from langchain_community.document_loaders import YoutubeLoader
"https://www.youtube.com/watch?v=HAn9vnJy6S4",
"https://www.youtube.com/watch?v=dA1cHGACXCo",
"https://www.youtube.com/watch?v=ZcEMLz27sL4",
"https://www.youtube.com/watch?v=hvAPnpSfSGo",
"https://www.youtube.com/watch?v=EhlPDL4QrWY",
"https://www.youtube.com/watch?v=mmBo8nlu2j0",
"https://www.youtube.com/watch?v=rQdibOsL1ps",
"https://www.youtube.com/watch?v=28lC4fqukoc",
"https://www.youtube.com/watch?v=es-9MgxB-uc",
"https://www.youtube.com/watch?v=wLRHwKuKvOE",
"https://www.youtube.com/watch?v=ObIltMaRJvY",
"https://www.youtube.com/watch?v=DjuXACWYkkU",
"https://www.youtube.com/watch?v=o7C9ld6Ln-M",
docs.extend(YoutubeLoader.from_youtube_url(url, add_video_info=True).load())
# Add some additional metadata: what year the video was published
doc.metadata["publish_year"] = int(
datetime.datetime.strptime(
doc.metadata["publish_date"], "%Y-%m-%d %H:%M:%S"