youtubesearchresultscraper 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +7 -0
- data/lib/youtube/searchresultscraper.rb +15 -9
- data/lib/youtube/searchresultscraper.rb~ +250 -0
- data/test/youtube_scraper_test.rb +3 -3
- data/test/youtube_scraper_test.rb~ +92 -0
- metadata +4 -2
data/CHANGELOG
CHANGED
@@ -5,3 +5,10 @@
|
|
5
5
|
Add rdoc.
|
6
6
|
Add each() method into YouTube::SearchResultScraper
|
7
7
|
|
8
|
+
0.0.3 2006-12-22
|
9
|
+
Add error check.
|
10
|
+
Add attribute for video_count, video_from, video_to
|
11
|
+
|
12
|
+
0.0.4 2007-02-01
|
13
|
+
Add error check for scraping of pagination.
|
14
|
+
Fix scraping rule for html markup change of youtube.
|
@@ -48,7 +48,7 @@ module Youtube #:nodoc:
|
|
48
48
|
# scraper.open
|
49
49
|
# scraper.scrape
|
50
50
|
# puts scraper.get_xml
|
51
|
-
#
|
51
|
+
#
|
52
52
|
# = More Information
|
53
53
|
# http://www.ark-web.jp/sandbox/wiki/184.html (japanese only)
|
54
54
|
#
|
@@ -64,7 +64,7 @@ module Youtube #:nodoc:
|
|
64
64
|
attr_reader :video_count
|
65
65
|
attr_reader :video_from
|
66
66
|
attr_reader :video_to
|
67
|
-
|
67
|
+
|
68
68
|
@@youtube_search_base_url = "http://www.youtube.com/results?search_query="
|
69
69
|
|
70
70
|
# Create Youtube::SearchResultScraper object specifying keyword and number of page.
|
@@ -123,7 +123,7 @@ module Youtube #:nodoc:
|
|
123
123
|
end
|
124
124
|
|
125
125
|
# Iterator for scraped videos.
|
126
|
-
def each
|
126
|
+
def each
|
127
127
|
@videos.each do |video|
|
128
128
|
yield video
|
129
129
|
end
|
@@ -131,7 +131,7 @@ module Youtube #:nodoc:
|
|
131
131
|
|
132
132
|
# Return videos information as XML Format.
|
133
133
|
def get_xml
|
134
|
-
xml = "<ut_response status=\"ok\">" +
|
134
|
+
xml = "<ut_response status=\"ok\">" +
|
135
135
|
"<video_count>" + @video_count.to_s + "</video_count>" +
|
136
136
|
"<video_list>\n"
|
137
137
|
each do |video|
|
@@ -199,23 +199,29 @@ module Youtube #:nodoc:
|
|
199
199
|
end
|
200
200
|
|
201
201
|
def scrape_result_header
|
202
|
-
@search_result.search("div[@id='sectionHeader']/div
|
202
|
+
@search_result.search("div[@id='sectionHeader']/div").inner_html
|
203
203
|
end
|
204
204
|
|
205
205
|
def scrape_video_count
|
206
|
-
scrape_result_header.sub(/.+of *(\d+)/m , '\1')
|
206
|
+
video_count = scrape_result_header.sub(/.+of *(\d+)/m , '\1')
|
207
|
+
raise "no video count" if video_count.empty?
|
208
|
+
video_count.to_i
|
207
209
|
end
|
208
210
|
|
209
211
|
def scrape_video_from
|
210
|
-
scrape_result_header.sub(/Results *(\d+)-.+/m, '\1')
|
212
|
+
video_from = scrape_result_header.sub(/Results *(\d+)-.+/m, '\1')
|
213
|
+
raise "no video from" if video_from.empty?
|
214
|
+
video_from.to_i
|
211
215
|
end
|
212
216
|
|
213
217
|
def scrape_video_to
|
214
|
-
scrape_result_header.sub(/Results.+-(\d+) *of.+/m, '\1')
|
218
|
+
video_to = scrape_result_header.sub(/Results.+-(\d+) *of.+/m, '\1')
|
219
|
+
raise "no video to" if video_to.empty?
|
220
|
+
video_to.to_i
|
215
221
|
end
|
216
222
|
|
217
223
|
def is_no_result
|
218
|
-
@
|
224
|
+
@html.include?('No Videos found')
|
219
225
|
end
|
220
226
|
|
221
227
|
def check_video video
|
@@ -0,0 +1,250 @@
|
|
1
|
+
#--
|
2
|
+
# Copyright (C) 2006 by in3c.org, ARK-Web co., ltd
|
3
|
+
#
|
4
|
+
# Permission is hereby granted, free of charge, to any person obtaining
|
5
|
+
# a copy of this software and associated documentation files (the
|
6
|
+
# "Software"), to deal in the Software without restriction, including
|
7
|
+
# without limitation the rights to use, copy, modify, merge, publish,
|
8
|
+
# distribute, sublicense, and/or sell copies of the Software, and to
|
9
|
+
# permit persons to whom the Software is furnished to do so, subject to
|
10
|
+
# the following conditions:
|
11
|
+
#
|
12
|
+
# The above copyright notice and this permission notice shall be
|
13
|
+
# included in all copies or substantial portions of the Software.
|
14
|
+
#
|
15
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
16
|
+
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
17
|
+
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
18
|
+
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
19
|
+
# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
20
|
+
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
21
|
+
# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
22
|
+
#++
|
23
|
+
# :main:Youtube::SearchResultScraper
|
24
|
+
# :title:Youtube::SearchResultScraper RDoc Documentation
|
25
|
+
|
26
|
+
require 'open-uri'
|
27
|
+
require 'cgi'
|
28
|
+
require 'rubygems'
|
29
|
+
require 'hpricot'
|
30
|
+
require 'youtube/video'
|
31
|
+
|
32
|
+
module Youtube #:nodoc:
|
33
|
+
|
34
|
+
# = Introduction
|
35
|
+
# Youtube::SearchResultScraper scrapes video information from search result page
|
36
|
+
# on http://www.youtube.com.
|
37
|
+
#
|
38
|
+
# You can get result as array or xml.
|
39
|
+
#
|
40
|
+
# XML format is same as YouTube Developer API
|
41
|
+
# (http://www.youtube.com/dev_api_ref?m=youtube.videos.list_by_tag).
|
42
|
+
#
|
43
|
+
# = Example
|
44
|
+
# require "rubygems"
|
45
|
+
# require "youtube/searchresultscraper"
|
46
|
+
#
|
47
|
+
# scraper = Youtube::SearchResultScraper.new(keyword, page)
|
48
|
+
# scraper.open
|
49
|
+
# scraper.scrape
|
50
|
+
# puts scraper.get_xml
|
51
|
+
#
|
52
|
+
# = More Information
|
53
|
+
# http://www.ark-web.jp/sandbox/wiki/184.html (japanese only)
|
54
|
+
#
|
55
|
+
# Author:: Yuki SHIDA <shida@in3c.org>
|
56
|
+
# Author:: Konuma Akio <konuma@ark-web.jp>
|
57
|
+
# Version:: 0.0.3
|
58
|
+
# License:: MIT license
|
59
|
+
|
60
|
+
class SearchResultScraper
|
61
|
+
|
62
|
+
attr_accessor :keyword
|
63
|
+
attr_accessor :page
|
64
|
+
attr_reader :video_count
|
65
|
+
attr_reader :video_from
|
66
|
+
attr_reader :video_to
|
67
|
+
|
68
|
+
@@youtube_search_base_url = "http://www.youtube.com/results?search_query="
|
69
|
+
|
70
|
+
# Create Youtube::SearchResultScraper object specifying keyword and number of page.
|
71
|
+
#
|
72
|
+
# You cannot specify number of videos per page.
|
73
|
+
# Always, the number of videos is 20 per page.
|
74
|
+
#
|
75
|
+
# * keyword - specify keyword that you want to search on YouTube.
|
76
|
+
# You must specify keyword encoded by UTF-8.
|
77
|
+
# * page - specify number of page
|
78
|
+
|
79
|
+
def initialize keyword, page=nil
|
80
|
+
@keyword = keyword
|
81
|
+
@page = page if not page == nil
|
82
|
+
end
|
83
|
+
|
84
|
+
# Get search result from youtube by specified keyword.
|
85
|
+
def open
|
86
|
+
url = @@youtube_search_base_url + CGI.escape(@keyword)
|
87
|
+
url += "&page=#{@page}" if not @page == nil
|
88
|
+
@html = Kernel.open(url).read
|
89
|
+
replace_document_write_javascript
|
90
|
+
@search_result = Hpricot.parse(@html)
|
91
|
+
end
|
92
|
+
|
93
|
+
# Scrape video information from search result html.
|
94
|
+
def scrape
|
95
|
+
@videos = []
|
96
|
+
|
97
|
+
@search_result.search("//div[@class='vEntry']").each do |video_html|
|
98
|
+
video = Youtube::Video.new
|
99
|
+
video.id = scrape_id(video_html)
|
100
|
+
video.author = scrape_author(video_html)
|
101
|
+
video.title = scrape_title(video_html)
|
102
|
+
video.length_seconds = scrape_length_seconds(video_html)
|
103
|
+
video.rating_avg = scrape_rating_avg(video_html)
|
104
|
+
video.rating_count = scrape_rating_count(video_html)
|
105
|
+
video.description = scrape_description(video_html)
|
106
|
+
video.view_count = scrape_view_count(video_html)
|
107
|
+
video.thumbnail_url = scrape_thumbnail_url(video_html)
|
108
|
+
video.tags = scrape_tags(video_html)
|
109
|
+
video.url = scrape_url(video_html)
|
110
|
+
|
111
|
+
check_video video
|
112
|
+
|
113
|
+
@videos << video
|
114
|
+
end
|
115
|
+
|
116
|
+
@video_count = scrape_video_count
|
117
|
+
@video_from = scrape_video_from
|
118
|
+
@video_to = scrape_video_to
|
119
|
+
raise "no video count" if @video_count == nil
|
120
|
+
raise "no video from" if @video_from == nil
|
121
|
+
raise "no video to" if @video_to == nil
|
122
|
+
|
123
|
+
raise "scraping error" if (is_no_result != @videos.empty?)
|
124
|
+
|
125
|
+
@videos
|
126
|
+
end
|
127
|
+
|
128
|
+
# Iterator for scraped videos.
|
129
|
+
def each
|
130
|
+
@videos.each do |video|
|
131
|
+
yield video
|
132
|
+
end
|
133
|
+
end
|
134
|
+
|
135
|
+
# Return videos information as XML Format.
|
136
|
+
def get_xml
|
137
|
+
xml = "<ut_response status=\"ok\">" +
|
138
|
+
"<video_count>" + @video_count.to_s + "</video_count>" +
|
139
|
+
"<video_list>\n"
|
140
|
+
each do |video|
|
141
|
+
xml += video.to_xml
|
142
|
+
end
|
143
|
+
xml += "</video_list></ut_response>"
|
144
|
+
end
|
145
|
+
|
146
|
+
private
|
147
|
+
|
148
|
+
def replace_document_write_javascript
|
149
|
+
@html.gsub!(%r{<script language="javascript" type="text/javascript">.*?document.write\('(.*?)'\).*?</script>}m, '\1')
|
150
|
+
end
|
151
|
+
|
152
|
+
def scrape_id video_html
|
153
|
+
scrape_thumbnail_url(video_html).sub(%r{.*/([^/]+)/[^/]+.jpg}, '\1')
|
154
|
+
end
|
155
|
+
|
156
|
+
def scrape_author video_html
|
157
|
+
video_html.search("div[@class='vfacets']").inner_html.sub(/.*From:<\/span> <a.*?>(.*?)<\/a>.*/m, '\1')
|
158
|
+
end
|
159
|
+
|
160
|
+
def scrape_title video_html
|
161
|
+
video_html.search("div[@class='vtitle']/a").inner_html
|
162
|
+
end
|
163
|
+
|
164
|
+
def scrape_length_seconds video_html
|
165
|
+
length_seconds = video_html.search("span[@class='runtime']").inner_html
|
166
|
+
length_seconds =~ /(\d\d):(\d\d)/
|
167
|
+
$1.to_i * 60 + $2.to_i
|
168
|
+
end
|
169
|
+
|
170
|
+
def scrape_rating_avg video_html
|
171
|
+
video_html.search("img[@src='/img/star_sm.gif']").size +
|
172
|
+
video_html.search("img[@src='/img/star_sm_half.gif']").size * 0.5
|
173
|
+
end
|
174
|
+
|
175
|
+
def scrape_rating_count video_html
|
176
|
+
video_html.search("div[@class='rating']").inner_html.sub(/(\d+) rating/, '\1').to_i
|
177
|
+
end
|
178
|
+
|
179
|
+
def scrape_description video_html
|
180
|
+
description = video_html.search("div[@class='vdesc']/span").inner_html.sub(/^\n\t(.*?)\n\t$/m, '\1')
|
181
|
+
end
|
182
|
+
|
183
|
+
def scrape_view_count video_html
|
184
|
+
video_html.search("div[@class='vfacets']").inner_html.sub(/.*Views:<\/span> (\d+).*/m, '\1').to_i
|
185
|
+
end
|
186
|
+
|
187
|
+
def scrape_tags video_html
|
188
|
+
tags = []
|
189
|
+
video_html.search("div[@class='vtagValue']/a").each do |tag|
|
190
|
+
tags << tag.inner_html
|
191
|
+
end
|
192
|
+
tags.join(" ")
|
193
|
+
end
|
194
|
+
|
195
|
+
def scrape_thumbnail_url video_html
|
196
|
+
video_html.search("img[@class='vimg120']").to_html.sub(/.*src="(.*?)".*/, '\1')
|
197
|
+
end
|
198
|
+
|
199
|
+
def scrape_url video_html
|
200
|
+
"http://www.youtube.com" +
|
201
|
+
video_html.search("div[@class='vtitle']/a").to_html.sub(/.*href="(.*?)".*/m, '\1')
|
202
|
+
end
|
203
|
+
|
204
|
+
def scrape_result_header
|
205
|
+
@search_result.search("div[@id='sectionHeader']/div[@class='my']").inner_html
|
206
|
+
end
|
207
|
+
|
208
|
+
def scrape_video_count
|
209
|
+
scrape_result_header.sub(/.+of *(\d+)/m , '\1').to_i
|
210
|
+
end
|
211
|
+
|
212
|
+
def scrape_video_from
|
213
|
+
scrape_result_header.sub(/Results *(\d+)-.+/m, '\1').to_i
|
214
|
+
end
|
215
|
+
|
216
|
+
def scrape_video_to
|
217
|
+
scrape_result_header.sub(/Results.+-(\d+) *of.+/m, '\1').to_i
|
218
|
+
end
|
219
|
+
|
220
|
+
def is_no_result
|
221
|
+
@search_result.search("div[@class='body']").inner_html.include?('No Videos found')
|
222
|
+
end
|
223
|
+
|
224
|
+
def check_video video
|
225
|
+
errors = []
|
226
|
+
|
227
|
+
errors << "author" if video.author.empty?
|
228
|
+
errors << "id" if video.id.empty?
|
229
|
+
errors << "title" if video.title.empty?
|
230
|
+
errors << "length_seconds" if video.length_seconds.to_s.empty?
|
231
|
+
errors << "rating_avg" if video.rating_avg.to_s.empty?
|
232
|
+
errors << "rating_count" if video.rating_count.to_s.empty?
|
233
|
+
errors << "description" if video.description.empty?
|
234
|
+
errors << "view_count" if video.view_count.to_s.empty?
|
235
|
+
errors << "tags" if video.tags.empty?
|
236
|
+
errors << "url" if video.url.empty?
|
237
|
+
errors << "thumbnail_url" if video.thumbnail_url.empty?
|
238
|
+
|
239
|
+
unless errors.empty? then
|
240
|
+
error_msg = "scraping error occurred.\n"
|
241
|
+
errors.each do |error|
|
242
|
+
error_msg << error + " is not setted.\n"
|
243
|
+
end
|
244
|
+
raise error_msg
|
245
|
+
end
|
246
|
+
end
|
247
|
+
|
248
|
+
end
|
249
|
+
|
250
|
+
end
|
@@ -1,13 +1,13 @@
|
|
1
1
|
#!/usr/bin/ruby
|
2
2
|
|
3
|
-
require
|
4
|
-
|
3
|
+
require 'test/unit'
|
4
|
+
|
5
5
|
|
6
6
|
require "rubygems"
|
7
7
|
require 'hpricot'
|
8
8
|
require "youtube/searchresultscraper"
|
9
9
|
|
10
|
-
class SearchResultScraperTest <
|
10
|
+
class SearchResultScraperTest < Test::Unit::TestCase
|
11
11
|
|
12
12
|
def test_scrape
|
13
13
|
|
@@ -0,0 +1,92 @@
|
|
1
|
+
#!/usr/bin/ruby
|
2
|
+
|
3
|
+
#require "runit/testcase"
|
4
|
+
#require "runit/cui/testrunner"
|
5
|
+
require 'test/unit'
|
6
|
+
|
7
|
+
|
8
|
+
require "rubygems"
|
9
|
+
require 'hpricot'
|
10
|
+
require "youtube/searchresultscraper"
|
11
|
+
|
12
|
+
class SearchResultScraperTest < Test::Unit::TestCase
|
13
|
+
#class SearchResultScraperTest < RUNIT::TestCase
|
14
|
+
|
15
|
+
def test_scrape
|
16
|
+
|
17
|
+
#
|
18
|
+
#�����
|
19
|
+
#
|
20
|
+
#������̤�����
|
21
|
+
open_and_scrape("http://www.youtube.com/results?search_query=", "doraemon", 2)
|
22
|
+
#������̤��ʤ�
|
23
|
+
open_and_scrape("http://www.youtube.com/results?search_query=", "aeudyr jahafudfhadf ahf", 2)
|
24
|
+
|
25
|
+
#
|
26
|
+
#�۾��
|
27
|
+
#
|
28
|
+
#������̤����뤬��Not Found��������
|
29
|
+
begin
|
30
|
+
open_local_file_and_scrape("html/dataY_noMsgY.htm")
|
31
|
+
assert_fail("������٤����顼��ȯ�����Ƥ��ʤ�")
|
32
|
+
rescue RuntimeError =>e
|
33
|
+
#puts e
|
34
|
+
end
|
35
|
+
#������̤��ʤ���Not Found��ʤ����
|
36
|
+
begin
|
37
|
+
open_local_file_and_scrape("html/dataN_noMsgN.htm")
|
38
|
+
assert_fail("������٤����顼��ȯ�����Ƥ��ʤ�")
|
39
|
+
rescue RuntimeError
|
40
|
+
#puts e
|
41
|
+
end
|
42
|
+
|
43
|
+
#�����ι��ܤ��������Ǥ��Ƥ��ʤ����
|
44
|
+
begin
|
45
|
+
open_local_file_and_scrape("html/scraping_error.html")
|
46
|
+
assert_fail("������٤����顼��ȯ�����Ƥ��ʤ�")
|
47
|
+
rescue RuntimeError => e
|
48
|
+
# puts e
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
def test_scrape_video_count
|
53
|
+
|
54
|
+
scraper = open_and_scrape("http://www.youtube.com/results?search_query=", "doraemon", 2)
|
55
|
+
puts scraper.video_count
|
56
|
+
assert( scraper.video_count > 0 )
|
57
|
+
|
58
|
+
scraper = open_and_scrape("http://www.youtube.com/results?search_query=", "doraemonifdadfa", 2)
|
59
|
+
puts scraper.video_count
|
60
|
+
assert( scraper.video_count == 0 )
|
61
|
+
end
|
62
|
+
|
63
|
+
def open_and_scrape url, keyword=nil, page=nil
|
64
|
+
scraper = MySearchResultScraper.new(url, keyword, page)
|
65
|
+
scraper.open
|
66
|
+
scraper.scrape
|
67
|
+
scraper
|
68
|
+
end
|
69
|
+
|
70
|
+
def open_local_file_and_scrape url
|
71
|
+
scraper = MySearchResultScraper.new(url)
|
72
|
+
scraper.open_local_file
|
73
|
+
scraper.scrape
|
74
|
+
end
|
75
|
+
|
76
|
+
end
|
77
|
+
|
78
|
+
class MySearchResultScraper < Youtube::SearchResultScraper
|
79
|
+
@@youtube_search_base_url = "http://www.youtube.com/results?search_query="
|
80
|
+
|
81
|
+
def initialize url, keyword=nil, page=nil
|
82
|
+
@@youtube_search_base_url = url
|
83
|
+
@keyword = keyword
|
84
|
+
@page = page if not page == nil
|
85
|
+
end
|
86
|
+
|
87
|
+
def open_local_file
|
88
|
+
@html = Kernel.open(@@youtube_search_base_url).read
|
89
|
+
replace_document_write_javascript
|
90
|
+
@search_result = Hpricot.parse(@html)
|
91
|
+
end
|
92
|
+
end
|
metadata
CHANGED
@@ -3,8 +3,8 @@ rubygems_version: 0.9.0
|
|
3
3
|
specification_version: 1
|
4
4
|
name: youtubesearchresultscraper
|
5
5
|
version: !ruby/object:Gem::Version
|
6
|
-
version: 0.0.
|
7
|
-
date:
|
6
|
+
version: 0.0.4
|
7
|
+
date: 2007-02-01 00:00:00 +09:00
|
8
8
|
summary: This gem provide function to scrape html of search result on youtube
|
9
9
|
require_paths:
|
10
10
|
- lib
|
@@ -30,10 +30,12 @@ authors:
|
|
30
30
|
- Yuki SHIDA
|
31
31
|
files:
|
32
32
|
- lib/youtube
|
33
|
+
- lib/youtube/searchresultscraper.rb~
|
33
34
|
- lib/youtube/video.rb
|
34
35
|
- lib/youtube/searchresultscraper.rb
|
35
36
|
- test/youtube_scraper_test.rb
|
36
37
|
- test/html
|
38
|
+
- test/youtube_scraper_test.rb~
|
37
39
|
- test/html/scraping_error.html
|
38
40
|
- test/html/dataY_noMsgY.htm
|
39
41
|
- test/html/dataN_noMsgN.htm
|