grab_epg 0.1.2 → 0.1.3

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    ZWZlNWRhZGY1NWRhNWU2NmQyYmQzZWUyNjI0NjcyOGYyZTIyMGI4NA==
+    ZGM4ZjA4YTk0ODU0ZDBkNjdlZjc1MGFiMDRjZGE5OTFlNTU5Nzc5Nw==
   data.tar.gz: !binary |-
-    MGUwNmQzZjQ1MTMyZTk0YzUxNmY1OTY1ZTAwM2QzMmVlNDQ1Yzg5Yg==
+    MzIwODc1NzdiZDEzYjhiNWI3MDVlNzFkMTUyNTFhMGNiZjEzODM4Yg==
 !binary "U0hBNTEy":
   metadata.gz: !binary |-
-    NDgzMzY4ZTRjNWNjOTBjOGM5YmY3YTQyZDZiZjQ1MjhiMjM3M2EzZTUyOWQx
-    ZTE4MjNmZjVjMWM3MTExMDI4YmI0MGZiMGFjZmJmNTJjM2IxMDQ4NWJjMWY0
-    NDRmNzc4ODNmN2ZiZTQ3MmJlNDAyMGQ0MTdlNzYwZmViMmNlNzA=
+    ZGQ5Nzc1MzdjYTVlODVlZjg2YmM3N2VkOTI5YjAwMzFjYTQ3MTFiMTlhOWI5
+    ZDY3OTgxNjllNDYyOTViZTViYTM0Njc1OGU2YmE2NzcyNTdhMzQ0ZDAzYzcz
+    MmMwYTk1MmFmZDE0YTM5YTBiNTk1NWM1YjAzNGJmNTRjZmExMzc=
   data.tar.gz: !binary |-
-    MWZlMzUzMzMzYzkwNGQ3NjQ0ZWJiNTJmYjczZjY0M2Q5ZGNjOTVmZmYyYzVm
-    MjBhNGZkOTE0NGU1ZDEzMzA3YTIzZWZhNjljNmNiY2E0MGNjMzZhYzc4NzMz
-    MDYyYjQ5ODFkMWZjOWRjNTJkMzZkMzJkNzZhNDc0MDQyMTEwNzI=
+    YTA5Y2IyMzFiOTkxMDIwMDJhOTBmMDQ5MGZhMDAxODI2MDcwZDRlM2M2Yzll
+    YTZmMDNjODY3MmQ5MzY2NWJhNjEwNWE5NDgyN2Y1ZDZjZTA2MDQ2YjkzMWFj
+    YjNlNDhlNTY3ZjhkOTkwODIwNzFhOTQ2ZWJlZWIyYzgwODAzMDg=

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       = "0.1.2"
+  gem.version       = "0.1.3"
   gem.homepage      = "https://github.com/hahazql/grab_epg"
 end

data/lib/grabepg.rb

@@ -98,7 +98,7 @@ module Grabepg
     @channel = []
     @site = DEFAULT_SITE
     channel_list = self.getchannels("/home/zql")
-    proxy_list=get_topfast_list
+    proxy_list=get_topfast_list(5)
     img_down_path = self.img_down_path
     p img_down_path
     channel_urls = channel_list["channel_urls"]
@@ -186,10 +186,114 @@ module Grabepg
     doc
   end
 
+  #获取某天的节目表
+  def self.get_schedulelist_atday(channel,url,proxylist)
+    p "Grab: #{url}"
+    doc = get_doc_with_proxy(proxylist,url)
+    show_type = []
+    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 = []
+    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
+      unless _herf
+        drama =schedule.css('a[class="drama"]')[0]
+        if drama
+          _herfs=drama.get_attribute("href").gsub("/episode/section","#%#")
+          schedule_herf = _herfs.split("#%#")[0]
+        end
+      end
+      if schedule.content.split(" ").size>1
+        time = schedule.content.split(" ")[0]
+        schedule = schedule.content.split(" ")[1]
+        show_name = ""
+        unless schedule_herf.nil?||schedule_herf.empty?
+          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} img:#{show_img}"
+        schedule_list << {"schedule_name"=>schedule,"schedule_logo"=>show_img,"schedule_start"=>time,"show_infomation_herf"=>schedule_herf,"type"=>show_type,"name"=>show_name}
+      end
+    end
+    schedule_list
+  end
+
+  #获取制定时间和长度url
+  #start_time 为int型 开始时间和今天的差值 正数代表之后的第几天 负数代表之前的第几天
+  #day_num 为int型 代表抓取的时间从开始时间计算的多少天
+  def get_assign_date_url(url,start_time,day_num)
+    _url = site
+    urls = []
+    _urls = url.split("-")
+
+    time = Time.now
+    _wday = time.wday
+    wday = _wday + start_time
+    if wday<0
+      wday = 1
+    end
+
+    end_day = wday + day_num
+
+    if end_day>(_wday+7)
+     end_day = _wday + 7
+    end
+
+    0.upto(1).each do |i|
+      _url = _url+"#{_urls[i]}"+"-"
+    end
+
+    wday.upto(end_day).each do |i|
+      urls << _url+"w#{i}.html"
+    end
+    urls
+  end
+
+
+
+  #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)
+    begin
+      day_num = 1 if day_num<1
+    rescue
+      day_num = 1
+    end
+    site="http://www.tvmao.com"
+    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
+    _img_url = "http://static.haotv.me/channel/logo/"
+    @show_schedule = {}
 
-  #获取节目表
-  def self.getschedule(channel,herf,proxylist,day_num=1,img_dir_down_path=@img_down_dir_path)
+    channel_schedule = {}
+    get_assign_date_url(herf,start_num,day_num).each do |url|
+      @date = ""
+      schedule_list = self.get_schedulelist_atday(channel,url,proxylist)
+      channel_schedule.merge!({@date=>schedule_list}) unless @date.empty?
+    end
+    @img_down_file.close
+    {"channel_schedule"=>channel_schedule,"show_schedule"=>@show_schedule}
+  end
+
+
+
+
+
+  #因原已调用所以保留
+  #获取一周节目表
+  def self.getschedule(channel,herf,proxylist,day_num=7,img_dir_down_path=@img_down_dir_path)
     p "Day Num is #{day_num}"
     begin
       day_num = 1 if day_num<1
@@ -223,40 +327,9 @@ module Grabepg
 
     channel_schedule = {}
     get_week_url.call(herf,day_num).each do |url|
-      p "Grab: #{url}"
-      doc = get_doc_with_proxy(proxylist,url)
-      show_type = []
-      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}"
-      schedule_list = []
-      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
-        unless _herf
-          drama =schedule.css('a[class="drama"]')[0]
-          if drama
-            _herfs=drama.get_attribute("href").gsub("/episode/section","#%#")
-            schedule_herf = _herfs.split("#%#")[0]
-          end
-        end
-        if schedule.content.split(" ").size>1
-          time = schedule.content.split(" ")[0]
-          schedule = schedule.content.split(" ")[1]
-          show_name = ""
-          unless schedule_herf.nil?||schedule_herf.empty?
-            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} img:#{show_img}"
-          schedule_list << {"schedule_name"=>schedule,"schedule_logo"=>show_img,"schedule_start"=>time,"show_infomation_herf"=>schedule_herf,"type"=>show_type,"name"=>show_name}
-        end
-      end
-      channel_schedule.merge!({"#{week}(#{date})"=>schedule_list})
+      @date = ""
+      schedule_list = self.get_schedulelist_atday(channel,url,proxylist)
+      channel_schedule.merge!({@date=>schedule_list}) unless @date.empty?
     end
     @img_down_file.close
     {"channel_schedule"=>channel_schedule,"show_schedule"=>@show_schedule}
@@ -333,14 +406,15 @@ module Grabepg
 
 
   #获取指定访问速度的代理服务器
-  def self.get_topfast_list()
+  #time为最慢速度的时间 int型 代表秒
+  def self.get_topfast_list(use_time)
     fast_list = []
     time_use = 0
     ips_ports = get_proxy_list()
     ips_ports.each do |ip_port|
       time_start = Time.now.to_i
       begin
-        timeout(5) do
+        timeout(use_time) do
           doc = Nokogiri::HTML(open("http://www.tvmao.com/program",:proxy=> "http://#{ip_port}"))
         end
         time_end = Time.now.to_i

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: grab_epg
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - hahazql
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-05-09 00:00:00.000000000 Z
+date: 2013-05-13 00:00:00.000000000 Z
 dependencies: []
 description: ! '"用于从TVMAO抓取EPG信息"'
 email: