1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
|
=begin
Feed2Imap - RSS/Atom Aggregator uploading to an IMAP Server
Copyright (c) 2005 Lucas Nussbaum <lucas@lucas-nussbaum.net>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
=end
# This class allows to retrieve a feed and parse it into a Channel
require 'rexml/document'
require 'time'
require 'rmail'
require 'feed2imap/textconverters'
require 'feed2imap/rubymail_patch'
require 'feed2imap/rexml_patch'
class UnknownFeedTypeException < RuntimeError
end
# an RSS/Atom channel
class Channel
attr_reader :title, :link, :description, :creator, :encoding, :items
# parse str to build a channel
def initialize(str = nil)
parse_str(str) if str
end
# Determines all the fields using a string containing an
# XML document
def parse_str(str)
# Dirty hack: some feeds contain the & char. It must be changed to &
str.gsub!(/&(\s+)/, '&\1')
doc = REXML::Document.new(str)
# get channel info
@encoding = doc.encoding
@title,@link,@description,@creator = nil
@items = []
if doc.root.elements['channel'] || doc.root.elements['rss:channel']
# We have a RSS feed!
# Title
if (e = doc.root.elements['channel/title'] ||
doc.root.elements['rss:channel/rss:title']) && e.text
@title = e.text.toUTF8(@encoding).rmWhiteSpace!
end
# Link
if (e = doc.root.elements['channel/link'] ||
doc.root.elements['rss:channel/rss:link']) && e.text
@link = e.text.rmWhiteSpace!
end
# Description
if (e = doc.root.elements['channel/description'] ||
doc.root.elements['rss:channel/rss:description']) && e.text
@description = e.text.toUTF8(@encoding).rmWhiteSpace!
end
# Creator
if ((e = doc.root.elements['channel/dc:creator']) && e.text) ||
((e = doc.root.elements['channel/author'] ||
doc.root.elements['rss:channel/rss:author']) && e.text)
@creator = e.text.toUTF8(@encoding).rmWhiteSpace!
end
# Items
if doc.root.elements['channel/item']
query = 'channel/item'
elsif doc.root.elements['item']
query = 'item'
elsif doc.root.elements['rss:channel/rss:item']
query = 'rss:channel/rss:item'
else
query = 'rss:item'
end
doc.root.each_element(query) { |e| @items << Item::new(e, self) }
elsif doc.root.elements['/feed']
# We have an ATOM feed!
# Title
if (e = doc.root.elements['/feed/title']) && e.text
@title = e.text.toUTF8(@encoding).rmWhiteSpace!
end
# Link
doc.root.each_element('/feed/link') do |e|
if e.attribute('type').value == 'text/html' or
e.attribute('type').value == 'application/xhtml' or
e.attribute('type').value == 'application/xhtml+xml'
if (h = e.attribute('href')) && h
@link = h.value.rmWhiteSpace!
end
end
end
# Description
if e = doc.root.elements['/feed/info']
@description = e.elements.to_s.toUTF8(@encoding).rmWhiteSpace!
end
# Items
doc.root.each_element('/feed/entry') do |e|
@items << AtomItem::new(e, self)
end
else
raise UnknownFeedTypeException::new
end
end
def to_s
s = "Title: #{@title}\nLink: #{@link}\n\n"
@items.each { |i| s += i.to_s }
s
end
end
# an Item from a channel
class Item
attr_accessor :title, :link, :content, :date, :creator, :subject,
:category, :cacheditem
attr_reader :channel
def initialize(item = nil, channel = nil)
@channel = channel
@title, @link, @content, @date, @creator, @subject, @category = nil
if item
# Title
if ((e = item.elements['title'] || item.elements['rss:title']) &&
e.text) ||
((e = item.elements['pubDate'] || item.elements['rss:pubDate']) &&
e.text)
@title = e.text.toUTF8(@channel.encoding).rmWhiteSpace!
end
# Link
if ((e = item.elements['link'] || item.elements['rss:link']) && e.text)||
(e = item.elements['guid'] || item.elements['rss:guid'] and
not (e.attribute('isPermaLink') and
e.attribute('isPermaLink').value == 'false'))
@link = e.text.rmWhiteSpace!
end
# Content
if (e = item.elements['content:encoded']) ||
(e = item.elements['description'] || item.elements['rss:description'])
if e.cdatas[0]
@content = e.cdatas[0].to_s.toUTF8(@channel.encoding).rmWhiteSpace!
elsif e.text
@content = e.text.toUTF8(@channel.encoding).text2html
end
end
# Date
if e = item.elements['dc:date'] || item.elements['pubDate'] ||
item.elements['rss:pubDate']
begin
@date = Time::xmlschema(e.text)
rescue
begin
@date = Time::rfc2822(e.text)
rescue
begin
@date = Time::parse(e.text)
rescue
@date = nil
end
end
end
end
# Creator
@creator = @channel.creator
if (e = item.elements['dc:creator'] || item.elements['author'] ||
item.elements['rss:author']) && e.text
@creator = e.text.toUTF8(@channel.encoding).rmWhiteSpace!
end
# Subject
if (e = item.elements['dc:subject']) && e.text
@subject = e.text.toUTF8(@channel.encoding).rmWhiteSpace!
end
# Category
if (e = item.elements['dc:category'] || item.elements['category'] ||
item.elements['rss:category']) && e.text
@category = e.text.toUTF8(@channel.encoding).rmWhiteSpace!
end
end
end
def to_s
"--------------------------------\n" +
"Title: #{@title}\nLink: #{@link}\n" +
"Date: #{@date.to_s}\nCreator: #{@creator}\n" +
"Subject: #{@subject}\nCategory: #{@category}\nContent:\n#{content}\n"
end
def to_text
s = ""
s += "Channel: "
s += @channel.title + ' ' if @channel.title
s += "<#{@channel.link}>" if @channel.link
s += "\n"
s += "Item: "
s += @title + ' ' if @title
s += "<#{@link}>" if @link
s += "\n"
s += "\nDate: #{@date.to_s}" if @date # TODO improve date rendering ?
s += "\nAuthor: #{@creator}" if @creator
s += "\nSubject: #{@subject}" if @subject
s += "\nCategory: #{@category}" if @category
s += "\n\n"
s += "#{@content.html2text}" if @content
s
end
def to_html
s = '<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">'
s += '<html>'
s += '<body>'
s += "<p>Channel: "
s += "<a href=\"#{@channel.link}\">" if @channel.link
s += @channel.title if @channel.title
s += "</a>" if @channel.link
s += "<br/>\nItem: "
s += "<a href=\"#{@link}\">" if @link
s += @title if @title
s += "</a>" if @link
s += "\n"
s += "<br/>Date: #{@date.to_s}" if @date # TODO improve date rendering ?
s += "<br/>Author: #{@creator}" if @creator
s += "<br/>Subject: #{@subject}" if @subject
s += "<br/>Category: #{@category}" if @category
s += "</p>"
s += "<p>#{@content}</p>" if @content
s += '</body></html>'
s
end
def to_mail(from = 'Feed2Imap')
message = RMail::Message::new
message.header['From'] = "#{from} <feed2imap@feed2imap.net>"
message.header['To'] = "#{from} <feed2imap@feed2imap.net>"
if @date.nil?
message.header['Date'] = Time::new.rfc2822
else
message.header['Date'] = @date.rfc2822
end
message.header['X-Feed2Imap-Version'] = F2I_VERSION if defined?(F2I_VERSION)
message.header['X-CacheIndex'] = "-#{@cacheditem.index}-"
message.header['X-F2IStatus'] = "Updated" if @cacheditem.updated
# TODO encode in ISO ?
if @title
message.header['Subject'] = @title
elsif @date
message.header['Subject'] = @date.to_s
elsif @link
message.header['Subject'] = @link
end
textpart = RMail::Message::new
textpart.header['Content-Type'] = 'text/plain; charset=UTF-8; format=flowed'
textpart.header['Content-Transfer-Encoding'] = '7bit'
textpart.body = to_text
htmlpart = RMail::Message::new
htmlpart.header['Content-Type'] = 'text/html; charset=UTF-8'
htmlpart.header['Content-Transfer-Encoding'] = '7bit'
htmlpart.body = to_html
message.add_part(textpart)
message.add_part(htmlpart)
return message.to_s
end
end
class AtomItem < Item
def initialize(item = nil, channel = nil)
@channel = channel
@title, @link, @content, @date, @creator, @subject, @category = nil
if item
# Title
if (e = item.elements['title']) && e.text
@title = e.text.toUTF8(@channel.encoding).rmWhiteSpace!
end
# Link
item.each_element('link') do |e|
if e.attribute('type').value == 'text/html' or
e.attribute('type').value == 'application/xhtml' or
e.attribute('type').value == 'application/xhtml+xml'
if (h = e.attribute('href')) && h.value
@link = h.value
end
end
end
# Content
if e = item.elements['content'] || item.elements['summary']
if (e.attribute('mode') and e.attribute('mode').value == 'escaped') &&
e.text
@content = e.text.toUTF8(@channel.encoding).rmWhiteSpace!
else
# go one step deeper in the recursion if possible
e = e.elements['div'] || e
@content = e.to_s.toUTF8(@channel.encoding).rmWhiteSpace!
end
end
# Date
if (e = item.elements['issued'] || e = item.elements['created']) && e.text
begin
@date = Time::xmlschema(e.text)
rescue
begin
@date = Time::rfc2822(e.text)
rescue
begin
@date = Time::parse(e.text)
rescue
@date = nil
end
end
end
end
# Creator
@creator = @channel.creator
if (e = item.elements['author/name']) && e.text
@creator = e.text.toUTF8(@channel.encoding).rmWhiteSpace!
end
end
end
end
|