1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
|
#!/usr/bin/env ruby
require 'bundler/setup'
Bundler.require
require 'parallel'
require 'faraday'
require 'nokogiri'
require 'charlock_holmes'
require 'unicode_utils'
FILE_PATH = '/Your/URLs/list/file'
RESULT_FILE = 'Result'
OTHER_ERROR_FILE = 'Other'
CONCURRENCY = 10
def is_garbled?(text)
text.include?('�') || text.chars.any? { |char| char.ord > 0xFFFF }
end
def clean_title(title)
title = title.chars.reject { |ch| UnicodeUtils.general_category(ch).start_with?('C') && !['(', ')', '[', ']', '{', '}', '【', '】', '「', '」', '（' ,'）' ].include?(ch) }.join
title = UnicodeUtils.nfkc(title)
title = title.chars.select(&:valid_encoding?).join
title.strip
end
def get_page_title(url)
conn = Faraday.new(url: url, ssl: { verify: false }) do |faraday|
faraday.adapter Faraday.default_adapter
faraday.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
end
response = conn.get do |req|
req.options.timeout = 30
end
content = response.body
encodings = ['UTF-8', 'Shift_JIS', 'EUC-JP', 'ISO-2022-JP', 'Windows-31J']
title = nil
encodings.each do |encoding|
begin
text = content.force_encoding(encoding).encode('UTF-8', invalid: :replace, undef: :replace)
doc = Nokogiri::HTML(text)
title = doc.at_css('title')&.text&.strip || 'No title found'
break unless is_garbled?(title)
rescue
next
end
end
if is_garbled?(title)
detection = CharlockHolmes::EncodingDetector.detect(content)
encoding = detection[:encoding] || 'UTF-8'
text = content.force_encoding(encoding).encode('UTF-8', invalid: :replace, undef: :replace)
doc = Nokogiri::HTML(text)
title = doc.at_css('title')&.text&.strip || 'No title found'
if is_garbled?(title)
title = url.split('/').last.gsub('-', ' ').gsub('_', ' ').capitalize
title = 'Error: Unable to extract title' if title.empty?
end
end
[url, clean_title(title)]
rescue => e
[url, "Error: #{e.class} - #{e.message}"]
end
def process_url(url)
url, title = get_page_title(url)
if title.start_with?('Error:')
File.open(OTHER_ERROR_FILE, 'a') { |f| f.puts "URL: #{url}\nError: #{title}\n\n" }
else
File.open(RESULT_FILE, 'a') { |f| f.puts "URL: #{url}\nTitle: #{title}\n\n" }
end
puts "URL: #{url}\nTitle: #{title}\n\n"
end
def process_urls(file_path)
unless File.exist?(file_path)
puts "エラー: 指定されたファイル '#{file_path}' が見つかりません。"
exit(1)
end
urls = File.readlines(file_path).map(&:strip).reject(&:empty?)
if urls.empty?
puts "警告: ファイル '#{file_path}' にURLが含まれていません。"
exit(0)
end
Parallel.each(urls, in_threads: CONCURRENCY) do |url|
process_url(url)
sleep(rand(1.0..3.0))
end
end
begin
process_urls(FILE_PATH)
rescue => e
puts "エラーが発生しました: #{e.message}"
puts e.backtrace
exit(1)
end
|
