I am getting trying to getting phone number
but give nothing from the xpath how to solve these problem these is page link https://aaos22.mapyourshow.com/8_0/exhibitor/exhibitor-details.cfm?exhid=999999999999
import scrapy
from scrapy.http import Request
from bs4 import BeautifulSoup
from selenium import webdriver
import time
from scrapy_selenium import SeleniumRequest
import requests
import json
import pandas as pd
class TestSpider(scrapy.Spider):
name = 'test'
def start_requests(self):
yield SeleniumRequest(
url="https://aaos22.mapyourshow.com/8_0/explore/exhibitor-gallery.cfm?featured=false",
wait_time=3,
screenshot=True,
callback=self.parse,
dont_filter=True
)
def parse(self, response):
books = response.xpath("//h3[@class='card-Title\nbreak-word\nf3\nmb1\nmt0']//a//@href").extract()
for book in books:
url = response.urljoin(book)
yield Request(url, callback=self.parse_book)
def parse_book(self, response):
phone = response.xpath("//li[@class='dib ml3 mr3'][2]").get()
print(phone)
CodePudding user response:
Assuming you get the concret HTML
you could adjust your xpath
- Select the <ul>
by its class
and the last <li>
. Cause the number is not included in the <span>
, you have to call its sibling
:
//ul[contains(@class,'showcase-web-phone')]/li[last()]/span/following-sibling::text()[1]
CodePudding user response:
If you want to get rid of indexing, this is how you can achieve that:
response.xpath("normalize-space(//*[starts-with(@class,'showcase-web-phone')]/li[./*[.='Phone:']]/span/following::text())").get()