from selenium import webdriver from selenium.webdriver.common.keys import Keys from bs4 import BeautifulSoup import re import time import pandas as pd from tabulate import tabulate import os from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.common.by import By from selenium.webdriver.support import expected_conditions as ec

#launch url url = "https://www.halodoc.com/obat-dan-vitamin/batuk-dan-flu/page/1"

# create a new Firefox session driver = webdriver.Firefox() driver.implicitly_wait(100) driver.get(url)

fastrack = WebDriverWait(driver, 10).until(ec.presence_of_element_located((By.XPATH, "//li[@class='list__item-container item']")));

soup_level1=BeautifulSoup(driver.page_source, 'lxml')

test=soup_level1.find("a", {"class": "pagination__last-page"}) test=test.find("span", {"class": "pagination__number"}) lastpage=int((test.contents)[0])

for i in range(1,lastpage): for part in soup_level1.find_all('li', class_ = 'list__item-container item'): urlTarget=part.find('a').attrs['href'] for link in part.find_all('a'): print(link.attrs['href']) driver.get("https://www.halodoc.com/"+link.attrs['href'])

disini detail obat tertentu apa aja yang mau di ambil

#next page driver.get("https://www.halodoc.com/obat-dan-vitamin/batuk-dan-flu/page/"+str(i+1)) fastrack = WebDriverWait(driver, 10).until(ec.presence_of_element_located((By.XPATH, "//li[@class='list__item-container item']"))); soup_level1=BeautifulSoup(driver.page_source, 'lxml')