Programme zum automatisierten Sammeln von Bildern aus der Google Bildersuche für Machine Learning Projekte
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

collectPictureWindowImages.py 1.9KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657
  1. #Imports Packages
  2. from selenium import webdriver
  3. from selenium.webdriver.common.keys import Keys
  4. import time
  5. #Opens up web driver and goes to Google Images
  6. #driver = webdriver.Chrome('C:/bin/chromedriver_win32/chromedriver.exe')
  7. driver = webdriver.Chrome()
  8. driver.get('https://www.google.ca/imghp?hl=en&tab=ri&authuser=0&ogbl')
  9. #maximize browser
  10. driver.maximize_window()
  11. driver.find_element_by_xpath('//*[@id="L2AGLb"]').click()
  12. time.sleep(2)
  13. box = driver.find_element_by_xpath('//*[@id="sbtc"]/div/div[2]/input')
  14. box.send_keys('window')
  15. box.send_keys(Keys.ENTER)
  16. #Will keep scrolling down the webpage until it cannot scroll no more
  17. last_height = driver.execute_script('return document.body.scrollHeight')
  18. while True:
  19. driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')
  20. time.sleep(2)
  21. new_height = driver.execute_script('return document.body.scrollHeight')
  22. try:
  23. driver.find_element_by_xpath('//*[@id="islmp"]/div/div/div/div/div[5]/input').click()
  24. time.sleep(2)
  25. except:
  26. pass
  27. if new_height == last_height:
  28. break
  29. last_height = new_height
  30. time.sleep(2)
  31. """
  32. #Small Pictures
  33. for i in range(1, 102):
  34. try:
  35. driver.find_element_by_xpath('//*[@id="islrg"]/div[1]/div['+str(i)+']/a[1]/div[1]/img').screenshot('C:/bin/chromedriver_win32/imagesPictureFrame/pictureFrame'+str(i)+'.png')
  36. except:
  37. pass
  38. """
  39. #Bigger Pictures
  40. for i in range(1, 31):
  41. try:
  42. driver.find_element_by_xpath('//*[@id="islrg"]/div[1]/div['+str(i)+']/a[1]/div[1]/img').click()
  43. time.sleep(2)
  44. picture = driver.find_element_by_xpath('//*[@id="Sva75c"]/div/div/div[3]/div[2]/c-wiz/div/div[1]/div[1]/div[2]/div[1]/a/img')
  45. picture.screenshot('C:/bin/chromedriver_win32/imagesWindow/pictureWindow'+str(i)+'.png')
  46. except:
  47. pass
  48. driver.close()