Skip to content

V
venjob
Commit ff7e4214 by Huynh Thien Phuoc
Options

Created crontab

parent b7d32095
Showing with 9 additions and 12 deletions
.~lock.jobs.csv# deleted 100644 → 0
,phuocht,devops-OptiPlex-3010,27.07.2020 10:41,file:///home/phuocht/.config/libreoffice/4;
\ No newline at end of file
jobs.csv
This source diff could not be displayed because it is too large. You can view the blob instead.
lib/src/crontab.rb
...@@ -6,17 +6,16 @@ class Crontab ...@@ -6,17 +6,16 @@ class Crontab
if link.include?('\u2019') if link.include?('\u2019')
link.gsub!('\u2019',"'") link.gsub!('\u2019',"'")
end end
if link == 'javascript:void(0);' next if link == 'javascript:void(0);'
next
elsif link != 'https://careerbuilder.vn/vi/nha-tuyen-dung/hr-vietnam\xE2\x80\x99s-ess-client.35A4EFBA.html' elsif link != 'https://careerbuilder.vn/vi/nha-tuyen-dung/hr-vietnam\xE2\x80\x99s-ess-client.35A4EFBA.html'
company_page = Nokogiri::HTML(URI.open(URI.parse(URI.escape(link)))) company_page = Nokogiri::HTML(URI.open(URI.parse(CGI.escape(link))))
if company_page.search('p.name').text != nil if !(company_page.search('p.name').text).nil?
begin begin
name_company = company_page.search('p.name').text name_company = company_page.search('p.name').text
address_company = company_page.css('div.content p').children[1].text address_company = company_page.css('div.content p').children[1].text
introduction_company = company_page.css('div.main-about-us').text introduction_company = company_page.css('div.main-about-us').text
get_name_company = Company.find_by(name: "#{name_company}") get_name_company = Company.find_by(name: name_company)
if get_name_company == nil if get_name_company.nil?
company = Company.create!(name: name_company, company = Company.create!(name: name_company,
address: address_company, address: address_company,
introduction: introduction_company) introduction: introduction_company)
...@@ -35,17 +34,17 @@ class Crontab ...@@ -35,17 +34,17 @@ class Crontab
if link.include?('\u2013') if link.include?('\u2013')
link.gsub!('\u2013','–') link.gsub!('\u2013','–')
end end
page_job = Nokogiri::HTML(URI.open(URI.parse(URI.escape(link)))) page_job = Nokogiri::HTML(URI.open(URI.parse(CGI.escape(link))))
get_row = page_job.search('div.bg-blue div.row') get_row = page_job.search('div.bg-blue div.row')
if get_row != "" if get_row != ""
get_name_company = page_job.search('div.job-desc a.job-company-name').text.strip get_name_company = page_job.search('div.job-desc a.job-company-name').text.strip
company_table = Company.find_by(name: "#{get_name_company}") company_table = Company.find_by(name: get_name_company)
title_job = page_job.search('div.job-desc p').text title_job = page_job.search('div.job-desc p').text
description = page_job.search('div.detail-row') description = page_job.search('div.detail-row')
arr_column = get_row.css('div.has-background').map{ |data| data.text.split(' ').join(' ') } arr_column = get_row.css('div.has-background').map{ |data| data.text.split(' ').join(' ') }
job_table = Job.find_by(title: "#{title_job}") job_table = Job.find_by(title: title_job)
arr_column.each_with_index do | val, key | arr_column.each_with_index do | val, key |
if company_table != nil if !company_table.nil?
if val.include?('Ngày cập nhật') if val.include?('Ngày cập nhật')
arr_data = val.gsub('Ngày cập nhật ','').split(' ') arr_data = val.gsub('Ngày cập nhật ','').split(' ')
date = arr_data.first date = arr_data.first
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment