Python Loop 读取相同的 CSV 数据

Question

我必须获取 csv 文件的第一行，并在处理完后将其删除，然后再恢复该行。

我正在尝试构建一个登录系统，从 csv 文件中获取帐户，然后一个一个地登录。

问题是每次启动循环时，它总是采用相同的帐户，我该如何解决？

import pandas as pd
import pyperclip
import selenium
import random
from selenium import webdriver
import undetected_chromedriver as uc
from selenium.webdriver.common.by import By
import time
from selenium.webdriver.common.keys import Keys
import names


df = pd.read_csv('/Users/giuseppeleonardi/Downloads/scraping2.csv')
def instagram_login():

    df2=df.at[0,'ID'] #Find the first row id
    pyperclip.copy(df2) #Copy the first row id to the clipboard
    print(pyperclip.paste()) #Print the first row id
    #apro il sito
    driver.get('https://www.instagram.com/')
    driver.maximize_window() #schermo intero
    time.sleep(2)
    try:
        consent= driver.find_element(By.XPATH,"/html/body/div[2]/div/div/div/div[2]/div/div/div[1]/div/div[2]/div/div/div/div/div[2]/div/button[2]").click() #clicco il consenso
    except:
        pass    
    time.sleep(5)
    put_username = driver.find_element(By.NAME,("username")).send_keys(pyperclip.paste()) #inserisco username
    df2=df.at[0,'PASSWORD'] #find the password
    pyperclip.copy(df2) #copy the password
    put_password = driver.find_element(By.NAME,("password")).send_keys(pyperclip.paste()) #inserisco password
    time.sleep(2)
    login = driver.find_element(By.XPATH,"//div[contains(text(),'Accedi')]").click() #Click login
    time.sleep(6)
    #here is where the first row got deleted and saved on csv
    df= pd.read_csv('/Users/giuseppeleonardi/Downloads/scraping2.csv').drop(0, axis=0)
    df.to_csv(r'/Users/giuseppeleonardi/Downloads/scraping2.csv', index=False)
    

    #this is the loop that always takes the same line of the file every time even though this is canceled at the end of the operation:

for line in len(df):
    instagram_login()
    time.sleep(5)
    driver.delete_all_cookies()

我在谷歌上搜索了很多但无法弄清楚，我读过文件句柄将读取文件一次，我需要循环来每次重置列表并取第一个值，我该怎么做？

抱歉，我还在学习

Answer 1

谷歌局部和全局变量。您正在函数内部更改 df。这不会更改“全局”df。您需要从函数中return您的 df 或首先将其声明为全局变量。

第一个选项：

df = pd.read_csv('/Users/giuseppeleonardi/Downloads/scraping2.csv')
def instagram_login():

    df2=df.at[0,'ID'] #Find the first row id
    .....
    #here is where the first row got deleted and saved on csv
    df= pd.read_csv('/Users/giuseppeleonardi/Downloads/scraping2.csv').drop(0, axis=0)
    df.to_csv(r'/Users/giuseppeleonardi/Downloads/scraping2.csv', index=False)
    return df


for line in len(df):
    df = instagram_login()
    time.sleep(5)
    driver.delete_all_cookies()

第二个选项：

df = pd.read_csv('/Users/giuseppeleonardi/Downloads/scraping2.csv')
def instagram_login():

    df2=df.at[0,'ID'] #Find the first row id
    .....
    #here is where the first row got deleted and saved on csv
    global df
    df = pd.read_csv('/Users/giuseppeleonardi/Downloads/scraping2.csv').drop(0, axis=0)
    df.to_csv(r'/Users/giuseppeleonardi/Downloads/scraping2.csv', index=False)


for line in len(df):
    instagram_login()
    time.sleep(5)
    driver.delete_all_cookies()

Answer 2

您在函数内部定义的 df 不会改变外部 df。 所以可以返回df，保存到外部df。

data_frame= pd.read_csv('/Users/giuseppeleonardi/Downloads/scraping2.csv')
def instagram_login(df):
    ......
    #here is where the first row got deleted and saved on csv
    df= pd.read_csv('/Users/giuseppeleonardi/Downloads/scraping2.csv').drop(0, axis=0)
    df.to_csv(r'/Users/giuseppeleonardi/Downloads/scraping2.csv', index=False)
    return df


#this is the loop that always takes the same line of the file every time even though this is canceled at the end of the operation:

for line in len(df):
    data_frame = instagram_login(data_frame)
    time.sleep(5)
    driver.delete_all_cookies()