写入 CSV 并且只得到一列

Question

我正在尝试写入 CSV 文件，但只得到 1 列公司名称。有谁知道我如何写入 CSV 文件并获取所有带有列标题的数据？

打印输出

'Agilent Technologies\n6,319\n2,912\n441\n1,619\n321\n189\n189\n1,347\n81
\n236\n1,210\n19.2%\n307', 'Alcoa\n12,152\n9,153\n31\n227\n664\n390\n390\n2,039\n195\n19\n429\n3.5%\n190',

写入 CSV 后的当前输出

Agilent Technologies
Alcoa

写入 CSV 后的期望输出

完整代码

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.service import Service
import pandas as pd
import requests
import csv
  
options = webdriver.ChromeOptions() 
options.add_argument("start-maximized")
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)
ser = Service("./chromedriver.exe")
browser = driver = webdriver.Chrome(service=ser)

driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
  "source": """
    Object.defineProperty(navigator, 'webdriver', {
      get: () => undefined
    })
  """
})
driver.execute_cdp_cmd("Network.enable", {})
driver.execute_cdp_cmd('Network.setUserAgentOverride', {"userAgent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.53 Safari/537.36'})
wait = WebDriverWait(driver, 30)
driver.get("https://stockrover.com")
wait.until(EC.visibility_of_element_located((By.XPATH, "/html/body/div[1]/div/section[2]/div/ul/li[2]"))).click()
user = driver.find_element(By.NAME, "username")
password = driver.find_element(By.NAME, "password")
user.clear()
user.send_keys("******")
password.clear()
password.send_keys("*******")
driver.find_element(By.NAME, "Sign In").click()
wait = WebDriverWait(driver, 30)


stocks_list = []
try:
    while True:
        # Print the stock symbols
        stocks_list.extend([my_elem.text for my_elem in WebDriverWait(driver, 30).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "table[id^='gridview-1072-record']")))])
        # Click on next page button
        wait.until(EC.visibility_of_element_located((By.XPATH, '//*[@id="button-1157"]'))).click()
except:
        print("Next button disabled")
print(stocks_list) # Prints entire list of stocks

df=pd.DataFrame(stocks_list)
df.to_csv('table.csv')

Answer 1

您可以在最后执行此 CSV 模块添加：

stocks_lists = [x.split('\n') for x in stocks_list]
for row in stocks_lists:
    with open('output.csv', 'a', encoding='utf-8', newline='') as csv_file:
        csv_write = csv.writer(csv_file)
        csv_write.writerow(row)

完整代码：

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.service import Service
import pandas as pd
import requests
import csv
  
options = webdriver.ChromeOptions() 
options.add_argument("start-maximized")
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)

driver = webdriver.Chrome('G://chromedriver.exe')

driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
  "source": """
    Object.defineProperty(navigator, 'webdriver', {
      get: () => undefined
    })
  """
})
driver.execute_cdp_cmd("Network.enable", {})
driver.execute_cdp_cmd('Network.setUserAgentOverride', {"userAgent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.53 Safari/537.36'})
wait = WebDriverWait(driver, 30)
driver.get("https://stockrover.com")
wait.until(EC.visibility_of_element_located((By.XPATH, "/html/body/div[1]/div/section[2]/div/ul/li[2]"))).click()
user = driver.find_element(By.NAME, "username")
password = driver.find_element(By.NAME, "password")
user.clear()
user.send_keys("********")
password.clear()
password.send_keys("********")
driver.find_element(By.NAME, "Sign In").click()
wait = WebDriverWait(driver, 30)



stocks_list = []
try:
    while True:
        # Print the stock symbols
        stocks_list.extend([my_elem.text for my_elem in WebDriverWait(driver, 30).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "table[id^='gridview-1072-record']")))])
        # Click on next page button
        wait.until(EC.visibility_of_element_located((By.XPATH, '//*[@id="button-1157"]'))).click()
except:
        print("Next button disabled")
# print(stocks_list) # Prints entire list of stocks

stocks_lists = [x.split('\n') for x in stocks_list]
for row in stocks_lists:
    with open('output.csv', 'a', encoding='utf-8', newline='') as csv_file:
        csv_write = csv.writer(csv_file)
        csv_write.writerow(row)

Answer 2

假设这是您的字符串列表

string_sock = ["""Agilent Technologies\n6,319\n2,912\n441\n1,619\n321\n189\n189\n1,347\n81
\n236\n1,210\n19.2%\n307""", """Alcoa\n12,152\n9,153\n31\n227\n664\n390\n390\n2,039\n195\n19\n429\n3.5%\n190"""]

你的专栏

columns = ['Company', 'Sales', 'Cost of Sales', 'R&D', 'SG&A', 'Depr', 'Capex', 'Maint Capex', 'Op income', 'Int Exp.', 'Dividends', 'Net Inc.', 'Net Margin', 'Diluted Sh', 'rs']

用分隔符拆分输入

splitted_rows = [v.split("\n") for v in string_sock]


pd.DataFrame(splitted_rows, columns=columns).to_csv(test.csv)

写入 CSV 并且只得到一列

Writing to CSV and only getting one column

python

export-to-csv

pandas