I am trying to extract URL link from webpage so I could download the audio as mp3, but still unsuccess... Here is a webpage code:
I would like to grab a value of 'scr' attribute: 'https://radio-arch-pp.stv.livebox.sk/a520/00/0024/002424/00242487-1.mp3'
None of these attempts prints that value:
1)
import requests
from bs4 import BeautifulSoup
re = requests.get("https://www.rtvs.sk/embed/audio/242500")
soup = BeautifulSoup(re.text, 'html.parser')
result = soup.findAll("div", id="player_audio_242500")
print(result)
for n in soup.findAll("div", id="player_audio_242500"):
if 'src' in n.attrs:
result = n['src']
else:
result = n.text
print(result)
for n in soup.find_all('script'):
print(n.get('src'))
for n in soup.find_all('script'):
if 'src' in n.attrs:
result = n['src']
else:
result = n.text
print(result)
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.chrome.service import Service
ser = Service("chromedriver")
op = webdriver.ChromeOptions()
chrome_browser = webdriver.Chrome(service=ser, options=op)
chrome_browser.maximize_window()
chrome_browser.get('https://www.rtvs.sk/embed/audio/242500')
enter = chrome_browser.find_element(by=By.CSS_SELECTOR, value="[id^=player_audio]")
print(enter)
print(enter.text)
Can anybody help please?
CodePudding user response:
Take a look at your css selector
, it should select the video
and should take its src
attribute like that:
chrome_browser.find_element(By.CSS_SELECTOR, 'video').get_attribute("src")