Class: HTML2FB::Parser
- Inherits:
-
Object
- Object
- HTML2FB::Parser
- Defined in:
- lib/Html2Feedbooks/parser.rb
Instance Method Summary collapse
-
#initialize(conf) ⇒ Parser
constructor
A new instance of Parser.
- #parse(txt) ⇒ Object
Constructor Details
#initialize(conf) ⇒ Parser
Returns a new instance of Parser.
11 12 13 |
# File 'lib/Html2Feedbooks/parser.rb', line 11 def initialize(conf) @conf=conf end |
Instance Method Details
#parse(txt) ⇒ Object
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 |
# File 'lib/Html2Feedbooks/parser.rb', line 15 def parse(txt) puts "Parsing HTML" pdoc=Nokogiri::HTML(txt) if @conf['conv'] mc=pdoc/'meta[@http-equiv="Content-Type"]' if mc.size>0 charset=mc.first.attributes['content'].to_s.split(';').find do |s| s.strip[0,7]=='charset' end unless charset.nil? tc=charset.split('=').last.strip end unless tc.nil? puts "Trying to convert source encoding from #{tc} to utf-8" require 'iconv' pdoc=Nokogiri::HTML(Iconv.conv('utf-8',tc.downcase,txt)) end end end doc=Document.new puts "Removing garbage elements" remove_objs(pdoc) ti=pdoc.at('title') doc.title= ti.text.strip unless ti.nil? # pdoc.search('//h3').each do |e| # doc.content.push(e.inner_text) # end puts "Building TOC" parse_text(pdoc,doc) # puts green(bold(doc.pretty_inspect)) return doc end |