Created
May 21, 2020 11:21
-
-
Save Coro365/410521304fbd9f164c1ce3d87bf9dc71 to your computer and use it in GitHub Desktop.
Download afp video
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
require 'open-uri' | |
require 'fileutils' | |
def add_log(recode) | |
recode = [Time.now, recode + "\n"].join(",\s") | |
File.write(File.join(__dir__, 'downlod.log'), recode, mode: 'a') | |
end | |
def load_log | |
File.open(File.join(__dir__, 'downlod.log')).read | |
end | |
def downlod(url) | |
dldir = File.join(__dir__, '/mp4') | |
Dir.mkdir(dldir) unless Dir.exist?(dldir) | |
Dir.chdir(dldir) | |
cmd = ['youtube-dl', url] | |
system(*cmd) | |
end | |
def scan_video_articles | |
url = 'https://www.afpbb.com/subcategory/m_afp_afpmov' | |
html = URI.open(url).read | |
reg = %r[a href="/articles/-/(\d{7})" class="block move">] | |
html.scan(reg).uniq.flatten | |
end | |
saved_video_ids = load_log | |
video_articles = scan_video_articles.reject { |article_id| saved_video_ids.include?(article_id) } | |
puts("Download #{video_articles.size}video") | |
video_articles.each do |article_id| | |
url = "https://www.afpbb.com/articles/-/#{article_id}" | |
downlod(url) || add_log(article_id) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment