Я работаю над парсером с использованием селена в python. Вот мой текущий код:
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from time import sleep
from selenium.common.exceptions import NoSuchElementException
import csv
driver = webdriver.Chrome("/Users/nzalle/Downloads/chromedriver")
driver.get("https://directory.bcsp.org/")
count = int(input("Number of Pages to Scrape: "))
body = driver.find_element_by_xpath("//body")
profile_count = driver.find_elements_by_xpath("//div[@align='right']/a")
while len(profile_count) < count: # Get links up to "count"
body.send_keys(Keys.END)
sleep(1)
profile_count = driver.find_elements_by_xpath("//div[@align='right']/a")
for link in profile_count: # Calling up links
temp = link.get_attribute('href') # temp for
driver.execute_script("window.open('');") # open new tab
driver.switch_to.window(driver.window_handles[1]) # focus new tab
driver.get(temp)
# Scrape Code
Name = driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[1]/div[2]/div').text or driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[1]/div[2]/div').text
IssuedBy = "Board of Certified Safety Professionals"
CertificationNumber = driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[3]/table/tbody/tr[1]/td[3]/div[2]').text or driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[3]/table/tbody/tr[1]/td[3]/div[2]').text
CertfiedSince = driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[3]/table/tbody/tr[3]/td[1]/div[2]').text or driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[3]/table/tbody/tr[3]/td[1]/div[2]')
RecertificationCycleORExperation = driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[3]/table/tbody/tr[3]/td[3]/div[2]').text or driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[3]/table/tbody/tr[3]/td[3]/div[2]')
try:
AccreditedBy = driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[3]/table/tbody/tr[5]/td[3]/div[2]/a').text
except NoSuchElementException:
AccreditedBy = "N/A"
try:
Expires = driver.find_element_by_xpath('/html/body/table/tbody/tr/td/table/tbody/tr/td[5]/div/table[1]/tbody/tr/td[3]/table/tbody/tr[5]/td[1]/div[2]').text
except NoSuchElementException:
Expires = "N/A"
Data = [Name + "," + IssuedBy + "," + CertificationNumber + "," + CertfiedSince + "," + RecertificationCycleORExperation + "," + Expires + "," + AccreditedBy + '\n']
with open('data.csv', 'w', newline='') as csvfile:
writer = csv.writer(csvfile)
h = ["Name", "Issued By", "Certification Number", "Certified Since", "Recertification Cycle/Expiration",
"Expires", "Accredited By"]
writer.writerow(h)
writer.writerow([Data] * len(h))
driver.close()
driver.switch_to.window(driver.window_handles[0])
driver.close()
После очистки данных из одного из профилей я перехожу к следующему, но данные из первого теряются. Мне было интересно, как я смогу собрать данные из всех профилей и поместить их в список или что-то в этом роде, чтобы я мог экспортировать их все в файл CSV.