실습

'사과' 자동검색하기

!pip install selenium

import requests as req
from bs4 import BeautifulSoup as bs
import pandas as pd

from selenium import webdriver as wb
from selenium.webdriver.common.keys import Keys

driver = wb.Chrome()  # 웹 페이지 띄워보기

url = 'https://www.google.com/'  # 웹 사이트 설정

driver.get(url)

input_search = driver.find_element_by_class_name('gLFyf')  # 개발자 모드 검색 창 클래스

input_search.send_keys('사과')

input_search.send_keys(Keys.ENTER)

 

실시간검색어 가져오기

from bs4 import BeautifulSoup as bs
import requests as req
url = "https://datalab.naver.com/keyword/realtimeList.naver?where=main"
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'}
res = req.get(url, headers=headers)
res

soup = bs(res.content, 'lxml')
soup

rank=[]
info=[]
info_list = soup.find_all('span', class_='item_title')
for i in range(len(info_list)):
    rank.append(str(i+1))
    info.append(info_list[i].text.strip())
    
search_info = {'순위':rank, '검색어':info}

import pandas as pd
search = pd.DataFrame(search_info)
search.set_index('순위', inplace=True)

search

 

쇼핑Best상품 가져오기

from selenium import webdriver as  wb
from selenium.webdriver.common.keys import Keys
import time
import pandas as pd
from tqdm import tqdm_notebook

driver = wb.Chrome()
url = 'https://front.wemakeprice.com/best'
driver.get(url)

numbers = []
names = []
prices =[]
navs =[]

for num in range(10):
    image_list = driver.find_elements_by_css_selector('div.flag_wrap')
    image_list[num].click()
    time.sleep(1)
    
    number = str(num+1)
    try:
        name = driver.find_element_by_css_selector('h3.deal_tit').text.strip()
    except:
        name = driver.find_element_by_css_selector('h4.deal_tit').text.strip()
    price = driver.find_element_by_css_selector('em.num').text.strip()
    try:
        nav = driver.find_element_by_css_selector('dl.origin p').text[6:]
    except:
        nav = "원산지가 없습니다."
    
    numbers.append(number)
    names.append(name)
    prices.append(price)
    navs.append(nav)

    driver.back()
    time.sleep(1)
    
list = {'순위':numbers, '상품명':names, '가격':prices, '원산지 정보':navs}

df = pd.DataFrame(list)
df.set_index('순위', inplace=True)

df

df.to_csv('WeMakePrice.csv', encoding='utf-8-sig')

 

스포츠승률 가져오기

import requests as req
from bs4 import BeautifulSoup as bs
from selenium import webdriver as wb
from selenium.webdriver.common.keys import Keys
import time

url = 'https://www.koreabaseball.com/TeamRank/TeamRank.aspx'

driver = wb.Chrome()
driver.get(url)

soup = bs(driver.page_source, 'lxml')

team_col = soup.select('th', limit=12)
team_col


play_data = soup.select('td', limit=120)
play_data


len(team_col), len(play_data)


col_list = []
for index in team_col:
    col_list.append(index.text)
    
data_list = []

for data in play_data:
    data_list.append(data.text)
    
import numpy as np
import pandas as pd

info_array = np.array(data_list).reshape(-1, 12)
info_array


kbo_info = pd.DataFrame(info_array, columns=col_list)
kbo_info.set_index('순위', inplace=True)

kbo_info = kbo_info[['팀명', '경기', '승', '패', '무', '승률']]

kbo_info


kbo_info.to_csv('kbo_info.csv', encoding='utf-8-sig')