Class: Rsssf::PageFetcher

Inherits:
Object
  • Object
show all
Includes:
Filters
Defined in:
lib/rsssf/fetch.rb

Instance Method Summary collapse

Methods included from Filters

#html_to_txt, #sanitize

Constructor Details

#initialize ⇒ PageFetcher

Returns a new instance of PageFetcher.



10
11
12
 
# File 'lib/rsssf/fetch.rb', line 10

def initialize
  @worker = Fetcher::Worker.new
end

Instance Method Details

#fetch(src_url) ⇒ Object 



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
 
# File 'lib/rsssf/fetch.rb', line 14

def fetch( src_url )

  ## note: assume plain 7-bit ascii for now
  ##  -- assume rsssf uses ISO_8859_15 (updated version of ISO_8859_1) -- does NOT use utf-8 character encoding!!!
  html = @worker.read( src_url )  

  ### todo/fix: first check if html is all ascii-7bit e.g.
  ## includes only chars from 64 to 127!!!

  ## normalize newlines
  ##   remove \r (form feed) used by Windows; just use \n (new line)
  html = html.gsub( "\r", '' )

  ## note:
  ##   assume (default) to ISO 3166-15 (an updated version of ISO 3166-1) for now
  ##
  ##  other possible alternatives - try:
  ##  - Windows CP 1562  or
  ##  - ISO 3166-2  (for eastern european languages )
  ##
  ## note: german umlaut use the same code (int)
  ##    in ISO 3166-1/15 and 2 and Windows CP1562  (other chars ARE different!!!)

  html = html.force_encoding( Encoding::ISO_8859_15 )
  html = html.encode( Encoding::UTF_8 )    # try conversion to utf-8

  ## check for html entities
  html = html.gsub( "ä", 'ä' )
  html = html.gsub( "ö", 'ö' )
  html = html.gsub( "ü", 'ü' )
  html = html.gsub( "Ä", 'Ä' )
  html = html.gsub( "Ö", 'Ö' )
  html = html.gsub( "Ü", 'Ü' )
  html = html.gsub( "ß", 'ß' )

  html = html.gsub( "&oulm;", 'ö' )    ## support typo in entity (ö)
  html = html.gsub( "&slig;", "ß" )    ## support typo in entity (ß)
  
  html = html.gsub( "É", 'É' )
  html = html.gsub( "ø", 'ø' )
  
  ## check for more entities
  html = html.gsub( /&[^;]+;/) do |match|
    puts "*** found unencoded html entity #{match}"
    match   ## pass through as is (1:1)
  end
  ## todo/fix: add more entities


  txt   = html_to_txt( html )

  header = <<EOS
<!--
   source: #{src_url}
  -->

EOS

  header+txt  ## return txt w/ header
end