bunto-import 2.0.0 → 3.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/LICENSE +21 -21
- data/README.markdown +33 -33
- data/lib/bunto-import.rb +49 -49
- data/lib/bunto-import/importer.rb +26 -26
- data/lib/bunto-import/importers.rb +10 -10
- data/lib/bunto-import/importers/behance.rb +80 -80
- data/lib/bunto-import/importers/blogger.rb +330 -264
- data/lib/bunto-import/importers/csv.rb +96 -96
- data/lib/bunto-import/importers/drupal6.rb +53 -139
- data/lib/bunto-import/importers/drupal7.rb +54 -111
- data/lib/bunto-import/importers/drupal_common.rb +157 -0
- data/lib/bunto-import/importers/easyblog.rb +96 -96
- data/lib/bunto-import/importers/enki.rb +74 -74
- data/lib/bunto-import/importers/ghost.rb +68 -68
- data/lib/bunto-import/importers/google_reader.rb +64 -64
- data/lib/bunto-import/importers/joomla.rb +92 -90
- data/lib/bunto-import/importers/joomla3.rb +91 -91
- data/lib/bunto-import/importers/jrnl.rb +125 -125
- data/lib/bunto-import/importers/marley.rb +72 -72
- data/lib/bunto-import/importers/mephisto.rb +99 -99
- data/lib/bunto-import/importers/mt.rb +257 -257
- data/lib/bunto-import/importers/posterous.rb +130 -130
- data/lib/bunto-import/importers/rss.rb +62 -62
- data/lib/bunto-import/importers/s9y.rb +60 -60
- data/lib/bunto-import/importers/s9y_database.rb +363 -0
- data/lib/bunto-import/importers/textpattern.rb +70 -70
- data/lib/bunto-import/importers/tumblr.rb +300 -289
- data/lib/bunto-import/importers/typo.rb +88 -88
- data/lib/bunto-import/importers/wordpress.rb +372 -372
- data/lib/bunto-import/importers/wordpressdotcom.rb +207 -207
- data/lib/bunto-import/util.rb +76 -76
- data/lib/bunto-import/version.rb +3 -3
- data/lib/bunto/commands/import.rb +79 -79
- metadata +84 -54
@@ -1,130 +1,130 @@
|
|
1
|
-
module BuntoImport
|
2
|
-
module Importers
|
3
|
-
class Posterous < Importer
|
4
|
-
|
5
|
-
def self.specify_options(c)
|
6
|
-
c.option 'email', '--email EMAIL', 'Posterous email address'
|
7
|
-
c.option 'password', '--password PW', 'Posterous password'
|
8
|
-
c.option 'api_token', '--token TOKEN', 'Posterous API Token'
|
9
|
-
end
|
10
|
-
|
11
|
-
def self.require_deps
|
12
|
-
BuntoImport.require_with_fallback(%w[
|
13
|
-
rubygems
|
14
|
-
bunto
|
15
|
-
fileutils
|
16
|
-
uri
|
17
|
-
json
|
18
|
-
net/http
|
19
|
-
])
|
20
|
-
end
|
21
|
-
|
22
|
-
def self.fetch(uri_str, limit = 10)
|
23
|
-
# You should choose better exception.
|
24
|
-
raise ArgumentError, 'Stuck in a redirect loop. Please double check your email and password' if limit == 0
|
25
|
-
|
26
|
-
response = nil
|
27
|
-
Net::HTTP.start('posterous.com') do |http|
|
28
|
-
req = Net::HTTP::Get.new(uri_str)
|
29
|
-
req.basic_auth @email, @pass
|
30
|
-
response = http.request(req)
|
31
|
-
end
|
32
|
-
|
33
|
-
case response
|
34
|
-
when Net::HTTPSuccess then response
|
35
|
-
when Net::HTTPRedirection then fetch(response['location'], limit - 1)
|
36
|
-
else response.error!
|
37
|
-
end
|
38
|
-
end
|
39
|
-
|
40
|
-
def self.fetch_images(directory, imgs)
|
41
|
-
def self.fetch_one(url, limit = 10)
|
42
|
-
raise ArgumentError, 'HTTP redirect too deep' if limit == 0
|
43
|
-
response = Net::HTTP.get_response(URI.parse(url))
|
44
|
-
case response
|
45
|
-
when Net::HTTPSuccess then response.body
|
46
|
-
when Net::HTTPRedirection then self.fetch_one(response['location'], limit - 1)
|
47
|
-
else
|
48
|
-
response.error!
|
49
|
-
end
|
50
|
-
end
|
51
|
-
|
52
|
-
FileUtils.mkdir_p directory
|
53
|
-
urls = Array.new
|
54
|
-
imgs.each do |img|
|
55
|
-
fullurl = img["full"]["url"]
|
56
|
-
uri = URI.parse(fullurl)
|
57
|
-
imgname = uri.path.split("/")[-1]
|
58
|
-
imgdata = self.fetch_one(fullurl)
|
59
|
-
open(directory + "/" + imgname, "wb") do |file|
|
60
|
-
file.write imgdata
|
61
|
-
end
|
62
|
-
urls.push(directory + "/" + imgname)
|
63
|
-
end
|
64
|
-
|
65
|
-
return urls
|
66
|
-
end
|
67
|
-
|
68
|
-
def self.process(options)
|
69
|
-
email = options.fetch('email')
|
70
|
-
pass = options.fetch('password')
|
71
|
-
api_token = options.fetch('api_token')
|
72
|
-
|
73
|
-
@email, @pass, @api_token = email, pass, api_token
|
74
|
-
defaults = { :include_imgs => false, :blog => 'primary', :base_path => '/' }
|
75
|
-
opts = defaults.merge(opts)
|
76
|
-
FileUtils.mkdir_p "_posts"
|
77
|
-
|
78
|
-
posts = JSON.parse(self.fetch("/api/v2/users/me/sites/#{opts[:blog]}/posts?api_token=#{@api_token}").body)
|
79
|
-
page = 1
|
80
|
-
|
81
|
-
while posts.any?
|
82
|
-
posts.each do |post|
|
83
|
-
title = post["title"]
|
84
|
-
slug = title.gsub(/[^[:alnum:]]+/, '-').downcase
|
85
|
-
date = Date.parse(post["display_date"])
|
86
|
-
content = post["body_html"]
|
87
|
-
published = !post["is_private"]
|
88
|
-
basename = "%02d-%02d-%02d-%s" % [date.year, date.month, date.day, slug]
|
89
|
-
name = basename + '.html'
|
90
|
-
|
91
|
-
# Images:
|
92
|
-
if opts[:include_imgs]
|
93
|
-
post_imgs = post["media"]["images"]
|
94
|
-
if post_imgs.any?
|
95
|
-
img_dir = "imgs/%s" % basename
|
96
|
-
img_urls = self.fetch_images(img_dir, post_imgs)
|
97
|
-
|
98
|
-
img_urls.map! do |url|
|
99
|
-
'<li><img src="' + opts[:base_path] + url + '"></li>'
|
100
|
-
end
|
101
|
-
imgcontent = "<ol>\n" + img_urls.join("\n") + "</ol>\n"
|
102
|
-
|
103
|
-
# filter out "posterous-content", replacing with imgs:
|
104
|
-
content = content.sub(/\<p\>\[\[posterous-content:[^\]]+\]\]\<\/p\>/, imgcontent)
|
105
|
-
end
|
106
|
-
end
|
107
|
-
|
108
|
-
# Get the relevant fields as a hash, delete empty fields and convert
|
109
|
-
# to YAML for the header
|
110
|
-
data = {
|
111
|
-
'layout' => 'post',
|
112
|
-
'title' => title.to_s,
|
113
|
-
'published' => published
|
114
|
-
}.delete_if { |k,v| v.nil? || v == ''}.to_yaml
|
115
|
-
|
116
|
-
# Write out the data and content to file
|
117
|
-
File.open("_posts/#{name}", "w") do |f|
|
118
|
-
f.puts data
|
119
|
-
f.puts "---"
|
120
|
-
f.puts content
|
121
|
-
end
|
122
|
-
end
|
123
|
-
|
124
|
-
page += 1
|
125
|
-
posts = JSON.parse(self.fetch("/api/v2/users/me/sites/#{opts[:blog]}/posts?api_token=#{@api_token}&page=#{page}").body)
|
126
|
-
end
|
127
|
-
end
|
128
|
-
end
|
129
|
-
end
|
130
|
-
end
|
1
|
+
module BuntoImport
|
2
|
+
module Importers
|
3
|
+
class Posterous < Importer
|
4
|
+
|
5
|
+
def self.specify_options(c)
|
6
|
+
c.option 'email', '--email EMAIL', 'Posterous email address'
|
7
|
+
c.option 'password', '--password PW', 'Posterous password'
|
8
|
+
c.option 'api_token', '--token TOKEN', 'Posterous API Token'
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.require_deps
|
12
|
+
BuntoImport.require_with_fallback(%w[
|
13
|
+
rubygems
|
14
|
+
bunto
|
15
|
+
fileutils
|
16
|
+
uri
|
17
|
+
json
|
18
|
+
net/http
|
19
|
+
])
|
20
|
+
end
|
21
|
+
|
22
|
+
def self.fetch(uri_str, limit = 10)
|
23
|
+
# You should choose better exception.
|
24
|
+
raise ArgumentError, 'Stuck in a redirect loop. Please double check your email and password' if limit == 0
|
25
|
+
|
26
|
+
response = nil
|
27
|
+
Net::HTTP.start('posterous.com') do |http|
|
28
|
+
req = Net::HTTP::Get.new(uri_str)
|
29
|
+
req.basic_auth @email, @pass
|
30
|
+
response = http.request(req)
|
31
|
+
end
|
32
|
+
|
33
|
+
case response
|
34
|
+
when Net::HTTPSuccess then response
|
35
|
+
when Net::HTTPRedirection then fetch(response['location'], limit - 1)
|
36
|
+
else response.error!
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
def self.fetch_images(directory, imgs)
|
41
|
+
def self.fetch_one(url, limit = 10)
|
42
|
+
raise ArgumentError, 'HTTP redirect too deep' if limit == 0
|
43
|
+
response = Net::HTTP.get_response(URI.parse(url))
|
44
|
+
case response
|
45
|
+
when Net::HTTPSuccess then response.body
|
46
|
+
when Net::HTTPRedirection then self.fetch_one(response['location'], limit - 1)
|
47
|
+
else
|
48
|
+
response.error!
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
FileUtils.mkdir_p directory
|
53
|
+
urls = Array.new
|
54
|
+
imgs.each do |img|
|
55
|
+
fullurl = img["full"]["url"]
|
56
|
+
uri = URI.parse(fullurl)
|
57
|
+
imgname = uri.path.split("/")[-1]
|
58
|
+
imgdata = self.fetch_one(fullurl)
|
59
|
+
open(directory + "/" + imgname, "wb") do |file|
|
60
|
+
file.write imgdata
|
61
|
+
end
|
62
|
+
urls.push(directory + "/" + imgname)
|
63
|
+
end
|
64
|
+
|
65
|
+
return urls
|
66
|
+
end
|
67
|
+
|
68
|
+
def self.process(options)
|
69
|
+
email = options.fetch('email')
|
70
|
+
pass = options.fetch('password')
|
71
|
+
api_token = options.fetch('api_token')
|
72
|
+
|
73
|
+
@email, @pass, @api_token = email, pass, api_token
|
74
|
+
defaults = { :include_imgs => false, :blog => 'primary', :base_path => '/' }
|
75
|
+
opts = defaults.merge(opts)
|
76
|
+
FileUtils.mkdir_p "_posts"
|
77
|
+
|
78
|
+
posts = JSON.parse(self.fetch("/api/v2/users/me/sites/#{opts[:blog]}/posts?api_token=#{@api_token}").body)
|
79
|
+
page = 1
|
80
|
+
|
81
|
+
while posts.any?
|
82
|
+
posts.each do |post|
|
83
|
+
title = post["title"]
|
84
|
+
slug = title.gsub(/[^[:alnum:]]+/, '-').downcase
|
85
|
+
date = Date.parse(post["display_date"])
|
86
|
+
content = post["body_html"]
|
87
|
+
published = !post["is_private"]
|
88
|
+
basename = "%02d-%02d-%02d-%s" % [date.year, date.month, date.day, slug]
|
89
|
+
name = basename + '.html'
|
90
|
+
|
91
|
+
# Images:
|
92
|
+
if opts[:include_imgs]
|
93
|
+
post_imgs = post["media"]["images"]
|
94
|
+
if post_imgs.any?
|
95
|
+
img_dir = "imgs/%s" % basename
|
96
|
+
img_urls = self.fetch_images(img_dir, post_imgs)
|
97
|
+
|
98
|
+
img_urls.map! do |url|
|
99
|
+
'<li><img src="' + opts[:base_path] + url + '"></li>'
|
100
|
+
end
|
101
|
+
imgcontent = "<ol>\n" + img_urls.join("\n") + "</ol>\n"
|
102
|
+
|
103
|
+
# filter out "posterous-content", replacing with imgs:
|
104
|
+
content = content.sub(/\<p\>\[\[posterous-content:[^\]]+\]\]\<\/p\>/, imgcontent)
|
105
|
+
end
|
106
|
+
end
|
107
|
+
|
108
|
+
# Get the relevant fields as a hash, delete empty fields and convert
|
109
|
+
# to YAML for the header
|
110
|
+
data = {
|
111
|
+
'layout' => 'post',
|
112
|
+
'title' => title.to_s,
|
113
|
+
'published' => published
|
114
|
+
}.delete_if { |k,v| v.nil? || v == ''}.to_yaml
|
115
|
+
|
116
|
+
# Write out the data and content to file
|
117
|
+
File.open("_posts/#{name}", "w") do |f|
|
118
|
+
f.puts data
|
119
|
+
f.puts "---"
|
120
|
+
f.puts content
|
121
|
+
end
|
122
|
+
end
|
123
|
+
|
124
|
+
page += 1
|
125
|
+
posts = JSON.parse(self.fetch("/api/v2/users/me/sites/#{opts[:blog]}/posts?api_token=#{@api_token}&page=#{page}").body)
|
126
|
+
end
|
127
|
+
end
|
128
|
+
end
|
129
|
+
end
|
130
|
+
end
|
@@ -1,62 +1,62 @@
|
|
1
|
-
module BuntoImport
|
2
|
-
module Importers
|
3
|
-
class RSS < Importer
|
4
|
-
def self.specify_options(c)
|
5
|
-
c.option 'source', '--source NAME', 'The RSS file or URL to import'
|
6
|
-
end
|
7
|
-
|
8
|
-
def self.validate(options)
|
9
|
-
if options['source'].nil?
|
10
|
-
abort "Missing mandatory option --source."
|
11
|
-
end
|
12
|
-
end
|
13
|
-
|
14
|
-
def self.require_deps
|
15
|
-
BuntoImport.require_with_fallback(%w[
|
16
|
-
rss
|
17
|
-
rss/1.0
|
18
|
-
rss/2.0
|
19
|
-
open-uri
|
20
|
-
fileutils
|
21
|
-
safe_yaml
|
22
|
-
])
|
23
|
-
end
|
24
|
-
|
25
|
-
# Process the import.
|
26
|
-
#
|
27
|
-
# source - a URL or a local file String.
|
28
|
-
#
|
29
|
-
# Returns nothing.
|
30
|
-
def self.process(options)
|
31
|
-
source = options.fetch('source')
|
32
|
-
|
33
|
-
content = ""
|
34
|
-
open(source) { |s| content = s.read }
|
35
|
-
rss = ::RSS::Parser.parse(content, false)
|
36
|
-
|
37
|
-
raise "There doesn't appear to be any RSS items at the source (#{source}) provided." unless rss
|
38
|
-
|
39
|
-
rss.items.each do |item|
|
40
|
-
formatted_date = item.date.strftime('%Y-%m-%d')
|
41
|
-
post_name = item.title.split(%r{ |!|/|:|&|-|$|,}).map do |i|
|
42
|
-
i.downcase if i != ''
|
43
|
-
end.compact.join('-')
|
44
|
-
name = "#{formatted_date}-#{post_name}"
|
45
|
-
|
46
|
-
header = {
|
47
|
-
'layout' => 'post',
|
48
|
-
'title' => item.title
|
49
|
-
}
|
50
|
-
|
51
|
-
FileUtils.mkdir_p("_posts")
|
52
|
-
|
53
|
-
File.open("_posts/#{name}.html", "w") do |f|
|
54
|
-
f.puts header.to_yaml
|
55
|
-
f.puts "---\n\n"
|
56
|
-
f.puts item.description
|
57
|
-
end
|
58
|
-
end
|
59
|
-
end
|
60
|
-
end
|
61
|
-
end
|
62
|
-
end
|
1
|
+
module BuntoImport
|
2
|
+
module Importers
|
3
|
+
class RSS < Importer
|
4
|
+
def self.specify_options(c)
|
5
|
+
c.option 'source', '--source NAME', 'The RSS file or URL to import'
|
6
|
+
end
|
7
|
+
|
8
|
+
def self.validate(options)
|
9
|
+
if options['source'].nil?
|
10
|
+
abort "Missing mandatory option --source."
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.require_deps
|
15
|
+
BuntoImport.require_with_fallback(%w[
|
16
|
+
rss
|
17
|
+
rss/1.0
|
18
|
+
rss/2.0
|
19
|
+
open-uri
|
20
|
+
fileutils
|
21
|
+
safe_yaml
|
22
|
+
])
|
23
|
+
end
|
24
|
+
|
25
|
+
# Process the import.
|
26
|
+
#
|
27
|
+
# source - a URL or a local file String.
|
28
|
+
#
|
29
|
+
# Returns nothing.
|
30
|
+
def self.process(options)
|
31
|
+
source = options.fetch('source')
|
32
|
+
|
33
|
+
content = ""
|
34
|
+
open(source) { |s| content = s.read }
|
35
|
+
rss = ::RSS::Parser.parse(content, false)
|
36
|
+
|
37
|
+
raise "There doesn't appear to be any RSS items at the source (#{source}) provided." unless rss
|
38
|
+
|
39
|
+
rss.items.each do |item|
|
40
|
+
formatted_date = item.date.strftime('%Y-%m-%d')
|
41
|
+
post_name = item.title.split(%r{ |!|/|:|&|-|$|,}).map do |i|
|
42
|
+
i.downcase if i != ''
|
43
|
+
end.compact.join('-')
|
44
|
+
name = "#{formatted_date}-#{post_name}"
|
45
|
+
|
46
|
+
header = {
|
47
|
+
'layout' => 'post',
|
48
|
+
'title' => item.title
|
49
|
+
}
|
50
|
+
|
51
|
+
FileUtils.mkdir_p("_posts")
|
52
|
+
|
53
|
+
File.open("_posts/#{name}.html", "w") do |f|
|
54
|
+
f.puts header.to_yaml
|
55
|
+
f.puts "---\n\n"
|
56
|
+
f.puts item.description
|
57
|
+
end
|
58
|
+
end
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
@@ -1,60 +1,60 @@
|
|
1
|
-
module BuntoImport
|
2
|
-
module Importers
|
3
|
-
class S9Y < Importer
|
4
|
-
def self.specify_options(c)
|
5
|
-
c.option 'source', '--source SOURCE', 'The URL of the S9Y RSS feed'
|
6
|
-
end
|
7
|
-
|
8
|
-
def self.validate(options)
|
9
|
-
if options['source'].nil?
|
10
|
-
abort "Missing mandatory option --source, e.g. --source \"http://blog.example.com/rss.php?version=2.0&all=1\""
|
11
|
-
end
|
12
|
-
end
|
13
|
-
|
14
|
-
def self.require_deps
|
15
|
-
BuntoImport.require_with_fallback(%w[
|
16
|
-
open-uri
|
17
|
-
rss
|
18
|
-
fileutils
|
19
|
-
safe_yaml
|
20
|
-
])
|
21
|
-
end
|
22
|
-
|
23
|
-
def self.process(options)
|
24
|
-
source = options.fetch('source')
|
25
|
-
|
26
|
-
FileUtils.mkdir_p("_posts")
|
27
|
-
|
28
|
-
text = ''
|
29
|
-
open(source) { |line| text = line.read }
|
30
|
-
rss = ::RSS::Parser.parse(text)
|
31
|
-
|
32
|
-
rss.items.each do |item|
|
33
|
-
post_url = item.link.match('.*(/archives/.*)')[1]
|
34
|
-
categories = item.categories.collect { |c| c.content }
|
35
|
-
content = item.content_encoded.strip
|
36
|
-
date = item.date
|
37
|
-
slug = item.link.match('.*/archives/[0-9]+-(.*)\.html')[1]
|
38
|
-
name = "%02d-%02d-%02d-%s.markdown" % [date.year, date.month, date.day,
|
39
|
-
slug]
|
40
|
-
|
41
|
-
data = {
|
42
|
-
'layout' => 'post',
|
43
|
-
'title' => item.title,
|
44
|
-
'categories' => categories,
|
45
|
-
'permalink' => post_url,
|
46
|
-
's9y_link' => item.link,
|
47
|
-
'date' => item.date,
|
48
|
-
}.delete_if { |k,v| v.nil? || v == '' }.to_yaml
|
49
|
-
|
50
|
-
# Write out the data and content to file
|
51
|
-
File.open("_posts/#{name}", "w") do |f|
|
52
|
-
f.puts data
|
53
|
-
f.puts "---"
|
54
|
-
f.puts content
|
55
|
-
end
|
56
|
-
end
|
57
|
-
end
|
58
|
-
end
|
59
|
-
end
|
60
|
-
end
|
1
|
+
module BuntoImport
|
2
|
+
module Importers
|
3
|
+
class S9Y < Importer
|
4
|
+
def self.specify_options(c)
|
5
|
+
c.option 'source', '--source SOURCE', 'The URL of the S9Y RSS feed'
|
6
|
+
end
|
7
|
+
|
8
|
+
def self.validate(options)
|
9
|
+
if options['source'].nil?
|
10
|
+
abort "Missing mandatory option --source, e.g. --source \"http://blog.example.com/rss.php?version=2.0&all=1\""
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.require_deps
|
15
|
+
BuntoImport.require_with_fallback(%w[
|
16
|
+
open-uri
|
17
|
+
rss
|
18
|
+
fileutils
|
19
|
+
safe_yaml
|
20
|
+
])
|
21
|
+
end
|
22
|
+
|
23
|
+
def self.process(options)
|
24
|
+
source = options.fetch('source')
|
25
|
+
|
26
|
+
FileUtils.mkdir_p("_posts")
|
27
|
+
|
28
|
+
text = ''
|
29
|
+
open(source) { |line| text = line.read }
|
30
|
+
rss = ::RSS::Parser.parse(text)
|
31
|
+
|
32
|
+
rss.items.each do |item|
|
33
|
+
post_url = item.link.match('.*(/archives/.*)')[1]
|
34
|
+
categories = item.categories.collect { |c| c.content }
|
35
|
+
content = item.content_encoded.strip
|
36
|
+
date = item.date
|
37
|
+
slug = item.link.match('.*/archives/[0-9]+-(.*)\.html')[1]
|
38
|
+
name = "%02d-%02d-%02d-%s.markdown" % [date.year, date.month, date.day,
|
39
|
+
slug]
|
40
|
+
|
41
|
+
data = {
|
42
|
+
'layout' => 'post',
|
43
|
+
'title' => item.title,
|
44
|
+
'categories' => categories,
|
45
|
+
'permalink' => post_url,
|
46
|
+
's9y_link' => item.link,
|
47
|
+
'date' => item.date,
|
48
|
+
}.delete_if { |k,v| v.nil? || v == '' }.to_yaml
|
49
|
+
|
50
|
+
# Write out the data and content to file
|
51
|
+
File.open("_posts/#{name}", "w") do |f|
|
52
|
+
f.puts data
|
53
|
+
f.puts "---"
|
54
|
+
f.puts content
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
59
|
+
end
|
60
|
+
end
|