Initial commit

scraper.py

@@ -0,0 +1,32 @@
+import base64
+import pickle
+from time import sleep
+from selenium import webdriver
+from selenium.webdriver.support.wait import WebDriverWait
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.action_chains import ActionChains
+from selenium.webdriver.support import expected_conditions
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+
+driver = webdriver.Chrome()
+driver.get("https://folio.rokus-klett.si/?credit=NPBPLUS4SDZ&layout=single&pages=i")
+print("Page title is: " + driver.title)
+WebDriverWait(driver, 30).until(expected_conditions.presence_of_element_located((By.CSS_SELECTOR, ".pdf-wrap")))
+element = driver.find_element(By.CSS_SELECTOR, ".next-page")
+i = -1
+
+while (element.is_enabled() == True):
+    WebDriverWait(driver, 30).until(expected_conditions.presence_of_element_located((By.XPATH, "//fl-single-leaf[contains(@style,'opacity: 1')]")))
+    src = driver.find_element(By.XPATH, "//fl-single-leaf[contains(@style,'opacity: 1')]/fl-page/fl-page-pdf/img").get_attribute("src")
+    print("Številka strani: " + str(i))
+    strImage = src.split("base64,")[1]
+    ime = str(i) + "-stran.jpeg"
+    file = open(ime, "wb")
+    file.write(base64.b64decode(strImage))
+    file.close()
+    driver.find_element(By.CSS_SELECTOR, ".next-page").click()
+    element = driver.find_element(By.CSS_SELECTOR, ".next-page")
+    i = i + 1
+driver.close()