我无法以 CSV 格式导出抓取的数据

Question

我无法以 CSV 格式获取所有数据，只能获取最后一个数据。抓取完成后，只有最后一个抓取的是保存 CSV 文件，但我想从所有页面保存。

import requests
from bs4 import BeautifulSoup
from selenium import webdriver
import time
import pandas as pd
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.common.by import By

driver = webdriver.Chrome()
mainurl = 'https://austin.craigslist.org/search/cta?s=0'
driver.get(mainurl)
res = driver.execute_script("return document.documentElement.outerHTML")
page_soup = BeautifulSoup(res, 'html.parser')

lnk_opener = driver.find_element_by_xpath('//*[@id="sortable-results"]/ul/li[1]/p/a').click()
time.sleep(4)
records = []
i = 1
while i <3:
    i+=1

    try:
        print(driver.current_url)
    except Exception:
        print('Internet Error Detected')

    try:
        title = driver.find_element_by_xpath('//*[@id="titletextonly"]').text
        print(title)
    except Exception:
        print('No Title Given')
    try:
        price = driver.find_element_by_xpath('/html/body/section/section/h2/span/span[2]').text
        print(price)
    except Exception:
        print('No Price Given')
    try:
        phone = driver.find_element_by_xpath('//*[@id="postingbody"]/h2[1]/big').text
        print(phone)
        records.append((phone))
    except Exception:
        print('No Mobile number avalible')
    try:
        loc = driver.find_element_by_xpath('/html/body/section/section/section/div[1]/div/div[2]').text
        print(loc)
    except Exception:
        print('No Location Data Avalible')
    try:
        img = page_soup.find('img')
        immg = print(img.get('src','\n'))
    except Exception:
        print('No img Found')

    nxtpg = driver.find_element_by_xpath('/html/body/section/section/header/div[1]/div/a[3]')
    nxtpg.click()
    time.sleep(4)
    url = driver.find_element_by_xpath("/html/body/section/section/header/div[1]/div/a[3]").get_attribute("href")
    if url == None:
        bckbtn = driver.find_element_by_class_name('backup').click()
        time.sleep(5)
        nextbuttton = driver.find_element_by_xpath('//*[@id="searchform"]/div[3]/div[3]/span[2]/a[3]').click()
        time.sleep(6)
        print(records)

records.append((driver.current_url, title, price, loc, immg))
df = pd.DataFrame(records, columns=['Product Url', 'Title/Model/Make', 'Price', 'GM Location', 'Image Link'])
print(df)
df.to_csv('zzz.csv')
time.sleep(4)
driver.quit()

Answer 1

我认为这条线

records.append((driver.current_url, title, price, loc, immg))

应该在while 语句中。另外，将i += 1 移动到语句的末尾，否则您将跳过第一次迭代。