Develop Reference

Scrape multiple pages with the same url using Python Selenium

I have the following code that scrapes some information I need from a website. However, there are 61 pages I need to go through and scrape the same data that requires me to click on the 'Next' button to go to the next page with the url remaining the same.
I know it is possible to use driver.find_element_by_link_text('Next').click() to go to the next page but I am not sure how to include this in my code.
from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd
import time
driver = webdriver.Chrome()
driver.get('https://mspotrace.org.my/Sccs_list')
time.sleep(20)
# Get list of elements
elements = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.XPATH, "//a[#title='View on Map']")))
# Loop through element popups and pull details of facilities into DF
pos = 0
df = pd.DataFrame(columns=['facility_name','other_details'])
for element in elements:
try:
data = []
element.click()
time.sleep(10)
facility_name = driver.find_element_by_xpath('//h4[#class="modal-title"]').text
other_details = driver.find_element_by_xpath('//div[#class="modal-body"]').text
time.sleep(5)
data.append(facility_name)
data.append(other_details)
df.loc[pos] = data
WebDriverWait(driver,10).until(EC.element_to_be_clickable((By.CSS_SELECTOR, "button[aria-label='Close'] > span"))).click() # close popup window
print("Scraping info for",facility_name,"")
time.sleep(15)
pos+=1
except Exception:
alert = driver.switch_to.alert
print("No geo location information")
alert.accept()
pass
print(df)

Answering to your question, "I don't know how I would put it in my code"
Counter iii is used to repeat your existing code 60 times.
I cannot test the entire code, but I tested the loops.
For the sake of simplicity, in the code below I removed the element scraping so I could focus the test on repeating the clicks in the Next button, which is your question.
If you are going to test on your side, ensure you replace
print('your stuff would stay here!')
with the actual element scraping block that you have in your original code.
Hope it helps!
from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd
import time
driver = webdriver.Chrome()
driver.get('https://mspotrace.org.my/Sccs_list')
time.sleep(20)
# Get list of elements
elements = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.XPATH, "//a[#title='View on Map']")))
# Loop through element popups and pull details of facilities into DF
pos = 0
df = pd.DataFrame(columns=['facility_name','other_details'])
for iii in range(1,60):
for element in elements:
print('your stuff would stay here!')
#click next
btnNext = driver.find_element(By.XPATH,'//*[#id="dTable_next"]/a')
driver.execute_script("arguments[0].scrollIntoView();", btnNext)
driver.execute_script("arguments[0].click();", btnNext)
time.sleep(5)
#print current df. You may want to store it and print in the end only?
print(df)
# Get list of elements again
elements = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.XPATH, "//a[#title='View on Map']")))
# Resetting vars again
pos = 0
df = pd.DataFrame(columns=['facility_name','other_details'])

Webscraping Multiple Pages in Python with Selenium - loop not working

I'm quite new to python and have written a script using selenium to scrape a website. I've tried everything but can't get the loop to cycle through pages. It currently just repeats the data on the first page 5 times. I want to scrape all the pages for 'BR1' any help would be great, currently the script below only scrapes the first page 5 times.
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
with open('rightmove.csv', 'w') as file:
file.write('PropertyCardcontent \n')
PATH = ("/usr/local/bin/chromedriver")
driver = webdriver.Chrome(PATH)
driver.get("https://www.rightmove.co.uk/house-prices.html")
print(driver.title)
elem = driver.find_element(By.NAME, 'searchLocation') # Find the search box
elem.send_keys('BR1' + Keys.RETURN)
try:
content = WebDriverWait(driver, 15).until(
EC.presence_of_element_located((By.ID,'content'))
)
finally:
time.sleep(3)
for p in range(5):
sold = content.find_elements(By.CLASS_NAME, 'sold-prices-content-wrapper ')
for solds in sold:
address = solds.find_elements(By.CLASS_NAME, 'sold-prices-content ')
for addresses in address:
result = addresses.find_elements(By.CLASS_NAME, 'results ')
for results in result:
card = results.find_elements(By.CLASS_NAME,'propertyCard')
for propertyCard in card:
header = propertyCard.find_elements(By.CLASS_NAME,'propertyCard-content')
for propertyCardcontent in header:
road = propertyCardcontent.find_elements(By.CLASS_NAME,'title')
for propertyCardcontent in header:
road = propertyCardcontent.find_elements(By.CLASS_NAME,'subTitle')
for subtitle in road:
bed = subtitle.find_elements(By.CLASS_NAME, 'propertyType')
with open('rightmove.csv', 'a') as file:
for i in range(len(result)):
file.write(header[i].text + '\n')
button = driver.find_element(By.XPATH, '//*[#id="content"]/div[2]/div[2]/div[4]/div[27]/div[3]/div')
button.click()
file.close()
time.sleep(3)
driver.quit()

Since the website link has page number on it, I recommend you put the base url as "https://www.rightmove.co.uk/house-prices/br1.html?page=1", and loop through the pages while changing the last index of the url with methods like format string.
One other thing, you don't need to implement all those for loops, you can simply assign each variable to its specific value since everything you need is inside an html block which is easy to navigate on it.
Update:
I'm sorry for being late, had unexpected stuff(...).
I've made some changes as I use Brave, so make sure you select your browser, Chrome I believe, the chromedriver(ver:102) stays the same (or depending your Chrome version).
I've also got the Price and Date and stored them in a tuple.
Every record is stored in a list[Title, propertyType, tupleof(Price_Date)]
At the end, it creates a csv and stores everything inside with a ";" as delimter.
You can if you prefer split the price and date for later use, up to you.
Note: This looping method only applies to websites in which the number of page is included within the URL. In this case, both the key and number of page is included in the URL.
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
import time
import random
import itertools
options = Options()
options.binary_location = r'C:\Program Files\BraveSoftware\Brave-Browser\Application\brave.exe'
driver = webdriver.Chrome(options = options, service = Service("chromedriver.exe"))
key_word = "BR1".lower()
base_url = f"https://www.rightmove.co.uk/house-prices/{key_word}.html?page=1"
driver.get(base_url)
#Number of pages
pages = driver.find_element(By.XPATH, '//span[#class="pagination-label"][2]').text
pages = int(pages.strip('of'))
WebDriverWait(driver, 15).until(
EC.presence_of_element_located((By.CLASS_NAME, 'results '))
)
data = []
pc = 0
for p in range(1,pages+1):
driver.get(f"https://www.rightmove.co.uk/house-prices/{key_word}.html?page={p}")
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.XPATH, '//div//div[#class="propertyCard"]'))
)
propertyCards = driver.find_elements(By.XPATH, '//div//div[#class="propertyCard"]')
for propertyCard in propertyCards:
title = propertyCard.find_element(By.CLASS_NAME, 'title').text
propertyType = propertyCard.find_element(By.CLASS_NAME, 'propertyType').text
price_list = propertyCard.find_elements(By.CLASS_NAME, 'price')
date_list = propertyCard.find_elements(By.CLASS_NAME, 'date-sold')
data.append([title,propertyType])
for p, d in itertools.zip_longest(price_list, date_list , fillvalue = None):
try:
price = p.text
date = d.text
data[pc].append((price, date))
except Exception as e:
print(e)
pc+=1
time.sleep(random.randint(1,4))
print(data)
with open('rightmove.csv', 'w') as file:
header = "Title;propertyType;Price_Date\n"
file.write(header)
for record in data:
file.write("{};{};{}\n".format(record[0],record[1],record[2:]))
driver.quit()

You don't have to go down to dom elem by elem, you can just use xpath or class_name (if it's unique, otherwise it's better xpath or css-selector) and get the item you are looking for.
Anyway follow this:
import time
import selenium.webdriver as webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
driver = webdriver.Chrome("/usr/local/bin/chromedriver")
driver.get("https://www.rightmove.co.uk/house-prices.html")
# send query
query = "BR1"
search_bar = driver.find_element(By.XPATH, '//input[#class="searchBox ac_input"]')
search_bar.send_keys(query)
search_bar.send_keys(Keys.ENTER)
# wait to result been loaded
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.CLASS_NAME, 'propertyCard'))
)
#get amount of pages
pages = driver.find_element(By.XPATH, '//span[#class="pagination-label"][2]').text
pages = int(pages.replace('of ', ''))
data = []
i = 1
while i <= pages:
WebDriverWait(driver, 10).until(
EC.element_to_be_clickable((By.XPATH, '//div[contains(text(), "Next")]'))
).click()
# wait page load result
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.XPATH, '//div//div[#class="propertyCard"]'))
)
propertyCards = driver.find_elements(By.XPATH, '//div//div[#class="propertyCard"]')
# loop over result and store data
for propertyCard in propertyCards:
title = propertyCard.find_element(By.CLASS_NAME, 'title').text
propertyType = propertyCard.find_element(By.CLASS_NAME, 'propertyType').text
data.append((title, propertyType))
time.sleep(1)
i += 1
print("you reach the last page")
#get number of results
printf(data)
driver.close()
I use a list of tuple cause in your example you want store 2 item, if you want store more data you can use a dict and then convert into csv with Dictwriter directly. Enjoy.

Selenium For Loop Stuck on a popup message

I have an application that is almost working as intended. The problem arises after it runs through the loop on the 5th instance. The search states there are two results which results in the same end result. When this occurs I'd like to select the first of the two.
The popup messages looks like the following:
I'm using the following code to create the list and then loop:
from selenium import webdriver
import pandas as pd
import random
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.common.proxy import Proxy, ProxyType
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
#service = Service('C:\Program Files\Chrome Driver\chromedriver.exe')
URL = "https://mor.nlm.nih.gov/RxClass/search?query=ALIMENTARY TRACT AND METABOLISM"
driver = webdriver.Chrome('C:\Program Files\Chrome Driver\chromedriver.exe')
driver.get(URL)
category = [my_elem.text for my_elem in WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "div.drug_class img+a")))]
classid = [my_elem.text for my_elem in WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "div.propText")))]
dfObj = pd.DataFrame(category)
dfObj.columns =['Category']
dfObj.dropna(inplace = True)
new = dfObj["Category"].str.split("(", n = 1, expand = True)
dfObj["New Category"]= new[0]
dfObj["Count"]= new[1]
dfObj.drop(columns =["Category"], inplace = True)
dfObj['Count'] = dfObj['Count'].str.rstrip(')')
dfObj['IsNumber'] = dfObj['Count'].str.isnumeric()
dfObj = dfObj[(dfObj['IsNumber'] == True)]
searchcat = dfObj['New Category'].tolist()
print(searchcat)
dfObj.to_csv('tabledf.csv',index=False)
time.sleep(8)
driver.quit()
for search in searchcat:
page = f"https://mor.nlm.nih.gov/RxClass/search?query={search}"
driver = webdriver.Chrome('C:\Program Files\Chrome Driver\chromedriver.exe')
driver.get(page)
time.sleep(4)
table = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CSS_SELECTOR, 'tr.dbsearch')))
time.sleep(4)
filename = search[0:30]+'table.csv'
pd.read_html(driver.page_source)[1].iloc[:,:-1].to_csv(filename,index=False)
time.sleep(4)
driver.quit()
The loop will continue to run if I manually click each search result. However, I would like for selenium to always select the first option. How would I go about this?
Updated Code:
from selenium import webdriver
import pandas as pd
import random
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.common.proxy import Proxy, ProxyType
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait, TimeoutException
import time
with webdriver.Chrome('C:\Program Files\Chrome Driver\chromedriver.exe') as driver:
URL = "https://mor.nlm.nih.gov/RxClass/search?query=ALIMENTARY TRACT AND METABOLISM"
driver.get(URL)
category = [my_elem.text for my_elem in WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "div.drug_class img+a")))]
dfObj = pd.DataFrame(category)
dfObj.columns =["Category"]
dfObj.dropna(inplace = True)
new = dfObj["Category"].str.split("(", n = 1, expand = True)
dfObj["New Category"]= new[0]
dfObj["Count"]= new[1]
dfObj.drop(columns =["Category"], inplace = True)
dfObj["Count"] = dfObj["Count"].str.rstrip(')')
dfObj["IsNumber"] = dfObj["Count"].str.isnumeric()
dfObj = dfObj[(dfObj["IsNumber"] == True)]
searchcat = dfObj["New Category"].tolist()
dfObj.to_csv('tabledf.csv',index=False)
time.sleep(3)
for search in searchcat:
page = f"https://mor.nlm.nih.gov/RxClass/search?query={search}"
driver = webdriver.Chrome('C:\Program Files\Chrome Driver\chromedriver.exe')
driver.get(page)
table = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CSS_SELECTOR, 'tr.dbsearch')))
modal_wait = WebDriverWait(driver, 1)
try:
modal_el = modal_wait.until(EC.visibility_of_element_located((By.ID, 'optionModal')))
modal_el.find_element(By.CSS_SELECTOR, '.uloption').click()
except TimeoutException:
pass
filename = search[0:30]+'table.csv'
classid = [my_elem.text for my_elem in WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "div.table-responsive div.propText strong:nth-child(2)")))]
classname = [my_elem.text for my_elem in WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "div.table-responsive div.propText strong:nth-child(1)")))]
classtype = [my_elem.text for my_elem in WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "div.table-responsive div.propText strong:nth-child(3)")))]
df = pd.read_html(driver.page_source)[1].iloc[:,:-1]
df["ClassID"] = pd.Series(classid)
df["ClassName"] = pd.Series(classname)
df["ClassType"] = pd.Series(classtype)
df.to_csv(filename,index=False)
time.sleep(4)
driver.quit()

First of, I will suggest that you use the with context manager. It will handle opening/closing the driver (Chrome) by itself. This ensure if any exception is raised that it will still be closed.
To do so, use:
with webdriver.Chrome() as driver:
...
In your code I see you close/open a new browser for each URL. This is not needed and not doing so will speed up your script. Just use driver.get() to change the URL.
For your main issue, just add a portion of code that will detect the modal and chose the first option. Something along those lines
modal_wait = WebDriverWait(driver, 1)
try:
modal_el = modal_wait.until(EC.element_to_be_clickable((By.ID, 'optionModal')))
modal_el.find_element(By.CSS_SELECTOR, '.uloption').click()
except TimeoutException:
pass
You must include the following imports:
from selenium.webdriver.support.wait import WebDriverWait, TimeoutException
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By

Selenium button not being clicked but is being highlighted

What I'm trying to do is making nike product auto buyer the problem is after selecting size it doesn't let me click through selenium I even tried to click manually but nothing pops up this is my code where I try to click (not full code):
from selenium import webdriver
from selenium.common.exceptions import JavascriptException
from selenium.webdriver import ChromeOptions
import re
from bs4 import BeautifulSoup
import requests
import json
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
import os
user = os.environ['USERNAME']
snkrsurl = "https://www.nike.com/t/air-zoom-pegasus-38-womens-running-shoe-wide-gg8GBK/CW7358-500" #input("Please input your SNKRS url \n")
size = float(input("Please input size \n"))
options = ChromeOptions()
options.add_experimental_option('excludeSwitches',['enable-logging'])
options.add_experimental_option("useAutomationExtension", False)
options.add_experimental_option("detach",True)
options.add_argument("--disable-notifications")
chrome = webdriver.Chrome(options=options)
if "https://" in snkrsurl:
pass
elif "http://" in snkrsurl:
pass
else:
snkrsurl = "http://"+snkrsurl
chrome.get(snkrsurl)
with requests.Session() as session:
soup = BeautifulSoup(session.get(snkrsurl).text, features="lxml")
script = soup.find("script", string=re.compile('INITIAL_REDUX_STATE')).string
redux = json.loads(script[script.find('{'):-1])
products = redux["Threads"]["products"]
wait = WebDriverWait(chrome, 15)
def step1(i,v):
for key, product in products.items():
if float(product["skus"][i]["nikeSize"]) == v:
print("Found")
if v.is_integer():
wait.until(EC.element_to_be_clickable((By.XPATH, '//*[#id="gen-nav-footer"]/nav/button'))).click()
wait.until(EC.element_to_be_clickable((By.XPATH, "//*[text()='{}']".format(int(v))))).click()
chrome.execute_script("window.scroll(0,609)")
wait.until(EC.element_to_be_clickable((By.XPATH, '//*[text()="Add to Bag"]'))).click()
break
else:
wait.until(EC.element_to_be_clickable((By.XPATH, '//*[#id="gen-nav-footer"]/nav/button'))).click()
wait.until(EC.element_to_be_clickable((By.XPATH, "//*[text()='{}']".format(v)))).click()
e = chrome.find_element_by_css_selector("#floating-atc-wrapper > div > button.ncss-btn-primary-dark.btn-lg.add-to-cart-btn")
chrome.execute_script("arguments[0].scrollIntoView(true);")
e.click()
break
else:
pass
for i,v in products.items():
global length
length = len(v['skus'])
break
for i in range(length):
length -=1
step1(length,size)
I use window.scroll to go to that element because if I don't it throws error saying element is not interactable and yes checkout is being only clickable from real chrome.
Thanks

python webscraping with selenium repeating certain process

i try to scrape the contact data from companies from this website:
https://de.statista.com/companydb/suche?idCountry=276&idBranch=0&revenueFrom=-1000000000000000000&revenueTo=1000000000000000000&employeesFrom=0&employeesTo=100000000&sortMethod=revenueDesc&p=4
I can do this with the following Code:
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
import pandas as pd
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
company_list= [] #create empty list
driver = webdriver.Chrome('/Users/rieder/Anaconda3/chromedriver_win32/chromedriver.exe') #define driver
driver.get('https://de.statista.com/companydb/suche?idCountry=276&idBranch=0&revenueFrom=-1000000000000000000&revenueTo=1000000000000000000&employeesFrom=0&employeesTo=100000000&sortMethod=revenueDesc&p=1') # open Website
driver.find_element_by_id("cookiesNotificationConfirm").click(); #accept cookies
driver.find_element_by_xpath("//*[#id='content']/section[3]/div/div/form/div/div[2]/div[2]/table/tr[2]/td[1]/a").click(); #click on the first company namelink
contact_data = WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.XPATH, "/html/body/div[3]/div[4]/section[6]/div/div[2]/div[2]/div/div"))) #get the contactdata from the company you chose before
for cn in contact_data:
company_list.append(cn.text) # this stores the text in the list
driver.back() #navigate to previous site
time.sleep(5) #wait for the pop-up window to appear
driver.find_element_by_xpath("/html/body/div[15]/div[3]/div[3]/div[1]/button[1]").click(), #deny the websites popup
time.sleep(5) #wait for the popup to vanish
driver.find_element_by_xpath("//*[#id='content']/section[3]/div/div/form/div/div[2]/div[2]/table/tr[3]/td[1]/a").click(); #click on the next company namelink
contact_data2 = WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.XPATH, "/html/body/div[3]/div[4]/section[6]/div/div[2]/div[2]/div/div"))) #get the contactdata from the company you chose before
for cn in contact_data2:
company_list.append(cn.text) # this stores the text in the list
print(company_list) #show the list
My Output is this:
['GUTex GmbH\nGerhard-Unland-Str. 1\n26683\nSaterland\nDeutschland', 'Robert Bosch GmbH\nRobert-Bosch-Platz 1\n70839\nGerlingen\nDeutschland']
Problem:
I want, that my code does this to the whole list on page 1 and then goes on on the next page and do it again. This shall go on until I have for example 100 adresses in the list. I would do this with a "while loop" but my xpaths for finding the adress are too specified, so it would always loop the same companies.
Thanks a lot inbefore

Try below code for one page data extract. Update the code for iterating over the next page records.
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
company_list= [] #create empty list
driver = webdriver.Chrome() #define driver
driver.get('https://de.statista.com/companydb/suche?idCountry=276&idBranch=0&revenueFrom=-1000000000000000000&revenueTo=1000000000000000000&employeesFrom=0&employeesTo=100000000&sortMethod=revenueDesc&p=1') # open Website
if len(driver.find_elements_by_id("cookiesNotificationConfirm")) > 0:
driver.find_element_by_id("cookiesNotificationConfirm").click(); # accept cookies
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, '//table[#class="zebraTable zebraTable--companies"]//td[1]')))
elementsSize = len(driver.find_elements_by_xpath('//table[#class="zebraTable zebraTable--companies"]//td[1]'))
# To iterate over the company list and click on the company name then capture the address on navigated page
# come back to previous page and repeat the same.
for i in range(elementsSize):
WebDriverWait(driver, 20).until(
EC.element_to_be_clickable((By.XPATH, '//table[#class="zebraTable zebraTable--companies"]//td[1]')))
elements = driver.find_elements_by_xpath('//table[#class="zebraTable zebraTable--companies"]//td[1]/a')
company_name = elements[i].text
elements[i].click() # click on the first company namelink
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH,
'//*[#id="contactInformation"]//div[#class="companyContactBox"]'))) # get the contactdata from the company you chose before
contact_data = driver.execute_script("return document.getElementsByClassName('companyContactBox')[0].innerText")
# print(contact_data)
company_list.append(company_name + " : " + contact_data)
driver.back() # navigate to previous site
print(company_list)

Thanks to Dilip Meghwals comment above i could finish my Code:
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd
import time
company_list= [] #create empty list
count = 25
chrome_options = webdriver.ChromeOptions()
prefs = {"profile.default_content_setting_values.notifications" : 2}
chrome_options.add_experimental_option("prefs",prefs)
driver = webdriver.Chrome('/Users/rieder/Anaconda3/chromedriver_win32/chromedriver.exe', chrome_options=chrome_options) #define driver
driver.get('https://de.statista.com/companydb/suche?idCountry=276&idBranch=0&revenueFrom=-1000000000000000000&revenueTo=1000000000000000000&employeesFrom=0&employeesTo=100000000&sortMethod=revenueDesc&p=1') # open Website
if len(driver.find_elements_by_id("cookiesNotificationConfirm")) > 0:
driver.find_element_by_id("cookiesNotificationConfirm").click(); # accept cookies
while len(company_list) < 1000:
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, '//table[#class="zebraTable zebraTable--companies"]//td[1]')))
elementsSize = len(driver.find_elements_by_xpath('//table[#class="zebraTable zebraTable--companies"]//td[1]'))
# To iterate over the company list and click on the company name then capture the address on navigated page
# come back to previous page and repeat the same.
for i in range(elementsSize):
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, '//table[#class="zebraTable zebraTable--companies"]//td[1]')))
elements = driver.find_elements_by_xpath('//table[#class="zebraTable zebraTable--companies"]//td[1]/a')
company_name = elements[i].text
elements[i].click() # click on the first company namelink
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH,'//*[#id="contactInformation"]//div[#class="companyContactBox"]'))) # get the contactdata from the company you chose before
contact_data = driver.execute_script("return document.getElementsByClassName('companyContactBox')[0].innerText")
# print(contact_data)
company_list.append(contact_data)
driver.back() # navigate to previous site
time.sleep(5)
driver.find_element_by_xpath("//*[#id='content']/section[3]/div/div/form/div/div[2]/div[2]/div[2]/div/button[2]").click();
company_list = [w.replace('\n', ', ') for w in company_list]
print(company_list)
df_company_name = pd.DataFrame(company_list, columns =['Name'])
df_company_name.to_excel("company_name.xlsx")