meiriyigua 0.0.7 → 0.0.8
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +8 -8
- data/lib/meiriyigua.rb +1 -1
- data/lib/meiriyigua/baidu_crawl.rb +3 -0
- data/lib/meiriyigua/detail_crawl.rb +2 -0
- data/lib/meiriyigua/list_crawl.rb +2 -0
- data/lib/meiriyigua/post_client.rb +5 -4
- data/lib/meiriyigua/post_client_two.rb +1 -1
- data/lib/meiriyigua/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
---
|
2
2
|
!binary "U0hBMQ==":
|
3
3
|
metadata.gz: !binary |-
|
4
|
-
|
4
|
+
ZTViNmFlYmUxODI5MDk5YzVjODQ0MDVlNmVlMDQ0OTU3NmE4MjM0MQ==
|
5
5
|
data.tar.gz: !binary |-
|
6
|
-
|
6
|
+
MzlkMGE2YWNmZmY4ODIzYzQ3ZGMxMjZkNGI1OWNiZDc2ZTdiY2Y4Mw==
|
7
7
|
SHA512:
|
8
8
|
metadata.gz: !binary |-
|
9
|
-
|
10
|
-
|
11
|
-
|
9
|
+
ODIzNGE2ZDNhZWU4MzhhZjM2M2M1NTk4ZTRmNDllNjE3MGE4NDJhMTI0Yjcw
|
10
|
+
NTUxMzljZTg3NmI4YjEyYTg3ODgwZWJjMDRkYWEyYjQzMTkyZGRhMjU3OGZk
|
11
|
+
MjUwZjlkZjVlODEwNWIxMjk2ZGI5MjMxZDJhMGFhZjQxODNkZWE=
|
12
12
|
data.tar.gz: !binary |-
|
13
|
-
|
14
|
-
|
15
|
-
|
13
|
+
ZmQ1NDNkODQ0OWZlYmUxMjgyNjlhODkwYWNhYzM4YWFkZDJmMzg3NDdmZDAy
|
14
|
+
ZmNmNTgwYjVkOTBiYjA4NDdlOGUzYjYxNzc3Y2Y0ZTMwMjFlMzkyZGUzYzZl
|
15
|
+
NTc3MWY0MzU3OWM3MTM2ZjZlOWYzODQ0NzM3ZmFkNWViMjllMzg=
|
data/lib/meiriyigua.rb
CHANGED
@@ -39,6 +39,9 @@ module Meiriyigua
|
|
39
39
|
result = ""
|
40
40
|
search_results.search('div.c-container div.c-abstract').each_with_index{|a, i| result << "提示#{i+1}\r\n #{a.text}\r\n\r\n"}
|
41
41
|
result
|
42
|
+
rescue
|
43
|
+
puts "抓取百度简介出错了 #{$!.class} #{$!.message}\n#{$!.backtrace.join("\n")}"
|
44
|
+
""
|
42
45
|
end
|
43
46
|
end
|
44
47
|
end
|
@@ -13,11 +13,9 @@ module Meiriyigua
|
|
13
13
|
|
14
14
|
def initialize
|
15
15
|
@agent = CrawlClient.create_agent
|
16
|
-
@agent.keep_alive = false
|
17
|
-
@agent.idle_timeout = 0.1
|
18
16
|
@category_ids = {}
|
19
17
|
|
20
|
-
login
|
18
|
+
raise "登录失败,请检测用户与密码是否正确" unless login
|
21
19
|
check_category
|
22
20
|
end
|
23
21
|
|
@@ -72,7 +70,7 @@ module Meiriyigua
|
|
72
70
|
|
73
71
|
def post_news(page_record, category_id)
|
74
72
|
post_params = {}
|
75
|
-
post_params['news_tit'] =
|
73
|
+
post_params['news_tit'] = page_record.title
|
76
74
|
post_params['author'] = random_zh
|
77
75
|
post_params['click'] = rand(600..13000)
|
78
76
|
post_params['biaoqian'] = page_record.category
|
@@ -82,6 +80,9 @@ module Meiriyigua
|
|
82
80
|
post_params['editorValue'] = "<pre>#{page_record.content} \r\n\r\n #{page_record.baidu_intro}</pre>"
|
83
81
|
result_page = @agent.post("http://#{Meiriyigua::Config.site_host}/admin/admin.php/News/insert", post_params)
|
84
82
|
!result_page.search('script').text.index('/admin/admin.php/News/index').nil?
|
83
|
+
rescue
|
84
|
+
puts "发布出错了 #{$!.class} #{$!.message}\n#{$!.backtrace.join("\n")}"
|
85
|
+
false
|
85
86
|
end
|
86
87
|
|
87
88
|
private
|
@@ -40,7 +40,7 @@ module Meiriyigua
|
|
40
40
|
|
41
41
|
def post_news(page_record)
|
42
42
|
post_params = {}
|
43
|
-
post_params['A'] =
|
43
|
+
post_params['A'] = page_record.title
|
44
44
|
downloads = page_record.downloads.split('#!#')
|
45
45
|
post_params['xiadizhi'] = downloads[0]
|
46
46
|
post_params['xiadizhi2'] = downloads[1]
|
data/lib/meiriyigua/version.rb
CHANGED