I am trying to scrape a website and fairly new to Python. I have managed to come up with below code. The problem however is it goes into an infinite loop after reaching the last page i.e Next button is greyed out. Also i don't think i am catching the Stale Element properly here. Any help would be greatly appreciated!`
pages_remaining = True
while pages_remaining:
button=driver.find_element_by_class_name("arrow-right")
href_data = button.get_attribute('href')
if href_data is not None:
soup=BeautifulSoup(driver.page_source,"html.parser")
data = soup.find_all("div",{"class":"shelfProductStamp-content row"})
count = 1
for item in data:
ProductText=item.find("a",attrs={"class":"shelfProductStamp-imageLink"})["title"]
if item.find("span",attrs={"class":"sf-pricedisplay"}) is not None:
Price=item.find("span",attrs={"class":"sf-pricedisplay"}).text
else:
Price=""
if item.find("p",attrs={"class":"sf-comparativeText"}) is not None:
SubPrice1=item.find("p",attrs={"class":"sf-comparativeText"}).text
else:
SubPrice1=""
if item.find("span",attrs={"class":"sf-regoption"}) is not None:
Option=item.find("span",attrs={"class":"sf-regoption"}).text
else:
Option=""
SubPrice=str(SubPrice1)+"-"+str(Option)
SaleDates=item.find("div",attrs={"class":"sale-dates"}).text
urll2=driver.current_url
PageNo=driver.find_element_by_class_name("current").text
writer.writerow([ProductText,Price,SubPrice,SaleDates,PageNo])
count+=1
try:
def find(driver):
element = driver.find_element_by_class_name("arrow-right")
if element:
return element
else:
pages_remaining=False
#driver.quit()
time.sleep(10)
driver.implicitly_wait(10)
element = WebDriverWait(driver, 60).until(find)
driver.execute_script("arguments[0].click();", element)
except StaleElementReferenceException:
pass
else:
break
Thanks
Thanks for your help here. I managed to fix this by simply adding another if statement at the end and swapping the time.sleep(10) as below
try:
def find(driver):
element = driver.find_element_by_class_name("arrow-right")
if element:
return element
driver.implicitly_wait(10)
element = WebDriverWait(driver, 60).until(find)
driver.execute_script("arguments[0].click();", element)
time.sleep(10)
except StaleElementReferenceException:
pass
if href_data is None:
break