baidu 0.2.2 → 0.2.3
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.
- data/lib/baidu.rb +11 -6
- metadata +2 -2
data/lib/baidu.rb
CHANGED
@@ -3,30 +3,33 @@ require 'mechanize'
|
|
3
3
|
class Baidu
|
4
4
|
def initialize(offset100=false)
|
5
5
|
@a = Mechanize.new {|agent| agent.user_agent_alias = 'Linux Mozilla'}
|
6
|
+
@a.max_history = 1
|
6
7
|
@perpage = 10
|
7
8
|
@perpage = 100 if offset100==true
|
8
9
|
@baseuri = "http://www.baidu.com/s?rn=#{@perpage}&wd="
|
9
10
|
end
|
10
11
|
def query(query)
|
12
|
+
query = "#{query}"
|
11
13
|
@uri = @baseuri+URI.encode(query.encode('GBK'))
|
12
14
|
@page = @a.get @uri
|
15
|
+
#File.open('/tmp/testpage','w'){|f|f.puts @page.body} if query=='1458 Italia'
|
13
16
|
self.clean
|
14
|
-
@number = self.
|
17
|
+
@number = self.how_many
|
15
18
|
@maxpage = (@number / @perpage.to_f).round
|
16
19
|
@maxpage =10 if @maxpage>10
|
17
20
|
@currpage =0
|
18
21
|
end
|
19
22
|
def how_many_pages(uri)
|
20
23
|
self.query("site:#{uri}")
|
21
|
-
return self.
|
24
|
+
return self.how_many
|
22
25
|
end
|
23
26
|
def how_many_links(uri)
|
24
27
|
self.query("domain:\"#{uri}\"")
|
25
|
-
return self.
|
28
|
+
return self.how_many
|
26
29
|
end
|
27
30
|
def how_many_pages_with(url,string)
|
28
31
|
self.query("site:#{url} inurl:#{string}")
|
29
|
-
return self.
|
32
|
+
return self.how_many
|
30
33
|
end
|
31
34
|
def rank(host)
|
32
35
|
@page.search("//table[@class=\"result\"]").each do |table|
|
@@ -39,7 +42,8 @@ class Baidu
|
|
39
42
|
end
|
40
43
|
return false
|
41
44
|
end
|
42
|
-
def
|
45
|
+
def how_many
|
46
|
+
return false if @page.search("//span[@class='nums']").first.nil?
|
43
47
|
return @page.search("//span[@class='nums']").first.content.gsub(/\D/,'').to_i
|
44
48
|
end
|
45
49
|
def next
|
@@ -50,7 +54,8 @@ class Baidu
|
|
50
54
|
return true
|
51
55
|
end
|
52
56
|
def clean
|
53
|
-
@page.body.
|
57
|
+
@page.body.force_encoding('GBK')
|
58
|
+
@page.body.encode!('UTF-8',:invalid => :replace, :undef => :replace, :replace => "")
|
54
59
|
@page.body.gsub! ("[\U0080-\U2C77]+") #mechanize will be confuzed without removing the few characters
|
55
60
|
end
|
56
61
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: baidu
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.3
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -39,7 +39,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
39
39
|
version: '0'
|
40
40
|
requirements: []
|
41
41
|
rubyforge_project:
|
42
|
-
rubygems_version: 1.8.
|
42
|
+
rubygems_version: 1.8.15
|
43
43
|
signing_key:
|
44
44
|
specification_version: 3
|
45
45
|
summary: to get data from www.baidu.com. this is built by a newbie, so please be careful
|