baidu 0.2.1 → 0.2.2
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.
- data/lib/baidu.rb +11 -8
- metadata +1 -1
data/lib/baidu.rb
CHANGED
@@ -8,22 +8,25 @@ class Baidu
|
|
8
8
|
@baseuri = "http://www.baidu.com/s?rn=#{@perpage}&wd="
|
9
9
|
end
|
10
10
|
def query(query)
|
11
|
-
@uri = @baseuri+URI.encode(
|
11
|
+
@uri = @baseuri+URI.encode(query.encode('GBK'))
|
12
12
|
@page = @a.get @uri
|
13
13
|
self.clean
|
14
|
-
@number = number
|
14
|
+
@number = self.number
|
15
15
|
@maxpage = (@number / @perpage.to_f).round
|
16
16
|
@maxpage =10 if @maxpage>10
|
17
17
|
@currpage =0
|
18
18
|
end
|
19
|
-
def how_many_pages(
|
20
|
-
self.query("site:#{
|
19
|
+
def how_many_pages(uri)
|
20
|
+
self.query("site:#{uri}")
|
21
|
+
return self.number
|
21
22
|
end
|
22
|
-
def how_many_links
|
23
|
-
self.query("domain:\"#{
|
23
|
+
def how_many_links(uri)
|
24
|
+
self.query("domain:\"#{uri}\"")
|
25
|
+
return self.number
|
24
26
|
end
|
25
27
|
def how_many_pages_with(url,string)
|
26
28
|
self.query("site:#{url} inurl:#{string}")
|
29
|
+
return self.number
|
27
30
|
end
|
28
31
|
def rank(host)
|
29
32
|
@page.search("//table[@class=\"result\"]").each do |table|
|
@@ -47,7 +50,7 @@ class Baidu
|
|
47
50
|
return true
|
48
51
|
end
|
49
52
|
def clean
|
50
|
-
@page.body
|
51
|
-
@page.body.gsub! ("[\U0080-\U2C77]+"
|
53
|
+
@page.body.encode!('UTF-8','GBK')
|
54
|
+
@page.body.gsub! ("[\U0080-\U2C77]+") #mechanize will be confuzed without removing the few characters
|
52
55
|
end
|
53
56
|
end
|