youtubescraper 0.0.7 → 0.0.8
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 +1 -2
- metadata +1 -2
- data/lib/youtube/searchresultscraper.rb~ +0 -263
data/CHANGELOG
CHANGED
@@ -174,7 +174,7 @@ module Youtube #:nodoc:
|
|
174
174
|
end
|
175
175
|
|
176
176
|
def scrape_description video_html
|
177
|
-
description = video_html.search("div[@class='vdesc']/span").inner_html.sub(/^\
|
177
|
+
description = video_html.search("div[@class='vdesc']/span").inner_html.sub(/^\s*(.*?)\s*$/m, '\1')
|
178
178
|
end
|
179
179
|
|
180
180
|
def scrape_view_count video_html
|
@@ -243,7 +243,6 @@ module Youtube #:nodoc:
|
|
243
243
|
errors << "length_seconds" if video.length_seconds.to_s.empty?
|
244
244
|
errors << "rating_avg" if video.rating_avg.to_s.empty?
|
245
245
|
errors << "rating_count" if video.rating_count.to_s.empty?
|
246
|
-
errors << "description" if video.description.empty?
|
247
246
|
errors << "view_count" if video.view_count.to_s.empty?
|
248
247
|
errors << "tags" if video.tags.empty?
|
249
248
|
errors << "url" if video.url.empty?
|
metadata
CHANGED
@@ -3,7 +3,7 @@ rubygems_version: 0.9.0
|
|
3
3
|
specification_version: 1
|
4
4
|
name: youtubescraper
|
5
5
|
version: !ruby/object:Gem::Version
|
6
|
-
version: 0.0.
|
6
|
+
version: 0.0.8
|
7
7
|
date: 2007-03-29 00:00:00 +09:00
|
8
8
|
summary: This gem provide function to scrape html of search result on youtube
|
9
9
|
require_paths:
|
@@ -31,7 +31,6 @@ authors:
|
|
31
31
|
files:
|
32
32
|
- lib/youtube
|
33
33
|
- lib/youtube/browsescraper.rb
|
34
|
-
- lib/youtube/searchresultscraper.rb~
|
35
34
|
- lib/youtube/video.rb
|
36
35
|
- lib/youtube/searchresultscraper.rb
|
37
36
|
- test/youtube_scraper_test.rb
|
@@ -1,263 +0,0 @@
|
|
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
|
-
|
120
|
-
raise "scraping error" if (is_no_result != @videos.empty?)
|
121
|
-
|
122
|
-
@videos
|
123
|
-
end
|
124
|
-
|
125
|
-
# Iterator for scraped videos.
|
126
|
-
def each
|
127
|
-
@videos.each do |video|
|
128
|
-
yield video
|
129
|
-
end
|
130
|
-
end
|
131
|
-
|
132
|
-
# Return videos information as XML Format.
|
133
|
-
def get_xml
|
134
|
-
xml = "<ut_response status=\"ok\">" +
|
135
|
-
"<video_count>" + @video_count.to_s + "</video_count>" +
|
136
|
-
"<video_list>\n"
|
137
|
-
each do |video|
|
138
|
-
xml += video.to_xml
|
139
|
-
end
|
140
|
-
xml += "</video_list></ut_response>"
|
141
|
-
end
|
142
|
-
|
143
|
-
private
|
144
|
-
|
145
|
-
def replace_document_write_javascript
|
146
|
-
@html.gsub!(%r{<script language="javascript" type="text/javascript">.*?document.write\('(.*?)'\).*?</script>}m, '\1')
|
147
|
-
end
|
148
|
-
|
149
|
-
def scrape_id video_html
|
150
|
-
scrape_thumbnail_url(video_html).sub(%r{.*/([^/]+)/[^/]+.jpg}, '\1')
|
151
|
-
end
|
152
|
-
|
153
|
-
def scrape_author video_html
|
154
|
-
video_html.search("div[@class='vfacets']").inner_html.sub(/.*From:<\/span> <a.*?>(.*?)<\/a>.*/m, '\1')
|
155
|
-
end
|
156
|
-
|
157
|
-
def scrape_title video_html
|
158
|
-
video_html.search("div[@class='vtitle']/a").inner_html
|
159
|
-
end
|
160
|
-
|
161
|
-
def scrape_length_seconds video_html
|
162
|
-
length_seconds = video_html.search("span[@class='runtime']").inner_html
|
163
|
-
length_seconds =~ /(\d\d):(\d\d)/
|
164
|
-
$1.to_i * 60 + $2.to_i
|
165
|
-
end
|
166
|
-
|
167
|
-
def scrape_rating_avg video_html
|
168
|
-
video_html.search("img[@src='/img/star_sm.gif']").size +
|
169
|
-
video_html.search("img[@src='/img/star_sm_half.gif']").size * 0.5
|
170
|
-
end
|
171
|
-
|
172
|
-
def scrape_rating_count video_html
|
173
|
-
video_html.search("div[@class='rating']").inner_html.sub(/(\d+) rating/, '\1').to_i
|
174
|
-
end
|
175
|
-
|
176
|
-
def scrape_description video_html
|
177
|
-
description = video_html.search("div[@class='vdesc']/span").inner_html.sub(/^\n\t(.*?)\n\t$/m, '\1')
|
178
|
-
end
|
179
|
-
|
180
|
-
def scrape_view_count video_html
|
181
|
-
video_html.search("div[@class='vfacets']").inner_html.sub(/.*Views:<\/span> (\d+).*/m, '\1').to_i
|
182
|
-
end
|
183
|
-
|
184
|
-
def scrape_tags video_html
|
185
|
-
tags = []
|
186
|
-
video_html.search("div[@class='vtagValue']/a").each do |tag|
|
187
|
-
tags << tag.inner_html
|
188
|
-
end
|
189
|
-
tags.join(" ")
|
190
|
-
end
|
191
|
-
|
192
|
-
def scrape_thumbnail_url video_html
|
193
|
-
video_html.search("img[@class='vimg120']").to_html.sub(/.*src="(.*?)".*/, '\1')
|
194
|
-
end
|
195
|
-
|
196
|
-
def scrape_url video_html
|
197
|
-
"http://www.youtube.com" +
|
198
|
-
video_html.search("div[@class='vtitle']/a").to_html.sub(/.*href="(.*?)".*/m, '\1')
|
199
|
-
end
|
200
|
-
|
201
|
-
def scrape_result_header
|
202
|
-
@search_result.search("div[@id='sectionHeader']").inner_html
|
203
|
-
end
|
204
|
-
|
205
|
-
def scrape_video_count
|
206
|
-
video_count = scrape_result_header
|
207
|
-
unless video_count.sub!(/.+Results \d+-\d+ of( | about )([0-9,]+)/m , '\2')
|
208
|
-
raise "no video count: " + @url unless is_no_result
|
209
|
-
end
|
210
|
-
video_count.gsub!(/,/, '')
|
211
|
-
video_count.to_i
|
212
|
-
end
|
213
|
-
|
214
|
-
def scrape_video_from
|
215
|
-
video_from = scrape_result_header
|
216
|
-
unless video_from.sub!(/.+Results (\d+)/m, '\1')
|
217
|
-
raise "no video from: " + @url unless is_no_result
|
218
|
-
end
|
219
|
-
video_from.to_i
|
220
|
-
end
|
221
|
-
|
222
|
-
def scrape_video_to
|
223
|
-
video_to = scrape_result_header
|
224
|
-
unless video_to.sub!(/.+Results \d+-(\d+)/m, '\1')
|
225
|
-
raise "no video to: " + @url unless is_no_result
|
226
|
-
end
|
227
|
-
video_to.to_i
|
228
|
-
end
|
229
|
-
|
230
|
-
def is_no_result
|
231
|
-
if @is_no_result == nil
|
232
|
-
@is_no_result = @html.include?('No Videos found')
|
233
|
-
end
|
234
|
-
@is_no_result
|
235
|
-
end
|
236
|
-
|
237
|
-
def check_video video
|
238
|
-
errors = []
|
239
|
-
|
240
|
-
errors << "author" if video.author.empty?
|
241
|
-
errors << "id" if video.id.empty?
|
242
|
-
errors << "title" if video.title.empty?
|
243
|
-
errors << "length_seconds" if video.length_seconds.to_s.empty?
|
244
|
-
errors << "rating_avg" if video.rating_avg.to_s.empty?
|
245
|
-
errors << "rating_count" if video.rating_count.to_s.empty?
|
246
|
-
errors << "description" if video.description.empty?
|
247
|
-
errors << "view_count" if video.view_count.to_s.empty?
|
248
|
-
errors << "tags" if video.tags.empty?
|
249
|
-
errors << "url" if video.url.empty?
|
250
|
-
errors << "thumbnail_url" if video.thumbnail_url.empty?
|
251
|
-
|
252
|
-
unless errors.empty? then
|
253
|
-
error_msg = "scraping error occurred.\n"
|
254
|
-
errors.each do |error|
|
255
|
-
error_msg << error + " is not setted.\n"
|
256
|
-
end
|
257
|
-
raise error_msg
|
258
|
-
end
|
259
|
-
end
|
260
|
-
|
261
|
-
end
|
262
|
-
|
263
|
-
end
|