資料被覆寫如何解決

在回圈中的每次迭代中，先前提取的資料都會被覆寫。我怎么解決這個問題？

from selenium import webdriver
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support.select import Select
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd


# url='https://www.amazon.com/dp/B00M0DWQYI?th=1'
# url='https://www.amazon.com/dp/B010RWD4GM?th=1'
PATH="C:\Program Files (x86)\chromedriver.exe"
driver =webdriver.Chrome(PATH)
df_urls = pd.read_csv('D:/selenium/inputs/amazone-asin.csv',encoding='utf-8')
list_dicts_urls =df_urls.to_dict('records')

item=dict()
product=[]
for url in list_dicts_urls:
    
    product_url = 'https://'   url['MARKETPLACE']   '/dp/'   url['ASIN']
    driver.get(product_url)


    try:
        item['title'] = driver.find_element(By.CSS_SELECTOR,'span#productTitle').text
    except:
        item['title'] = ''
        
    try:
        item['brand'] = driver.find_element(By.CSS_SELECTOR,'a#bylineInfo').text.replace('Visit the','').replace('Store','').strip()
    except:
        item['brand'] = ''
    try:
        rating = driver.find_element(By.CSS_SELECTOR,'span#acrCustomerReviewText').text.replace('ratings','').strip()
        rating = int(rating.replace(',', ''))
        item['rating'] = rating
    except:
        item['rating'] = ''
        
    time.sleep(2)
    try:
        p1=driver.find_element(By.XPATH, '//span[@]').text
        p2= driver.find_element(By.XPATH, '//span[@]').text
        item['price']=p1 p2
    except:
        item['price']=''
        
    product.append(item)
    
df=pd.DataFrame(product)
df.to_csv("ama.csv")

uj5u.com熱心網友回復：

我認為您需要item=dict()在for回圈內定義。否則，這是item在所有回圈迭代中使用的相同的單個物件。
嘗試這個：

from selenium import webdriver
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support.select import Select
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd


# url='https://www.amazon.com/dp/B00M0DWQYI?th=1'
# url='https://www.amazon.com/dp/B010RWD4GM?th=1'
PATH="C:\Program Files (x86)\chromedriver.exe"
driver =webdriver.Chrome(PATH)
df_urls = pd.read_csv('D:/selenium/inputs/amazone-asin.csv',encoding='utf-8')
list_dicts_urls =df_urls.to_dict('records')

product=[]
for url in list_dicts_urls:

    item=dict()
    
    product_url = 'https://'   url['MARKETPLACE']   '/dp/'   url['ASIN']
    driver.get(product_url)


    try:
        item['title'] = driver.find_element(By.CSS_SELECTOR,'span#productTitle').text
    except:
        item['title'] = ''
        
    try:
        item['brand'] = driver.find_element(By.CSS_SELECTOR,'a#bylineInfo').text.replace('Visit the','').replace('Store','').strip()
    except:
        item['brand'] = ''
    try:
        rating = driver.find_element(By.CSS_SELECTOR,'span#acrCustomerReviewText').text.replace('ratings','').strip()
        rating = int(rating.replace(',', ''))
        item['rating'] = rating
    except:
        item['rating'] = ''
        
    time.sleep(2)
    try:
        p1=driver.find_element(By.XPATH, '//span[@]').text
        p2= driver.find_element(By.XPATH, '//span[@]').text
        item['price']=p1 p2
    except:
        item['price']=''
        
    product.append(item)
    
df=pd.DataFrame(product)
df.to_csv("ama.csv")

uj5u.com熱心網友回復：

嘗試：

product=[]
for url in list_dicts_urls:
    
    product_url = 'https://'   url['MARKETPLACE']   '/dp/'   url['ASIN']
    driver.get(product_url)


    try:
        title = driver.find_element(By.CSS_SELECTOR,'span#productTitle').text
    except:
        title = ''
        
    try:
        brand = driver.find_element(By.CSS_SELECTOR,'a#bylineInfo').text.replace('Visit the','').replace('Store','').strip()
    except:
        brand= ''
    try:
        rating = driver.find_element(By.CSS_SELECTOR,'span#acrCustomerReviewText').text.replace('ratings','').strip()
        rating = int(rating.replace(',', ''))
        rating = rating
    except:
        rating = ''
        
    time.sleep(2)
    try:
        p1=driver.find_element(By.XPATH, '//span[@]').text
        p2= driver.find_element(By.XPATH, '//span[@]').text
        price=p1 p2
    except:
        price=''
        
    product.append({
        'title':title,
        'brand':brand,
        'rating':rating,
        'price':price

    })
    
df=pd.DataFrame(product)
df.to_csv("ama.csv")

標籤：Python熊猫数据框硒for循环

上一篇：Groupby均值不顯示所有資料

下一篇：使用json列讀取csv，該列多次嵌套到資料框中