Class: GooglePageRank

Inherits:
Object
  • Object
show all
Defined in:
lib/googlepagerank.rb

Constant Summary collapse

M =

modulo for unsigned int 32bit(4byte)

0x100000000

Class Method Summary collapse

Class Method Details

.get(url = "http://sample/index.html", port = 80, proxy = nil, proxy_port = nil) ⇒ Object

Calculates the PageRank for the given url New algorithm version (16 july 2007)

:call-seq: GooglePageRank.get(“url”,,[proxy_url],) -> Fixnum

If an error ocurrs with the connection or the domain isn’t indexed returns -1

Parameters

url<String>
port<Fixnum>
proxy<String>
proxy_port<Fixnum>

Returns

Fixnum

The PageRank for the given url.

Examples

GooglePageRank.get("www.mabishu.com") # => 4
GooglePageRank.get("www.mabishu.com", 80) # => 4
GooglePageRank.get("www.mabishu.com", 80, "http://proxy.example.com", 8080) # => 4



72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
 
# File 'lib/googlepagerank.rb', line 72

def self.get(url="http://sample/index.html",port=80,proxy=nil,proxy_port=nil)
	# get Google PageRank
	# 2007.07.10
	ch = checkSum(url);
	# printf("CheckSUM: 6%u\n", ch);
	###### format changed
	#g_path=sprintf("/search?client=navclient-auto&failedip=216.239.51.102;821&ch=6%u&q=info:%s", ch, url);
	g_path=sprintf("/search?client=navclient-auto&features=Rank&failedip=216.239.51.102;821&q=info:%s&ch=6%u", url, ch);
	p="" # rank
	# printf("%s\n",g_path)
	# http://www.google.co.jp/search?client=navclient-auto&ch=63055969557&features=Rank&q=info:http://www.hyperposition.com/se3blog/
	# http://www.google.co.jp/search?client=navclient-auto&features=Rank&q=info:http://www.hyperposition.com/&ch=6768349016
	g_server="toolbarqueries.google.com"  # toolbarqueries.google.co.jp
	Net::HTTP::new(g_server, port, proxy, proxy_port).get(g_path){|line|
		# printf("%s\n", line)
		###### format changed
		pos=line.index("Rank_1:1:") # format: Rank_1:1:4
		if( pos != nil) then p=(line[pos+9,2]).to_i; break; end;
	}
	if (p.size>0) then return p.to_i; else return -1; end
end

.get0(url = "http://sample/index.html", port = 80, proxy = nil, proxy_port = nil) ⇒ Object

Calculates the PageRank for the given url ATENTION: Old version, use the GooglePageRak.get() instead

:call-seq: GooglePageRank.get0(“url”,,[proxy_url],) -> Fixnum

If an error ocurrs with the connection or the domain isn’t indexed returns -1

Parameters

url<String>
port<Fixnum>
proxy<String>
proxy_port<Fixnum>

Returns

Fixnum

The PageRank for the given url.

Examples

GooglePageRank.get0("www.mabishu.com") # => 4
GooglePageRank.get0("www.mabishu.com", 80) # => 4
GooglePageRank.get0("www.mabishu.com", 80, "http://proxy.example.com", 8080) # => 4



29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
 
# File 'lib/googlepagerank.rb', line 29

def self.get0(url="http://sample/index.html",port=80,proxy=nil,proxy_port=nil)
	# get Google PageRank
	# old version
	ch = checkSum(url);
	# printf("CheckSUM: 6%u\n", ch);
	g_path=sprintf("/search?client=navclient-auto&failedip=216.239.51.102;821&ch=6%u&q=info:%s", ch, url);
	p="" # rank
	##
	printf("%s\n",g_path)
	# http://www.google.co.jp/search?client=navclient-auto&ch=63055969557&features=Rank&q=info:http://www.hyperposition.com/se3blog/
	# http://www.google.co.jp/search?client=navclient-auto&features=Rank&q=info:http://www.hyperposition.com/&ch=6768349016
	g_server="toolbarqueries.google.com"
	# toolbarqueries.google.co.jp
	#g_server="www.google.co.jp"
	Net::HTTP::new(g_server, port, proxy, proxy_port).get(g_path){|line|
		printf("%s\n", line)
		pos=line.index("<RK>") # format: <RK>(rank)</RK>
		if( pos != nil) then p=(line[pos+4,2]).to_i; break; end;
	}
	if (p.size>0) then return p.to_i; else return -1; end
end