# -*- encoding: utf-8 -*-
from urllib.request import urlopen
from bs4 import BeautifulSoup
import csv
import pandas as pd
find_year = ['2019','2020','2021']
find_week = '12' # 1 ~ 52
for year in find_year:
for i in range(1,55):
week = str(i)
html = urlopen("http://gaonchart.co.kr/main/section/chart/online.gaon?nationGbn=T&serviceGbn=ALL&targetTime="+week+"&hitYear="+year+"&termGbn=week")
print(html)
#bsObject = BeautifulSoup(html, "html.parser")
bsObject = BeautifulSoup(html, "lxml", from_encoding='utf-8')
cnt_artist = 0
cnt_title = 0
singer = []
count = []
song = []
for link1 in bsObject.find_all(name="td", attrs={"class":"subject"}):
cnt_artist +=1
cnt_title += 1
singer.append(link1.find(name="p",attrs={"class":"singer"}).text)
cnt_artist = 0
cnt_title = 0
for link2 in bsObject.find_all(name="td", attrs={"class":"count"}):
cnt_artist +=1
cnt_title += 1
count.append(link2.find('p').text)
cnt_artist = 0
cnt_title = 0
for link3 in bsObject.find_all(name="td", attrs={"class":"subject"}):
cnt_artist +=1
cnt_title += 1
song.append(link3.find('p').text)
gaon_list = list(zip(song,singer,count))
#print(data)
data = pd.DataFrame(gaon_list)
data = data.assign(year=year, week=week)
data.columns = ['song','singer','count','year','week']
filename = 'gaon'+year+week+'.csv'
data.to_csv(filename, encoding='euc-kr')
Python
복사