Add media_files_extractor.py

This commit is contained in:
Benjamin Loison 2023-02-04 14:18:26 +01:00
parent 2624ab5ef2
commit c73b0e0f5d
Signed by: Benjamin_Loison
SSH Key Fingerprint: SHA256:BtnEgYTlHdOg1u+RmYcDE0mnfz1rhv5dSbQ2gyxW8B8

50
media_files_extractor.py Normal file
View File

@ -0,0 +1,50 @@
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.firefox.options import Options
#from selenium.webdriver.common.action_chains import ActionChains
import json
"""
As there is something looking as an anti-bot for downloading media files, we use a Selenium-based approach.
"""
profile_path = '/home/benjamin/.mozilla/firefox/ilfnifi0.default-release'
fp = webdriver.FirefoxProfile(profile_path)
# I wasn't easily able to use not deprecated code, my try consists in the commented code.
#options = Options()
#options.set_preference('profile', profile_path)
browser = webdriver.Firefox(fp)#options = options)
browser.get('https://studio.youtube.com/channel/UC/music')
"""
For `Music` tab, YouTube UI returns 3,000 entries while my reverse-engineering approach returns 5,819 entries.
For `Sound effects` tab, YouTube UI returns 400 entries while my reverse-engineering approach returns 2021 entries.
So I assume YouTube UI pagination doesn't work fine, so to retrieve all media files, the idea is to filter by `Track title` and download all returned entries, as some tracks have the same titles.
We could verify the `trackId` or `viperId` to avoid downloading other media files containing the provided title.
"""
#actions = ActionChains(browser)
with open('music.json') as json_file:
tracks = json.load(json_file)
for track in tracks:
#browser.find_element(By.ID, 'text-input').click()
#browser.find_element(By.ID, 'text-item-2').click()
#actions.send_keys(track['title'])
#ctions.perform()
browser.find_element(By.ID, 'text-input').send_keys(track['title'])
browser.find_element(By.XPATH, '/html/body/ytcp-text-menu/tp-yt-paper-dialog/tp-yt-paper-listbox/tp-yt-paper-item[2]/ytcp-ve/div/div/yt-formatted-string/span[1]').click()
#browser.find_element(By.XPATH, '/html/body/ytcp-filter-dialog/tp-yt-paper-dialog/div[2]/ytcp-button/div').click()
number_of_results = int(browser.find_element(By.CSS_SELECTOR, '.page-description').get_attribute('innerHTML').split()[-1])
print(number_of_results)
# `DOWNLOAD`
browser.find_element(By.XPATH, 'div.overflow-actions:nth-child(12) > ytcp-button:nth-child(1) > div:nth-child(2)').click()
break
#browser.quit()