Class: Yarss::Rss::ItemParser

Inherits:
Object
  • Object
show all
Defined in:
lib/yarss/rss/item_parser.rb

Overview

Extract id, title, updated, link and content from a feed item.

validator.w3.org/feed/docs/rss2.html#hrelementsOfLtitemgt

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(data, feed_link: '') ⇒ ItemParser

Returns a new instance of ItemParser.

Parameters:

  • data (Hash) —

    Parsed RSS feed item.

  • feed_link (String) (defaults to: '') —

    Feed link URL.



23
24
25
26
 
# File 'lib/yarss/rss/item_parser.rb', line 23

def initialize(data, feed_link: '')
  self.data      = data
  self.feed_link = feed_link
end

Instance Attribute Details

#data ⇒ Hash

Parsed RSS feed item.

Returns:

  • (Hash) 


14
15
16
 
# File 'lib/yarss/rss/item_parser.rb', line 14

def data
  @data
end

#feed_link ⇒ String

Feed link URL.

Returns:

  • (String) 


19
20
21
 
# File 'lib/yarss/rss/item_parser.rb', line 19

def feed_link
  @feed_link
end

Instance Method Details

#author ⇒ String

Extract the author.

Returns:

  • (String)

Raises:



96
97
98
99
100
101
102
103
104
105
106
107
108
 
# File 'lib/yarss/rss/item_parser.rb', line 96

def author
  author = if data['dc:creator']
             data['dc:creator']
           elsif data['creator']
             data['creator']
           elsif data['author']
             data['author']
           else
             ''
           end

  Attribute.value(author)
end

#description ⇒ String

Extract the content.

Returns:

  • (String) 


113
114
115
116
117
118
119
120
121
122
123
124
 
# File 'lib/yarss/rss/item_parser.rb', line 113

def description
  content = if data['content:encoded']
              data['content:encoded']
            elsif data['description']
              data['description']
            else
              ''
            end

  content = Attribute.value(content)
  Attribute.absolutize_urls(content, feed_link)
end

#guid ⇒ String

Extract the ID. Use the title if guid is not present and title is.

Returns:

  • (String)

Raises:



50
51
52
53
54
55
 
# File 'lib/yarss/rss/item_parser.rb', line 50

def guid
  Attribute.value(data.fetch('guid'))
rescue KeyError => e
  return Digest::MD5.hexdigest(data['title']) if data['title']
  raise ParseError, e
end

#link ⇒ String

Extract the link.

Returns:

  • (String)

Raises:



85
86
87
88
89
 
# File 'lib/yarss/rss/item_parser.rb', line 85

def link
  Attribute.link_value(data.fetch('link'))
rescue KeyError => e
  raise ParseError, e
end

#parse ⇒ Item

Parse out the feed item id, title, updated, link and content and wrap them in a data object.

Returns:

Raises:

  • (ParseError) —

    If a required field is not found.



34
35
36
37
38
39
40
41
42
43
 
# File 'lib/yarss/rss/item_parser.rb', line 34

def parse
  Item.new(
    id:         guid,
    title:      title,
    updated_at: pub_date,
    link:       link,
    author:     author,
    content:    description
  )
end

#pub_date ⇒ DateTime

Extract the updated date.

Returns:

  • (DateTime) 


72
73
74
75
76
77
78
 
# File 'lib/yarss/rss/item_parser.rb', line 72

def pub_date
  DateTime.parse(data.fetch('pubDate'))
rescue ArgumentError => e
  raise ParseError, e
rescue KeyError
  DateTime.now
end

#title ⇒ String

Extract the title. Use guid if title is not present and guid is.

Returns:

  • (String)

Raises:



62
63
64
65
66
67
 
# File 'lib/yarss/rss/item_parser.rb', line 62

def title
  Attribute.value(data.fetch('title'))
rescue KeyError => e
  return Attribute.value(data['guid']) if data['guid']
  raise ParseError, e
end