使用 scrapy 找不到 Xpath

Question

我想提取 email 和 phone 但我找不到它的 xpath。我只会检索 website 的 xpath，这是我提取数据的页面的 link：https://www.fiduciairesuisse-vd.ch/directory/abc-gestion-sa

from scrapy import Spider
from scrapy.http import Request


class AuthorSpider(Spider):
    name = 'pushpa'
    start_urls = ['https://www.fiduciairesuisse-vd.ch/fr/adhesion/trouver-un-membre-partenaire-de-confiance?state=All&section=461&class=All&lang=All']
    custom_settings = {
        'CONCURRENT_REQUESTS_PER_DOMAIN': 1,
        'DOWNLOAD_DELAY': 1,
        'USER_AGENT': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
    }



    def parse(self, response):
        books = response.xpath("//td[@class='views-field views-field-title']//@href").extract()
        for book in books:
            url = response.urljoin(book)
            yield Request(url, callback=self.parse_book)

    def parse_book(self, response):
        link = response.xpath("//a[@class='field__item link link--external']//@href").get()
        yield{
            'website':link

        }

Answer 1

现在，它正在工作。

from scrapy import Spider
from scrapy.http import Request


class AuthorSpider(Spider):
    name = 'pushpa'
    start_urls = ['https://www.fiduciairesuisse-vd.ch/fr/adhesion/trouver-un-membre-partenaire-de-confiance?state=All&section=461&class=All&lang=All']
    custom_settings = {
        'CONCURRENT_REQUESTS_PER_DOMAIN': 1,
        'DOWNLOAD_DELAY': 1,
        'USER_AGENT': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
    }



    def parse(self, response):
        books = response.xpath("//td[@class='views-field views-field-title']//@href").extract()
        for book in books:
            url = response.urljoin(book)
            yield Request(url, callback=self.parse_book)

    def parse_book(self, response):
        link = response.xpath("//a[@class='field__item link link--external']//@href").get()
        yield{
            'website':link,
            'phone':response.xpath('normalize-space(//*[@class="s-mrgb-05 s-mrgt-05"]//text()[2])').get(),
            'email':response.xpath('normalize-space(//*[@class="s-mrgb-05 s-mrgt-05"]/div[1]//text()[2])').get()
            }

使用 scrapy 找不到 Xpath

Xpath not found using scrapy

python

scrapy

web-scraping