grab_epg 0.2.9 → 0.3.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +8 -8
- data/.grabepg.gemspec +1 -1
- data/lib/debug.rb +1 -1
- data/lib/grab_tvmao.rb +28 -23
- data/lib/grabepg/grab_base.rb +2 -2
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
---
|
2
2
|
!binary "U0hBMQ==":
|
3
3
|
metadata.gz: !binary |-
|
4
|
-
|
4
|
+
MGJjOWQ0MTYxNDVjNjBiNTRkYzZlMTE5ZWU1MzNiZjRiZTIwMmY5Zg==
|
5
5
|
data.tar.gz: !binary |-
|
6
|
-
|
6
|
+
YjVlYWZlNDgwOWQzNGMzNDk4YmIwOWMyNmU5NWMzZTY3NTM4ZTgwZA==
|
7
7
|
!binary "U0hBNTEy":
|
8
8
|
metadata.gz: !binary |-
|
9
|
-
|
10
|
-
|
11
|
-
|
9
|
+
YzdhNjczNDA2ZDc3MmQwMzEyZjI1OWJhYzI3MTQwYmJjNzJiOGY0NDRhZWMw
|
10
|
+
NGUzZDg2OWM0ODhlYTI5ODc3MjhmN2Y4MWQwMzc4YmQ0OTQzYzVlMjc5ZTkw
|
11
|
+
ZWM5ZmJhM2ViNjZlNzRlYzYyNGExOTc1OTI0MjBkNGQzNDA4ZjU=
|
12
12
|
data.tar.gz: !binary |-
|
13
|
-
|
14
|
-
|
15
|
-
|
13
|
+
YzkzODFkOTlkYjllYjU4NjMwYWY4NDNlMTJjYTBjZjg1NDZjYmEzNGU4NWRj
|
14
|
+
NGIxMDg2OThlNTRhNzhjODFhZWExZjAyYzFjZTA1YTFkOThjMjdlMmUzNDdk
|
15
|
+
OWU2MWUxZWVmNDAxNzU0NTkwM2RiZDU0NDkzNmU3YTdmNWQ1MDc=
|
data/.grabepg.gemspec
CHANGED
data/lib/debug.rb
CHANGED
data/lib/grab_tvmao.rb
CHANGED
@@ -28,6 +28,7 @@ module Grabepg
|
|
28
28
|
|
29
29
|
def initialize
|
30
30
|
@grabbase = GrabBase.new
|
31
|
+
@@proxyindex = 0
|
31
32
|
end
|
32
33
|
|
33
34
|
|
@@ -46,11 +47,12 @@ module Grabepg
|
|
46
47
|
end
|
47
48
|
url = get_show_type_url(url,date)
|
48
49
|
schedules = get_schedulelist_atday(channel,url,proxylist)
|
49
|
-
type =
|
50
|
+
type = []
|
50
51
|
schedules.each do |schedule|
|
52
|
+
begin
|
51
53
|
schedule_time_num = schedule["schedule_start"].gsub(":","").to_i
|
52
54
|
if _schedule.has_key?(schedule_time_num)
|
53
|
-
_schedule[schedule_time_num]["type"]=_schedule[schedule_time_num]["type"]|schedule["type"]
|
55
|
+
_schedule[schedule_time_num]["type"]=_schedule[schedule_time_num]["type"]|schedule["type"] if schedule["type"]
|
54
56
|
p "*****************************************************************************************"
|
55
57
|
p "Schedule: #{_schedule[schedule_time_num]}"
|
56
58
|
p "schedule_logo_1: #{_schedule[schedule_time_num]["schedule_logo"]}"
|
@@ -61,6 +63,9 @@ module Grabepg
|
|
61
63
|
end
|
62
64
|
end
|
63
65
|
end
|
66
|
+
rescue
|
67
|
+
next
|
68
|
+
end
|
64
69
|
end
|
65
70
|
ret = []
|
66
71
|
_schedule.each do |key,value|
|
@@ -150,7 +155,9 @@ module Grabepg
|
|
150
155
|
when 6
|
151
156
|
ret += "六"
|
152
157
|
when 7
|
153
|
-
ret += "
|
158
|
+
ret += "日"
|
159
|
+
when 0
|
160
|
+
ret += "日"
|
154
161
|
end
|
155
162
|
ret
|
156
163
|
end
|
@@ -320,7 +327,6 @@ module Grabepg
|
|
320
327
|
def getchannels(img_dir_path)
|
321
328
|
@channel = []
|
322
329
|
@site=DEFAULT_SITE
|
323
|
-
@proxyindex = 0
|
324
330
|
@img_down_dir_path = img_dir_path
|
325
331
|
@img_down_file = File.new(File.join(img_dir_path,"channel_img_down_path"),'w+')
|
326
332
|
|
@@ -364,7 +370,7 @@ module Grabepg
|
|
364
370
|
|
365
371
|
def err_doc_proxy(proxy,proxylist,url="",err="")
|
366
372
|
if proxy.empty?||proxy.nil?
|
367
|
-
proxylist.delete_at[
|
373
|
+
proxylist.delete_at[@@proxyindex]
|
368
374
|
end
|
369
375
|
|
370
376
|
|
@@ -375,10 +381,10 @@ module Grabepg
|
|
375
381
|
@no_firest += 1
|
376
382
|
p "*************************Proxy:#{proxy}, url:#{url} Error:#{err}"
|
377
383
|
#proxylist.delete(proxy) #删除出错的代理 但如果是此网页错误则会引起BUG待修复
|
378
|
-
|
379
|
-
|
380
|
-
doc=get_doc_with_proxy(proxylist,url) if @no_firest<
|
381
|
-
unless @no_firest<
|
384
|
+
@@proxyindex += 1
|
385
|
+
@@proxyindex=@@proxyindex%@size
|
386
|
+
doc=get_doc_with_proxy(proxylist,url) if @no_firest<10
|
387
|
+
unless @no_firest<10
|
382
388
|
@no_firest=0
|
383
389
|
raise RuntimeError,"Error: #{err}"
|
384
390
|
end
|
@@ -389,15 +395,17 @@ module Grabepg
|
|
389
395
|
#使用代理获取url的html的doc值
|
390
396
|
def get_doc_with_proxy(proxylist,url)
|
391
397
|
unless proxylist.nil?||proxylist.empty?
|
392
|
-
unless
|
393
|
-
|
398
|
+
unless @@proxyindex
|
399
|
+
@@proxyindex = 0
|
394
400
|
end
|
395
401
|
@size = proxylist.size
|
396
|
-
|
397
|
-
|
398
|
-
|
402
|
+
@@proxyindex=@@proxyindex+1
|
403
|
+
@@proxyindex=@@proxyindex%@size
|
404
|
+
if(proxylist[@@proxyindex])
|
405
|
+
proxy = proxylist[@@proxyindex]
|
399
406
|
else
|
400
|
-
|
407
|
+
@@proxyindex=@@proxyindex+1
|
408
|
+
proxy = proxylist[@@proxyindex]
|
401
409
|
end
|
402
410
|
begin
|
403
411
|
doc = Nokogiri::HTML(open(url,:proxy=>"#{proxy}").read) unless proxy.nil?||proxy.empty?
|
@@ -412,12 +420,10 @@ module Grabepg
|
|
412
420
|
doc=err_doc_proxy(proxy,proxylist,url,err.to_s)
|
413
421
|
@no_firest=0
|
414
422
|
p "Get DOC"
|
415
|
-
|
416
|
-
|
423
|
+
@@proxyindex=@@proxyindex+1
|
424
|
+
@@proxyindex=@@proxyindex%@size
|
417
425
|
return doc
|
418
426
|
end
|
419
|
-
@proxyindex += 1
|
420
|
-
@proxyindex=@proxyindex%@size
|
421
427
|
else
|
422
428
|
begin
|
423
429
|
doc = Nokogiri::HTML(open(url).read) if proxy.nil?||proxy.empty?
|
@@ -600,7 +606,6 @@ module Grabepg
|
|
600
606
|
#获取节目详细信息
|
601
607
|
def get_show_infomation(proxy_list,schedule_herf)
|
602
608
|
begin
|
603
|
-
@proxyindex = 0
|
604
609
|
unless @site
|
605
610
|
@site = "http://www.tvmao.com"
|
606
611
|
end
|
@@ -633,10 +638,10 @@ module Grabepg
|
|
633
638
|
unless @show_schedule
|
634
639
|
@show_schedule={}
|
635
640
|
end
|
636
|
-
|
641
|
+
#@show_schedule.merge!(name=>get_show_schedule(proxy_list,schedule_herf)) unless @show_schedule.has_key?(name)
|
637
642
|
{"type"=>type,"name"=>name,"img"=>schedule_img_down_path}
|
638
|
-
|
639
|
-
|
643
|
+
rescue => e
|
644
|
+
p "Error In get_show_infomation msg : #{e.to_s}"
|
640
645
|
end
|
641
646
|
end
|
642
647
|
|
data/lib/grabepg/grab_base.rb
CHANGED
@@ -140,8 +140,8 @@ module Grabepg
|
|
140
140
|
#proxylist.delete(proxy) #删除出错的代理 但如果是此网页错误则会引起BUG待修复
|
141
141
|
@proxyindex += 1
|
142
142
|
@proxyindex=@proxyindex%@size
|
143
|
-
doc=get_doc_with_proxy(proxylist,url) if @no_firest<
|
144
|
-
unless @no_firest<
|
143
|
+
doc=get_doc_with_proxy(proxylist,url) if @no_firest<10
|
144
|
+
unless @no_firest<10
|
145
145
|
@no_firest=0
|
146
146
|
raise RuntimeError,"Error: #{err}"
|
147
147
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: grab_epg
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2
|
4
|
+
version: 0.3.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- hahazql
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2013-06-
|
11
|
+
date: 2013-06-14 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: ! '"用于抓取EPG信息"'
|
14
14
|
email:
|