Cộng đồng Hỏi & Đáp của Inflearn

from bs4 import BeautifulSoup
import requests
import pandas as pd
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.suppor import expected_conditions as EC
from selenium.webdriver.common.by import By

browser = webdriver.Chrome('chromdriver')
bills = list()

for i in range(1, 2):
    response = requests.get('http://watch.peoplepower21.org/index.php?mid=Euian&show=1&page={}&title=&rec_num=15&lname=&sangim=&bill_result='.format(i))
    html = response.text


    soup = BeautifulSoup(html, 'lxml')
    body = soup.body

    div_ea_list = body.find(id='ea_list')
    table = div_ea_list.table
    tbody = table.tbody

    lines = tbody.find_all('tr')

    for line in lines:
        td_list = line.find_all('td')
        bills.append(
            [td_list[0].text, td_list[1].text, td_list[2].text, td_list[3].text, td_list[4].text]
        )
        bill_url = 'http://watch.peoplepower21.org' +  td_list[1].a.get('href')

        print(bill_url)

        browser.get(bill_url)
        browser.implicitly_wait(5)
        WebDriverWait(browser, 20).until(EC.presence_of_element_located(
                (By.ID, 'collapseTwo')

        ))

        html = browser.page_source
        soup = BeautifulSoup(html, 'lxml')

        body = soup.body
        proposers = body.find(id='collapseTwoe').text.replace('','')

        bills.append(
            [td_list[0].text, td_list[1].text, td_list[2].text, td_list[3].text, td_list[4].text]
        )



df = pd.DataFrame(bills, columns=['제안일', '의안명', '발의자명단','상임위','상태' ])
df.to_excel('bill.xlsx')

browser.quit()