Class: Rspider::HTMLDocument

Inherits:
Hash
  • Object
show all
Defined in:
lib/rspider/Document.rb

Instance Method Summary collapse

Instance Method Details

#get_head_data(html) ⇒ Object

得到head区的内容



17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
 
# File 'lib/rspider/Document.rb', line 17

def get_head_data(html)
	r=Regexp.compile('<head[^>]*>(.*?)<\/head>',Regexp::IGNORECASE|Regexp::MULTILINE)
	m=html.scan(r)
	return nil if m.nil?
	return nil if m[0].nil?
	head={}
	head[:title]=""
	head[:keywords]=""
	head[:robots]=""
	head[:description]=""
	head[:nofollow]=false
	head[:noindex]=false
	head[:base]=""

	
	h=m[0][0]
	begin
		r_robots=/<meta +name *=[\"']?robots[\"']? *content=[\"']?([^<>'\"]+)[\"']?/im
		robots=h.scan(r_robots)[0][0]
		head[:robots]=robots
	rescue
	end	
	begin
		r_desc=/<meta +name *=[\"']?description[\"']? *content=[\"']?([^<>'\"]+)[\"']?/im
		head[:description]=h.scan(r_desc)[0][0]
	rescue
	end	
	begin
		r_keys=/<meta +name *=[\"']?keywords[\"']? *content=[\"']?([^<>'\"]+)[\"']?/im
		head[:keywords]=h.scan(r_keys)[0][0]
	rescue
	end

	begin
		r_charset=/<meta +http\-equiv*=[\"']?Content-Type[\"']? *content=[\"']?([^<>'\"]+)[\"']?/im
		head[:charset]=h.scan(r_charset)[0][0].split("=").pop
	rescue
	end

	begin
		r_base=/<base +href *= *[\"']?([^<>'\"]+)[\"']?/im
		head[:base]=h.scan(r_base)[0][0]
	rescue
	end
	begin
		r_title=/<title *>(.*?)<\/title*>/im
		head[:title]=h.scan(r_title)[0][0].gsub("\n","")
	rescue
	end

	begin
		archives=[]
		r_archives=/<link +rel*=[\"']?archives[\"']? *[^\>]+href=[\"']?([^<>'\"]+)[\"']?/im
		h.scan(r_archives).each{ |l|
			archives.push l[0]
		}
		head[:archives]=archives
	rescue
	end
	begin
		links=[]
		r_alternates=/<link +rel*=[\"']?alternate[\"']? *[^\>]+href=[\"']?([^<>'\"]+)[\"']?/im
		h.scan(r_alternates).each{ |l|
			links.push l[0]
		}
		head[:rss_links]=links
	rescue
	end
	robots.downcase.split(",").each{ |j|
		head[:noindex]=true if j=="noindex"
		head[:nofollow]=true if j=="nofollow"
	}	unless robots.nil?
	head
end

#get_headlines(html) ⇒ Object

得到头条之类的大纲



6
7
8
9
10
11
12
13
14
15
 
# File 'lib/rspider/Document.rb', line 6

def get_headlines(html)
	r=Regexp.compile('<h[0-9][^>]*>(.*?)<\/h[0-9]>',Regexp::IGNORECASE|Regexp::MULTILINE)
	lines=[]
	ms=html.scan(r)
	return nil if ms.nil?
	ms.each{|m|
		lines.push m[0]	
	}
	lines.join("\n")
end