scripts/czsearch.cgi at master · queria/scripts · GitHub

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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
#!/usr/bin/ruby
require 'uri'
require 'net/http'
require 'yaml'
require 'cgi'

class Logger
	QUIET = 0
	WARN = 1
	INFO = 2
	DEBUG = 3

	@@level = Logger::DEBUG
	@@messages = []

	def Logger.level
		return @@level
	end
	def Logger.level=(new_level)
		@@level = new_level
	end

	def Logger.log(level, message)
		if level == 0
			raise 'Sending zero level log messages is prohibited! Zero is meant for quiet behavior'
		end

		if level <= @@level
			@@messages << message
		end
	end

	def Logger.messages
		return @@messages
	end
end

class CZShareParser
    def initialize()
		@line_regexps = {
            'name'=>Regexp.new('<a[^>]+>(.*)</a>'),
            'url'=>Regexp.new('<a href="([^"]+)"'),
            'size'=>Regexp.new('<td class="col4">(.*)</td>'),
            'desc'=>Regexp.new("</a>[ \t]*(.*?)[ \t]*</td>")
		}
        @next_regexp = Regexp.new('<a href="([^"]+)" class="btn-next">')
	end

	def parse_line(line)
		parsed = {}
		@line_regexps.each_key { |k|
			m = @line_regexps[k].match(line)
			if m
				parsed[k] = m[1].strip
			else
				parsed[k] = ''
			end
		}
		if parsed['name'].empty?
			Logger.log(Logger::WARN, line)
		end
		#parsed['name'] = 'ERROR - ' + parsed['url'] if parsed['name'].empty?
		return parsed
	end

    def find_next(line)
        url = @next_regexp.match(line)
        if url:
			if url[1].include? 't=txt'
				Logger.log(Logger::INFO, 'found next url: '+url.to_s)
				if not url[1][0] == '/'
					return '/'+url[1]
				end
				return url[1]
			end
		end
        return nil
	end
end
class CZShare

	def initialize()
		@server = 'czshare.com'
		@parser = CZShareParser.new
		@con = Net::HTTP.new(@server, 80)
	end

	def parse_page(lines)
		Logger.log(Logger::INFO, 'parsing page with '+lines.size.to_s+' lines')
		Logger.log(Logger::INFO, lines.to_s.length.to_s)
		waiting_for_table = false
		started = false

		downloads = []
		next_url = nil

		lines.each do |line|
			#line.strip!

			if not next_url
				next_url = @parser.find_next(line)
			end

			if line.include? 'id="tab-table-all"'
				waiting_for_table = true
			end

			if waiting_for_table and line.include? '<table>'
				waiting_for_table = false
				started = true
			end

			if started and line.include? 'col2'
				downloads << @parser.parse_line(line)
			end

			if started and line.include? '</table>'
				started = false
				break
			end
		end

		return {'downloads'=>downloads, 'next'=>next_url }
	end

	def load_search(page_url)
		Logger.log(Logger::INFO, 'loading page ' + page_url)

		page_source = ''
		@con.get(page_url) { |body|
			page_source += body
		}
		return parse_page(page_source.split("\n"))
	end


	def search(term)
		Logger.log(Logger::INFO, 'searching for '+term)
		downloads = []
		next_url = '/search.php?q='+URI.escape(term)
		while next_url
			res = load_search(next_url)
			downloads = downloads + res['downloads']
			next_url = res['next']
		end
		#downloads.sort(key=lambda d: d['name'])
		downloads.sort! { |a,b| a['name'] <=> b['name'] }
		return downloads
	end
end

class Printer
	def initialize
		@use_html = true
	end

	def use_html
		return @use_html
	end
	def use_html=(should_use_html)
		@use_html = should_use_html
	end

	def out(txt)
		puts(txt)
	end

	def print_downloads(downloads)
		out('<div class="downloads">')
		out("<div class=\"count\">Found #{downloads.size} entries (displayed <span id=\"displayedCount\">#{downloads.size}</span>):</div>")
		downloads.each_with_index do |down, idx|
			out('<div class="download">' + idx.to_s + ') ' +
			"<a target=\"_blank\" href=\"#{down['url']}\">#{down['name']}</a>" +
			' - '+down['size']+' - '+down['desc'] +
			'</div>')
			$stdout.flush
		end
		out('</div>')
	end

	def print_header(term)
		return if not @use_html
		out('Content-Type: text/html')
		out('')
		out('<! DOCTYPE html >')
		out('<html>')
		out('<head>')
		out('<meta charset="utf-8"><title>CZShare Search</title>')
		out('<style>')
		out('.error { color:red; }')
		out('.download { font-size:11px; }')
		out('.log { color: #ccc; background-color:#333; font-size:x-small; margin-top: 2em; border-top: 1px solid gray; }')
		out('.log { height: 1.1em; overflow:hidden;}')
		out('.log:hover { height: auto; }')
		out('</style>')
		out('<script type="text/javascript" src="https://ajax.googleapis.com/ajax/libs/jquery/1.6.4/jquery.min.js"></script>')
		out('<script type="text/javascript">')
		out('$(document).ready(function() {')
		out('	var filterInput = $("#filter");')
		out('	var filterTimeOut = 0;')
		out('	var lastFilter = "";')
		out('	var allDown = $(".download");')
		out('	var displayedCount = $("#displayedCount");')
		out('	var doFilter = function () { ')
		out('		var fv = $.trim(filterInput.val()).toLowerCase();')
		out('		if( fv == lastFilter ) { return; } else { lastFilter = fv; }')
		out('		var displ = 0;')
		out('		allDown.each(function(){')
		out('			var d = $(this);')
		out('			if(!d.attr("textLower")) { d.attr("textLower", d.text().toLowerCase()); }')
		out('			if(fv == "" || d.attr("textLower").indexOf(fv) != -1) {')
		out('				d.show();')
		out('				displ++;')
		out('			} else { ')
		out('				d.hide();')
		out('			}')
		out('		});')
		out('		displayedCount.text(displ);')
		out('	};')
		out('	var requestFilter = function () { ')
		out('		clearTimeout(filterTimeOut);')
		out('		filterTimeOut = setTimeout(doFilter, 250);')
		out('	};')
		out('	filterInput.bind("change", requestFilter);')
		out('	filterInput.bind("input", requestFilter);')
		out('	filterInput.bind("keyup", requestFilter);')
		out('});')
		out('</script>')
		out('</head>')
		out('<body><h1>CZShare Search</h1>')
		out('<form action="" method="post"><div>')
		out('<label for="term">What to look for?</label>')
		out('<input type="text" name="term" id="term" value="'+term+'" />')
		out('<input type="submit" value="Search" />')
		out('</div></form>')
		out('<div>Filter results: <input type="text" id="filter" /></div>');
		$stdout.flush
	end

	def print_footer
		print_logs
		return if not @use_html
		out('</body>')
		out('</html>')
	end

	def print_logs
		out('<div class="log">')
		out('Progress log:<br />')
		Logger.messages.each do |msg|
			out('<div class="message">')
			out(CGI.escapeHTML(msg))
			out('</div>')
		end
		out('</div>')
	end
end

cgi = CGI.new
czs = CZShare.new
printer = Printer.new

if cgi.key? 'plaintext'
	printer.use_html = false
end

printer.print_header cgi['term']

if cgi.key?('inputfile')
	p czs.parse_page(open(cgi['inputfile']))
elsif cgi.key?('term')
	downloads = czs.search(cgi['term'])
	printer.print_downloads(downloads)
end

printer.print_footer