1. ### Browse through all the 10 pages on the web-site
2. ## https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=1
3. ## collect/print all the hyperlinks that lead to each individual profile in terminal/CSV
4. ## Concatenate the collected urls and go through each profile (you can create another program, by just looping through the list)
5. ## Collect the below information (if existent on each profile) and print it in CSV file
6. ## name, DOB, nationality, address,start and end date, case referrence
7.  
8. ## Desired output:
9. ## profileUrl + ‘!’ + name + ‘!’ + dob + ‘!’ + nationality + ‘!’ + address + ‘!’  + startDate + ‘!’ + endDate  + ‘!’ + caseReference + ‘n’
10.  
11. from selenium import webdriver
12. from selenium.webdriver.common.by import By
13. import time
14. import csv
15. from selenium.common.exceptions import NoSuchElementException
16.  
17. driver = webdriver.Chrome()
18.  
19. # Creating/Opening a file to write te data in. Please change the pasth to the correct csv file on your computer
20. with open(r'C:UsersKarolina.GugudisDesktopFind and update company info.csv', 'w', encoding="utf-8") as f:  # w is for writing a new file
21.     f.write('profilesurls n')
22.  
23.  
24. driver.get('https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A')
25. driver.maximize_window()
26. driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
27. time.sleep(5)
28.  
29. urls = ['https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=1',
30.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=2',
31.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=3',
32.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=4',
33.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=5',
34.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=6',
35.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=7',
36.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=8',
37.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=9',
38.         'https://find-and-update.company-information.service.gov.uk/register-of-disqualifications/A?page=10'
39.         ]
40.  
41. for link in urls:
42.     driver.get(link)
43.     time.sleep(3)
44.  
45.     for i in range(2, 52): # the hyperlink of the names to each profile
46.         x = '//*[@id="search-container"]/div[1]/table/tbody/tr['
47.         x = x + str(i) + ']/td[1]/a'
48.         # //*[@id="search-container"]/div[1]/table/tbody/tr[2]/td[1]/a
49.         # //*[@id="search-container"]/div[1]/table/tbody/tr[3]/td[1]/a
50.         # //*[@id="search-container"]/div[1]/table/tbody/tr[4]/td[1]/a
51.         # //*[@id="search-container"]/div[1]/table/tbody/tr[5]/td[1]/a
52.         # //*[@id="search-container"]/div[1]/table/tbody/tr[51]/td[1]/a
53.         # //*[@id="search-container"]/div[1]/table/tbody/tr[25]/td[1]/a - last page # 10
54.  
55.         try:
56.             profileurl = driver.find_element(By.XPATH,x).get_attribute('href')  
57.         except NoSuchElementException:
58.             profileurl = 'no name'
59.         print(profileurl)
60.  
61.         with open(r'C:UsersKarolina.GugudisDesktopFind and update company info.csv', 'a', encoding="utf-8") as f: # a is for appending information to the file
62.             f.write(profileurl + 'n')
63.    
64. print('the job is done')
65.