baiduserp 2.3.5 → 2.3.7
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 +4 -4
- data/lib/baiduserp/analyser.rb +19 -6
- data/lib/baiduserp/version.rb +1 -1
- metadata +16 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 2886ad6a97fe01a9cc1ba3ab6f9893a7b37495d3
|
4
|
+
data.tar.gz: 3e78db82105ef932cf65253655fc49f01f2f7118
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 83192c563fb0ca280cbfccf647c52474bc0e4b286923e4d06060de574a146260476162b126cc98a006357928e8b4f2d96ab4607f5cef7fcf774427d21a244f56
|
7
|
+
data.tar.gz: d99d993c78e32fe16f66768c684cb441123250a27f774296e4dcf4189db1bc0b04ac87a7fc57b847ae20ee964e1bf2ce13b59063f0b0a763cf66979032e268e3
|
data/lib/baiduserp/analyser.rb
CHANGED
@@ -2,6 +2,7 @@ require 'sequel'
|
|
2
2
|
require 'csv'
|
3
3
|
require 'date'
|
4
4
|
require 'yaml'
|
5
|
+
require 'ruby-progressbar'
|
5
6
|
|
6
7
|
module Baiduserp
|
7
8
|
class Analyser
|
@@ -54,26 +55,36 @@ module Baiduserp
|
|
54
55
|
end
|
55
56
|
|
56
57
|
def search(date=Date.today)
|
58
|
+
p = ProgressBar.create(:title => "Search Keywords", :total => @keywords.all.count)
|
57
59
|
@keywords.each do |k|
|
58
|
-
|
59
|
-
|
60
|
+
if @htmls.where(:date => date, :keyword_id => k[:id]).count > 0
|
61
|
+
p.increment
|
62
|
+
next
|
63
|
+
end
|
64
|
+
p.log k.to_hash
|
60
65
|
html = Baiduserp.get_search_html(k[:term])
|
61
|
-
serp = Baiduserp.parse(html)
|
62
66
|
@htmls.find_or_create(:keyword_id => k[:id], :date => date) {|r| r.content = html}
|
63
|
-
|
67
|
+
p.increment
|
64
68
|
end
|
65
69
|
end
|
66
70
|
|
67
71
|
def generate_serps(date=Date.today)
|
68
|
-
@htmls.where(:date => date)
|
72
|
+
htmls = @htmls.where(:date => date)
|
73
|
+
p = ProgressBar.create(:title => "Generating SERPS", :total => htmls.count)
|
74
|
+
htmls.each do |html|
|
69
75
|
keyword_id = html[:keyword_id]
|
70
76
|
html = html[:content]
|
71
77
|
@serps.find_or_create(:date => date, :keyword_id => keyword_id) {|r| r.content = YAML.dump(Baiduserp.parse(html))}
|
78
|
+
|
79
|
+
p.log keyword_id
|
80
|
+
p.increment
|
72
81
|
end
|
73
82
|
end
|
74
83
|
|
75
84
|
def generate_weights(date=Date.today)
|
76
|
-
@serps.where(:date => date)
|
85
|
+
serps = @serps.where(:date => date)
|
86
|
+
p = ProgressBar.create(:title => "Generating Weights", :total => serps.count)
|
87
|
+
serps.where(:date => date).each do |s|
|
77
88
|
keyword_id = s[:keyword_id]
|
78
89
|
serp = YAML.load(s[:content])
|
79
90
|
|
@@ -100,6 +111,8 @@ module Baiduserp
|
|
100
111
|
r.normalized_weight = normalized_weight
|
101
112
|
end
|
102
113
|
end
|
114
|
+
p.log keyword_id
|
115
|
+
p.increment
|
103
116
|
end
|
104
117
|
end
|
105
118
|
|
data/lib/baiduserp/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: baiduserp
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 2.3.
|
4
|
+
version: 2.3.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- MingQian Zhang
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2013-12-
|
11
|
+
date: 2013-12-12 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -80,6 +80,20 @@ dependencies:
|
|
80
80
|
- - '>='
|
81
81
|
- !ruby/object:Gem::Version
|
82
82
|
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: ruby-progressbar
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
83
97
|
description: Parse Baidu SERP result page.
|
84
98
|
email:
|
85
99
|
- zmingqian@qq.com
|