baidu 1.2.5 → 1.2.7
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/baidu.rb +7 -6
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: fff1b4daafda243caeb45c9a0f61328fcf99339e
|
|
4
|
+
data.tar.gz: e01864f549e755132840dfb46ed48199c9d93f42
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 6bcd416445c07cabad3e68dd485b250af63a0d95dec654aacace1591bb02e9c0d51207cdfb810f05eac265d85407bbfb7a35a736ff3059251fa423c612777667
|
|
7
|
+
data.tar.gz: 4ee5fdcdcc2adc5d587521950d72afde0f5082ed0d90d01897e3dcf2e8886a4008a1eefeaef7d8ab466a764b92d2d90da9fca6f585cd409d7b78657e10dd015c
|
data/lib/baidu.rb
CHANGED
|
@@ -75,7 +75,8 @@ class QihooResult < SearchResult
|
|
|
75
75
|
def ranks
|
|
76
76
|
return @ranks unless @ranks.nil?
|
|
77
77
|
@ranks = Hash.new
|
|
78
|
-
id = (@pagenumber - 1) * 10
|
|
78
|
+
# id = (@pagenumber - 1) * 10
|
|
79
|
+
id = 0
|
|
79
80
|
@page.search('//li[@class="res-list"]').each do |li|
|
|
80
81
|
a = li.search("h3/a").first
|
|
81
82
|
url = li.search("cite")
|
|
@@ -85,7 +86,7 @@ class QihooResult < SearchResult
|
|
|
85
86
|
href = a['href']
|
|
86
87
|
url = url.first.text
|
|
87
88
|
host = Addressable::URI.parse(URI.encode("http://#{url}")).host
|
|
88
|
-
@ranks[id.to_s] = {'href'=>
|
|
89
|
+
@ranks[id.to_s] = {'href'=>a['href'],'text'=>text,'host'=>host}
|
|
89
90
|
end
|
|
90
91
|
@ranks
|
|
91
92
|
end
|
|
@@ -93,7 +94,7 @@ class QihooResult < SearchResult
|
|
|
93
94
|
id = 0
|
|
94
95
|
result = []
|
|
95
96
|
@page.search("//ul[@id='djbox']/li").each do |li|
|
|
96
|
-
id+=1
|
|
97
|
+
id += 1
|
|
97
98
|
title = li.search("a").first.text
|
|
98
99
|
href = li.search("cite").first.text.downcase
|
|
99
100
|
host = Addressable::URI.parse(URI.encode(href)).host
|
|
@@ -126,7 +127,7 @@ class QihooResult < SearchResult
|
|
|
126
127
|
next_href = next_href.first['href']
|
|
127
128
|
next_href = URI.join(@baseuri,next_href).to_s
|
|
128
129
|
# next_href = URI.join("http://#{@host}",next_href).to_s
|
|
129
|
-
next_page = HTTParty.get(next_href).
|
|
130
|
+
next_page = HTTParty.get(next_href).next
|
|
130
131
|
return QihooResult.new(next_page,next_href,@pagenumber+1)
|
|
131
132
|
#@page = MbaiduResult.new(Mechanize.new.click(@page.link_with(:text=>/下一页/))) unless @page.link_with(:text=>/下一页/).nil?
|
|
132
133
|
end
|
|
@@ -186,7 +187,7 @@ class MbaiduResult < SearchResult
|
|
|
186
187
|
id = nil
|
|
187
188
|
else
|
|
188
189
|
id = id.first.first.to_i
|
|
189
|
-
id = (@pagenumber-1)*10+id
|
|
190
|
+
# id = (@pagenumber-1)*10+id
|
|
190
191
|
end
|
|
191
192
|
=begin
|
|
192
193
|
result.children.each do |elem|
|
|
@@ -372,7 +373,7 @@ class BaiduResult < SearchResult
|
|
|
372
373
|
@ranks[id] = Hash.new
|
|
373
374
|
url = table.search("[@class=\"g\"]").first
|
|
374
375
|
url = url.text unless url.nil?
|
|
375
|
-
a = table.search("
|
|
376
|
+
a = table.search("h3").first
|
|
376
377
|
next if a.nil?
|
|
377
378
|
@ranks[id]['text'] = a.text
|
|
378
379
|
@ranks[id]['href'] = url #a.first['href'].sub('http://www.baidu.com/link?url=','').strip
|