I was hoping to ask a question about the process of scrapping information from a website using selenium/selenium base into an excel sheet. I have been playing around with selenium and selenium base for a few days and I am at the point where I want to begin scrapping data points into an excel sheet. This is my code so far:
import selenium
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
import time
import os
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.remote.webelement import WebElement
from selenium.webdriver.common.keys import Keys
from seleniumbase import BaseCase
from seleniumbase import js_utils
import pandas as pd
s=Service('/Users/[name]/Desktop/chromedriver')
chromeOptions = Options()
chromeOptions.headless = False
driver = webdriver.Chrome(service=s, options=chromeOptions)
class RecorderTest(BaseCase):
def test_recording(self):
self.open("https://www.finestrahealth.com/")
self.assert_exact_text("finestra", 'a[href="/"] span')
self.type('input[placeholder="Procedure"]', "mri")
self.type('input[placeholder="Zip code"]', "60007")
self.type('input[placeholder="Insurance"]', "atena")
self.click('button:contains("Search")')
self.assert_element('main p:contains("Hospitals")')
out_pocket_price = driver.find_element(By.CLASS_NAME, "text-[40px] text-[#2962FF] leading-[58px] mb-3 tracking-tight smooth")
print("out of pocket price:" out_pocket_price)
self.sleep(20)
if __name__ == "__main__":
from pytest import main
main([__file__])
Well to begin, the out_pocket_price is coded incorrectly, so I would love some insight on that. Assuming that this part is figured out, though, how would I take this value and put it into an excel sheet, amongst other data points? The website is a bit strange because the HTML code does not have a VALUE attribute, like how most tutorials suggest using.
Thanks very much! Its been fun playing around with this framework. Stack Overflow has helped a lot thus far.
CodePudding user response:
It looks like you have multiple drivers up, and a lot of extra code, and not a good selector for the out-of-pocket price. Here's a script that does everything, prints the prices, and outputs the results to a CSV file, which is the easiest way to have something that opens easily in Excel:
import codecs
import os
from seleniumbase import BaseCase
class MedicalTest(BaseCase):
def test_medical_list(self):
self.open("https://www.finestrahealth.com/")
self.assert_exact_text("finestra", 'a[href="/"] span')
self.type('input[placeholder="Procedure"]', "mri")
self.type('input[placeholder="Zip code"]', "02142")
self.type('input[placeholder="Insurance"]', "aetna")
self.click('button:contains("Search")')
self.assert_element('main p:contains("Hospitals")')
self.wait_for_element("div.items-center div.flex")
data_to_save = []
print("\nFound prices:")
for item in self.find_elements("div.text-white"):
print(item.text)
data_to_save.append(item.text)
file_name = os.path.join(".", "data_file.csv")
data_file = codecs.open(file_name, "w ", "utf-8")
data_file.writelines("\r\n".join(data_to_save))
data_file.close()
print("Data saved to data_file.csv")
self.sleep(2)
if __name__ == "__main__": # Use "python" to call "pytest"
from pytest import main
main([__file__, "-s"])
Here's the console output I got from running that:
Found prices:
$44934
$27139
$17134
$30009
$11
Data saved to data_file.csv
(Since there are print()
statements, which pytest
captures by default, run with pytest -s
, unless you already have a pytest.ini
file with that configuration set.)