diff --git a/media_files_extractor.py b/media_files_extractor.py index 8b166b3..1a3fe27 100644 --- a/media_files_extractor.py +++ b/media_files_extractor.py @@ -1,26 +1,23 @@ -from selenium import webdriver +import undetected_chromedriver.v2 as uc from selenium.webdriver.common.by import By -from selenium.webdriver.firefox.options import Options +from selenium.webdriver.chrome.options import Options 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) - -browser = webdriver.Firefox(fp) +options = Options() +options.add_argument("--user-data-dir=selenium") +browser = uc.Chrome(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 (for `Music`), the idea is to filter by `Track title` and download one entry that perfectly (not just `contains`) matches `artist/name`, `title` and `duration/nanos` (converted if only `seconds`), as some tracks have the same titles. -Only `trackId` and `viperId` differ when identifying with `artist/name`, `title` and `duration/nanos` (cf above comment) (example: `Dyalla_Ringside_116`), as I verified all duplicates, they are binary identical. -So we will have to duplicate the media file with the different `trackId`s for files being *identitcal* (note that `trackId`, as well as `viperId` are uniquely identified). -Otherwise I could clean the metadata by removing duplicates (but then if we update the database we have to make sure that ids that we have kept are still kept). +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 entries, preferably only those that have the title we are looking for, as some tracks have the same titles. +As for `Sound effects`, even with `Sound effect`, `Duration`, `Category` and `Added` there is an ambiguity on which files do we refer to (for instance for `Truck Driving in Parking Structure`, as they all are different). """ with open('music.json') as json_file: