[Résumé du scraping] | Python Node.js PHP Ruby Go VBA | Scraping Yahoo Top en 6 langues

Python

Vidéo

Dépôt

https://github.com/yuzuru-program/scraping-python-yahoo

La source

index.py

import urllib.request as request
from bs4 import BeautifulSoup

req = request.Request(
    "https://www.yahoo.co.jp",
    None,
    {}
)

instance = request.urlopen(req)
soup = BeautifulSoup(instance, "html.parser")

li = soup.select('main article section ul')[0].select('li')

for m in li:
    print(m.text)
    print(m.select("a")[0].get("href"))
    print()

Node.js

Vidéo

Dépôt

https://github.com/yuzuru-program/scraping-node-yahoo

La source

package.json

{
  "dependencies": {
    "cheerio": "^1.0.0-rc.3",
    "node-fetch": "^2.6.0"
  }
}

index.js

const fetch = require('node-fetch');
const cheerio = require('cheerio');

const main = async () => {
  // https://www.yahoo.co.jp/Lancer une demande à
  const _ret = await fetch('https://www.yahoo.co.jp/', {
    method: 'get',
    headers: {
      'User-Agent':
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
    },
    referrer: '',
  }).catch((err) => {
    console.log(err);
  });

  if (_ret.status !== 200) {
    console.log(`error status:${_ret.status}`);
    return;
  }

  //Converti pour être utilisé avec les ticks jquery
  const $ = cheerio.load(await _ret.text());

  const _li = $('main article section ul').eq(0).find('li');

  //Afficher les principales actualités Yahoo
  _li.map(function (i) {
    console.log(_li.eq(i).text());
    console.log(_li.eq(i).find('a').attr()['href']);
    console.log();
  });
};

main();

PHP

Vidéo

Dépôt

https://github.com/yuzuru-program/scraping-php-yahoo

La source

index.php

<?php

require_once './phpQuery-onefile.php';

function my_curl($url)
{
  $cp = curl_init();

  /*option:Obtenir la page vers laquelle rediriger une fois redirigé*/
  curl_setopt($cp, CURLOPT_RETURNTRANSFER, 1);

  /*option:Spécifiez l'URL*/
  curl_setopt($cp, CURLOPT_URL, $url);

  /*option:Spécifiez le délai d'expiration*/
  curl_setopt($cp, CURLOPT_TIMEOUT, 30);

  /*option:Spécifiez un agent utilisateur*/
  curl_setopt($cp, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36');

  $data = curl_exec($cp);

  curl_close($cp);

  return $data;
}

$url = 'https://www.yahoo.co.jp';
$doc = phpQuery::newDocument(my_curl($url));

$ul = $doc->find('main article section')->find("ul:eq(0)");

for ($i = 0; $i < count($ul->find("li")); ++$i) {
  $li = $ul->find("li:eq($i)");
  echo  $li[0]->text();
  echo "\n";
  echo $li[0]->find("a")->attr('href').PHP_EOL;
  echo "\n";
}
?>

phpQuery-onefile.php https://github.com/yuzuru-program/scraping-php-yahoo/blob/master/phpQuery-onefile.php

Ruby

Vidéo

Dépôt

https://github.com/yuzuru-program/scraping-ruby-yahoo

La source

index.rb

require "nokogiri"
require "open-uri"

doc = Nokogiri::HTML(open("https://www.yahoo.co.jp"))

test = doc.css("main article section ul")[0].css("li")

test.each do |li|
  puts li.content
  puts li.css("a")[0][:href]
  puts
end

Go

Vidéo

Dépôt

https://github.com/yuzuru-program/scraping-go-yahoo

La source

index.go

package main

import (
  "fmt"
  "log"
  "net/http"

  "github.com/PuerkitoBio/goquery"
)

func main() {
  req, _ := http.NewRequest("GET", "http://yahoo.co.jp", nil)
  req.Header.Set("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36")
  res, _ := new(http.Client).Do(req)

  if res.StatusCode != 200 {
    log.Fatalf("status code error: %d %s\n", res.StatusCode, res.Status)
  }

  doc, err := goquery.NewDocumentFromReader(res.Body)
  if err != nil {
    log.Println(err)
  }

  li := doc.Find("main article section ul").Eq(0).Find("li")
  li.Each(func(index int, s *goquery.Selection) {
    fmt.Println(s.Text())

    tmp, err := s.Find("a").Attr("href")
    if err != true {
      log.Fatal(err)
    }
    fmt.Println(tmp + "\n")
  })
}

VBA

Vidéo

La source

'Microsoft HTML Object Library
'Microsoft Internet Controls

'Fonction pour supprimer un processus IE
Function IeProcessKill()
    CreateObject("WScript.Shell").Exec ("taskkill.exe /F /IM iexplore.exe")
    Application.Wait Now + TimeValue("0:00:2")
End Function


'Yahoo Top Scraping
Sub main()
    Dim ie As InternetExplorer

    'Supprimer le processus IE'
    Call IeProcessKill
    
    'Démarrage IE
    Set ie = New InternetExplorer
    
    'Masquer le site
    ie.Visible = False
    
    Debug.Print "Chargement..."
    Debug.Print
    
    'Yahoo
    ie.Navigate "https://www.yahoo.co.jp/"
    
    Do While ie.Busy = True Or ie.readyState < READYSTATE_COMPLETE
    Loop
    
    For Each tmp In ie.document.querySelector("main article section ul").getElementsByTagName("li")
        Debug.Print Trim(tmp.textContent)
        Debug.Print tmp.getElementsByTagName("a")(0).href
        Debug.Print
    Next tmp
    
    'Fermer le navigateur
    ie.Quit
    Set ie = Nothing
End Sub