webwatchr 0.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/Gemfile +13 -0
- data/LICENSE +674 -0
- data/README.md +122 -0
- data/Rakefile +11 -0
- data/lib/sites/bandcamp.rb +60 -0
- data/lib/sites/bsky.rb +176 -0
- data/lib/sites/postch.rb +112 -0
- data/lib/sites/songkick.rb +28 -0
- data/lib/webwatchr/alerting.rb +129 -0
- data/lib/webwatchr/base.rb +119 -0
- data/lib/webwatchr/logger.rb +31 -0
- data/lib/webwatchr/main.rb +51 -0
- data/lib/webwatchr/site.rb +575 -0
- data/lib/webwatchr.rb +1 -0
- data/tests/helpers.rb +32 -0
- data/tests/infra_test.rb +271 -0
- data/webwatchr.gemspec +12 -0
- metadata +56 -0
data/tests/infra_test.rb
ADDED
|
@@ -0,0 +1,271 @@
|
|
|
1
|
+
#!/usr/bin/ruby
|
|
2
|
+
require "fileutils"
|
|
3
|
+
require "logger"
|
|
4
|
+
require_relative "../lib/webwatchr/site"
|
|
5
|
+
require_relative "./helpers"
|
|
6
|
+
require "tmpdir"
|
|
7
|
+
require "test/unit"
|
|
8
|
+
|
|
9
|
+
class BaseWebrickTest < Test::Unit::TestCase
|
|
10
|
+
require "webrick"
|
|
11
|
+
|
|
12
|
+
TEST_CONFIG = {
|
|
13
|
+
wwwroot: File.join(File.dirname(__FILE__), "www-root"),
|
|
14
|
+
wwwport: 8001,
|
|
15
|
+
content_is_string_file: "content_is_string.html",
|
|
16
|
+
content_is_array_file: "content_is_array.html"
|
|
17
|
+
}.freeze
|
|
18
|
+
|
|
19
|
+
class TestFileHandler < WEBrick::HTTPServlet::FileHandler
|
|
20
|
+
def do_GET(req, res) # rubocop:disable Metrics/MethodName
|
|
21
|
+
res.status = 200
|
|
22
|
+
res["Content-Encoding"] = "utf-8"
|
|
23
|
+
res["Content-Type"] = "text/html; charset=utf-8"
|
|
24
|
+
res.body = File.open(File.join(TEST_CONFIG[:wwwroot], req.path)).read()
|
|
25
|
+
end
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
def restart_webrick()
|
|
29
|
+
@webrick = WEBrick::HTTPServer.new(
|
|
30
|
+
AccessLog: [],
|
|
31
|
+
Logger: WEBrick::Log.new("/dev/null", 7),
|
|
32
|
+
Port: TEST_CONFIG[:wwwport]
|
|
33
|
+
)
|
|
34
|
+
@webrick.mount("/", TestFileHandler, TEST_CONFIG[:wwwroot])
|
|
35
|
+
|
|
36
|
+
@serv_thread = Thread.new do
|
|
37
|
+
@webrick.start
|
|
38
|
+
end
|
|
39
|
+
end
|
|
40
|
+
|
|
41
|
+
def setup
|
|
42
|
+
@workdir = Dir.mktmpdir
|
|
43
|
+
@logger_test_io = StringIO.new()
|
|
44
|
+
MyLog.instance.configure(@logger_test_io, nil, Logger::DEBUG)
|
|
45
|
+
restart_webrick()
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
def teardown()
|
|
49
|
+
@webrick.stop
|
|
50
|
+
@serv_thread.join
|
|
51
|
+
[TEST_CONFIG[:content_is_string_file], TEST_CONFIG[:content_is_array_file]].each do |tf|
|
|
52
|
+
File.open(File.join(TEST_CONFIG[:wwwroot], tf), "w") do |f|
|
|
53
|
+
f.puts ""
|
|
54
|
+
end
|
|
55
|
+
end
|
|
56
|
+
FileUtils.remove_entry_secure(@workdir)
|
|
57
|
+
end
|
|
58
|
+
end
|
|
59
|
+
|
|
60
|
+
class TestSimpleStringSite < BaseWebrickTest
|
|
61
|
+
class TestStringSite < Site::SimpleString
|
|
62
|
+
def initialize
|
|
63
|
+
super()
|
|
64
|
+
@wait = 3600
|
|
65
|
+
end
|
|
66
|
+
|
|
67
|
+
def get_content()
|
|
68
|
+
return ResultObject.new(@parsed_content.css("div.content").text)
|
|
69
|
+
end
|
|
70
|
+
end
|
|
71
|
+
|
|
72
|
+
def test_content_is_string
|
|
73
|
+
content_html = "👌 👌 👌 💯 💯 💯 💯 -KYop-R11Iqo.mp"
|
|
74
|
+
whole_html = Site::HTML_HEADER.dup
|
|
75
|
+
whole_html += "<title>test</title><div class='content'>#{content_html}</div>"
|
|
76
|
+
File.open(File.join(TEST_CONFIG[:wwwroot], TEST_CONFIG[:content_is_string_file]), "w") do |f|
|
|
77
|
+
f.write whole_html
|
|
78
|
+
end
|
|
79
|
+
url = "http://localhost:#{TEST_CONFIG[:wwwport]}/#{TEST_CONFIG[:content_is_string_file]}"
|
|
80
|
+
wait = 10 * 60
|
|
81
|
+
|
|
82
|
+
c = TestStringSite.new
|
|
83
|
+
c.url = url
|
|
84
|
+
a = TestAlerter.new()
|
|
85
|
+
c.alerters = [a]
|
|
86
|
+
assert { c.load_state_file() == {} }
|
|
87
|
+
assert { c.should_update?(-9_999_999_999_999) }
|
|
88
|
+
assert { c.should_update?((Time.now() - wait + 30).to_i) == false }
|
|
89
|
+
html = c.fetch_url(url)
|
|
90
|
+
assert { whole_html == html }
|
|
91
|
+
assert { c.parse_noko(html).css("title").text == "test" }
|
|
92
|
+
cache_dir = File.join(@workdir, "cache")
|
|
93
|
+
last_dir = File.join(@workdir, ".lasts")
|
|
94
|
+
FileUtils.mkdir_p(cache_dir)
|
|
95
|
+
FileUtils.mkdir_p(last_dir)
|
|
96
|
+
c.update(cache_dir: cache_dir, last_dir: last_dir)
|
|
97
|
+
assert { c.state_file.end_with?("last-localhost-2182cd5c8685baed48f692ed72d7a89f") }
|
|
98
|
+
expected_error = "DEBUG -- TestSimpleStringSite::TestStringSite: Alerting new stuff"
|
|
99
|
+
last_error = @logger_test_io.string.split("\n")[-1]
|
|
100
|
+
assert { last_error.end_with?(expected_error) }
|
|
101
|
+
first_pass_content = Site::HTML_HEADER + content_html
|
|
102
|
+
assert { c.content.to_html == content_html }
|
|
103
|
+
assert { c.generate_html_content == first_pass_content }
|
|
104
|
+
assert { a.result == c.content }
|
|
105
|
+
|
|
106
|
+
File.open(File.join(TEST_CONFIG[:wwwroot], TEST_CONFIG[:content_is_string_file]), "w+") do |f|
|
|
107
|
+
f.write whole_html.gsub("</div>", " new ! </div>")
|
|
108
|
+
end
|
|
109
|
+
c = TestStringSite.new
|
|
110
|
+
c.url = url
|
|
111
|
+
cache_dir = File.join(@workdir, "cache")
|
|
112
|
+
last_dir = File.join(@workdir, ".lasts")
|
|
113
|
+
FileUtils.mkdir_p(cache_dir)
|
|
114
|
+
FileUtils.mkdir_p(last_dir)
|
|
115
|
+
c.update(cache_dir: cache_dir, last_dir: last_dir)
|
|
116
|
+
c.comment = "lol"
|
|
117
|
+
expected_error = "INFO -- TestSimpleStringSite::TestStringSite: Too soon to update #{url}"
|
|
118
|
+
last_error = @logger_test_io.string.split("\n")[-1]
|
|
119
|
+
assert { last_error.end_with?(expected_error) }
|
|
120
|
+
assert { c.content.nil? }
|
|
121
|
+
assert { c.generate_html_content.nil? }
|
|
122
|
+
assert { c.name == url }
|
|
123
|
+
|
|
124
|
+
c.every = 0
|
|
125
|
+
c.update(cache_dir: cache_dir, last_dir: last_dir)
|
|
126
|
+
expected_error = "DEBUG -- TestSimpleStringSite::TestStringSite: Alerting new stuff"
|
|
127
|
+
last_error = @logger_test_io.string.split("\n")[-1]
|
|
128
|
+
assert { last_error.end_with?(expected_error) }
|
|
129
|
+
assert { c.content.to_html == "#{content_html} new ! " }
|
|
130
|
+
assert { c.generate_html_content == "#{first_pass_content} new ! " }
|
|
131
|
+
assert { c.name == url }
|
|
132
|
+
result_last = JSON.parse(File.read(c.state_file), create_additions: true)
|
|
133
|
+
result_last.delete("time")
|
|
134
|
+
assert { result_last["url"] == url }
|
|
135
|
+
assert { result_last["content"].message == "#{content_html} new ! " }
|
|
136
|
+
assert { result_last["wait"] == 0 }
|
|
137
|
+
end
|
|
138
|
+
end
|
|
139
|
+
|
|
140
|
+
class TestArraySites < BaseWebrickTest
|
|
141
|
+
class TestArraySite < Site::Articles
|
|
142
|
+
def initialize
|
|
143
|
+
super()
|
|
144
|
+
@wait = 3600
|
|
145
|
+
end
|
|
146
|
+
|
|
147
|
+
def get_content()
|
|
148
|
+
res = []
|
|
149
|
+
@parsed_content.css("div").each do |x|
|
|
150
|
+
a, b = x.text.split("-").map(&:strip)
|
|
151
|
+
add_article({ "id" => a, "url" => a, "title" => b })
|
|
152
|
+
end
|
|
153
|
+
return res
|
|
154
|
+
end
|
|
155
|
+
end
|
|
156
|
+
|
|
157
|
+
def test_content_is_array
|
|
158
|
+
whole_html = "#{Site::HTML_HEADER.dup}<title>test</title>👌 👌 👌 💯 💯 💯 💯 -KYop-R11Iqo.mp4<div> lol - lilo</div> <div> fi - fu</div>"
|
|
159
|
+
File.open(File.join(TEST_CONFIG[:wwwroot], TEST_CONFIG[:content_is_array_file]), "w") do |f|
|
|
160
|
+
f.write whole_html
|
|
161
|
+
end
|
|
162
|
+
url = "http://localhost:#{TEST_CONFIG[:wwwport]}/#{TEST_CONFIG[:content_is_array_file]}"
|
|
163
|
+
wait = 10 * 60
|
|
164
|
+
|
|
165
|
+
c = TestArraySite.new
|
|
166
|
+
c.url = url
|
|
167
|
+
a = TestAlerter.new()
|
|
168
|
+
c.alerters = [a]
|
|
169
|
+
assert { c.load_state_file() == {} }
|
|
170
|
+
assert { c.should_update?(-9_999_999_999_999) }
|
|
171
|
+
assert { !c.should_update?((Time.now() - wait + 30).to_i) }
|
|
172
|
+
html = c.fetch_url(url)
|
|
173
|
+
assert { html == whole_html }
|
|
174
|
+
assert { c.parse_noko(html).css("title").text == "test" }
|
|
175
|
+
|
|
176
|
+
# First full run, Get 2 things
|
|
177
|
+
cache_dir = File.join(@workdir, "cache")
|
|
178
|
+
last_dir = File.join(@workdir, ".lasts")
|
|
179
|
+
FileUtils.mkdir_p(cache_dir)
|
|
180
|
+
FileUtils.mkdir_p(last_dir)
|
|
181
|
+
c.update(cache_dir: cache_dir, last_dir: last_dir)
|
|
182
|
+
assert { c.state_file.end_with?("last-localhost-35e711989b197f20f3d4936e91a2c079") }
|
|
183
|
+
expected_error = "DEBUG -- TestArraySites::TestArraySite: Alerting new stuff"
|
|
184
|
+
last_error = @logger_test_io.string.split("\n")[-1].strip()
|
|
185
|
+
assert { last_error.end_with?(expected_error) }
|
|
186
|
+
expected_html = Site::HTML_HEADER.dup + [
|
|
187
|
+
"<ul style='list-style-type: none;'>",
|
|
188
|
+
"<li id='lol'><a href='lol'>lilo</a></li>",
|
|
189
|
+
"<li id='fi'><a href='fi'>fu</a></li>",
|
|
190
|
+
"</ul>"
|
|
191
|
+
].join("\n")
|
|
192
|
+
c.content.each { |x| x.delete('_timestamp') }
|
|
193
|
+
assert {
|
|
194
|
+
c.content == [
|
|
195
|
+
{ "id" => "lol", "url" => "lol", "title" => "lilo" },
|
|
196
|
+
{ "id" => "fi", "url" => "fi", "title" => "fu" }
|
|
197
|
+
]
|
|
198
|
+
}
|
|
199
|
+
assert { c.generate_html_content == expected_html }
|
|
200
|
+
|
|
201
|
+
result = ""
|
|
202
|
+
|
|
203
|
+
File.open(File.join(TEST_CONFIG[:wwwroot], TEST_CONFIG[:content_is_array_file]), "a+") do |f|
|
|
204
|
+
f.write "<div>new! - new </div>"
|
|
205
|
+
end
|
|
206
|
+
c = TestArraySite.new
|
|
207
|
+
c.url = url
|
|
208
|
+
a = TestAlerter.new()
|
|
209
|
+
c.alerters = [a]
|
|
210
|
+
# Second run don't d anything because we shouldn't rerun
|
|
211
|
+
c.update(cache_dir: cache_dir, last_dir: last_dir)
|
|
212
|
+
expected_error = "INFO -- TestArraySites::TestArraySite: Too soon to update #{url}"
|
|
213
|
+
last_error = @logger_test_io.string.split("\n")[-1]
|
|
214
|
+
assert { last_error.end_with?(expected_error) }
|
|
215
|
+
assert { result == "" }
|
|
216
|
+
|
|
217
|
+
result = ""
|
|
218
|
+
|
|
219
|
+
c.content.each { |x| x.delete('_timestamp') }
|
|
220
|
+
|
|
221
|
+
c.every = 0
|
|
222
|
+
# This time we set new things, and wait is 0 so we are good to go
|
|
223
|
+
c.update(cache_dir: cache_dir, last_dir: last_dir)
|
|
224
|
+
expected_error = "DEBUG -- TestArraySites::TestArraySite: Alerting new stuff"
|
|
225
|
+
last_error = @logger_test_io.string.split("\n")[-1]
|
|
226
|
+
assert { last_error.end_with?(expected_error) }
|
|
227
|
+
expected_html = Site::HTML_HEADER.dup + [
|
|
228
|
+
"<ul style='list-style-type: none;'>",
|
|
229
|
+
"<li id='new!'><a href='new!'>new</a></li>",
|
|
230
|
+
"</ul>"
|
|
231
|
+
].join("\n")
|
|
232
|
+
|
|
233
|
+
c.content.each { |x| x.delete('_timestamp') }
|
|
234
|
+
assert { c.content == [{ "id" => "new!", "url" => "new!", "title" => "new" }] }
|
|
235
|
+
assert { c.generate_html_content == expected_html }
|
|
236
|
+
expected_last = { "url" => "http://localhost:#{TEST_CONFIG[:wwwport]}/#{TEST_CONFIG[:content_is_array_file]}",
|
|
237
|
+
"previous_content" => [{ "id" => "lol", "url" => "lol", "title" => "lilo" },
|
|
238
|
+
{ "id" => "fi", "url" => "fi", "title" => "fu" }],
|
|
239
|
+
"wait" => 0,
|
|
240
|
+
"content" => [{ "id" => "lol", "title" => "lilo", "url" => "lol" },
|
|
241
|
+
{ "id" => "fi", "title" => "fu", "url" => "fi" },
|
|
242
|
+
{ "id" => "new!", "title" => "new", "url" => "new!" }] }
|
|
243
|
+
result_last = JSON.parse(File.read(c.state_file))
|
|
244
|
+
result_last.delete("time")
|
|
245
|
+
result_last["content"].each do |item|
|
|
246
|
+
item.delete("_timestamp")
|
|
247
|
+
end
|
|
248
|
+
result_last["previous_content"].each do |item|
|
|
249
|
+
item.delete("_timestamp")
|
|
250
|
+
end
|
|
251
|
+
assert { expected_last == result_last }
|
|
252
|
+
|
|
253
|
+
result = ""
|
|
254
|
+
|
|
255
|
+
c = TestArraySite.new
|
|
256
|
+
c.url = url
|
|
257
|
+
a = TestAlerter.new()
|
|
258
|
+
c.alerters = [a]
|
|
259
|
+
c.every = 0
|
|
260
|
+
# Now, we don't call the alert Proc because we have no new things
|
|
261
|
+
c.update(cache_dir: cache_dir, last_dir: last_dir)
|
|
262
|
+
expected_error = "INFO -- TestArraySites::TestArraySite: Nothing new for #{url}"
|
|
263
|
+
last_error = @logger_test_io.string.split("\n")[-1]
|
|
264
|
+
assert { last_error.end_with?(expected_error) }
|
|
265
|
+
expected_html = Site::HTML_HEADER.dup + [
|
|
266
|
+
"<ul style=\"list-style-type: none;\">",
|
|
267
|
+
"</ul>"
|
|
268
|
+
].join("\n")
|
|
269
|
+
assert { result == "" }
|
|
270
|
+
end
|
|
271
|
+
end
|
data/webwatchr.gemspec
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
Gem::Specification.new do |s|
|
|
2
|
+
s.name = "webwatchr"
|
|
3
|
+
s.version = "0.0.2"
|
|
4
|
+
s.summary = "Scrapes stuff and tells you of updates."
|
|
5
|
+
s.description = "Scrapes stuff and tells you of updates. Exciting!"
|
|
6
|
+
s.authors = ["Renzo"]
|
|
7
|
+
s.email = "webwatchr-gem@renzokuken.eu"
|
|
8
|
+
s.files = Dir['README.md', 'tests/**.*', 'lib/**/*', 'Rakefile', 'Gemfile', 'LICENSE', 'webwatchr.gemspec']
|
|
9
|
+
s.homepage = "https://github.com/conchyliculture/webwatchr"
|
|
10
|
+
s.license = "GPL-3.0-or-later"
|
|
11
|
+
s.required_ruby_version = ">=2.5.0"
|
|
12
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: webwatchr
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.2
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Renzo
|
|
8
|
+
bindir: bin
|
|
9
|
+
cert_chain: []
|
|
10
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
11
|
+
dependencies: []
|
|
12
|
+
description: Scrapes stuff and tells you of updates. Exciting!
|
|
13
|
+
email: webwatchr-gem@renzokuken.eu
|
|
14
|
+
executables: []
|
|
15
|
+
extensions: []
|
|
16
|
+
extra_rdoc_files: []
|
|
17
|
+
files:
|
|
18
|
+
- Gemfile
|
|
19
|
+
- LICENSE
|
|
20
|
+
- README.md
|
|
21
|
+
- Rakefile
|
|
22
|
+
- lib/sites/bandcamp.rb
|
|
23
|
+
- lib/sites/bsky.rb
|
|
24
|
+
- lib/sites/postch.rb
|
|
25
|
+
- lib/sites/songkick.rb
|
|
26
|
+
- lib/webwatchr.rb
|
|
27
|
+
- lib/webwatchr/alerting.rb
|
|
28
|
+
- lib/webwatchr/base.rb
|
|
29
|
+
- lib/webwatchr/logger.rb
|
|
30
|
+
- lib/webwatchr/main.rb
|
|
31
|
+
- lib/webwatchr/site.rb
|
|
32
|
+
- tests/helpers.rb
|
|
33
|
+
- tests/infra_test.rb
|
|
34
|
+
- webwatchr.gemspec
|
|
35
|
+
homepage: https://github.com/conchyliculture/webwatchr
|
|
36
|
+
licenses:
|
|
37
|
+
- GPL-3.0-or-later
|
|
38
|
+
metadata: {}
|
|
39
|
+
rdoc_options: []
|
|
40
|
+
require_paths:
|
|
41
|
+
- lib
|
|
42
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
43
|
+
requirements:
|
|
44
|
+
- - ">="
|
|
45
|
+
- !ruby/object:Gem::Version
|
|
46
|
+
version: 2.5.0
|
|
47
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
48
|
+
requirements:
|
|
49
|
+
- - ">="
|
|
50
|
+
- !ruby/object:Gem::Version
|
|
51
|
+
version: '0'
|
|
52
|
+
requirements: []
|
|
53
|
+
rubygems_version: 3.6.7
|
|
54
|
+
specification_version: 4
|
|
55
|
+
summary: Scrapes stuff and tells you of updates.
|
|
56
|
+
test_files: []
|