Dec-09-2022, 11:13 PM
I have some code that opens a website, submits search criteria, and loops through each resulting table row for the link to the details behind it. The results may be broken into pages so it keeps track of that too. It works largely fine with the exception that occasionally, and usually on the first row of a newly loaded page, it will just sit there and not follow the link. I can see the link indicate that it was hovered over, but nothing happens, until I click on it with the mouse, then the process continues. I just don't know what I am missing, as it is placed within a loop that should retry the click as long as the right page is there, which is identified by the presence of known elements. The while loop that starts at line 29 is the functional part in question, and line 31 is where the link is clicked. Code below:
def pagescrape(driver,page_no):
global page_count, resume_record_number
results_table_details_link_xpath="//table[@class='results']/tbody/tr/td[1]/a[contains(@href,'inquiryDetail')]"
captcha_page_element_xpath="//*[@class='captcha__human__title' and text()='You have been blocked.']"
try:
wait=WebDriverWait(driver,20)
wait.until(EC.element_to_be_clickable((By.XPATH,results_table_details_link_xpath)))
try:
result_banner=driver.find_element(By.CLASS_NAME,"pagebanner").text #Search Results page
result_banner_list=result_banner.split()
search_total=int(result_banner_list[0])
if search_total<=25:
min_rec=1
max_rec=search_total
else:
min_rec = int(result_banner_list[4])
max_rec = int(result_banner_list[6].replace('.', ''))
record_count=max_rec-min_rec+1
page_header_tag=str(str(page_no)+'/'+str(page_count)).ljust(10,' ')
print(f"Page:{page_header_tag} Search Total:{str(search_total).ljust(6,' ')} Search Letter:{letter_current} Profile:{profile_current}")
wait=WebDriverWait(driver,6)
for i in range(resume_record_number,record_count+1):
row_tag=f"{i}/{record_count}".ljust(10,' ')
case_status=driver.find_element("xpath", f"//table[@class='results']/tbody/tr[{i}]/td[7]").text
if case_status=='Open' or case_status=='ACTIVE CASE':
Case_Number=driver.find_element("xpath", f"/html/body/div/table[4]/tbody/tr[{i}]/td[1]/a").text
case_type=driver.find_element("xpath", f"/html/body/div/table[4]/tbody/tr[{i}]/td[6]").text
time.sleep(1)
while True:
try:
details_link=driver.find_element("xpath", f"/html/body/div/table[4]/tbody/tr[{i}]/td[1]/a")
driver.execute_script("return arguments[0].scrollIntoView();", details_link)
details_link.click()
wait.until(EC.any_of
(EC.text_to_be_present_in_element((By.CLASS_NAME,'InfoStatement'),'This is an electronic case record'),
EC.element_to_be_clickable((By.XPATH,"//div[@class='Subheader']/a[text()='Go Back']"))
))
html=driver.find_element(By.TAG_NAME, "html") #Details page
for j in range(randrange(5)):
html.send_keys(Keys.PAGE_DOWN)
driver.find_element("xpath",f"/html/body").click();
for j in range(randrange(5)):
html.send_keys(Keys.PAGE_UP)
driver.find_element("xpath",f"/html/body").click();
time.sleep(1)
details=getrecord(driver,Case_Number,page_no,case_type)
values_list=list(details.values())
print(f"{row_tag} {values_list[8]}")
with open(proc_path, 'a',encoding="utf-8",newline="") as f:
writer = csv.writer(f)
writer.writerow(values_list)
driver.back()
time.sleep(1)
break
except TimeoutException as timeout_results_page:
try:
wait.until(
EC.any_of(
EC.element_to_be_clickable((By.XPATH,results_table_details_link_xpath)),
EC.text_to_be_present_in_element((By.CLASS_NAME,'captcha__human__title'),'You have been blocked.'),
EC.text_to_be_present_in_element_value((By.NAME,'button'),'Go Back'),
EC.element_to_be_clickable((By.ID,"btnDisclaimerAgree")),
)
)
if len(driver.find_elements(By.XPATH,results_table_details_link_xpath))>0: #Search results page
time.time(1)
print(f'Retrying record: {i}')
continue
elif len(driver.find_elements(By.XPATH,captcha_page_element_xpath))>0: #captcha page
continue
elif len(driver.find_elements(By.NAME,"button"))>0: #Error page. Title: An Error has occurred
print(f"{row_tag} -- Error page loaded")
backbutton=driver.find_element(By.NAME,"button")
backbutton.click()
time.sleep(2)
break
else: #Back at home/disclaimer page
resume_record_number=i
return i
except Exception as err_long_timeout:
if 'Search Results' in driver.title:
continue
else:
print(f"Page Title: {driver.title} - {err_long_timeout} -- in-search page wait")
continue
except Exception as err_other:
print(err_other)
continue
while True:
try:
wait.until(EC.element_to_be_clickable((By.XPATH,results_table_details_link_xpath)))
break
except Exception as err_results:
print(f"Page Title: {driver.title} - {err_results} -- Results page expected")
else:
print(f"{row_tag} -- Closed Case")
continue
resume_record_number=1
return -1
except Exception as err_results_page:
return -3
except Exception as e:
print(f"{e} -- Catch-all")
return -3Any insight would be greatly appreciated