I'm getting the following error when trying to retrieve elements as .text from a website: 'str' object has no attribute 'text'
I have read that Python does not recognize the .text command but I am unable to fix this in my code.
Part of the code:
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
import pandas as pd
import numpy as np
import re
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.common.action_chains import ActionChains
#Set up the path to the chrome driver
driver = webdriver.Chrome()
html = driver.find_element_by_tag_name('html')
all_details = []
for c in range(1,2):
try:
driver.get("https://www.delpher.nl/nl/kranten/results?query=kernenergie&facets%5Bpapertitle%5D%5B%5D=Algemeen+Dagblad&facets%5Bpapertitle%5D%5B%5D=De+Volkskrant&facets%5Bpapertitle%5D%5B%5D=De+Telegraaf&facets%5Bpapertitle%5D%5B%5D=Trouw&page={}&sortfield=date&cql%5B%5D=(date+_gte_+%2201-01-1970%22)&cql%5B%5D=(date+_lte_+%2201-01-2018%22)&coll=ddd".format(c))
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
incategory = driver.find_elements_by_class_name("search-result")
print(driver.current_url)
links = [ i.find_element_by_class_name("search-result__thumbnail-link").get_attribute("href") for i in incategory]
# Loop through each link to acces the page of each article
for link in links:
# get one book url
driver.get(link)
# newspaper
newspaper = driver.find_element_by_xpath("//*[@id='content']/div[2]/div/div[2]/header/h1/span[2]").text
# date of the article
date = driver.find_element_by_xpath("//*[@id='content']/div[2]/div/div[2]/header/div/ul/li[1]").text
Aucun commentaire:
Enregistrer un commentaire