content.py 3.27 KB
import csv
import time
import random
import os
import re
import pandas as pd

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from bs4 import BeautifulSoup
from datetime import datetime, timedelta

def sleeptime():
    time.sleep(random.randint(1, 3))

def Click(xpath):
    element = driver.find_element_by_xpath(xpath)
    driver.execute_script("arguments[0].click();", element)
    sleeptime()

login_info = {
    'userID' : 'id',
    'userpw' : '********'

}

options = webdriver.ChromeOptions()
# options.add_argument('headless')
options.add_argument('no-sandbox')
options.add_argument('window-size=1920x1080')
options.add_argument('disable-gpu')
options.add_argument('disable-dev-shm-usage')
options.add_argument('lang=ko_KR')
options.add_argument('user-agent=Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.183 Safari/537.36 Vivaldi/1.96.1147.47')

driver = webdriver.Chrome(r'C:\Users\E_N__\Desktop\chromedriver.exe', options=options)

driver.get('about:blank')
driver.execute_script("Object.defineProperty(navigator, 'plugins', {get: function() {return[1, 2, 3, 4, 5];},});")
sleeptime()
driver.get('https://everytime.kr/login')

sleeptime()
driver.find_element_by_name('userid').send_keys(login_info['userID'])
driver.find_element_by_name('password').send_keys(login_info['userpw'])
driver.find_element_by_class_name('submit').click()
sleeptime()

# 국제캠 자게
sleeptime()
yesterday = (datetime.today() - timedelta(1)).strftime('%m/%d %H:%M')
print(yesterday)
swt = True
page = 0

post_df = pd.DataFrame(columns=['title', 'content'])
while swt:
    if page < 1:
        Click('//*[@id="submenu"]/div/div[2]/ul/li[1]/a')
        page += 1
    else:
        if page == 1:
            Click('//*[@id="container"]/div[2]/div[2]/a')
            page += 1
        elif page == 2:
            Click('//*[@id="container"]/div[2]/div[2]/a[2]')
            page += 1
        else:
            Click('//*[@id="container"]/div[2]/div[2]/a[3]')

    html = driver.page_source
    soup = BeautifulSoup(html, 'html.parser')

    TitleList = soup.select('#container > div.wrap.articles > article > a > h2')
    DateList = soup.select('#container > div.wrap.articles > article > a > time')

    for post in zip(TitleList, DateList):
        title = re.sub(pattern='[^\w\s]', repl='', string=post[0].text)
        try:
            Click("//h2[contains(text(), '{}')]".format(title))
        except NoSuchElementException:
            continue
        content = driver.find_element_by_xpath('//*[@id="container"]/div[2]/article/a/p').text
        driver.back()
        sleeptime()

        if not (post_df['title'] == title).any():
            # Click('//*[@id="container"]/div[2]/article[{}]'.format(idx))
            content = re.sub(pattern='[^\w\s]', repl='', string=content)
            post_df = post_df.append(pd.DataFrame([[title, content]],
                                                  columns=['title', 'content']))
            # print("{0}. {1} : {2}".format(idx, title, content))
        print(post[1].text)
        if post[1].text < yesterday:
            break

post_df.to_csv('data.csv', mode='w', encoding='utf-8-sig')
print("CVS file saved")
post_df.to_json('data.json', orient='records', encoding='utf-8-sig')
print("JSON file saved")