Last active
June 23, 2022 16:50
-
-
Save seanbreckenridge/44854575b03e7f643b19bf40cf7e21bd to your computer and use it in GitHub Desktop.
A script to download all the videos for the Berkley Computer Science 61A class
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# A script to download all the videos from | |
# https://archive.org/details/ucberkeley-webcast-PL3E89002AA9B9879E?sort=titleSorter | |
# python3.7 | |
# pip3 install --user selenium youtube-dl | |
import youtube_dl | |
from selenium import webdriver | |
driver = None | |
def main(): | |
global driver | |
table = "https://archive.org/details/ucberkeley-webcast-PL3E89002AA9B9879E?sort=titleSorter" | |
driver = webdriver.Chrome() | |
driver.get(table) | |
videos = driver.find_elements_by_css_selector("div.item-ia > div > div > a") | |
links = list(map(lambda x: x.get_attribute("href"), videos)) | |
for l in links: | |
driver.get(l) | |
link_for_video_download = driver.find_element_by_partial_link_text("MPEG4").get_attribute('href') | |
print(link_for_video_download) | |
ydl = youtube_dl.YoutubeDL() | |
with ydl: | |
ydl.extract_info(link_for_video_download, download=True) | |
if __name__ == "__main__": | |
try: | |
main() | |
finally: | |
if driver: driver.quit() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment