Scrapy : tout savoir sur cet outil Python de web scraping

# import de scrapy
import scrapy

# définition du sipder
class TrustpilotspiderSpider(scrapy.Spider):
    """
    name: a class attribute that gives a name to the spider.
    We will use this when running our spider later scrapy crawl
    <spider_name>.

    allowed_domains: a class attribute that tells Scrapy that it
    should only ever scrape pages of the chocolate.co.uk domain.
    This prevents the spider going

    star_urls: a class attribute that tells Scrapy the first url
    it should scrape. We will be changing this in a bit.


    parse: the parse function is called after a response has been
    recieved from the target website.
    """
    name = "trustpilotspider"
    allowed_domains = ["fr.trustpilot.com"]
    start_urls = ["https://fr.trustpilot.com/review/datascientest.com"] # Maj de l'URL

    def parse(self, response):
        """
        Module permettant d'extraire les informations
        """

        # Boucle sur tous les blocs d'information
        selectors = response.css('.styles_reviewContentwrapper__zH_9M')

        # Extraction itérative des informations
        for selector in selectors:
            # Les informations à retourner
            yield{
                'notes' : selector.css('img::attr(alt)').extract(),
                'titre' : selector.css('.typography_heading-s__f7029::text').get(), # .extract()[0]
                'exp_date' : selector.css('.typography_color-black__5LYEn::text').extract()[-1],
                'comments' : ''.join([text for text in selector.css('.typography_color-black__5LYEn::text').extract()[:-1]]),
                'comment_date' : selector.css('div.typography_body-m__xgxZ_.typography_appearance-subtle__8_H2l.styles_datesWrapper__RCEKH > time::text').get()
            }