공모전 사이트 Crawling(크롤링) 해보자

from bs4 import BeautifulSoup from selenium import * from urllib.request import urlopen from urllib.parse import quote_plus import requests from urllib.parse import quote_plus from wordcloud import WordCloud, STOPWORDS import pandas as pd import openpyxl print("라이브러리 임포트 완료".rjust(20, "=")) def get_title(): url = "https://www.wevity.com/?c=find&s=1&gub=1" page = "&gp=" num = 1 title_li = [] for ..

2020.05.09

Naver Image Crawling

from urllib.request import urlopen from urllib.parse import quote_plus from bs4 import BeautifulSoup from selenium import webdriver print("라이브러리 임포트 완료\n".rjust(20, '-')) base_url = "https://search.naver.com/search.naver?where=image&sm=tab_jum&query=" plus_url = input("무엇을 검색하시겠습니까? ") url = base_url + quote_plus(plus_url) print(url) html = urlopen(url).read() soup = BeautifulSoup(html, 'html.pa..

2020.04.17

Google Image Crawling

import errno import sys, os from bs4 import BeautifulSoup from selenium import webdriver import urllib, urllib.request import requests import random import time from selenium.webdriver.common.keys import Keys folder = "image" url = "https://www.google.com/search" webDriver = "chromedriver.exe" searchItem = input("검색어를 입력하세요: ") size = 300 params = { "q": searchItem , "tbm": "isch" , "sa": "1" , ..

2020.04.17