使用scrapy找不到Xpath-有解無憂

我想提取email，phone但我找不到它的 xpath。我只會檢索 xpath website，這是我提取資料的頁面的鏈接：使用scrapy找不到Xpath

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

        }

uj5u.com熱心網友回復：

現在，它正在作業。

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(//*[@]//text()[2])').get(),
            'email':response.xpath('normalize-space(//*[@]/div[1]//text()[2])').get()
            }

轉載請註明出處，本文鏈接：https://www.uj5u.com/shujuku/431619.html

標籤：Python 网页抓取刮擦

上一篇：用beautifulsoup從雅虎財務中抓取，導致狀態碼：404

下一篇：在R中使用Rvest進行禮貌的Webscraping