以下代码会废弃网站的不同部分。基本上我对每个部分都有一些方法,然后是一个方法(parse_details
),它将所有哈希合并为一个:
class Parser
def parse_details(html)
merged_hashes = {}
array_of_hashes = [
self.parse_department(html),
self.parse_super_saver(html),
]
array_of_hashes.inject(merged_hashes,:update)
return merged_hashes
end
def parse_department(file)
html = file
data = Nokogiri::HTML(open(html))
department = data.css('#ref_2619534011')
@department_hash = {}
department.css('li').drop(1).each do | department |
department_title = department.css('.refinementLink').text
department_count = department.css('.narrowValue').text[/[\d,]+/].delete(",").to_i
@department_hash[:department] ||= {}
@department_hash[:department]["Pet Supplies"] ||= {}
@department_hash[:department]["Pet Supplies"][department_title] = department_count
end
return @department_hash
end
def parse_super_saver(file)
html = file
data = Nokogiri::HTML(open(html))
super_saver = data.css('#ref_2661623011')
@super_saver_hash = {}
super_saver.css('li').each do | super_saver |
super_saver_title = super_saver.css('.refinementLink').text
super_saver_count = super_saver.css('.narrowValue').text[/[\d,]+/].delete(",").to_i
@super_saver_hash[:super_saver] ||= {}
@super_saver_hash[:super_saver][super_saver_title] = super_saver_count
end
return @super_saver_hash
end
正如您所看到的,我正在多次呼叫Nokogiri::HTML(open(html))
。
有人建议我做这样的事情:
def self.parse(html)
doc = Nokogiri::HTML html
self.parse_details(doc) unless doc.nil?
end
所以我只打电话给Nokogiri::HTML
一次。
但是我被卡住了,例如我不知道如果他们使用新的department = data.css('#ref_2619534011')
方法,他们应该使用parse
这样的部分怎么办?我还对如何处理html
和file
参数感到困惑。使用新的parse
方法后,我应该将它们留在那里还是删除它们?
关于如何实现我想要的任何建议?
答案 0 :(得分:1)
简单转换:
class Parser
def initialize(url)
@data = Nokogiri.HTML(open(url))
end
def parse_details()
{}.tap do |merged_hashes|
array_of_hashes = [
parse_department(),
parse_super_saver(),
]
array_of_hashes.inject(merged_hashes,:update)
end
end
def parse_department()
department = @data.css('#ref_2619534011')
@department_hash = {}
department.css('li').drop(1).each do | department |
department_title = department.css('.refinementLink').text
department_count = department.css('.narrowValue').text[/[\d,]+/].delete(",").to_i
@department_hash[:department] ||= {}
@department_hash[:department]["Pet Supplies"] ||= {}
@department_hash[:department]["Pet Supplies"][department_title] = department_count
end
@department_hash
end
def parse_super_saver()
super_saver = @data.css('#ref_2661623011')
@super_saver_hash = {}
super_saver.css('li').each do | super_saver |
super_saver_title = super_saver.css('.refinementLink').text
super_saver_count = super_saver.css('.narrowValue').text[/[\d,]+/].delete(",").to_i
@super_saver_hash[:super_saver] ||= {}
@super_saver_hash[:super_saver][super_saver_title] = super_saver_count
end
@super_saver_hash
end
end
如果您实际上不需要@department_hash
和@super_saver_hash
作为实例变量,则可以选择将它们转换为我在tap
中使用的parse_details
样式。
如果你根本不需要将它作为一个类,而只是一组方法,那么请考虑:
module Parser
def self.parse_details(url)
data = Nokogiri.HTML(open(url))
{}.tap do |merged_hashes|
array_of_hashes = [
parse_department(data),
parse_super_saver(data),
]
array_of_hashes.inject(merged_hashes,:update)
end
end
def self.parse_department(data)
{}.tap do |department_hash|
data.css('#ref_2619534011 li').drop(1).each do | department |
department_title = department.css('.refinementLink').text
department_count = department.css('.narrowValue').text[/[\d,]+/].delete(",").to_i
department_hash[:department] ||= {}
department_hash[:department]["Pet Supplies"] ||= {}
department_hash[:department]["Pet Supplies"][department_title] = department_count
end
end
end
def self.parse_super_saver(data)
{}.tap do |super_saver_hash|
data.css('#ref_2661623011 li').each do |super_saver|
super_saver_title = super_saver.css('.refinementLink').text
super_saver_count = super_saver.css('.narrowValue').text[/[\d,]+/].delete(",").to_i
super_saver_hash[:super_saver] ||= {}
super_saver_hash[:super_saver][super_saver_title] = super_saver_count
end
end
end