SW과정 머신러닝 1007(3)

1. 뷰티풀숲 태그 관련

tab누르면 자동완성됨
주피터에 뷰티풀숩 소스 작성

import requests
url = 'http://www.naver.com'
naver_html = requests.get(url).text
print(naver_html)

뷰티풀숲 설치 태그
$ pip install beautifulsoup4

선택자 종류와 예시
블로그 바로가기

strip() 앞뒤 공백 제거 함수

2. 네이버 환율 태그

import requests
from bs4 import BeautifulSoup

url = 'https://finance.naver.com/marketindex/exchangeList.naver'
res = requests.get(url).text
soup = BeautifulSoup(res, 'html.parser')

name = []
price = []
result = soup.select('td.tit >a')
# print(result)
for a in result:
    #print(type(a.string))
    #print(a.string.strip())
    name.append(a.string.strip())

result1 = soup.select('td.sale')
for td in result1:
    print(float(td.string.strip().replace(',',''))) # ' , '를 찾아서 ' '(아무것도없는)것으로 바꿔라
    price.append(float(td.string.strip().replace(',','')))
# b = a.string.strip()
# print(b)
# print(name)
# print(price)

items = list(zip(name,price))
print(items)

3. CGV 영화 제목

url1 = 'http://www.cgv.co.kr/movies/'

res1 = requests.get(url1).text
soup1 = BeautifulSoup(res1, 'html.parser')

result2 = soup1.select('strong.title')
for strong in result2:
    print(strong.text)

4. Bugs 차트 제목

import requests
from bs4 import BeautifulSoup as bs

url='https://music.bugs.co.kr/chart/track/realtime/total'
res = requests.get(url).text  #html
soup = bs(res,"html.parser")

musicdata = soup.select('#CHARTrealtime > table > tbody > tr')
musiclist=[]
for item in musicdata:
    musictitle = item.select_one('th>p>a')
    musistion = item.select_one('td> p > a')
    musiclist.append((musictitle.text,musistion.text))
    # print('--------------------------')
    # print('노래제목 - '+ musictitle.text.strip())
    # print('가    수 - ' + musistion.text.strip())
a=0
for i in musiclist:
    a=a+1
    print('------------------------')
    print(a)
    print(i)

5. 네이버 뉴스 불러오기

import requests
import urllib.request
from bs4 import BeautifulSoup

url='https://news.naver.com/main/read.naver?mode=LSD&mid=shm&sid1=100&oid=366&aid=0000765143'
#res = requests.get(url).text  #html
res = urllib.request.urlopen(url)
soup = BeautifulSoup(res,'html.parser')

news = soup.select('ul.list_txt li a')
# print(len(news))
# print(news)
news_list=[]
for n in news:
    news_dic = {}
    title = n['title'].strip()
    #print('제목 :',title,'\n')
    news_dic['title'] = title

    url = n['href']
    res = urllib.request.urlopen(url)
    soup = BeautifulSoup(res,'html.parser')
    content = soup.select_one('#articleBodyContents')
    #print(content.text.replace('동영상 뉴스','').strip())

    news_dic['content'] = content.text.replace('동영상 뉴스','').strip()
    news_list.append(news_dic)
print(news_list)