meiriyigua 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.gitignore +20 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +1 -0
- data/lib/meiriyigua/baidu_crawl.rb +41 -0
- data/lib/meiriyigua/config.rb +36 -0
- data/lib/meiriyigua/crawl_client.rb +32 -0
- data/lib/meiriyigua/detail_crawl.rb +160 -0
- data/lib/meiriyigua/list_crawl.rb +97 -0
- data/lib/meiriyigua/models.rb +47 -0
- data/lib/meiriyigua/post_client.rb +105 -0
- data/lib/meiriyigua/version.rb +4 -0
- data/lib/meiriyigua.rb +43 -0
- data/meiriyigua.gemspec +28 -0
- data/set.yml.example +22 -0
- metadata +144 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
N2VhZDc2ODBjYTliYzkxMTliNzQyNDYyNmZiZGI3NGM3YTJkZmM3MA==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
YmZlZjE0YTE4N2U2ODY1ZDdkNTAwOTRiNjE5YjMyMTMwZWJlMjU1Mg==
|
7
|
+
SHA512:
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
YWE3NmNlYmIwYjExZTA3MDIxOWRmMTc4NDMxYWEwMmJmNDEzNTE3OTcxYzMy
|
10
|
+
ZGViMjNiNGZlZDkyYTBhZDBkZWJkNTgxNGNiYzkyNDMxN2UxZTg5ZmMzODgx
|
11
|
+
NDdjYWFmYmYzZjlkYTE4MGExNDQ2N2ZlMzYzNzdhMTRiNjRmZGE=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
ZmI0MTQ2MzJmZDgyOTcyNzRlMGEwNDMwNDQ5OWMwNDRhOTZiMTA0MWM4NTg3
|
14
|
+
ODk4NWJmMmVlMzJjMWNkODMxMDZjZmJlZGRkNzg0ZWJkNWJmNGVjNDNmOGFk
|
15
|
+
MmMxMjdkNTk1NjFmYWQwYmVlZDBjYWIwNTcwNTk1OTQwNGJjN2U=
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 mangege
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# Meiriyigua
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'meiriyigua'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install meiriyigua
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,41 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require 'meiriyigua/crawl_client'
|
3
|
+
require 'meiriyigua/models'
|
4
|
+
|
5
|
+
module Meiriyigua
|
6
|
+
class BaiduCrawl
|
7
|
+
include Meiriyigua::Models
|
8
|
+
|
9
|
+
def initialize
|
10
|
+
@agent = CrawlClient.create_agent
|
11
|
+
end
|
12
|
+
|
13
|
+
def run
|
14
|
+
UrlRecord.all(:baidu_at => nil).each do |url_record|
|
15
|
+
page_record = url_record.page_record
|
16
|
+
baidu_intro = get_intro(page_record.title)
|
17
|
+
CrawlClient.random_sleep
|
18
|
+
if baidu_intro.empty?
|
19
|
+
print "抓取百度简介 #{url_record.url} "
|
20
|
+
puts "失败"
|
21
|
+
else
|
22
|
+
page_record.baidu_intro = baidu_intro
|
23
|
+
page_record.save
|
24
|
+
url_record.baidu_at = Time.now
|
25
|
+
url_record.save
|
26
|
+
print "抓取百度简介 #{url_record.url} "
|
27
|
+
puts "成功"
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
def get_intro(title)
|
33
|
+
page = @agent.get('http://www.baidu.com/')
|
34
|
+
sleep 1
|
35
|
+
search_form = page.form_with(:name => "f1")
|
36
|
+
search_form.field_with(:name => "wd").value = title
|
37
|
+
search_results = @agent.submit search_form
|
38
|
+
search_results.search('div.c-container:first-of-type div.c-abstract').text
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require 'uri'
|
3
|
+
require 'yaml'
|
4
|
+
|
5
|
+
module Meiriyigua
|
6
|
+
class Config
|
7
|
+
class << self
|
8
|
+
def load
|
9
|
+
YAML::ENGINE.yamler = 'syck'
|
10
|
+
@@hashs = YAML.load(File.read "#{Dir.pwd}/set.yml")
|
11
|
+
end
|
12
|
+
|
13
|
+
def site_host
|
14
|
+
URI(login_url).host
|
15
|
+
end
|
16
|
+
|
17
|
+
{login_url: '提交地址',
|
18
|
+
username: '用户名',
|
19
|
+
password: '密码',
|
20
|
+
encode: '编码',
|
21
|
+
day_num: '每天发布',
|
22
|
+
post_time: '发布延时',
|
23
|
+
update_time: '监控延时'}.each do |k, v|
|
24
|
+
define_method(k) do
|
25
|
+
@@hashs['基础'][v]
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
def categories
|
30
|
+
@@hashs['栏目']
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
self.load
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require 'mechanize'
|
3
|
+
|
4
|
+
module Meiriyigua
|
5
|
+
class CrawlClient
|
6
|
+
USER_AGENTS = [
|
7
|
+
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6",
|
8
|
+
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_2; de-at) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
|
9
|
+
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/534.51.22 (KHTML, like Gecko) Version/5.1.1 Safari/534.51.22",
|
10
|
+
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.32 Safari/537.36",
|
11
|
+
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
|
12
|
+
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
|
13
|
+
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
|
14
|
+
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
|
15
|
+
]
|
16
|
+
|
17
|
+
def self.create_agent
|
18
|
+
Mechanize.new do |a|
|
19
|
+
a.user_agent = USER_AGENTS.shuffle.first
|
20
|
+
a.max_history = 1
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def self.random_sleep
|
25
|
+
sleep(rand(1..3))
|
26
|
+
end
|
27
|
+
|
28
|
+
def self.set_page_encoding(page)
|
29
|
+
page.encoding = 'gbk' if page.encoding.downcase == 'gb2312'
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,160 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require 'meiriyigua/crawl_client'
|
3
|
+
require 'meiriyigua/models'
|
4
|
+
|
5
|
+
module Meiriyigua
|
6
|
+
class DetailCrawl
|
7
|
+
include Meiriyigua::Models
|
8
|
+
|
9
|
+
def initialize(detail_urls)
|
10
|
+
@detail_urls = detail_urls
|
11
|
+
@agent = CrawlClient.create_agent
|
12
|
+
end
|
13
|
+
|
14
|
+
def run
|
15
|
+
while !@detail_urls.empty?
|
16
|
+
uri = URI(@detail_urls.pop)
|
17
|
+
handle_url(uri)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
def handle_url(uri)
|
22
|
+
|
23
|
+
if UrlRecord.exist_url?(uri.to_s)
|
24
|
+
#print "抓取详情页 #{uri.to_s} "
|
25
|
+
#puts "重复,跳过"
|
26
|
+
return
|
27
|
+
end
|
28
|
+
|
29
|
+
page = @agent.get(uri)
|
30
|
+
CrawlClient.set_page_encoding(page)
|
31
|
+
name = uri.host.to_s.split('.')[1]
|
32
|
+
|
33
|
+
url_record = UrlRecord.new
|
34
|
+
url_record.url = uri.to_s
|
35
|
+
url_record.detail_at = Time.now
|
36
|
+
|
37
|
+
page_record = PageRecord.new
|
38
|
+
url_record.page_record = page_record
|
39
|
+
|
40
|
+
page_record = send("handle_#{name}", page, page_record)
|
41
|
+
if page_record.nil?
|
42
|
+
print "抓取详情页 #{uri.to_s} "
|
43
|
+
puts "失败"
|
44
|
+
else
|
45
|
+
print "抓取详情页 #{uri.to_s} "
|
46
|
+
if url_record.save
|
47
|
+
puts "成功"
|
48
|
+
else
|
49
|
+
puts "保存失败"
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
CrawlClient.random_sleep
|
54
|
+
end
|
55
|
+
|
56
|
+
def handle_1234wg(page, page_record)
|
57
|
+
page_record.title = page.search('td[width="583"] > font > strong font').text.strip
|
58
|
+
return if page_record.title.empty?
|
59
|
+
page_record.category = page.search('body > table[background="/images/hgf-4.gif"] td[style="padding-left:6px;"] a:last-of-type').text
|
60
|
+
page_record.content = strip_content(page.search('td#intro'))
|
61
|
+
filename = page.search('td[valign="top"] > script:last-of-type').text.split(',')[1][6..-2]
|
62
|
+
page_record.downloads = "http://dx2down.bugwg.com:801/#{URI.escape filename}"
|
63
|
+
page_record
|
64
|
+
end
|
65
|
+
|
66
|
+
def handle_qh24(page, page_record)
|
67
|
+
page_record.title = page.search('//*[@id="sintro"]/h1/text()').text.strip
|
68
|
+
return if page_record.title.empty?
|
69
|
+
page_record.category = page.search('h2.classname > a:last-of-type').text
|
70
|
+
page_record.content = strip_content(page.search('div.cnt'))
|
71
|
+
page_record.downloads = join_downloads(page.search('div#intext dd a').collect{|a| a['href']})
|
72
|
+
page_record
|
73
|
+
end
|
74
|
+
|
75
|
+
def handle_nanawg(page, page_record)
|
76
|
+
page_record.title = page.search('div.right_tit').text.strip
|
77
|
+
return if page_record.title.empty?
|
78
|
+
page_record.category = page.search('div#index3 a:last-of-type').text
|
79
|
+
page_record.content = page.search('div.rightsum_text4').text
|
80
|
+
page_record.downloads = join_downloads(page.search('ul.ul2 a').collect{|a| a['href'] =~ /^http/ ? a['href'] : "http://www.nanawg.com#{a['href']}"})
|
81
|
+
page_record
|
82
|
+
end
|
83
|
+
|
84
|
+
def handle_ucbug(page, page_record)
|
85
|
+
page_record.title = page.search('div.spmain_1 a').text.strip
|
86
|
+
return if page_record.title.empty?
|
87
|
+
page_record.category = page.search('div.slhead_1 a:last-of-type').text
|
88
|
+
page_record.content = page.search('div.spmain_5').text
|
89
|
+
page_record.downloads = join_downloads(page.search('ul.ul_Address a').collect{|a| a['href']})
|
90
|
+
page_record
|
91
|
+
end
|
92
|
+
|
93
|
+
def handle_gg1z(page, page_record)
|
94
|
+
page_record.title = page.search('div.software-info > div.cp-top > h3').text.strip
|
95
|
+
return if page_record.title.empty?
|
96
|
+
page_record.category = page.search('div.nav-breadcrumb a:nth-last-of-type(2)').text
|
97
|
+
content = page.search('div.cp-main > div.cp-main')
|
98
|
+
content.search('font[color="red"]').remove
|
99
|
+
page_record.content = strip_content(content)
|
100
|
+
|
101
|
+
downloads = page.search('ul.download-list a').collect{|a| "http://www.gg1z.com#{a['href']}"}
|
102
|
+
downloads = [downloads.first, downloads.last].uniq
|
103
|
+
final_downloads = []
|
104
|
+
downloads.each do |down|
|
105
|
+
down_page = @agent.get(down, nil, page.uri.to_s)
|
106
|
+
CrawlClient.set_page_encoding(down_page)
|
107
|
+
final_downloads.concat( down_page.search('div.downarea a').collect{|a| a['href'] =~ /^http/ ? a['href'] : "http://www.gg1z.com#{a['href']}"} )
|
108
|
+
end
|
109
|
+
page_record.downloads = join_downloads(final_downloads)
|
110
|
+
page_record
|
111
|
+
end
|
112
|
+
|
113
|
+
def handle_dongdongwg(page, page_record)
|
114
|
+
page_record.title = page.search('//div[@class="pageMainArea"]/h1/text()').text.strip
|
115
|
+
return if page_record.title.empty?
|
116
|
+
page_record.category = page.search('span.current1 a:last-of-type').text
|
117
|
+
content = page.search('div#mainSoftIntro')
|
118
|
+
content.search('p:last-of-type').remove
|
119
|
+
page_record.content = strip_content(content)
|
120
|
+
page_record.downloads = join_downloads(page.search('ul.downlistbox a').collect{|a| a['href']})
|
121
|
+
page_record
|
122
|
+
end
|
123
|
+
|
124
|
+
def handle_uuuwg(page, page_record)
|
125
|
+
page_record.title = page.search('div.spmain_1').text.strip
|
126
|
+
return if page_record.title.empty?
|
127
|
+
page_record.category = page.search('div.slhead_1 a:last-of-type').text
|
128
|
+
page_record.content = strip_content(page.search('div.spmain_5'))
|
129
|
+
page_record.downloads = join_downloads(page.search('ul.spmain_3_2 > li:last-of-type a').collect{|a| a['href']})
|
130
|
+
page_record
|
131
|
+
end
|
132
|
+
|
133
|
+
def handle_xixiwg(page, page_record)
|
134
|
+
page_record.title = page.search('div.r2 h2').text.strip
|
135
|
+
return if page_record.title.empty?
|
136
|
+
page_record.category = page.search('div.location a:last-of-type').text
|
137
|
+
page_record.content = strip_content(page.search('div#intro'))
|
138
|
+
filename = page.search('div.xzk script:last-of-type').text.split(',')[1].strip[6..-3]
|
139
|
+
page_record.downloads = "http://dxdown1.xixiwg.com/#{URI.escape filename}"
|
140
|
+
page_record
|
141
|
+
end
|
142
|
+
|
143
|
+
def handle_xiaolinzi(page, page_record)
|
144
|
+
page_record.title = page.search('div.dlbt_wz').text.strip
|
145
|
+
return if page_record.title.empty?
|
146
|
+
page_record.category = page.search('div.head_dh a:last-of-type').text
|
147
|
+
page_record.content = strip_content(page.search('div#content_all'))
|
148
|
+
page_record.downloads = join_downloads(page.search('div.dl_link_bd a[target="_blank"]').collect{|a| a['href']})
|
149
|
+
page_record
|
150
|
+
end
|
151
|
+
|
152
|
+
def strip_content(content)
|
153
|
+
content.text
|
154
|
+
end
|
155
|
+
|
156
|
+
def join_downloads(downloads)
|
157
|
+
downloads.uniq.join('#!#')
|
158
|
+
end
|
159
|
+
end
|
160
|
+
end
|
@@ -0,0 +1,97 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require 'meiriyigua/crawl_client'
|
3
|
+
|
4
|
+
module Meiriyigua
|
5
|
+
class ListCrawl
|
6
|
+
attr_reader :detail_urls
|
7
|
+
|
8
|
+
def initialize
|
9
|
+
@list_urls = Queue.new
|
10
|
+
@detail_urls = Queue.new
|
11
|
+
@agent = CrawlClient.create_agent
|
12
|
+
|
13
|
+
init_url
|
14
|
+
end
|
15
|
+
|
16
|
+
def run
|
17
|
+
while !@list_urls.empty?
|
18
|
+
uri = URI(@list_urls.pop)
|
19
|
+
handle_url(uri)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
def handle_url(uri)
|
24
|
+
page = @agent.get(uri)
|
25
|
+
CrawlClient.set_page_encoding(page)
|
26
|
+
name = uri.host.to_s.split('.')[1]
|
27
|
+
urls = send("handle_#{name}", page)
|
28
|
+
if urls.empty?
|
29
|
+
print "抓取列表页 #{uri.to_s} "
|
30
|
+
puts "失败"
|
31
|
+
else
|
32
|
+
urls.each {|a| @detail_urls << a}
|
33
|
+
print "抓取列表页 #{uri.to_s} "
|
34
|
+
puts "成功"
|
35
|
+
end
|
36
|
+
CrawlClient.random_sleep
|
37
|
+
end
|
38
|
+
|
39
|
+
def handle_1234wg(page)
|
40
|
+
urls = page.search('td[width="470"] a[href^="/1234/"]')
|
41
|
+
urls.collect {|a| "http://www.1234wg.com#{a['href']}" }
|
42
|
+
end
|
43
|
+
|
44
|
+
def handle_qh24(page)
|
45
|
+
urls = page.search('div#downhot table a')
|
46
|
+
urls.collect{|a| "http://www.qh24.com#{a['href']}"}
|
47
|
+
end
|
48
|
+
|
49
|
+
def handle_nanawg(page)
|
50
|
+
urls = page.search('td[width="362"] a:last-of-type')
|
51
|
+
urls.collect{|a| "http://www.nanawg.com#{a['href']}"}
|
52
|
+
end
|
53
|
+
|
54
|
+
def handle_ucbug(page)
|
55
|
+
urls = page.search('li.slmain2_2_2 a')
|
56
|
+
urls.collect{|a| a['href']}
|
57
|
+
end
|
58
|
+
|
59
|
+
def handle_gg1z(page)
|
60
|
+
urls = page.search('span.app-name a')
|
61
|
+
urls.collect{|a| "http://www.gg1z.com#{a['href']}"}
|
62
|
+
end
|
63
|
+
|
64
|
+
def handle_dongdongwg(page)
|
65
|
+
urls = page.search('span.list_title > a')
|
66
|
+
urls.collect{|a| "http://www.dongdongwg.com#{a['href']}"}
|
67
|
+
end
|
68
|
+
|
69
|
+
def handle_uuuwg(page)
|
70
|
+
urls = page.search('table.main_table tr > td:nth-child(2) a')
|
71
|
+
urls.collect{|a| "http://www.uuuwg.com#{a['href']}"}
|
72
|
+
end
|
73
|
+
|
74
|
+
def handle_xixiwg(page)
|
75
|
+
urls = page.search('div.entry > h2 > a')
|
76
|
+
urls.collect{|a| "http://www.xixiwg.com#{a['href']}"}
|
77
|
+
end
|
78
|
+
|
79
|
+
def handle_xiaolinzi(page)
|
80
|
+
urls = page.search('td.rewid1 > a')
|
81
|
+
urls.collect{|a| "http://www.xiaolinzi.com#{a['href']}"}
|
82
|
+
end
|
83
|
+
|
84
|
+
private
|
85
|
+
def init_url
|
86
|
+
@list_urls << 'http://www.1234wg.com/new.html'
|
87
|
+
@list_urls << 'http://www.qh24.com/new.html'
|
88
|
+
@list_urls << 'http://www.nanawg.com/soft/html/newlist-1.html'
|
89
|
+
@list_urls << 'http://www.ucbug.com/new.html'
|
90
|
+
@list_urls << 'http://www.gg1z.com/soft/html/newlist-1.html'
|
91
|
+
@list_urls << 'http://www.dongdongwg.com/soft/html/newlist-1.html'
|
92
|
+
@list_urls << 'http://www.uuuwg.com/newlist.html'
|
93
|
+
@list_urls << 'http://www.xixiwg.com/new/'
|
94
|
+
@list_urls << 'http://www.xiaolinzi.com/update/'
|
95
|
+
end
|
96
|
+
end
|
97
|
+
end
|
@@ -0,0 +1,47 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require 'data_mapper'
|
3
|
+
|
4
|
+
#DataMapper::Logger.new($stdout, :debug)
|
5
|
+
DataMapper::Model.raise_on_save_failure = true
|
6
|
+
DataMapper.setup(:default, "sqlite://#{Dir.pwd}/data.db")
|
7
|
+
|
8
|
+
module Meiriyigua
|
9
|
+
module Models
|
10
|
+
class UrlRecord
|
11
|
+
include DataMapper::Resource
|
12
|
+
|
13
|
+
property :id, Serial
|
14
|
+
property :url, String, length: 1024
|
15
|
+
property :detail_at, DateTime
|
16
|
+
property :baidu_at, DateTime
|
17
|
+
property :publish_at, DateTime
|
18
|
+
property :created_at, DateTime
|
19
|
+
property :updated_at, DateTime
|
20
|
+
|
21
|
+
has 1, :page_record
|
22
|
+
|
23
|
+
def self.exist_url?(url)
|
24
|
+
self.count(url: url) > 0
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
class PageRecord
|
29
|
+
include DataMapper::Resource
|
30
|
+
|
31
|
+
property :id, Serial
|
32
|
+
property :title, String, length: 1024
|
33
|
+
property :category, String, length: 1024
|
34
|
+
property :content, Text
|
35
|
+
property :downloads, Text
|
36
|
+
property :baidu_intro, Text
|
37
|
+
property :created_at, DateTime
|
38
|
+
property :updated_at, DateTime
|
39
|
+
|
40
|
+
belongs_to :url_record
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
DataMapper.finalize
|
46
|
+
|
47
|
+
DataMapper.auto_upgrade!
|
@@ -0,0 +1,105 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require 'meiriyigua/models'
|
3
|
+
require 'meiriyigua/config'
|
4
|
+
require 'meiriyigua/crawl_client'
|
5
|
+
|
6
|
+
module Meiriyigua
|
7
|
+
class PostClient
|
8
|
+
include Meiriyigua::Models
|
9
|
+
|
10
|
+
ZHS = 0x4e00..0x9fff
|
11
|
+
|
12
|
+
attr_reader :category_ids
|
13
|
+
|
14
|
+
def initialize
|
15
|
+
@agent = CrawlClient.create_agent
|
16
|
+
@category_ids = {}
|
17
|
+
|
18
|
+
login
|
19
|
+
check_category
|
20
|
+
end
|
21
|
+
|
22
|
+
def run
|
23
|
+
today_count = UrlRecord.count(:publish_at.gte => Date.today)
|
24
|
+
|
25
|
+
if today_count >= Meiriyigua::Config.day_num
|
26
|
+
return
|
27
|
+
end
|
28
|
+
|
29
|
+
time_limit = Time.now - 60 * Meiriyigua::Config.post_time.to_i
|
30
|
+
UrlRecord.all(:detail_at.lte => time_limit, :baidu_at.not => nil, :publish_at => nil).each do |url_record|
|
31
|
+
today_count += 1
|
32
|
+
if today_count >= Meiriyigua::Config.day_num
|
33
|
+
return
|
34
|
+
end
|
35
|
+
|
36
|
+
page_record = url_record.page_record
|
37
|
+
if post_news(page_record, @category_ids[URI(url_record.url).host])
|
38
|
+
url_record.publish_at = Time.now
|
39
|
+
url_record.save
|
40
|
+
print "发布 #{url_record.url} "
|
41
|
+
puts "成功"
|
42
|
+
else
|
43
|
+
print "发布 #{url_record.url} "
|
44
|
+
puts "失败"
|
45
|
+
end
|
46
|
+
sleep 1
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
def login
|
51
|
+
page = @agent.get(Meiriyigua::Config.login_url)
|
52
|
+
login_form = page.form_with(name: 'login')
|
53
|
+
login_form.field_with(name: 'ad_name').value = Meiriyigua::Config.username
|
54
|
+
login_form.field_with(name: 'ad_pwd').value = Meiriyigua::Config.password
|
55
|
+
login_results = @agent.submit(login_form)
|
56
|
+
login_results.search('a[href="/admin/admin.php/Index/index"]').size > 0
|
57
|
+
end
|
58
|
+
|
59
|
+
def check_category
|
60
|
+
page = @agent.get "http://#{Meiriyigua::Config.site_host}/admin/admin.php/News/add"
|
61
|
+
options = page.search('select#news_type > option').collect{|o| [o.text.strip, o['value'].to_i]}
|
62
|
+
options = Hash[options]
|
63
|
+
Meiriyigua::Config.categories.each do |host, name|
|
64
|
+
unless options.keys.include?(name)
|
65
|
+
@category_ids[host] = options[name]
|
66
|
+
@agent.post("http://#{Meiriyigua::Config.site_host}/admin/admin.php/NewsType/add", news_type: name)
|
67
|
+
end
|
68
|
+
end
|
69
|
+
load_category_ids
|
70
|
+
end
|
71
|
+
|
72
|
+
def post_news(page_record, category_id)
|
73
|
+
post_params = {}
|
74
|
+
post_params['news_tit'] = "#{page_record.category}最新版辅助外挂免费下载 #{page_record.title}"
|
75
|
+
post_params['author'] = random_zh
|
76
|
+
post_params['click'] = rand(600..13000)
|
77
|
+
post_params['biaoqian'] = page_record.category
|
78
|
+
post_params['download_url'] = page_record.downloads.split('#!#')[0..1].join('|')
|
79
|
+
post_params['news_type'] = category_id
|
80
|
+
post_params['jianjie'] = page_record.content.to_s[0..16]
|
81
|
+
post_params['editorValue'] = "<pre>#{page_record.content} \r\n\r\n 提示一:\r\n#{page_record.baidu_intro}</pre>"
|
82
|
+
result_page = @agent.post("http://#{Meiriyigua::Config.site_host}/admin/admin.php/News/insert", post_params)
|
83
|
+
!result_page.search('script').text.index('/admin/admin.php/News/index').nil?
|
84
|
+
end
|
85
|
+
|
86
|
+
private
|
87
|
+
def random_zh
|
88
|
+
s = ""
|
89
|
+
rand(2..4).times do
|
90
|
+
s << rand(ZHS)
|
91
|
+
end
|
92
|
+
s
|
93
|
+
end
|
94
|
+
|
95
|
+
def load_category_ids
|
96
|
+
page = @agent.get "http://#{Meiriyigua::Config.site_host}/admin/admin.php/News/add"
|
97
|
+
options = page.search('select#news_type > option').collect{|o| [o.text.strip, o['value'].to_i]}
|
98
|
+
options = Hash[options]
|
99
|
+
Meiriyigua::Config.categories.each do |host, name|
|
100
|
+
@category_ids[host] = options[name]
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
end
|
105
|
+
end
|
data/lib/meiriyigua.rb
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require "meiriyigua/version"
|
3
|
+
require 'meiriyigua/config'
|
4
|
+
require "meiriyigua/list_crawl"
|
5
|
+
require "meiriyigua/detail_crawl"
|
6
|
+
require "meiriyigua/baidu_crawl"
|
7
|
+
require "meiriyigua/post_client"
|
8
|
+
|
9
|
+
module Meiriyigua
|
10
|
+
def run
|
11
|
+
while true
|
12
|
+
begin
|
13
|
+
|
14
|
+
threads = []
|
15
|
+
threads << Thread.new do
|
16
|
+
list_crawl = ListCrawl.new
|
17
|
+
list_crawl.run
|
18
|
+
detail_crawl = DetailCrawl.new(list_crawl.detail_urls)
|
19
|
+
detail_crawl.run
|
20
|
+
sleep(Meiriyigua::Config.update_time.to_i * 60)
|
21
|
+
end
|
22
|
+
threads << Thread.new do
|
23
|
+
baidu_crawl = BaiduCrawl.new
|
24
|
+
baidu_crawl.run
|
25
|
+
sleep(Meiriyigua::Config.update_time.to_i * 60)
|
26
|
+
end
|
27
|
+
threads << Thread.new do
|
28
|
+
post_client = PostClient.new
|
29
|
+
post_client.run
|
30
|
+
sleep(Meiriyigua::Config.post_time.to_i * 60)
|
31
|
+
end
|
32
|
+
threads.each { |thr| thr.join }
|
33
|
+
|
34
|
+
rescue
|
35
|
+
puts "出错了 #{$!.message}"
|
36
|
+
end
|
37
|
+
sleep 60*10
|
38
|
+
end
|
39
|
+
end
|
40
|
+
module_function :run
|
41
|
+
end
|
42
|
+
|
43
|
+
Meiriyigua.run
|
data/meiriyigua.gemspec
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'meiriyigua/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "meiriyigua"
|
8
|
+
spec.version = Meiriyigua::VERSION
|
9
|
+
spec.authors = ["mangege"]
|
10
|
+
spec.email = ["cxh116@126.com"]
|
11
|
+
spec.description = %q{nil}
|
12
|
+
spec.summary = %q{nil}
|
13
|
+
spec.homepage = "http://github.com/mangege"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_runtime_dependency "mechanize", '~> 2.7'
|
22
|
+
spec.add_runtime_dependency "sqlite3", '~> 1.3'
|
23
|
+
spec.add_runtime_dependency "data_mapper", '~> 1.2'
|
24
|
+
spec.add_runtime_dependency "dm-sqlite-adapter", '~> 1.2'
|
25
|
+
|
26
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
27
|
+
spec.add_development_dependency "rake"
|
28
|
+
end
|
data/set.yml.example
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
保留头:
|
2
|
+
勿删除: 0
|
3
|
+
|
4
|
+
基础:
|
5
|
+
提交地址: http://www.meiriyigua.com/admin/admin.php
|
6
|
+
用户名: admin
|
7
|
+
密码: admin888
|
8
|
+
编码: utf8
|
9
|
+
每天发布: 300
|
10
|
+
发布延时: 60
|
11
|
+
监控延时: 30
|
12
|
+
|
13
|
+
栏目:
|
14
|
+
www.1234wg.com: 1234外挂网
|
15
|
+
www.qh24.com: 艾艾游戏网
|
16
|
+
www.nanawg.com: 娜娜网
|
17
|
+
www.ucbug.com: ucbug游戏网
|
18
|
+
www.gg1z.com: 挂挂一族
|
19
|
+
www.dongdongwg.com: 东东游戏网
|
20
|
+
www.uuuwg.com: 西西游戏网
|
21
|
+
www.xixiwg.com: 西西外挂网
|
22
|
+
www.xiaolinzi.com: 小林子软件站
|
metadata
ADDED
@@ -0,0 +1,144 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: meiriyigua
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- mangege
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-04-07 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: mechanize
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '2.7'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '2.7'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: sqlite3
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.3'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.3'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: data_mapper
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.2'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.2'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: dm-sqlite-adapter
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.2'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.2'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: bundler
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ~>
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '1.3'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ~>
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '1.3'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: rake
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ! '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ! '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description: nil
|
98
|
+
email:
|
99
|
+
- cxh116@126.com
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- .gitignore
|
105
|
+
- Gemfile
|
106
|
+
- LICENSE.txt
|
107
|
+
- README.md
|
108
|
+
- Rakefile
|
109
|
+
- lib/meiriyigua.rb
|
110
|
+
- lib/meiriyigua/baidu_crawl.rb
|
111
|
+
- lib/meiriyigua/config.rb
|
112
|
+
- lib/meiriyigua/crawl_client.rb
|
113
|
+
- lib/meiriyigua/detail_crawl.rb
|
114
|
+
- lib/meiriyigua/list_crawl.rb
|
115
|
+
- lib/meiriyigua/models.rb
|
116
|
+
- lib/meiriyigua/post_client.rb
|
117
|
+
- lib/meiriyigua/version.rb
|
118
|
+
- meiriyigua.gemspec
|
119
|
+
- set.yml.example
|
120
|
+
homepage: http://github.com/mangege
|
121
|
+
licenses:
|
122
|
+
- MIT
|
123
|
+
metadata: {}
|
124
|
+
post_install_message:
|
125
|
+
rdoc_options: []
|
126
|
+
require_paths:
|
127
|
+
- lib
|
128
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
129
|
+
requirements:
|
130
|
+
- - ! '>='
|
131
|
+
- !ruby/object:Gem::Version
|
132
|
+
version: '0'
|
133
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
134
|
+
requirements:
|
135
|
+
- - ! '>='
|
136
|
+
- !ruby/object:Gem::Version
|
137
|
+
version: '0'
|
138
|
+
requirements: []
|
139
|
+
rubyforge_project:
|
140
|
+
rubygems_version: 2.2.2
|
141
|
+
signing_key:
|
142
|
+
specification_version: 4
|
143
|
+
summary: nil
|
144
|
+
test_files: []
|