Spider d'extraction de la page d'accueil du forum Python pour le tutoriel Scrapy

developpez_spider.py

# coding: utf8

import scrapy


class DeveloppezSpyder(scrapy.Spider):
    name = 'forum-python-developpez'

    start_urls = ['https://www.developpez.net/forums/f1155/autres-langages/python-zope/general-python/']

    def parse(self, response):
        for fil_discussion in response.css('#threads .inner'):
            yield {
                'titre': fil_discussion.css('.threadtitle a::text').extract_first(),
                'auteur': fil_discussion.css('a.username::text').extract_first(),
                'date': fil_discussion.css('.author span::text').re(r'\d{2}/\d{2}/\d{4}|Hier|Aujourd\'hui')
            }