Created
March 15, 2020 02:50
-
-
Save Coro365/1c34ef5609aa65d7e8f5406728ce64d2 to your computer and use it in GitHub Desktop.
Download photos from f.hatena.ne.jp
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 set_username | |
return ARGV[0] if ARGV[0] | |
raise('Specify the user name in the argument.') | |
end | |
def get_photo_urls | |
puts("Get photo urls from #{$user}'s #{$page_limit}fotolife pages.") | |
photo_urls = 1.upto($page_limit).map do |page| | |
page_param = "?page=#{page}" | |
url = ['https://f.hatena.ne.jp', $user, page_param].join('/') | |
fotolife_html = URI.open(url).read | |
scrape_photo_url(fotolife_html) | |
end | |
photo_urls.flatten | |
end | |
def scrape_photo_url(fotolife_html) | |
url_reg = %r{https://cdn-ak\.f\.st-hatena\.com/images/fotolife} | |
file_type_reg = /jpg|jpeg|gif|png|bmp/ | |
thumbnail_url_reg = %r[(#{url_reg}/./.*?/\d{8}/.*?\.(?:#{file_type_reg}))] | |
thumbnail_urls = fotolife_html.scan(thumbnail_url_reg) | |
thumbnail_urls.map { |e| e.first.sub('_120.', '_original.') } | |
end | |
def compare_by(log, photo_urls) | |
if log | |
photo_urls.reject { |e| log.include?(file_name(e)) } | |
else | |
photo_urls | |
end | |
end | |
def download(photo_urls) | |
puts('Download photo') | |
url_size = photo_urls.size | |
photo_urls.each_with_index do |photo_url, i| | |
formated_i = format("%0#{url_size.to_s.size}d", i + 1) | |
file_name = file_name(photo_url) | |
puts("[#{formated_i}/#{url_size}] #{file_name}") | |
save_path = File.join(__dir__, 'photo', $user, file_name) | |
try_count = 0 | |
begin | |
save_photo(save_path, photo_url) | |
add_log(file_name) | |
$download_n += 1 | |
rescue | |
photo_url = photo_url.sub('_original', '') | |
try_count += 1 | |
try_count <= 2 ? retry : next | |
end | |
end | |
end | |
def save_photo(save_path, url) | |
File.write(save_path, URI.open(url).read) | |
end | |
def file_name(url) | |
File.basename(url).sub('_original', '') | |
end | |
def create_user_dir | |
puts('Scan log') | |
user_dir = File.join(__dir__, 'photo', $user) | |
FileUtils.mkdir_p(user_dir) unless File.exist?(user_dir) | |
end | |
def add_log(recode) | |
recode = [Time.now, recode + "\n"].join(",\s") | |
File.write($log_path, recode, mode: 'a') | |
end | |
def load_log(log_path) | |
if File.exist?(log_path) | |
File.read(log_path) | |
else | |
FileUtils.touch(log_path) | |
nil | |
end | |
end | |
def macos_niti(title, message) | |
%x[osascript -e 'display notification "#{message}" with title "#{title}" sound name "purr"'] | |
end | |
def end_message | |
if $download_n.zero? | |
puts('Not found new photo.') | |
else | |
puts("#{$download_n}items download complete.") | |
macos_niti('Fotolife downloader', "#{$download_n}items download complete") | |
end | |
end | |
$user = set_username | |
$page_limit = ARGV[1] ? ARGV[1].to_i : 20 | |
$download_n = 0 | |
$log_path = File.join(__dir__, 'log', "#{$user}.log") | |
log = load_log($log_path) | |
create_user_dir | |
photo_urls = compare_by(log, get_photo_urls) | |
download(photo_urls) | |
end_message |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment