python - 将抓取的数据导出到具有特定列的 CSV

Question

我的代码当前正在命令屏幕上打印结果。

期望的结果(参见所附屏幕截图):将最终输出写入 CSV 文件的“a2”列中并将 sku# 输出到“a1”列sku# 始终是 url 中第 5 个“/”之后的文本

这是代码

from bs4 import BeautifulSoup
import urllib.request
import csv
def get_bullets(url):
    page = urllib.request.urlopen(url)
    soup = BeautifulSoup(page,'lxml')
    content = soup.find('div', class_='js-productHighlights product-highlights c28 fs14 js-close')
    bullets = content.find_all('li', class_='top-section-list-item')
    for bullet in bullets:
     print(bullet.string)

get_bullets('https://www.bhphotovideo.com/c/product/1225875-REG/canon_1263c004_eos_80d_dslr_camera.html')

期望的结果:

谢谢!

Answer 1

from bs4 import BeautifulSoup
import urllib.request
import pandas as pd


def get_bullets(url):
    sku = url.split('/')[5]
    page = urllib.request.urlopen(url)
    soup = BeautifulSoup(page,'lxml')
    content = soup.find('div', class_='js-productHighlights product-highlights c28 fs14 js-close')
    bullets = content.find_all('li', class_='top-section-list-item')

    bullets_text = '\n'.join([ bullet.text for bullet in bullets ])

    temp_df = pd.DataFrame([[sku, bullets_text]], columns = ['sku','bullets'])
    temp_df.to_csv('path/filename.csv', index=False)


get_bullets('https://www.bhphotovideo.com/c/product/1225875-REG/canon_1263c004_eos_80d_dslr_camera.html')