ruby-feedparser 0.9.7 → 0.11.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Rakefile +29 -28
- data/lib/feedparser/html-output.rb +86 -34
- data/lib/feedparser/version.rb +1 -1
- data/test/tc_item_htmloutput.rb +17 -0
- metadata +8 -8
- data/ChangeLog.md +0 -66
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: '09a6faaf07007f6b349f2655b4e113d5e2603ebb511335860aa04c7b731710bd'
|
4
|
+
data.tar.gz: d8ae04113897d7fec060c875c2989e20d6d77e5c9b29a95403557054baa2242a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 20d3c60812c4a56ef287e9fbf797e283451f6f045fdf368cc9d8e8689f88251ea9e26e53ca91666a46e73f073bd6b05cc1e7c21a6adc89e67d278b0a1176d097
|
7
|
+
data.tar.gz: d0375bf45d0dfd6fa47408b9135ed6e30af4d031e06085ade50b3c2c85060e4c3cd9c0cefe6c7292cb516ed73e0e11f8001786097fc28fc14f6358f7c465f92d
|
data/Rakefile
CHANGED
@@ -9,13 +9,13 @@ require_relative 'lib/feedparser/version.rb'
|
|
9
9
|
PKG_NAME = 'ruby-feedparser'
|
10
10
|
PKG_VERSION = FeedParser::VERSION
|
11
11
|
|
12
|
-
PKG_FILES = [ '
|
12
|
+
PKG_FILES = [ 'README', 'COPYING', 'LICENSE', 'setup.rb', 'Rakefile']
|
13
13
|
Find.find('lib/', 'test/', 'tools/') do |f|
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
14
|
+
if FileTest.directory?(f) and f =~ /\.svn/
|
15
|
+
Find.prune
|
16
|
+
else
|
17
|
+
PKG_FILES << f
|
18
|
+
end
|
19
19
|
end
|
20
20
|
|
21
21
|
PKG_FILES.reject! { |f| f =~ /^test\/(source|.*_output)\// }
|
@@ -23,8 +23,9 @@ PKG_FILES.reject! { |f| f =~ /^test\/(source|.*_output)\// }
|
|
23
23
|
task :default => [:test]
|
24
24
|
|
25
25
|
Rake::TestTask.new do |t|
|
26
|
-
|
27
|
-
|
26
|
+
t.libs << "test"
|
27
|
+
t.test_files = FileList['test/tc_*.rb']
|
28
|
+
t.verbose = true
|
28
29
|
end
|
29
30
|
|
30
31
|
Rake::RDocTask.new do |rd|
|
@@ -50,36 +51,36 @@ end
|
|
50
51
|
|
51
52
|
task :doctoweb => [:rdoc] do |t|
|
52
53
|
# copies the rdoc to the CVS repository for ruby-feedparser website
|
53
|
-
|
54
|
+
# repository is in $CVSDIR (default: ~/dev/ruby-feedparser-web)
|
54
55
|
sh "tools/doctoweb.bash"
|
55
56
|
end
|
56
57
|
|
57
58
|
Rake::PackageTask.new(PKG_NAME, PKG_VERSION) do |p|
|
58
|
-
|
59
|
+
p.need_tar = true
|
59
60
|
p.need_zip = true
|
60
|
-
|
61
|
+
p.package_files = PKG_FILES
|
61
62
|
end
|
62
63
|
|
63
64
|
# "Gem" part of the Rakefile
|
64
65
|
begin
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
66
|
+
spec = Gem::Specification.new do |s|
|
67
|
+
s.platform = Gem::Platform::RUBY
|
68
|
+
s.summary = "Ruby library to parse ATOM and RSS feeds"
|
69
|
+
s.name = PKG_NAME
|
70
|
+
s.version = PKG_VERSION
|
71
|
+
s.requirements << 'none'
|
72
|
+
s.require_path = 'lib'
|
73
|
+
s.autorequire = 'feedparser'
|
74
|
+
s.files = PKG_FILES
|
75
|
+
s.description = "Ruby library to parse ATOM and RSS feeds"
|
76
|
+
s.authors = ['Lucas Nussbaum']
|
77
|
+
s.add_runtime_dependency 'magic'
|
78
|
+
end
|
78
79
|
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
80
|
+
Gem::PackageTask.new(spec) do |pkg|
|
81
|
+
pkg.need_zip = true
|
82
|
+
pkg.need_tar = true
|
83
|
+
end
|
83
84
|
rescue LoadError
|
84
85
|
puts "Will not generate gem."
|
85
86
|
end
|
@@ -2,38 +2,88 @@ require 'feedparser'
|
|
2
2
|
require 'feedparser/filesizes'
|
3
3
|
|
4
4
|
module FeedParser
|
5
|
+
STYLESHEET = <<~EOF
|
6
|
+
<style type="text/css">
|
7
|
+
body {
|
8
|
+
margin: 1em auto;
|
9
|
+
padding: 0px 1em;
|
10
|
+
max-width: 960px;
|
11
|
+
}
|
12
|
+
|
13
|
+
img {
|
14
|
+
max-width: 100%;
|
15
|
+
height: auto;
|
16
|
+
}
|
17
|
+
|
18
|
+
figure {
|
19
|
+
margin: 0px;
|
20
|
+
}
|
21
|
+
|
22
|
+
table.header {
|
23
|
+
margin-bottom: 1em;
|
24
|
+
}
|
25
|
+
|
26
|
+
table.header, table.metadata, table.attachments {
|
27
|
+
font-family: Helvetica, Verdana, sans-serif;
|
28
|
+
}
|
29
|
+
|
30
|
+
table.header, table.metadata, table.attachments, pre {
|
31
|
+
width: 100%;
|
32
|
+
padding: 0.5em;
|
33
|
+
background: #eeeeec;
|
34
|
+
border: 1px solid #babdb6;
|
35
|
+
}
|
36
|
+
|
37
|
+
table.header th, table.metadata th, table.attachments th {
|
38
|
+
text-align: right;
|
39
|
+
width: 50px;
|
40
|
+
}
|
41
|
+
|
42
|
+
blockquote {
|
43
|
+
font-style: italic;
|
44
|
+
color: #2e3436;
|
45
|
+
border-left: 2px solid #babdb6;
|
46
|
+
padding-left: 0.5em;
|
47
|
+
}
|
48
|
+
|
49
|
+
hr {
|
50
|
+
border: none;
|
51
|
+
border-top: 1px solid #babdb6;
|
52
|
+
margin: 1em auto
|
53
|
+
}
|
54
|
+
</style>
|
55
|
+
EOF
|
5
56
|
class Feed
|
6
57
|
def to_html(localtime = true)
|
7
58
|
s = ''
|
8
|
-
s +=
|
9
|
-
s += "
|
10
|
-
s += "<html>\n"
|
59
|
+
s += "<!doctype html>\n"
|
60
|
+
s += "<html lang=en>\n"
|
11
61
|
s += "<head>\n"
|
62
|
+
s += "<meta charset=\"utf-8\"/>\n"
|
12
63
|
s += "<title>#{@title.escape_html}</title>\n"
|
13
|
-
s +=
|
64
|
+
s += FeedParser::STYLESHEET
|
14
65
|
s += "</head>\n"
|
15
66
|
s += "<body>\n"
|
16
67
|
|
17
68
|
s += <<-EOF
|
18
|
-
<table
|
19
|
-
<table width="100%" bgcolor="#EDEDED" cellpadding="4" cellspacing="2">
|
69
|
+
<table class="feed-header">
|
20
70
|
EOF
|
21
71
|
r = ""
|
22
72
|
r += "<a href=\"#{@link}\">\n" if @link
|
23
73
|
if @title
|
24
|
-
r +=
|
74
|
+
r += @title.escape_html
|
25
75
|
elsif @link
|
26
|
-
r +=
|
76
|
+
r += @link.escape_html
|
27
77
|
else
|
28
|
-
r += "
|
78
|
+
r += "Unnamed feed"
|
29
79
|
end
|
30
80
|
r += "</a>\n" if @link
|
31
|
-
headline = "<tr><
|
81
|
+
headline = "<tr><th>%s</th>\n<td>%s</td></tr>"
|
32
82
|
s += (headline % ["Feed title:", r])
|
33
83
|
s += (headline % ["Type:", @type])
|
34
84
|
s += (headline % ["Encoding:", @encoding])
|
35
85
|
s += (headline % ["Creator:", @creator.escape_html]) if @creator
|
36
|
-
s += "</table
|
86
|
+
s += "</table>\n"
|
37
87
|
|
38
88
|
if @description and @description !~ /\A\s*</m
|
39
89
|
s += "<br/>\n"
|
@@ -51,44 +101,47 @@ module FeedParser
|
|
51
101
|
|
52
102
|
class FeedItem
|
53
103
|
def to_html_with_headers(localtime = true)
|
54
|
-
s =
|
55
|
-
|
56
|
-
<
|
57
|
-
<
|
58
|
-
|
104
|
+
s = "<!doctype html>\n"
|
105
|
+
s += '<html lang="en">'
|
106
|
+
s += '<head>'
|
107
|
+
s += '<meta charset="utf-8"/>'
|
108
|
+
s += "<title>#{@title.escape_html}</title>\n"
|
109
|
+
s += FeedParser::STYLESHEET
|
110
|
+
s += '</head>'
|
111
|
+
s += '<body>'
|
59
112
|
s += to_html(localtime)
|
60
|
-
s += "
|
113
|
+
s += "</body>"
|
114
|
+
s += "</html>"
|
61
115
|
s
|
62
116
|
end
|
63
117
|
|
64
118
|
def to_html(localtime = true)
|
65
119
|
s = <<-EOF
|
66
|
-
<table
|
67
|
-
<table width="100%" bgcolor="#EDEDED" cellpadding="4" cellspacing="2">
|
120
|
+
<table class="header">
|
68
121
|
EOF
|
69
122
|
r = ""
|
70
123
|
r += "<a href=\"#{@feed.link}\">\n" if @feed.link
|
71
124
|
if @feed.title
|
72
|
-
r +=
|
125
|
+
r += @feed.title.escape_html
|
73
126
|
elsif @feed.link
|
74
|
-
r +=
|
127
|
+
r += @feed.link.escape_html
|
75
128
|
else
|
76
|
-
r += "
|
129
|
+
r += "Unnamed feed"
|
77
130
|
end
|
78
131
|
r += "</a>\n" if @feed.link
|
79
|
-
headline = "<tr><
|
132
|
+
headline = "<tr><th>%s</th>\n<td>%s</td></tr>"
|
80
133
|
s += (headline % ["Feed:", r])
|
81
134
|
|
82
135
|
r = ""
|
83
136
|
r += "<a href=\"#{link}\">" if link
|
84
137
|
if @title
|
85
|
-
r +=
|
138
|
+
r += @title.escape_html
|
86
139
|
elsif link
|
87
|
-
r +=
|
140
|
+
r += link.escape_html
|
88
141
|
end
|
89
142
|
r += "</a>\n" if link
|
90
143
|
s += (headline % ["Item:", r])
|
91
|
-
s += "</table
|
144
|
+
s += "</table>\n"
|
92
145
|
s += "\n"
|
93
146
|
if @content and @content !~ /\A\s*</m
|
94
147
|
s += "<br/>\n"
|
@@ -96,19 +149,18 @@ module FeedParser
|
|
96
149
|
s += "#{@content}" if @content
|
97
150
|
if @enclosures and @enclosures.length > 0
|
98
151
|
s += <<-EOF
|
99
|
-
<table
|
100
|
-
<table width="100%" bgcolor="#EDEDED" cellpadding="2" cellspacing="2">
|
152
|
+
<table class="attachments">
|
101
153
|
EOF
|
102
|
-
s += '<tr><
|
154
|
+
s += '<tr><th>Files:</th></tr>'
|
103
155
|
s += "\n"
|
104
156
|
@enclosures.each do |e|
|
105
|
-
s += "<tr><td
|
157
|
+
s += "<tr><td><a href=\"#{e[0]}\">#{e[0].split('/')[-1]}</a> (#{e[1].to_i.to_human_readable}, #{e[2]})</td></tr>\n"
|
106
158
|
end
|
107
|
-
s += "</table
|
159
|
+
s += "</table>\n"
|
108
160
|
end
|
109
|
-
s += "\n<hr
|
110
|
-
s += '<table
|
111
|
-
l = '<tr><
|
161
|
+
s += "\n<hr/>\n"
|
162
|
+
s += '<table class="metadata">' + "\n"
|
163
|
+
l = '<tr><th>%s</th><td>%s</td></tr>' + "\n"
|
112
164
|
if @date
|
113
165
|
if localtime
|
114
166
|
s += l % [ 'Date:', @date.to_s ]
|
data/lib/feedparser/version.rb
CHANGED
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require 'feedparser'
|
3
|
+
require 'feedparser/html-output'
|
4
|
+
|
5
|
+
|
6
|
+
class ItemHTMLOutputTest < Test::Unit::TestCase
|
7
|
+
def test_html_with_headers
|
8
|
+
feed = FeedParser::Feed.new
|
9
|
+
item = FeedParser::FeedItem.new(nil, feed)
|
10
|
+
item.title = "Some great title"
|
11
|
+
item.content = "Lorem ipsum ..."
|
12
|
+
html = item.to_html_with_headers(false)
|
13
|
+
assert_match(/Some great title/, html)
|
14
|
+
assert_match(/Lorem ipsum .../, html)
|
15
|
+
assert_match(/<style type="text\/css">/, html)
|
16
|
+
end
|
17
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ruby-feedparser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.11.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Lucas Nussbaum
|
8
8
|
autorequire: feedparser
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2023-02-11 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: magic
|
@@ -25,13 +25,12 @@ dependencies:
|
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
27
|
description: Ruby library to parse ATOM and RSS feeds
|
28
|
-
email:
|
28
|
+
email:
|
29
29
|
executables: []
|
30
30
|
extensions: []
|
31
31
|
extra_rdoc_files: []
|
32
32
|
files:
|
33
33
|
- COPYING
|
34
|
-
- ChangeLog.md
|
35
34
|
- LICENSE
|
36
35
|
- README
|
37
36
|
- Rakefile
|
@@ -50,16 +49,17 @@ files:
|
|
50
49
|
- test/tc_feeditem.rb
|
51
50
|
- test/tc_html2text_parser.rb
|
52
51
|
- test/tc_htmloutput.rb
|
52
|
+
- test/tc_item_htmloutput.rb
|
53
53
|
- test/tc_parser.rb
|
54
54
|
- test/tc_sgml_parser.rb
|
55
55
|
- test/tc_textoutput.rb
|
56
56
|
- test/tc_textwrappedoutput.rb
|
57
57
|
- test/ts_feedparser.rb
|
58
58
|
- tools/doctoweb.bash
|
59
|
-
homepage:
|
59
|
+
homepage:
|
60
60
|
licenses: []
|
61
61
|
metadata: {}
|
62
|
-
post_install_message:
|
62
|
+
post_install_message:
|
63
63
|
rdoc_options: []
|
64
64
|
require_paths:
|
65
65
|
- lib
|
@@ -75,8 +75,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
75
75
|
version: '0'
|
76
76
|
requirements:
|
77
77
|
- none
|
78
|
-
rubygems_version: 3.
|
79
|
-
signing_key:
|
78
|
+
rubygems_version: 3.3.15
|
79
|
+
signing_key:
|
80
80
|
specification_version: 4
|
81
81
|
summary: Ruby library to parse ATOM and RSS feeds
|
82
82
|
test_files: []
|
data/ChangeLog.md
DELETED
@@ -1,66 +0,0 @@
|
|
1
|
-
# 0.9.4 (25/03/2016)
|
2
|
-
|
3
|
-
Bug fixes:
|
4
|
-
|
5
|
-
* feedparser: relax exception check for Magic errors; by Eric Wong
|
6
|
-
* Always sort author list to avoid unecessary invalidation of caches; by Sébastien Dailly
|
7
|
-
|
8
|
-
# 0.7 (27/07/2009)
|
9
|
-
|
10
|
-
* Handled several creators per feed item
|
11
|
-
* Fix bug with urls into tag attributes
|
12
|
-
* Better item categories support
|
13
|
-
* Reworked text output formatting
|
14
|
-
* Ignore ­, as some blog software (dotclear2) misuse it.
|
15
|
-
|
16
|
-
# 0.6 (23/07/2008)
|
17
|
-
|
18
|
-
* Moved `to_human_readable` from class Fixnum to class Integer.
|
19
|
-
* Correctly parse http://www.tbray.org/ongoing/ongoing.atom. Thanks
|
20
|
-
to Janico Greifenberg for reporting this.
|
21
|
-
* String#html2text now takes an additional wrapto parameter, allowing
|
22
|
-
to wrap the text to a specified number of chars. Thanks to
|
23
|
-
Maxime Petazzoni for the patch.
|
24
|
-
|
25
|
-
# 0.5 (26/10/2007)
|
26
|
-
|
27
|
-
* Fixed a bug with items with both non-escaped and escaped HTML. Reported,
|
28
|
-
then patch provided by Gregory Hartman <gghartma@cs.cmu.edu>.
|
29
|
-
* In Atom feeds, use the date provided in <updated>, and use it in
|
30
|
-
preference to the one in <published> if both are available.
|
31
|
-
Closes gna bug #8987.
|
32
|
-
* "require 'feedparser'" now requires 'feedparser/text-output'. Fixes a bug
|
33
|
-
reported by Sebastian Probst Eide.
|
34
|
-
* Make checks for HTML tags case-insensitive. Broke Dilbert feeds!!
|
35
|
-
Reported by Michal Čihař. Closes gna bug #10199.
|
36
|
-
|
37
|
-
# 0.4 (01/05/2007)
|
38
|
-
|
39
|
-
* Fixed a problem with html entities in the items' titles.
|
40
|
-
* Date was not fetched for blogspot's atom feeds.
|
41
|
-
Patch from Jason Ling <jason.ling@jeyel.com>.
|
42
|
-
* Tests are now timezone-friendly. (closes GNA bug #8145).
|
43
|
-
* Much nicer text output.
|
44
|
-
|
45
|
-
# 0.3 (01/12/2006)
|
46
|
-
|
47
|
-
* Much nicer HTML output
|
48
|
-
* Fixed a problem with some feeds with broken enclosures (without url)
|
49
|
-
* Now automatically fixes non-absolute `<a href>` or `<img src>`
|
50
|
-
* Fixed small parser bugs
|
51
|
-
* Now displays enclosures in the text and html outputs. Ready for
|
52
|
-
podcasting :-)
|
53
|
-
* Now escape title, creator, subject and category internally. This minor
|
54
|
-
fix avoids & stuff in the titles, for example.
|
55
|
-
|
56
|
-
* 0.2 (05/06/2006)
|
57
|
-
|
58
|
-
* Fixed a problem when parsing some ATOM feeds with <link> without type
|
59
|
-
attribute. (Thanks Michal Cihar !)
|
60
|
-
* FeedParser::Feed and FeedParser::FeedItem now have an xml attribute to
|
61
|
-
get the related REXML::Element.
|
62
|
-
* <enclosure/> support in RSS.
|
63
|
-
|
64
|
-
# 0.1 (24/11/2005)
|
65
|
-
|
66
|
-
* first public release.
|