Module: Tzispa::Helpers::Crawler
- Includes:
- HashTrans
- Defined in:
- lib/tzispa/helpers/crawler.rb
Defined Under Namespace
Classes: CrawlerError
Instance Method Summary collapse
- #crawler_save_file(url, dest_file, accept_schemes = ['http', 'https', 'ftp']) ⇒ Object
- #crawler_table(noko, table_path, columns) ⇒ Object
- #crawler_table_to_dl(noko, table_path, columns, excluded_terms: [], fussion_terms: {}) ⇒ Object
- #crawler_table_to_list(noko, table_path, excluded_terms: []) ⇒ Object
- #crawler_to_markdown(source) ⇒ Object
Methods included from HashTrans
Instance Method Details
#crawler_save_file(url, dest_file, accept_schemes = ['http', 'https', 'ftp']) ⇒ Object
20 21 22 23 24 25 26 27 28 29 30 31 |
# File 'lib/tzispa/helpers/crawler.rb', line 20 def crawler_save_file(url, dest_file, accept_schemes = ['http', 'https', 'ftp']) begin uri = URI(url) raise ArgumentError.new "Inavlid url: #{url}" unless accept_schemes.include?(uri.scheme) && uri.host File.delete(dest_file) if File.exist?(dest_file) File.open("#{dest_file}", 'wb') do |fo| fo.write open(url).read end rescue => ex raise CrawlerError.new "Error in crawler_save_file '#{url}': #{ex.}" end end |
#crawler_table(noko, table_path, columns) ⇒ Object
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 |
# File 'lib/tzispa/helpers/crawler.rb', line 66 def crawler_table(noko, table_path, columns) Hash.new.tap { |sections| htmee = HTMLEntities.new(:expanded) noko = noko.xpath(table_path) colspans = "td[@colspan=\"#{columns}\"]" if noko.xpath(colspans).count == 0 noko.collect { |row| dterm = htmee.decode(row.at_xpath('td[1]')&.content).gsub(/\n|\r|\t/,' ').strip unless dterm.empty? sections[dterm] ||= Array.new sections[dterm] << (2..columns).map { |i| ReverseMarkdown.convert( htmee.decode(row.at_xpath("td[#{i}]")&.children&.to_s || row.at_xpath("td[#{i}]")&.to_s).strip, unknown_tags: :bypass ).gsub(/\r|\t/,' ').strip }.join('\n') end } else current_section = nil noko.collect { |row| unless row.xpath(colspans)&.text.strip.empty? current_section = htmee.decode(row.xpath("td[@colspan=\"#{columns}\"]").text).gsub(/\n|\r|\t/,' ').strip sections[current_section] ||= Array.new else if current_section sections[current_section] << (1..columns).map { |i| ReverseMarkdown.convert( htmee.decode(row.at_xpath("td[#{i}]")&.children&.to_s.strip || row.at_xpath("td[#{i}]")&.to_s.strip), unknown_tags: :bypass ).strip }.join(': ') end end } end } end |
#crawler_table_to_dl(noko, table_path, columns, excluded_terms: [], fussion_terms: {}) ⇒ Object
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
# File 'lib/tzispa/helpers/crawler.rb', line 42 def crawler_table_to_dl(noko, table_path, columns, excluded_terms: [], fussion_terms:{}) String.new.tap { |content| markdown = Redcarpet::Markdown.new(Redcarpet::Render::HTML.new) sections = crawler_table(noko, table_path, columns) hash_fussion! sections, fussion_terms unless sections.empty? content << '<dl>' sections.sort.each { |key, value| unless key.empty? || value.empty? || excluded_terms.include?(UnicodeUtils.downcase key) content << "<dt>#{key}</dt>" if value.is_a?(Array) && value.count > 1 content << '<ul>' << value.map { |item| "<li>#{markdown.render item}</li>"}.join("\n") << '</ul>' elsif value.is_a?(Array) && value.count == 1 content << "<dd>#{markdown.render value.first}</dd>" else content << "<dd>#{markdown.render value}</dd>" end end } content << "</dl>" end } end |
#crawler_table_to_list(noko, table_path, excluded_terms: []) ⇒ Object
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 |
# File 'lib/tzispa/helpers/crawler.rb', line 103 def crawler_table_to_list(noko, table_path, excluded_terms: []) htmee = HTMLEntities.new(:expanded) markdown = Redcarpet::Markdown.new(Redcarpet::Render::HTML.new) String.new.tap { |list| list << '<ul>' list << Array.new.tap { |lines| noko.xpath(table_path).collect { |td| line = if td.xpath('table/tr/td').count > 0 crawler_table(td, 'table/tr', 2) else raw_ln = ReverseMarkdown.convert(td&.children&.to_s.strip, unknown_tags: :bypass) raw_ln unless raw_ln.empty? || excluded_terms.include?(raw_ln) end if line&.is_a? String lines << "<li>#{htmee.decode(markdown.render line)}</li>" elsif line.is_a? Hash line&.map { |key, value| lines << "<li><strong>#{key}</strong>: #{value} </li>" unless excluded_terms.include?(key) || excluded_terms.include?(value) }.join("\n") else line&.map { |v| lines << "<li>#{v}</li>" unless excluded_terms.include?(v) }.join("\n") end } }.join("\n") list << '</ul>' } end |
#crawler_to_markdown(source) ⇒ Object
33 34 35 36 37 38 39 40 |
# File 'lib/tzispa/helpers/crawler.rb', line 33 def crawler_to_markdown(source) begin source = source.read if source.respond_to? :read htmee = HTMLEntities.new ReverseMarkdown.convert(htmee.decode(source).strip, unknown_tags: :bypass) rescue Encoding::UndefinedConversionError end end |