Created
November 25, 2015 00:45
-
-
Save StephenFiser/c4ded819638826e5b037 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'open-uri' | |
class Webpage | |
attr_reader :address | |
def initialize(address) | |
@address = address | |
end | |
def headlines | |
HeadlineFinder.new(page_content).results | |
end | |
private | |
def page_content | |
@content ||= open(address).read | |
end | |
end | |
class HeadlineFinder | |
attr_reader :text | |
TAG_NAMES = ["h1", "h2", "h3", "h4"] | |
def initialize(text) | |
@text = text | |
end | |
def results | |
TAG_NAMES.map do |tag_name| | |
TagBuilder.all_content_for(tag_name, text) | |
end.flatten.compact | |
end | |
end | |
class TagBuilder | |
class << self | |
def all_content_for(name, context) | |
headlines = [] | |
offset = 0 | |
until offset == "at the end" | |
headline = new(name, context, offset) | |
headlines << headline | |
offset = headline.next_offset | |
end | |
headlines | |
end | |
end | |
attr_reader :name, :context, :opening, :closing | |
def initialize(name, context, offset = 0) | |
@name = name | |
@context = context | |
@opening = OpeningTag.new(name, context, offset) | |
@closing = ClosingTag.new(name, context, offset) | |
end | |
def content | |
return nil unless content_available? | |
if context.index(name) != nil | |
context[content_start..content_finish] | |
else | |
"Could not find any #{name} tags." | |
end | |
end | |
def content_start | |
opening.finish + 1 | |
end | |
def content_finish | |
closing.start - 1 | |
end | |
def next_offset | |
if opening.start != nil | |
closing.final_position | |
else | |
"at the end" | |
end | |
end | |
def content_available? | |
opening.present? && closing.present? | |
end | |
end | |
class OpeningTag | |
attr_reader :name, :context, :offset | |
def initialize(name, context, offset = 0) | |
@name = name | |
@context = context | |
@offset = offset | |
end | |
def present? | |
start != nil && finish != nil | |
end | |
def start | |
context.index("<#{name}", offset) | |
end | |
def finish | |
context.index(">", start) | |
end | |
end | |
class ClosingTag | |
attr_reader :name, :context, :offset | |
def initialize(name, context, offset = 0) | |
@name = name | |
@context = context | |
@offset = offset | |
end | |
def present? | |
start != nil | |
end | |
def start | |
context.index("</#{name}>", offset) | |
end | |
def final_position | |
# 3 for the <, /, and > | |
start + 3 + name.length | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment