require 'nokogiri'
require 'open-uri'

response = open('https://elcomercio.pe/politica?ref=home&ft=menu')
page = Nokogiri::HTML(response)
articles = []

page.css("article .flow-detail .flow-title").each do |title_info|
  articles << {
    link: title_info.search("a").attr("href").content,
    title: title_info.content.strip
  }
end

puts articles

import requests
from bs4 import BeautifulSoup

response = requests.get("https://elcomercio.pe/politica?ref=home&ft=menu")
page = BeautifulSoup(response.text, "html.parser")
articles = []

for article in page.select("article .flow-detail .flow-title"):
    article_info = {
      "link": article.a["href"],
      "title": article.get_text()
    }
    articles.append(article_info)

print(articles)

require 'nokogiri'
require 'open-uri'
require 'json'

url = 'http://www2.congreso.gob.pe/Sicr/TraDocEstProc/CLProLey2016.nsf/Local%20Por%20Numero%20Inverso?OpenView'
response = open(url)
page = Nokogiri::HTML(response)
projects = []

page.css('table')[1].css('tr').each do |tr|
  a_tag = tr.css('td').first
  next if a_tag.nil?

  project_url = 'http://www2.congreso.gob.pe' + a_tag.search('a').attr('href').content
  project_page = Nokogiri::HTML(open(project_url))
  projects << {
    link: project_url,
    name: tr.css('td')[4].content,
    group: project_page.css('table table tr td')[11].content
  }
end

File.open("proyectos_de_ley.json", "w") do |file|
  file.puts projects.to_json
end

import requests
from bs4 import BeautifulSoup

url = "http://www2.congreso.gob.pe/Sicr/TraDocEstProc/CLProLey2016.nsf/Local%20Por%20Numero%20Inverso?OpenView"
response = requests.get(url)
page = BeautifulSoup(response.text, "html.parser")
projects = []

for tr in page.select("table")[1].select("tr"):
    a_tag = tr.select('td')
    if not a_tag:
        continue
    
    project_url = 'http://www2.congreso.gob.pe' + a_tag[0].a['href']
    project_page = BeautifulSoup(requests.get(project_url).text, "html.parser")
    projects.append({
        'link': project_url,
        'name': tr.select('td')[4].get_text(),
        'group': project_page.select('table table tr td')[10].get_text()
    })

print(projects)