def request_url(site, uri): res = requests.get(site) soup = BeautifulSoup(res.text, 'html.parser') uri = uri url = soup.select_one(uri) result = url.get('src') iframe = urls.urljoin(urls.getHostname(site, True), result) print (iframe) return iframe
from bs4 import BeautifulSoup import requests import urls bbsUrl = "https://blog.naver.com/korea_diary/221433346994" # bbsUrl = "https://blog.naver.com/d_ahae/221436343740" # bbsUrl = "https://blog.naver.com/kkomataku/221437665643" # bbsUrl = "https://blog.naver.com/baekmg1988/221405485574" html = requests.get(bbsUrl).text soup = BeautifulSoup(html, 'html.parser') ifrSel = "iframe#mainFrame" ifr = soup.select_one(ifrSel) src = ifr.get('src') orgUrl = urls.urljoin(urls.getHostname(bbsUrl, True), src) orgHtml = requests.get(orgUrl).text orgSoup = BeautifulSoup(orgHtml, 'html.parser') titleSel = "div.se-title-text span" titleEle = orgSoup.select_one(titleSel) if not titleEle: titleEle = orgSoup.select_one('div.se_title') if titleEle: title = titleEle.text.strip() else: title = 'Title 못찾음!! ' + bbsUrl # print("-->", title) # exit()
from bs4 import BeautifulSoup import requests import urls url_marketindex = "https://finance.naver.com/marketindex/" html = requests.get(url_marketindex).text soup = BeautifulSoup(html, 'html.parser') ifrSel = "iframe#frame_ex1" ifr = soup.select_one(ifrSel) src = ifr.get('src') orgUrl = urls.urljoin( urls.getHostname(url_marketindex, True), src ) # print(orgUrl) orgHtml = requests.get(orgUrl).text orgSoup = BeautifulSoup(orgHtml, 'html.parser') # print(orgHtml) # divSel = "div.tbl_area tbody td.tit a" # divEles = orgSoup.select(divSel) # print(divEles) # table = orgSoup.html.tbody # print(table) # tr = table.tr # print(trt)
from bs4 import BeautifulSoup import requests import urls url = "https://finance.naver.com/marketindex/" html = requests.get(url).text soup = BeautifulSoup( html, 'html.parser') iframe = 'iframe#frame_ex1' ifsoup = soup.select_one(iframe) ifsrc = ifsoup.get('src') joinUrl = urls.urljoin( urls.getHostname(url, True), ifsrc) joinHtml = requests.get(joinUrl).text joinSoup = BeautifulSoup(joinHtml, 'html.parser') source_len_tr = joinSoup.select('body > div > table > tbody > tr') real_len = len(source_len_tr) tr_sel = 'body > div > table > tbody > tr' trs = joinSoup.select(tr_sel) finance = [] print(" 국가 / 살 때 / 팔 때 / 환율차이 ") for tr in trs : nation = tr.select('td')[0].text.split()[0] buy = tr.select('td')[1].text