82.84:23684", "219.234.82.84:18253", "219.234.82.84:33987", "219.234.82.84:17183", "219.234.82.84:13243", "219.234.82.84:16158", "219.234.82.84:14826", "219.234.82.84:8489", "219.234.82.84:22222", "219.234.82.84:6370", "219.234.82.84:7571", "219.234.82.84:33944", "219.234.82.84:9743", "219.234.82.84:8089", "219.234.82.84:20991", "219.234.82.84:34032", "219.234.82.84:9415", "219.234.82.84:26149", "219.234.82.84:11095", "219.234.82.84:21724", "219.234.82.84:9177", "219.234.82.84:34034", "219.234.82.84:17945", "219.234.82.85:32229", "219.234.82.85:28341", "219.234.82.85:36314", "219.234.82.85:30605", "219.234.82.85:23684", "219.234.82.85:34015", "219.234.82.85:33919", "219.234.82.85:30639", "219.234.82.85:33965", "219.234.82.85:37299", "219.234.82.85:20747", "219.234.82.86:6666", "219.234.82.86:34106", "219.234.82.86:25301", "219.234.82.86:32896", "219.234.82.86:23034", "219.234.82.86:22685", "219.234.82.86:13078", "219.234.82.86:38770", "219.234.82.86:28402", "219.234.82.86:18887", "219.234.82.86:6588", "219.234.82.86:7292", "219.234.82.86:24268", "219.234.82.86:16472", "219.234.82.86:32597", "219.234.82.86:31122", "219.234.82.88:8817", "219.234.82.88:8160", "219.234.82.88:9239", "219.234.82.88:6133", "114.141.162.53:8080", "123.125.116.243:17656", "123.125.116.241:29156", "123.125.116.243:6938", "219.234.82.88:29484", "219.234.82.88:8084", "219.234.82.88:32229", "219.234.82.88:22758", "219.234.82.88:5616", "124.225.52.14:8080", "219.234.82.88:30028", "219.234.82.88:23685", "219.234.82.88:29037", "219.234.82.88:8755"]
 
   def self.test_get_doc_with_proxy(proxylist)
     herf = "http://www.tvmao.com/drama/HS5oLCs="
@@ -33,9 +33,19 @@ class Debug
     Grabepg.get_show_schedule(proxylist,herf)
   end
 
+  def self.test_get_schedulelist_atday(proxylist)
+    Grabepg.get_schedulelist_atday("CCTV1"," http://www.tvmao.com/program/CCTV-CCTV1-w1.html",proxylist)
+  end
+
+  def self.debug_all
+    Grabepg.start
+  end
+
  #Grabepg.start
  #p test_get_show_schedule(proxylist)
  #p test_getschedule(proxylist)
  # p test_get_show_infomation(proxylist)
-  p test_get_assign_date_url
+  #p test_get_assign_date_url
+ # p test_get_schedulelist_atday(proxylist)
+  p debug_all
 end

data/lib/grabepg.rb

@@ -95,17 +95,111 @@ module Grabepg
 
   #调用此方法的例子
   def self.start
-    @channel = []
-    @site = DEFAULT_SITE
-    channel_list = self.getchannels("/home/zql")
-    proxy_list=get_topfast_list(5)
-    img_down_path = self.img_down_path
-    p img_down_path
-    channel_urls = channel_list["channel_urls"]
+    #作用是获取俩个字符串的相似度
+    #get str1 and str2 similarity
+    get_similarity_string = lambda { |str1,str2|
+      _length = 0
+      type = 0
+      if str1.length>str2.length
+        _length=str2.length
+        type = 2
+      else
+        _length=str1.length
+        type =1
+      end
+      _str_list = []
+      _str = ""
+      for i in 0.._length
+        case type
+          when 2
+            n=i
+            0.upto(str1.length-1).each do |j|
+              p "N: #{n}"
+              if(str2[n]==str1[j])
+                _str =_str+str2[n]
+                n = n+1
+                p "Str = #{_str}"
+              else
+                _str_list << _str
+                _str = ""
+              end
+            end
+          when 1
+            n=i
+            0.upto(str2.length-1).each do |j|
+              p "N: #{n}"
+              if(str1[n]==str2[j])
+                _str =_str+str1[n]
+                n=n+1
+                p "Str = #{_str}"
+              else
+                _str_list << _str
+                _str = ""
+              end
+            end
+        end
+      end
+      p _str_list
+      _str = ""
+      _str_list.each do |str|
+        if _str.length<str.length
+          _str=str
+        end
+      end
+      _str
+    }
+
+
+    path = "/home/zql/workspace/New/smart_remote/img_path"
+    channel_list = Grabepg.getchannels(path)
+    channel_urls = channel_list['channel_urls']
+    channel_infos = channel_list['channel_info']
+    p "Channel img save file,path='#{Grabepg.img_down_path}'"
+    proxy_list=Grabepg.get_topfast_list(5)  #get_topfast_list 参数是代表最慢用时 单位秒
+
+
+    #Use for Test
+
+    p "************************************"
+    p "proxy_list:#{proxy_list}"
+    p "************************************"
+
+    bool_start = false
+
+
     channel_urls.each do |channel,url|
-      p "****************************************GetSchedule : #{getschedule(channel,url,proxy_list)}"
+
+      if(channel=="CCTV16")
+        bool_start = true
+      end
+
+      if bool_start
+        previous_show_name = ""
+        channel_info = channel_infos[channel]
+        channel_name = channel_info["channel_name"]
+        channel_type = channel_info["channel_type"]
+        channel_id = channel_info["channel_id"]
+        channel_img_path = channel_info["img_path"]
+
+        #channel,herf,proxylist,day_num=7
+
+
+        start_time=0
+        use_num =1
+
+        #getScheduleAssignDate参数：
+        # channel 频道
+        # herf 频道地址
+        # proxylist 代理列表
+        # start_num 开始时间 int 为开始时间与今天的差值 正数代表今天之后的第几天   负数代表今天之前的第几天
+        # day_num 抓取的时间段天数
+        # img_dir_down_path 图片网络地址保存路径 有默认值 可不设置
+        schedule_list=Grabepg.getScheduleAssignDate(channel,url,proxy_list,start_time,use_num)  #抓取的七天后的1天的数据
+
+
+        end
+      end
     end
-  end
 
   def self.img_down_path
     @img_down_path
@@ -174,6 +268,11 @@ module Grabepg
       doc = Nokogiri::HTML(open(url)) if proxy.nil?||proxy.empty?
       @no_firest = 0
     rescue => err
+
+      unless @no_firest
+        @no_firest = 0
+      end
+
       @no_firest += 1
       p "*************************Proxy:#{proxy}, url:#{url}"
       proxylist.delete(proxy)
@@ -192,13 +291,25 @@ module Grabepg
     p "Grab: #{url}"
     doc = get_doc_with_proxy(proxylist,url)
     show_type = []
+
+
+    _img_url = "http://static.haotv.me/channel/logo/"
     img_url = _img_url + channel+".jpg"
+
+
     data=doc.css('div[class="mt10 clear"]')[0].content.split(" ")
     date = data[0]
     week = data[1]
     p "Channel: #{channel}  Date: #{date} Week: #{week}"
     @date = "#{week}(#{date})"
     schedule_list = []
+
+    _herf = doc.css("h1[style='float:left']").xpath('img[@src]')[0]
+    img_url = _herf.get_attribute("src") if _herf
+
+    p "**************IMG: #{img_url}"
+
+
     doc.css('ul[id="pgrow"]')[0].css("li").each do |schedule|
       _herf= schedule.xpath('a[@href]')[0]
       schedule_herf=_herf.get_attribute("href") if _herf
@@ -246,7 +357,7 @@ module Grabepg
       wday = 1
     end
 
-    end_day = wday + day_num
+    end_day = wday + day_num - 1
 
     if end_day>(_wday+7)
      end_day = _wday + 7
@@ -265,7 +376,7 @@ module Grabepg
 
 
   #获取指定时间段的节目表
-  def self.getScheduleAssignDate(channel,herf,proxylist,start_num,day_num,img_dir_down_path=@img_down_dir_path)
+  def self.getScheduleAssignDate(channel,herf,proxylist,start_num,day_num=0,img_dir_down_path=@img_down_dir_path)
     begin
       day_num = 1 if day_num<1
     rescue

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: grab_epg
 version: !ruby/object:Gem::Version
-  version: 0.1.5
+  version: 0.1.6
 platform: ruby
 authors:
 - hahazql