네이버 증권뉴스 크롤링(2)

import pandas as pd
import re
import requests
from bs4 import BeautifulSoup
from urllib.request import urlopen
from urllib.request import HTTPError
from urllib import parse
from tqdm import trange

data = pd.read_csv("이지케어텍_url.csv")

data = data['url']

hh = []
ii = []

for i in trange(len(data)):
    
    url = data[i]
    req = requests.get(url)
    bs = BeautifulSoup(req.content, "html.parser")

    div = bs.find_all('div',{'class' : 'articleCont'})

    for body in div:
        aa = body.text[1:]
        
    wdate = bs.find_all('span', {'class' : 'article_date'})
    for body in wdate:
        bb = body.text
        ii.append(bb)
    start_idx = aa.find('▶')
    rst = aa[ : start_idx]
    hh.append(rst)
    
ii = pd.DataFrame(ii)
hh = pd.DataFrame(hh)

ss = pd.concat([hh,ii],axis = 1)
ss = ss.rename(columns = {"0" : "news_text" , "0" : "news_dati" })

ss.columns=['text','dati']

ss.to_csv("news.csv")