vortex_client 0.6.0 → 0.7.0
Sign up to get free protection for your applications and to get access to all the features.
- data/VERSION +1 -1
- data/examples/README.rdoc +30 -0
- data/examples/create_personpresentations.rb +147 -0
- data/examples/dice.gif +0 -0
- data/examples/import_static_site.rb +211 -0
- data/examples/no_right_margin.rb +11 -0
- data/examples/propfind_proppatch.rb +7 -0
- data/examples/replace_spike.rb +42 -0
- data/examples/scrape_hero_publications.rb +38 -0
- data/examples/scrape_holocaust.rb +351 -0
- data/examples/scrape_holocaust_related_links.rb +134 -0
- data/examples/scrape_vortex_search.rb +44 -0
- data/examples/search_replace_documents.rb +57 -0
- data/examples/search_replace_documents_frontpage.rb +88 -0
- data/examples/test_searc_replace.rb +3 -0
- data/examples/unpublish.rb +11 -0
- data/examples/upload_image.rb +8 -0
- data/examples/upload_image_flymake.rb +8 -0
- data/lib/vortex_client.rb +2 -1
- data/test/test_vortex_article_publish.rb +3 -16
- metadata +48 -17
- data/.gitignore +0 -21
@@ -0,0 +1,38 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'rubygems'
|
3
|
+
require 'open-uri'
|
4
|
+
require 'vortex_client'
|
5
|
+
require 'uri'
|
6
|
+
require 'nokogiri'
|
7
|
+
require 'htmlentities'
|
8
|
+
require 'json'
|
9
|
+
require 'iconv'
|
10
|
+
|
11
|
+
class MigrateHeroPublications
|
12
|
+
attr :vortex, :uri
|
13
|
+
|
14
|
+
def initialize(url)
|
15
|
+
@vortex = Vortex::Connection.new(url,:use_osx_keychain => true)
|
16
|
+
@uri = URI.parse(url)
|
17
|
+
end
|
18
|
+
|
19
|
+
def migrate_publications(url)
|
20
|
+
doc = Nokogiri::HTML.parse(open(url))
|
21
|
+
doc.encoding = 'utf-8'
|
22
|
+
doc.xpath("//td").each do |element|
|
23
|
+
if(element.inner_text =~ /\d*:\d*/)then
|
24
|
+
puts element.inner_text
|
25
|
+
puts "-------"
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
end
|
31
|
+
|
32
|
+
# Scrape all webpages found in src_url and store in dest_url
|
33
|
+
dest_url = 'https://nyweb1-dav.uio.no/konv/hero/publikasjoner'
|
34
|
+
# src_url = 'http://www.hero.uio.no/publicat/2003/'
|
35
|
+
# src_url = 'http://www.hero.uio.no/nyheter.html'
|
36
|
+
src_url = 'http://www.hero.uio.no/publications_all/publications10.html'
|
37
|
+
migration = MigrateHeroPublications.new(dest_url)
|
38
|
+
migration.migrate_publications(src_url)
|
@@ -0,0 +1,351 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'rubygems'
|
3
|
+
require 'vortex_client'
|
4
|
+
require 'nokogiri'
|
5
|
+
require 'open-uri'
|
6
|
+
require 'uri'
|
7
|
+
require 'pry'
|
8
|
+
require "net/http"
|
9
|
+
require 'pathname'
|
10
|
+
require 'json'
|
11
|
+
require 'pp'
|
12
|
+
|
13
|
+
# Scrape content from the Norwegian Center for Studies of Holocaust and Religious Minorities'
|
14
|
+
# website http://www.hlsenteret.no/ and re-publish content to University of Oslo's CMS
|
15
|
+
# using the WebDAV API.
|
16
|
+
|
17
|
+
# TODO
|
18
|
+
# ok - Hente ut tittel på mappen
|
19
|
+
# ok - Hente ut content/type på bilder
|
20
|
+
# ok - Kopiere over ingress bilde
|
21
|
+
# ok - Luke ut rare tegn i overskriftene
|
22
|
+
# ok - Kjøre alle dokumenter uten kræsj
|
23
|
+
# ok - Kopiere over flere bilder
|
24
|
+
# ok - Få logging til fil til å fungere
|
25
|
+
# - Logg publisering til fil
|
26
|
+
# - Hvorfor konverteres og publiseres /konv/kunnskapsbasen/-a-hrefhttp-.html
|
27
|
+
# - Håndtere /konv/kunnskapsbasen/hl-senterets-kunnskapsbase.html spesielt?
|
28
|
+
|
29
|
+
@vortex = Vortex::Connection.new("https://nyweb4-dav.uio.no", :use_osx_keychain => true)
|
30
|
+
|
31
|
+
# Simple logger
|
32
|
+
def log(str)
|
33
|
+
puts str
|
34
|
+
File.open("scrape_holocaust.log", 'a') do |f|
|
35
|
+
f.write( Time.now.iso8601 + ";" + str + "\n" )
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
def http_content_type(url)
|
40
|
+
uri = URI.parse(url)
|
41
|
+
http = Net::HTTP.new(uri.host, uri.port)
|
42
|
+
|
43
|
+
request = Net::HTTP::Get.new(uri.request_uri)
|
44
|
+
request["User-Agent"] = "My Ruby Script"
|
45
|
+
request["Accept"] = "*/*"
|
46
|
+
|
47
|
+
response = http.request(request)
|
48
|
+
return response['content-type']
|
49
|
+
end
|
50
|
+
|
51
|
+
def scrape_folder_title(url)
|
52
|
+
begin
|
53
|
+
doc = Nokogiri::HTML.parse(open(scrape_url))
|
54
|
+
doc.encoding = 'utf-8'
|
55
|
+
|
56
|
+
title = nil
|
57
|
+
begin
|
58
|
+
title = doc.css(".folder .title").first.inner_html
|
59
|
+
rescue
|
60
|
+
end
|
61
|
+
if(title == nil)then
|
62
|
+
title = doc.css(".article .title").first.inner_html
|
63
|
+
end
|
64
|
+
rescue
|
65
|
+
end
|
66
|
+
return title
|
67
|
+
end
|
68
|
+
|
69
|
+
def create_path(dest_path)
|
70
|
+
destination_path = "/"
|
71
|
+
dest_path.split("/").each do |folder|
|
72
|
+
if(folder != "")then
|
73
|
+
folder = folder.downcase
|
74
|
+
destination_path = destination_path + folder + "/"
|
75
|
+
|
76
|
+
if( not(@vortex.exists?(destination_path)) )then
|
77
|
+
|
78
|
+
puts "Creating folder " + destination_path
|
79
|
+
|
80
|
+
uri = URI.parse(@url)
|
81
|
+
|
82
|
+
title = scrape_folder_title( 'http://' + uri.host + destination_path.gsub('/konv','') )
|
83
|
+
|
84
|
+
if(title)then
|
85
|
+
title = title[0..0].upcase + title[1..title.length]
|
86
|
+
puts "Mappetittel: " + title.to_s
|
87
|
+
end
|
88
|
+
|
89
|
+
@vortex.mkdir(destination_path)
|
90
|
+
@vortex.proppatch(destination_path,'<v:collection-type xmlns:v="vrtx">article-listing</v:collection-type>')
|
91
|
+
if(title)then
|
92
|
+
@vortex.proppatch(destination_path,'<v:userTitle xmlns:v="vrtx">' + title.to_s + '</v:userTitle>')
|
93
|
+
end
|
94
|
+
end
|
95
|
+
end
|
96
|
+
end
|
97
|
+
end
|
98
|
+
|
99
|
+
|
100
|
+
# Return an array images and captions
|
101
|
+
def scrape_images(doc)
|
102
|
+
images = []
|
103
|
+
i = 0
|
104
|
+
doc.css(".imageSeriesImage").each do |item|
|
105
|
+
url = item.attr("src")
|
106
|
+
caption = doc.css(".imageText")[i].text
|
107
|
+
images << { :url => url, :caption => caption }
|
108
|
+
i = i + 1
|
109
|
+
end
|
110
|
+
return images
|
111
|
+
end
|
112
|
+
|
113
|
+
|
114
|
+
# Resize an image using the unix command line utility 'sips' available on osx
|
115
|
+
def resize_image(content, content_type, size)
|
116
|
+
filename = "/tmp/" + (1 + rand(10000000)).to_s + "." + content_type
|
117
|
+
filename_resized = "/tmp/" + (1 + rand(10000000)).to_s + "_resized." + content_type
|
118
|
+
File.open(filename, 'w') do |f|
|
119
|
+
f.write( content)
|
120
|
+
end
|
121
|
+
result = %x[sips --resampleWidth #{size} #{filename} --out #{filename_resized}]
|
122
|
+
content_resized = IO.readlines(filename_resized,'r').to_s
|
123
|
+
return content_resized
|
124
|
+
end
|
125
|
+
|
126
|
+
|
127
|
+
# Download graphic to dest_path and return absolute filename
|
128
|
+
def download_image(src_url,dest_path)
|
129
|
+
src_url = src_url.gsub(/\?.*/,'')
|
130
|
+
content_type = http_content_type(src_url)
|
131
|
+
content_type = content_type.gsub("image/", "").gsub("jpeg","jpg")
|
132
|
+
content = open(src_url).read
|
133
|
+
basename = Pathname.new(src_url).basename.to_s.gsub(/\..*/,'')
|
134
|
+
vortex_url = dest_path + basename + "." + content_type
|
135
|
+
vortex_url = vortex_url.downcase
|
136
|
+
begin
|
137
|
+
@vortex.put_string(vortex_url, content)
|
138
|
+
rescue Exception => e
|
139
|
+
puts e.message
|
140
|
+
pp e.backtrace.inspect
|
141
|
+
puts "vortex_url: " + vortex_url
|
142
|
+
exit
|
143
|
+
end
|
144
|
+
|
145
|
+
# Store a resized image to vortex
|
146
|
+
puts "Nedskalerer bilde: " + src_url
|
147
|
+
content_resized = resize_image(content, content_type,300)
|
148
|
+
vortex_url_resized = dest_path + basename + "_width_300." + content_type
|
149
|
+
|
150
|
+
vortex_url_resized = vortex_url_resized.downcase
|
151
|
+
begin
|
152
|
+
@vortex.put_string(vortex_url_resized, content_resized)
|
153
|
+
rescue Exception => e
|
154
|
+
puts e.message
|
155
|
+
pp e.backtrace.inspect
|
156
|
+
puts "vortex_url_resized: " + vortex_url_resized
|
157
|
+
exit
|
158
|
+
end
|
159
|
+
|
160
|
+
return { :vortex_url_resized => vortex_url_resized, :vortex_url => vortex_url}
|
161
|
+
end
|
162
|
+
|
163
|
+
|
164
|
+
def publish_article(path, title, introduction, body, doc)
|
165
|
+
dest_path = "/konv" + path.gsub(/\d*$/,'')
|
166
|
+
|
167
|
+
if(not(dest_path =~ /\/$/))then
|
168
|
+
dest_path = dest_path + "/"
|
169
|
+
end
|
170
|
+
|
171
|
+
puts "Publishing to: '#{dest_path}'"
|
172
|
+
|
173
|
+
create_path(dest_path)
|
174
|
+
@vortex.cd(dest_path)
|
175
|
+
|
176
|
+
# images = []
|
177
|
+
# Comment out this line to prevent scraper from downloading images
|
178
|
+
images = scrape_images(doc)
|
179
|
+
|
180
|
+
images.each do |image|
|
181
|
+
filenames = download_image(image[:url], dest_path)
|
182
|
+
image[:vortex_url] = filenames[:vortex_url_resized]
|
183
|
+
image[:vortex_url_org] = filenames[:vortex_url]
|
184
|
+
end
|
185
|
+
|
186
|
+
url = dest_path + Vortex::StringUtils.create_filename(title.gsub(":","_")).gsub(/-$/,'') + '.html'
|
187
|
+
url = url.downcase
|
188
|
+
|
189
|
+
attributes = {:title => title,
|
190
|
+
:introduction => introduction,
|
191
|
+
:body => body,
|
192
|
+
:publishedDate => Time.now,
|
193
|
+
:url => url}
|
194
|
+
|
195
|
+
if(images and images.first)then
|
196
|
+
attributes[:picture] = images.first[:vortex_url]
|
197
|
+
end
|
198
|
+
|
199
|
+
article = Vortex::StructuredArticle.new(attributes )
|
200
|
+
begin
|
201
|
+
url = @vortex.publish(article)
|
202
|
+
rescue Exception => e
|
203
|
+
puts e.message
|
204
|
+
require 'pp'
|
205
|
+
pp e.backtrace.inspect
|
206
|
+
pp attributes
|
207
|
+
puts "Path: " + dest_path
|
208
|
+
exit
|
209
|
+
end
|
210
|
+
|
211
|
+
# Add additional images to bottom of page
|
212
|
+
images_html = ""
|
213
|
+
if(images and images.size > 1)then
|
214
|
+
images[1..images.size].each do |image|
|
215
|
+
image_html = <<EOF
|
216
|
+
<p>
|
217
|
+
<div class="vrtx-introduction-image" style="width: 300px; ">
|
218
|
+
<a title="Last ned bilde i full størrelse" href="#{image[:vortex_url_org]}">
|
219
|
+
<img src="#{image[:vortex_url]}" style="width: 300px;" />
|
220
|
+
</a>
|
221
|
+
<div class="vrtx-imagetext">
|
222
|
+
<div class="vrtx-imagedescription">
|
223
|
+
#{image[:caption]}
|
224
|
+
</div>
|
225
|
+
</div>
|
226
|
+
</div>
|
227
|
+
</p>
|
228
|
+
EOF
|
229
|
+
images_html = images_html + image_html
|
230
|
+
end
|
231
|
+
end
|
232
|
+
|
233
|
+
# Reopen document and set caption on article image
|
234
|
+
if(images and images.first)then
|
235
|
+
@vortex.find(url) do |item|
|
236
|
+
data = JSON.parse(item.content)
|
237
|
+
|
238
|
+
caption = ""
|
239
|
+
if(images.first[:caption])then
|
240
|
+
caption = images.first[:caption]
|
241
|
+
end
|
242
|
+
caption = caption + " <a href=\"#{images.first[:vortex_url_org]}\">Last ned i full størrelse</a>"
|
243
|
+
data["properties"]["caption"] = caption
|
244
|
+
|
245
|
+
# Add addiitional images at bottom
|
246
|
+
data["properties"]["content"] = data["properties"]["content"] + images_html
|
247
|
+
item.content = data.to_json
|
248
|
+
end
|
249
|
+
end
|
250
|
+
|
251
|
+
return url
|
252
|
+
end
|
253
|
+
|
254
|
+
def scrape_article(url)
|
255
|
+
# puts "Scraping article: " + url
|
256
|
+
doc = Nokogiri::HTML.parse(open(url))
|
257
|
+
doc.encoding = 'utf-8'
|
258
|
+
if(doc.css(".article .title").size() == 0)then
|
259
|
+
puts "Warning. No title. Ignoring: " + url
|
260
|
+
return
|
261
|
+
end
|
262
|
+
title = doc.css(".article .title").first.inner_html
|
263
|
+
introduction = ""
|
264
|
+
begin
|
265
|
+
introduction = doc.css(".article .abstract").first.inner_html
|
266
|
+
rescue
|
267
|
+
end
|
268
|
+
|
269
|
+
body = ""
|
270
|
+
doc.css(".article .text").each do |p|
|
271
|
+
body = body + "<p>" + p.inner_html + "</p>"
|
272
|
+
end
|
273
|
+
|
274
|
+
title = title.gsub('','–') # Fjern bindestrek
|
275
|
+
|
276
|
+
uri = URI.parse(url)
|
277
|
+
path = uri.path
|
278
|
+
|
279
|
+
# Remove inline css
|
280
|
+
introduction = introduction.gsub(/style=\"[^\"]*\"/,"")
|
281
|
+
body = body.gsub(/style=\"[^\"]*\"/,"")
|
282
|
+
|
283
|
+
published_path = publish_article(path, title, introduction, body, doc)
|
284
|
+
# log = path + ";" + URI.parse(published_path).path
|
285
|
+
log = url + ";" + published_path + "\n"
|
286
|
+
File.open("scrape_holocaust.log", 'a') {|f| f.write(log) }
|
287
|
+
puts title + " => " + published_path
|
288
|
+
end
|
289
|
+
|
290
|
+
def http_status_code(url)
|
291
|
+
uri = URI.parse(url)
|
292
|
+
Net::HTTP.start(uri.host, uri.port) do |http|
|
293
|
+
return http.head(uri.request_uri).code.to_i
|
294
|
+
end
|
295
|
+
end
|
296
|
+
|
297
|
+
def scrape_article_listing(url)
|
298
|
+
|
299
|
+
if( http_status_code(url) == 404)then
|
300
|
+
puts "Advarsel: Status code 404: " + url
|
301
|
+
return
|
302
|
+
end
|
303
|
+
|
304
|
+
# Ad-hoc rule to ignore path
|
305
|
+
if(url =~ /\/kunnskapsbasen\/Presse/)then
|
306
|
+
puts "Advarsel: Ignorerer pressesidene har for store bilder for vortex: url"
|
307
|
+
return
|
308
|
+
end
|
309
|
+
|
310
|
+
doc = Nokogiri::HTML.parse(open(url))
|
311
|
+
doc.encoding = 'utf-8'
|
312
|
+
|
313
|
+
if(doc.css(".folder .list").size > 0 )then
|
314
|
+
puts "Scraping article listing page: " + url
|
315
|
+
doc.css(".folder .list .article").each do |article|
|
316
|
+
href = article.css(".title a").attr("href").text
|
317
|
+
begin
|
318
|
+
href = href.gsub("%20","")
|
319
|
+
rescue
|
320
|
+
end
|
321
|
+
scrape_article_listing(href)
|
322
|
+
end
|
323
|
+
else
|
324
|
+
# Pages without .folder .list is articles
|
325
|
+
puts "Scraping article: " + url
|
326
|
+
scrape_article(url)
|
327
|
+
end
|
328
|
+
|
329
|
+
end
|
330
|
+
|
331
|
+
# if @vortex.exists?('/konv/kunnskapsbasen/aktor') then
|
332
|
+
# @vortex.delete('/konv/kunnskapsbasen/aktor')
|
333
|
+
# end
|
334
|
+
@url = "http://www.hlsenteret.no/kunnskapsbasen/"
|
335
|
+
File.open("scrape_holocaust.log", 'w') {|f| f.write("") }
|
336
|
+
scrape_article_listing(@url)
|
337
|
+
|
338
|
+
|
339
|
+
# Denne har 4 bilder
|
340
|
+
# scrape_article("http://www.hlsenteret.no/kunnskapsbasen/folkemord/armenerne/1334")
|
341
|
+
|
342
|
+
# Denne har ingen tittel og skal ignoreres
|
343
|
+
# scrape_article('http://www.hlsenteret.no/kunnskapsbasen/tradisjoner/86')
|
344
|
+
|
345
|
+
# Denne returnerer 404
|
346
|
+
# scrape_article_listing("http://www.hlsenteret.no/kunnskapsbasen/tema/kunst")
|
347
|
+
|
348
|
+
# Denne har bilder som er for store vortex
|
349
|
+
# scrape_article_listing("http://www.hlsenteret.no/kunnskapsbasen/Presse/")
|
350
|
+
|
351
|
+
# scrape_article('http://www.hlsenteret.no/kunnskapsbasen/tema/relpol/10129')
|
@@ -0,0 +1,134 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'rubygems'
|
3
|
+
require 'vortex_client'
|
4
|
+
require 'nokogiri'
|
5
|
+
require 'open-uri'
|
6
|
+
require 'uri'
|
7
|
+
require 'pry'
|
8
|
+
require 'net/http'
|
9
|
+
require 'pathname'
|
10
|
+
require 'json'
|
11
|
+
require 'pp'
|
12
|
+
|
13
|
+
# The method String.cleanpath seems to be missing in my version of ruby
|
14
|
+
# Since it is not important to us, we can define it:
|
15
|
+
class String
|
16
|
+
def cleanpath
|
17
|
+
return self
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
# Relativize url's
|
22
|
+
def relative_url(from,to)
|
23
|
+
pn = Pathname.new(to)
|
24
|
+
return pn.relative_path_from(from).to_s.gsub(/^\.\.\//,'')
|
25
|
+
end
|
26
|
+
|
27
|
+
# Read link database from file. Return hashmaps
|
28
|
+
def read_linkbase_from_file
|
29
|
+
old_pages = { }
|
30
|
+
File.open('scrape_holocaust.log').each do |line|
|
31
|
+
line = line.chop
|
32
|
+
pages = line.split(/;/)
|
33
|
+
if(pages[0])then
|
34
|
+
old_pages[pages[0]] = pages[1]
|
35
|
+
end
|
36
|
+
end
|
37
|
+
return old_pages
|
38
|
+
end
|
39
|
+
|
40
|
+
# Generate html content for right column box in vortex:
|
41
|
+
def generate_related_content(old_url,new_url)
|
42
|
+
related_content_html = ""
|
43
|
+
doc = Nokogiri::HTML.parse(open(old_url))
|
44
|
+
doc.encoding = 'utf-8'
|
45
|
+
doc.css(".related .title").each do |related_title|
|
46
|
+
related_content_html += "<p><b>#{related_title.text}</b></p>\n"
|
47
|
+
# puts " Title: '" + related_title.text + "'"
|
48
|
+
# # puts "Old url :'" + old_url + "'"
|
49
|
+
# # puts " url :'" + new_url + "'"
|
50
|
+
next_element = related_title.next_element
|
51
|
+
related_content_html += "<ul>\n"
|
52
|
+
while(next_element)
|
53
|
+
href = next_element.css("a").attr("href").to_s
|
54
|
+
text = next_element.css("a").text
|
55
|
+
link_to = href
|
56
|
+
if(@old_pages[href])
|
57
|
+
# puts " New: '" + @old_pages[href] + "'"
|
58
|
+
# puts " Relt:'" + relative_url(new_url,@old_pages[href])
|
59
|
+
link_to = relative_url(new_url,@old_pages[href])
|
60
|
+
else
|
61
|
+
# puts " Warning: Extern url: " + href
|
62
|
+
end
|
63
|
+
next_element = next_element.next_element
|
64
|
+
related_content_html += " <li><a href=\"#{link_to}\">#{text}</a>\n"
|
65
|
+
end
|
66
|
+
related_content_html += "</ul>\n\n"
|
67
|
+
end
|
68
|
+
return related_content_html
|
69
|
+
end
|
70
|
+
|
71
|
+
def update_links_in_tekst(html,new_url)
|
72
|
+
doc = Nokogiri::HTML.parse(html)
|
73
|
+
doc.css("a").each do |link|
|
74
|
+
if(link.attributes["href"])
|
75
|
+
href = link.attr("href")
|
76
|
+
if(@old_pages[href])then
|
77
|
+
link_to = relative_url(new_url,@old_pages[href])
|
78
|
+
puts " Replace link in body:" + link_to
|
79
|
+
html = html.gsub(href,link_to)
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
return html
|
84
|
+
end
|
85
|
+
|
86
|
+
|
87
|
+
# # Debugg code
|
88
|
+
# @vortex = Vortex::Connection.new("https://nyweb4-dav.uio.no", :use_osx_keychain => true)
|
89
|
+
# @old_pages = read_linkbase_from_file
|
90
|
+
# old_url = "http://www.hlsenteret.no/kunnskapsbasen/tradisjoner/buddhisme/1049"
|
91
|
+
# new_url = "https://nyweb4-dav.uio.no/konv/kunnskapsbasen/tradisjoner/buddhisme/hellige-skrifter-i-buddhismen.html"
|
92
|
+
|
93
|
+
# # old_url = "http://www.hlsenteret.no/kunnskapsbasen/tema/religionsfrihet"
|
94
|
+
# # new_url = "https://nyweb4-dav.uio.no/konv/kunnskapsbasen/tema/religionsfrihet/religions-og-livssynsfrihet.html"
|
95
|
+
|
96
|
+
# src = @vortex.get(URI.parse(new_url).path)
|
97
|
+
# data = JSON.parse(src)
|
98
|
+
# data['properties']['hideAdditionalContent'] = "false"
|
99
|
+
# # data['properties']['related-content'] = related_content_html
|
100
|
+
# content = data['properties']['content']
|
101
|
+
# content = update_links_in_tekst(content,new_url)
|
102
|
+
# puts content
|
103
|
+
# exit
|
104
|
+
|
105
|
+
# update_links_in_tekst("http://www.hlsenteret.no/kunnskapsbasen/Holocaust_og_andre_folkemord",nil)
|
106
|
+
# exit
|
107
|
+
|
108
|
+
|
109
|
+
@vortex = Vortex::Connection.new("https://nyweb4-dav.uio.no", :use_osx_keychain => true)
|
110
|
+
|
111
|
+
@old_pages = read_linkbase_from_file
|
112
|
+
count = 1
|
113
|
+
@old_pages.each do |old_url, new_url|
|
114
|
+
puts count
|
115
|
+
puts old_url
|
116
|
+
puts new_url
|
117
|
+
puts "Url: '" + URI.parse(new_url).path.to_s + "'"
|
118
|
+
related_content_html = generate_related_content(old_url,new_url)
|
119
|
+
|
120
|
+
|
121
|
+
src = @vortex.get(URI.parse(new_url).path)
|
122
|
+
data = JSON.parse(src)
|
123
|
+
data['properties']['hideAdditionalContent'] = "false"
|
124
|
+
data['properties']['related-content'] = related_content_html
|
125
|
+
|
126
|
+
content = data['properties']['content']
|
127
|
+
content = update_links_in_tekst(content,new_url)
|
128
|
+
data['properties']['content'] = content
|
129
|
+
@vortex.put_string(URI.parse(new_url).path, data.to_json)
|
130
|
+
puts "-------"
|
131
|
+
|
132
|
+
count += 1
|
133
|
+
# exit if count > 10
|
134
|
+
end
|