continue
for i in range(0, len(population), 3):
try:
n = names[i]
place_population = int(population[i].replace(',', ''))
employment_ratio = population[i + 1]
unemployment_ratio = population[i + 2]
print(n, place_population, employment_ratio, unemployment_ratio)
cur.execute('INSERT INTO UNEMPLOYMENT VALUES(?, ?, ?, ?)', (n, place_population, employment_ratio, unemployment_ratio))
conn.commit()
except:
traceback.print_exc()
print('')
for header in headers:
total_names.append(header)
driver.execute_script("stepshift('h', 'f')")
time.sleep(1)
except:
traceback.print_exc()
print()
driver = get_headless_driver(no_sandbox=True)
driver.set_page_load_timeout(60)
driver.get(
'https://factfinder.census.gov/faces/tableservices/jsf/pages/productview.xhtml?pid=ACS_16_5YR_S2301&prodType=table')
modify_table(driver)
extract_values(driver)
def get_tax_data(input_file, output_file):
counter = 0
driver = get_headless_driver()
driver.get("https://propertytax.jpso.com/PropertyTax/propsrch.aspx#result")
# with open('super_output' + str(sys.argv[1]) + '.txt', 'a+') as real_output:
with open(output_file + '.txt', 'a') as real_output:
counter = sum(1 for line in real_output)
# with open('output' + str(sys.argv[1]) + '.txt', 'r') as parcels:
with open(input_file + '.txt', 'r') as parcels:
skipped = 0
for index, parcel in enumerate(parcels):
if index < counter:
continue
try:
print counter, skipped
select = driver.find_element_by_xpath(
'//*[@id="ContentPlaceHolder1_body_cboSearchBy"]')
select.send_keys('pp')
bar = driver.find_element_by_xpath(
'//*[@id="ContentPlaceHolder1_body_txtParcel_In"]')
bar.send_keys(parcel.split('"')[0].strip())
bar.send_keys(Keys.ENTER)
hex = driver.find_element_by_xpath(
'//*[@id="ContentPlaceHolder1_body_lblHEX"]')
tax = driver.find_element_by_xpath(
'//*[@id="ContentPlaceHolder1_body_lblTaxAmt"]')
hextax = hex.text + '"' + tax.text
string_to_concat = parcel.strip() + '"' + hextax
history_button = driver.find_element_by_xpath(
'//*[@id="ContentPlaceHolder1_body_btViewHistory"]')
history_button.click()
rows = driver.find_elements_by_class_name('text_smaller')
tax = {}
for i in range(1, 4):
year = ''
tax_notice = ''
assessment = ''
original_tax_due = ''
paid_amount = ''
date_paid = ''
balance_due = ''
year = get_selenium_xpath_if_exists(
driver,
'//*[@id="ContentPlaceHolder1_body_dgHistory"]/tbody/tr['
+ str(i + 1) + ']/td[1]')
tax_notice = get_selenium_xpath_if_exists(
driver,
'//*[@id="ContentPlaceHolder1_body_dgHistory"]/tbody/tr['
+ str(i + 1) + ']/td[2]')
assessment = get_selenium_xpath_if_exists(
driver,
'//*[@id="ContentPlaceHolder1_body_dgHistory"]/tbody/tr['
+ str(i + 1) + ']/td[3]')
original_tax_due = get_selenium_xpath_if_exists(
driver,
'//*[@id="ContentPlaceHolder1_body_dgHistory"]/tbody/tr['
+ str(i + 1) + ']/td[4]')
paid_amount = get_selenium_xpath_if_exists(
driver,
'//*[@id="ContentPlaceHolder1_body_dgHistory"]/tbody/tr['
+ str(i + 1) + ']/td[5]')
date_paid = get_selenium_xpath_if_exists(
driver,
'//*[@id="ContentPlaceHolder1_body_dgHistory"]/tbody/tr['
+ str(i + 1) + ']/td[6]')
balance_due = get_selenium_xpath_if_exists(
driver,
'//*[@id="ContentPlaceHolder1_body_dgHistory"]/tbody/tr['
+ str(i + 1) + ']/td[7]')
tax_concat = '"' + year + '"' + tax_notice + '"' + assessment + '"' + original_tax_due + '"' + paid_amount + '"' + date_paid + '"' + balance_due
string_to_concat += tax_concat
real_output.write(string_to_concat + '\n')
print(string_to_concat)
back_button = driver.find_element_by_xpath(
'//*[@id="MAIN_OUTLINE_TABLE"]/div[1]/div/div[2]/a/img'
)
back_button.click()
counter += 1
except:
driver.close()
driver = get_headless_driver()
driver.get(
"https://propertytax.jpso.com/PropertyTax/propsrch.aspx#result"
)
skipped += 1
continue