Текст разбивается на новые строки из-за тега <br> при очистке

Question

Привет всем, я пытаюсь очистить страницу и данные на ней, но не могу получить ожидаемые данные в одной строке из-за тегов br, присутствующих в тексте, из-за которых данные перемещаются в новую строку, любая помощь будет оценена.

Вот мой код:

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
import time
import random
import re

driver = webdriver.Chrome(r"C:\Users\Acer\AppData\Local\Programs\Python\Python36-32\chromedriver.exe")
with open(r"E:\office\Zoro\Zoro11.txt" ,'r')as f:
    content = f.readlines()
    content = [x.strip() for x in content]
    currentIndex = 0
    with open(r"E:\office\Zoro\Zoro16.csv", 'a')as f1:
        f1.write("Product Url" + "," + "Main category"+"," + "Sub category"+"," + "Leaf category"+","+"Title" + "," + "Prodcutid"+","+"Manufacturer Name" + "," + "Manufacturer's number"+","+"reviews"+","+"Price"+","+"smalldesc"+","+"Product Dimensions"+","+"Main Image"+","+"Sub Image")
        f1.write("\n")
        for link in content[currentIndex:]:
            driver.get(link)
            time.sleep(5)
            aj = driver.find_element_by_class_name('zcl-breadcrumb__list').text.replace("Home\n","").replace("\n",">").replace(",","")
            try:
                title = driver.find_element_by_xpath("//*[@data-za='product-name']").text.replace(",","").replace("\n","")
            except:
                title = "No title"
            try:
                brand = driver.find_element_by_xpath("//*[@data-za='product-brand-name']").text.replace(",","")
            except:
                brand = "No Brand"
            try:
                productid = driver.find_element_by_xpath("//*[@data-za='PDPZoroNo']").text.replace(",", "")
            except:
                productid = "No productid"

            maincategory = aj[:aj.find(">")]
            Leafcategory = aj[aj.rindex('>')+1:]
            Subcategory = aj[(aj.find(">"))+1:aj.rindex('>')]
            mfrnu = driver.find_element_by_xpath("//*[@data-za='PDPMfrNo']").text.replace(",", "")
            try:
                mainimage = driver.find_element_by_xpath('//*[@id="app"]/div[3]/div[2]/div/div/main/div[1]/div[3]/div/div[1]/div/div/div/div/div/img').get_attribute('src')
            except:
                mainimage = "No mainimage"
            try:
                price = driver.find_element_by_class_name('product-price__price').text
            except:
                price = "No price"
            try:
                smalldesc = driver.find_element_by_class_name('product-attributes').text.replace("\n",";").replace(",","")
            except:
                smalldesc = "No desc"
            try:
                specification = driver.find_element_by_css_selector('.product-specifications__table.table.table-striped').text.replace("\n",";").replace(",","").strip()
                print(specification)

            except:
                specification = "No sepcs"
            try:
                productdesc = driver.find_element_by_css_selector('.product-description__text').text.replace(",","")
                
            except:
                productdesc = "No productfields"
            f1.write(link + "," + maincategory + "," + Subcategory + ","+ Leafcategory + ","+title + "," + productid + "," + brand + "," + mfrnu + "," + price +"," + smalldesc +"," + specification +"," + productdesc +"," + mainimage +"\n")

в приведенном выше коде в productdesc я получаю следующий вывод

Pro Series Swivel Head LED Work Light
  280 lumens
Beam Distance 54 meters
Run time 3 hrs

ожидаемый результат находится в одной строке с пробелом, ссылка, которую я использую для очистки, https://www.zoro.com/dorcy-pro-s-swivel-head-led-worklght-187-lumen-41-2392/i/G9576141/

Answer 1

Похоже, вам просто нужно обновить строку для чтения описания. Добавьте замену новой строки, как вы это делали в других полях:

Измените это:

productdesc = driver.find_element_by_css_selector('.product-description__text').text.replace(",","")

К этому:

productdesc = driver.find_element_by_css_selector('.product-description__text').text.replace("\n",";").replace(",","")