如何将数据从 Python 导出到 a.csv 文件？

Question

I am in the final steps of a scraping project and am looking for some guidance on exporting the data that I have collected into a.csv file. Here is my current code:

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from time import sleep
from selenium.common.exceptions import NoSuchElementException

driver = webdriver.Chrome("MY DIRECTORY")
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"

    print(Name + "," + IssuedBy + "," + CertificationNumber + "," + CertfiedSince + "," + RecertificationCycleORExperation + "," + Expires + "," + AccreditedBy)

    driver.close()
    driver.switch_to.window(driver.window_handles[0])
driver.close()

At this point, I am able to print my data into a list, but I am not sure how to put that list into a spreadsheet. I want my columns to be Name, Issued By, Certification Number, Certified SInce, Recertification Cycle/Expiration, Expires, and Accredited By. Lastly, I want to make rows based on my variables with the corresponding names.

How can I go about executing this?

Answer 1

You are probably looking for the csv module:

import csv

with open('data.csv', 'w', newline='') as csvfile:
    writer = csv.writer(csvfile, delimiter=';')
    h = ["Name", "Issued By", "Certification Number", "Certified SInce", "Recertification", "Cycle/Expiration", "Expires", "Accredited By"]
    writer.writerow(h)
    writer.writerow(["data"] * len(h))

And result: