크롤링 리스트 가져오기

import requests

from bs4 import BeautifulSoup

import pandas as pd

# Step 1: Send an HTTP GET request to the URL

pg_num = 66

data = []

for i in range(1,pg_num+1):

    url = f'https://jilbyungcase.comwel.or.kr/service/dataList?qw=&q=&gubun=%EC%A7%81%EC%97%85%EC%84%B1%EC%95%94+%EB%93%B1+%EC%95%85%EC%84%B1%EC%8B%A0%EC%83%9D%EB%AC%BC&gubun2=&viewType=&sortField=sort5&sortOrder=desc&pageIndex={i}&pageUnit=20'

    response = requests.get(url)

    # Step 2: Parse the HTML content of the page with BeautifulSoup

    soup = BeautifulSoup(response.content, 'html.parser')

    # Step 3: Locate the table and iterate through rows

    table = soup.find('table', {'class': 'table-list table-case'})  # replace 'your_table_class' with the actual class name of the table

    rows = table.find_all('tr')[1:]  # assuming the first row is the header

    # Step 4: Extract the desired data from each row

   

    for row in rows:

        cols = row.find_all('td')

        cols = [elem.text.strip() for elem in cols]

        data.append(cols)

   

   

   

# Step 5: Create a DataFrame

df = pd.DataFrame(data, columns=['연번', '신청질병 내용', '심의결과', '심의연도', '주문', '청구취지', '신청내용', '신청인주장', '진료기록 및 의학적 소견', '인정사실', '관계법령', '위원회 판단 및 결론'])

#버튼 누르기

# driver.find_elements(By.CLASS_NAME,'btn-badge')[0].click()

# Step 6: Save the DataFrame to a file

# df.to_csv('output.csv', index=False)