url_common 0.1.0 → 0.1.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile +8 -1
- data/Gemfile.lock +82 -0
- data/README.md +4 -2
- data/lib/url_common/version.rb +1 -1
- data/lib/url_common.rb +288 -11
- data/url_common.gemspec +4 -0
- metadata +33 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 0ab8c804a828390106ee6e442cd46362ef5648ff9d41d36317f2644cb9f21e15
|
4
|
+
data.tar.gz: 7d6068a766ed82a3c4fe724fe426549c9c56047acbf373eb46d87aba763dfab0
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: bddc296b7dae2781ec1ae7f8b8c79a1327e93bc1bfe30c761366033ef0882049948ea8c2ebbd7ce425aa7d437086b7ec38a4b30ebf0e976a4213990ef1e2d2b6
|
7
|
+
data.tar.gz: 395a2d6fec4519067d4dbb08f78c3e67cd4b1d2b1c7c8083299398790c5b9f9e6db81aade8c093f6b2eb39975f30b6923a80634d928e9c6fad159e12bb6a840d
|
data/Gemfile
CHANGED
@@ -3,8 +3,15 @@ source "https://rubygems.org"
|
|
3
3
|
# Specify your gem's dependencies in url_common.gemspec
|
4
4
|
gemspec
|
5
5
|
|
6
|
+
ruby "3.1.2"
|
7
|
+
|
6
8
|
gem "rake", "~> 12.0"
|
7
9
|
gem "rspec", "~> 3.0"
|
8
10
|
gem "fuzzyurl", '~> 0.9.0'
|
9
|
-
gem 'mechanize', '~> 2.6'
|
10
11
|
gem "byebug"
|
12
|
+
|
13
|
+
gem "hpricot", "~> 0.8.6"
|
14
|
+
gem 'net-http-persistent', github: 'drbrain/net-http-persistent'
|
15
|
+
gem "mechanize", "~> 2.7"
|
16
|
+
|
17
|
+
gem "webrick", "~> 1.7"
|
data/Gemfile.lock
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
GIT
|
2
|
+
remote: https://github.com/drbrain/net-http-persistent.git
|
3
|
+
revision: 857c3baaa541644fa437328b535042a500414119
|
4
|
+
specs:
|
5
|
+
net-http-persistent (4.0.1)
|
6
|
+
connection_pool (~> 2.2)
|
7
|
+
|
8
|
+
PATH
|
9
|
+
remote: .
|
10
|
+
specs:
|
11
|
+
url_common (0.1.3)
|
12
|
+
fuzzyurl (~> 0.9.0)
|
13
|
+
mechanize (~> 2.6)
|
14
|
+
|
15
|
+
GEM
|
16
|
+
remote: https://rubygems.org/
|
17
|
+
specs:
|
18
|
+
byebug (11.1.3)
|
19
|
+
connection_pool (2.2.5)
|
20
|
+
diff-lcs (1.4.4)
|
21
|
+
domain_name (0.5.20190701)
|
22
|
+
unf (>= 0.0.5, < 1.0.0)
|
23
|
+
fuzzyurl (0.9.0)
|
24
|
+
hpricot (0.8.6)
|
25
|
+
http-cookie (1.0.3)
|
26
|
+
domain_name (~> 0.5)
|
27
|
+
mechanize (2.7.6)
|
28
|
+
domain_name (~> 0.5, >= 0.5.1)
|
29
|
+
http-cookie (~> 1.0)
|
30
|
+
mime-types (>= 1.17.2)
|
31
|
+
net-http-digest_auth (~> 1.1, >= 1.1.1)
|
32
|
+
net-http-persistent (>= 2.5.2)
|
33
|
+
nokogiri (~> 1.6)
|
34
|
+
ntlm-http (~> 0.1, >= 0.1.1)
|
35
|
+
webrobots (>= 0.0.9, < 0.2)
|
36
|
+
mime-types (3.3.1)
|
37
|
+
mime-types-data (~> 3.2015)
|
38
|
+
mime-types-data (3.2020.0512)
|
39
|
+
mini_portile2 (2.4.0)
|
40
|
+
net-http-digest_auth (1.4.1)
|
41
|
+
nokogiri (1.10.10)
|
42
|
+
mini_portile2 (~> 2.4.0)
|
43
|
+
ntlm-http (0.1.1)
|
44
|
+
rake (12.3.3)
|
45
|
+
rspec (3.9.0)
|
46
|
+
rspec-core (~> 3.9.0)
|
47
|
+
rspec-expectations (~> 3.9.0)
|
48
|
+
rspec-mocks (~> 3.9.0)
|
49
|
+
rspec-core (3.9.2)
|
50
|
+
rspec-support (~> 3.9.3)
|
51
|
+
rspec-expectations (3.9.2)
|
52
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
53
|
+
rspec-support (~> 3.9.0)
|
54
|
+
rspec-mocks (3.9.1)
|
55
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
56
|
+
rspec-support (~> 3.9.0)
|
57
|
+
rspec-support (3.9.3)
|
58
|
+
unf (0.1.4)
|
59
|
+
unf_ext
|
60
|
+
unf_ext (0.0.7.7)
|
61
|
+
webrick (1.7.0)
|
62
|
+
webrobots (0.1.2)
|
63
|
+
|
64
|
+
PLATFORMS
|
65
|
+
ruby
|
66
|
+
|
67
|
+
DEPENDENCIES
|
68
|
+
byebug
|
69
|
+
fuzzyurl (~> 0.9.0)
|
70
|
+
hpricot (~> 0.8.6)
|
71
|
+
mechanize (~> 2.7)
|
72
|
+
net-http-persistent!
|
73
|
+
rake (~> 12.0)
|
74
|
+
rspec (~> 3.0)
|
75
|
+
url_common!
|
76
|
+
webrick (~> 1.7)
|
77
|
+
|
78
|
+
RUBY VERSION
|
79
|
+
ruby 3.1.2p20
|
80
|
+
|
81
|
+
BUNDLED WITH
|
82
|
+
2.1.4
|
data/README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1
1
|
# UrlCommon
|
2
2
|
|
3
|
-
|
3
|
+
This is a gem for performing common Url centric things. I wrote this years ago and have always just moved it from project to project leading to a huge number of different versions on my development system. Finally I'm creating a gem out of it to aid in its use across projects.
|
4
4
|
|
5
|
-
|
5
|
+
I don't claim that these are great, perfect, etc. I claim that they are workman like tools which I FIND USEFUL and I want to use them more easily across multiple projects hence the open sourcing of them.
|
6
6
|
|
7
7
|
## Installation
|
8
8
|
|
@@ -24,6 +24,8 @@ Or install it yourself as:
|
|
24
24
|
|
25
25
|
TODO: Write usage instructions here
|
26
26
|
|
27
|
+
This is a todo.
|
28
|
+
|
27
29
|
## Development
|
28
30
|
|
29
31
|
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
data/lib/url_common/version.rb
CHANGED
data/lib/url_common.rb
CHANGED
@@ -30,6 +30,17 @@ module UrlCommon
|
|
30
30
|
end
|
31
31
|
end
|
32
32
|
|
33
|
+
# UrlCommon.parse_fid_from_amazon_url("https://www.amazon.com/Original-GEN-2-0-Screwdriver-Industrial-Technician/dp/B0845919P2/?_encoding=UTF8&pd_rd_w=cekvo&content-id=amzn1.sym.bbb6bbd8-d236-47cb-b42f-734cb0cacc1f&pf_rd_p=bbb6bbd8-d236-47cb-b42f-734cb0cacc1f&pf_rd_r=3WP00V89EKYCQ1PB16VY&pd_rd_wg=HlQVt&pd_rd_r=30b33abe-2010-435e-b2cc-338f2ffbf3cf&ref_=pd_gw_ci_mcx_mi")
|
34
|
+
def self.parse_fid_from_amazon_url(url)
|
35
|
+
tmp = /\/dp\/([A-Za-z0-9]+)/.match(url)
|
36
|
+
if tmp && tmp[1]
|
37
|
+
return tmp[1]
|
38
|
+
else
|
39
|
+
return nil
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
|
33
44
|
def self.parse_country_from_itunes_url(url)
|
34
45
|
country = /https?:\/\/itunes\.apple\.com\/(..)\//.match(url)
|
35
46
|
if country
|
@@ -39,9 +50,22 @@ module UrlCommon
|
|
39
50
|
return 'us'
|
40
51
|
end
|
41
52
|
|
53
|
+
# original
|
54
|
+
# def self.get_base_domain(url)
|
55
|
+
# parts = URI.parse(url)
|
56
|
+
# return parts.host.gsub(/^www./,'')
|
57
|
+
# end
|
58
|
+
|
42
59
|
def self.get_base_domain(url)
|
43
|
-
|
44
|
-
|
60
|
+
#debugger if url =~ /c06rh22whx1g/
|
61
|
+
begin
|
62
|
+
url = url.gsub(/ /,'%20')
|
63
|
+
parts = URI.parse(url)
|
64
|
+
return parts.host.gsub(/^www./,'')
|
65
|
+
rescue StandardError => e
|
66
|
+
fu = Fuzzyurl.from_string(url)
|
67
|
+
return fu.hostname.gsub(/^www./,'')
|
68
|
+
end
|
45
69
|
end
|
46
70
|
|
47
71
|
def self.join(base, rest, debug = false)
|
@@ -60,9 +84,19 @@ module UrlCommon
|
|
60
84
|
end
|
61
85
|
end
|
62
86
|
|
63
|
-
#TODO
|
64
87
|
def self.count_links(html)
|
65
|
-
|
88
|
+
if html =~ /<html/i
|
89
|
+
content_type = "html"
|
90
|
+
else
|
91
|
+
content_type = "ascii"
|
92
|
+
end
|
93
|
+
parts = html.split(" ")
|
94
|
+
link_ctr = 0
|
95
|
+
parts.each do |part|
|
96
|
+
link_ctr = link_ctr + 1 if part =~ /https:?\/\// && content_type == 'ascii'
|
97
|
+
link_ctr = link_ctr + 1 if part =~ /<a [^>]+.+<\/a>/i && content_type == 'html'
|
98
|
+
end
|
99
|
+
link_ctr
|
66
100
|
end
|
67
101
|
|
68
102
|
def self.agent
|
@@ -82,13 +116,23 @@ module UrlCommon
|
|
82
116
|
#
|
83
117
|
def self.url_base(url, base_domain=nil)
|
84
118
|
if base_domain.nil?
|
85
|
-
base_domain = get_base_domain(url)
|
119
|
+
base_domain = UrlCommon.get_base_domain(url)
|
120
|
+
end
|
121
|
+
begin
|
122
|
+
url = url.gsub(/ /,'%20')
|
123
|
+
parts = URI.parse(url)
|
124
|
+
extra = ""
|
125
|
+
extra = "?#{parts.query}" if parts.query
|
126
|
+
url_base = "#{base_domain}#{parts.path}#{extra}"
|
127
|
+
return url_base[0..254]
|
128
|
+
rescue StandardError => e
|
129
|
+
fu = Fuzzyurl.from_string(url)
|
130
|
+
base_domain = UrlCommon.get_base_domain(url)
|
131
|
+
extra = ""
|
132
|
+
extra = "?#{fu.query}" if fu.query
|
133
|
+
url_base = "#{base_domain}#{fu.path}#{extra}"
|
134
|
+
return url_base[0..254]
|
86
135
|
end
|
87
|
-
parts = URI.parse(url)
|
88
|
-
extra = ""
|
89
|
-
extra = "?#{parts.query}" if parts.query
|
90
|
-
url_base = "#{base_domain}#{parts.path}#{extra}"
|
91
|
-
return url_base[0..254]
|
92
136
|
end
|
93
137
|
|
94
138
|
#tested #https://www.amazon.com/gp/product/B01DT4A2R4/ref=as_li_qf_sp_asin_il_tl?ie=UTF8&tag=nickjanetakis-20&camp=1789&creative=9325&linkCode=as2&creativeASIN=B01DT4A2R4&linkId=496be5e222b6291369c0a393c797c2c0
|
@@ -262,8 +306,241 @@ module UrlCommon
|
|
262
306
|
#TODO needs tests
|
263
307
|
def self.create_mechanize_page_from_html(url, html)
|
264
308
|
mechanize_page = Mechanize::Page.new(nil, {'content-type'=>'text/html'}, html, nil, Mechanize.new)
|
309
|
+
url = url.gsub(/ /,'%20')
|
265
310
|
mechanize_page.uri = URI.parse(url)
|
266
|
-
|
311
|
+
|
267
312
|
return mechanize_page
|
268
313
|
end
|
314
|
+
|
315
|
+
#TODO needs tests
|
316
|
+
def self.get_meta_description(url, html)
|
317
|
+
page = UrlCommon.create_mechanize_page_from_html(url, html)
|
318
|
+
description = ""
|
319
|
+
begin
|
320
|
+
description = page.parser.at("meta[name='description']")['content']
|
321
|
+
rescue StandardError => e
|
322
|
+
end
|
323
|
+
return description
|
324
|
+
end
|
325
|
+
|
326
|
+
#TODO needs tests
|
327
|
+
# UrlCommon.get_page_title("https://gist.github.com/fuzzygroup/811a9334b1a6dc394de74a23cb7e12fa")
|
328
|
+
def self.get_page_title(url, html)
|
329
|
+
page = UrlCommon.create_mechanize_page_from_html(url, html)
|
330
|
+
title = ""
|
331
|
+
begin
|
332
|
+
title = page.parser.css('title').first.content
|
333
|
+
rescue StandardError => e
|
334
|
+
end
|
335
|
+
return title
|
336
|
+
end
|
337
|
+
|
338
|
+
def self.extract_links_from_text(text)
|
339
|
+
agent = Mechanize.new
|
340
|
+
html = "<HTML><BODY>#{text}</BODY></HTML>"
|
341
|
+
page = Mechanize::Page.new(nil,{'content-type'=>'text/html'},html,nil,agent)
|
342
|
+
return page.links
|
343
|
+
end
|
344
|
+
|
345
|
+
# https://docs.aylien.com/textapi/#using-the-api
|
346
|
+
def self.summarize_url(url)
|
347
|
+
#GET /summarize?url=http://www.bbc.com/sport/0/football/25912393
|
348
|
+
agent = Mechanize.new
|
349
|
+
summarization_url = ""
|
350
|
+
page = agent.get(url)
|
351
|
+
end
|
352
|
+
|
353
|
+
# fucking idiotic test case for this fucking idiot is: https://devslopes.com/
|
354
|
+
def self.test_random_url(url_or_host)
|
355
|
+
random_filename = TextCommon.sha(Time.now.to_s) + ".xml"
|
356
|
+
if url_or_host =~ /http/
|
357
|
+
url = File.join(url_or_host, random_filename)
|
358
|
+
else
|
359
|
+
url = File.join("http://", host, random_filename)
|
360
|
+
end
|
361
|
+
status, url = UrlCommon.check_for_404(url, true)
|
362
|
+
#
|
363
|
+
# Key bit of logic -- if we get a return value for a randomized sha then that means that
|
364
|
+
# a) the destination site owner is a fucking moron
|
365
|
+
# b) that the destination site owner has set his site so it NEVER returns a 404
|
366
|
+
# c) they're a fucking moron
|
367
|
+
# d) if I get a 200 back then it means that they return you to the home page for anything and NOT
|
368
|
+
# a proper 404 so need to flip flop the logic and return error on a 200; sheesh
|
369
|
+
#
|
370
|
+
return :error, url if status == :ok
|
371
|
+
return :ok, url
|
372
|
+
end
|
373
|
+
|
374
|
+
def self.select_best_rssurl_from_rssurls(urls)
|
375
|
+
return urls.sort_by(&:length).first
|
376
|
+
end
|
377
|
+
|
378
|
+
def self.possible_rssurls(site_url, skip_slash_blog = false)
|
379
|
+
# urls we will probe
|
380
|
+
possible_rssurl_formats = []
|
381
|
+
|
382
|
+
# normal baselines
|
383
|
+
possible_rssurl_formats << "feed.xml"
|
384
|
+
possible_rssurl_formats << "rss.xml"
|
385
|
+
possible_rssurl_formats << "atom.xml"
|
386
|
+
possible_rssurl_formats << "feed/"
|
387
|
+
|
388
|
+
# optionally look at /blog/
|
389
|
+
possible_rssurl_formats << "/blog/feed.xml"
|
390
|
+
possible_rssurl_formats << "/blog/rss.xml"
|
391
|
+
possible_rssurl_formats << "/blog/atom.xml"
|
392
|
+
possible_rssurl_formats << "/blog/feed/"
|
393
|
+
|
394
|
+
possible_rssurls = []
|
395
|
+
possible_rssurl_formats.each do |url_format|
|
396
|
+
possible_rssurls << UrlCommon.join(site_url, url_format)
|
397
|
+
end
|
398
|
+
|
399
|
+
return possible_rssurls
|
400
|
+
end
|
401
|
+
|
402
|
+
def self.parse_html_for_rssurl_from_head(site_url, page = nil, debug = false)
|
403
|
+
if page
|
404
|
+
status = :ok
|
405
|
+
else
|
406
|
+
status, page = UrlCommon.get_page(site_url)
|
407
|
+
end
|
408
|
+
puts "Into html parse for rssurl" if debug
|
409
|
+
possibles = []
|
410
|
+
if status == :ok && page
|
411
|
+
#results = page.css("link[rel='alternate']")
|
412
|
+
results = page.css("link[rel='alternate'][type='application/rss+xml']")
|
413
|
+
#
|
414
|
+
# If only a single one then return it
|
415
|
+
#
|
416
|
+
#return results.first['href'] if results.first['type'] =~ /application\/rss\+xml/i && results.size == 1
|
417
|
+
return results.first['href'] if results.size == 1
|
418
|
+
|
419
|
+
#
|
420
|
+
# If an array then filter out the comments
|
421
|
+
#
|
422
|
+
results.each do |result|
|
423
|
+
possibles << result unless result['title'] =~ /comments? feed/i
|
424
|
+
end
|
425
|
+
|
426
|
+
#
|
427
|
+
# Loop over the possibles and just return the shortest url
|
428
|
+
#
|
429
|
+
# Todo -- can likely do a better job on this
|
430
|
+
#
|
431
|
+
urls = []
|
432
|
+
possibles.each do |possible|
|
433
|
+
urls << possible['href']
|
434
|
+
end
|
435
|
+
return UrlCommon.select_best_rssurl_from_rssurls(urls)
|
436
|
+
#return urls.sort_by(&:length).first
|
437
|
+
|
438
|
+
|
439
|
+
# results.each do |result|
|
440
|
+
#
|
441
|
+
# end
|
442
|
+
# end
|
443
|
+
# doc = Nokogiri::HTML(page.body)
|
444
|
+
# results << doc.at('link[rel="alternate"]')
|
445
|
+
# results = results.flatten
|
446
|
+
end
|
447
|
+
end
|
448
|
+
|
449
|
+
def self.get_protocol(url)
|
450
|
+
parts = url.to_s.split(":")
|
451
|
+
return parts.first
|
452
|
+
end
|
453
|
+
|
454
|
+
#https://500hats.com/feed
|
455
|
+
# UrlCommon.discover_feed_url("https://nickjanetakis.com")
|
456
|
+
def self.discover_feed_url(site_url, debug = false)
|
457
|
+
# step 1: remove the file from the site_url if it has one
|
458
|
+
# step 2: problem the common ones and 404 check
|
459
|
+
|
460
|
+
#
|
461
|
+
# Build a set of possibles
|
462
|
+
#
|
463
|
+
possible_rssurls = UrlCommon.possible_rssurls(site_url)
|
464
|
+
|
465
|
+
#
|
466
|
+
# Keep track of failures
|
467
|
+
#
|
468
|
+
failed_probes = Set.new
|
469
|
+
|
470
|
+
# step 3: parse the html
|
471
|
+
#<link rel="alternate" type="application/rss+xml" href="http://scripting.com/rss.xml" />
|
472
|
+
#<link rel="alternate" type="application/rss+xml" title="Matt Mullenweg » Feed" href="https://ma.tt/feed/" />
|
473
|
+
#<link rel="alternate" type="application/rss+xml" title="Matt Mullenweg » Comments Feed" href="https://ma.tt/comments/feed/" />
|
474
|
+
|
475
|
+
#
|
476
|
+
# Stage 1 -- do http head probing
|
477
|
+
#
|
478
|
+
possible_rssurls.each do |rssurl|
|
479
|
+
puts "Head Probing for: #{rssurl}" if debug
|
480
|
+
|
481
|
+
# abort if we doubled blog i.e. /blog/blog/ in the url
|
482
|
+
next if rssurl =~ /blog\/blog/
|
483
|
+
next if failed_probes.include?(rssurl)
|
484
|
+
|
485
|
+
status, url = UrlCommon.check_for_404(rssurl, true)
|
486
|
+
random_status, random_url = UrlCommon.test_random_url(site_url)
|
487
|
+
#debugger
|
488
|
+
return rssurl if status == :ok && random_status == :ok
|
489
|
+
failed_probes << rssurl
|
490
|
+
end
|
491
|
+
|
492
|
+
puts "After probe, failed_probes as: #{failed_probes.inspect}"
|
493
|
+
|
494
|
+
#
|
495
|
+
# Stage 2-- if subdirectory go up one level and probe again
|
496
|
+
#
|
497
|
+
# TODO
|
498
|
+
|
499
|
+
|
500
|
+
|
501
|
+
#
|
502
|
+
# Stage 3 -- Goto root and probe again
|
503
|
+
#
|
504
|
+
#test for this is the nick site
|
505
|
+
fuzzy_url_parts = Fuzzyurl.new(site_url)
|
506
|
+
base_url = "#{fuzzy_url_parts.protocol}://#{fuzzy_url_parts.hostname}"
|
507
|
+
possible_rssurls = UrlCommon.possible_rssurls(base_url)
|
508
|
+
#debugger
|
509
|
+
possible_rssurls.each do |rssurl|
|
510
|
+
puts "Head Probing for: #{rssurl} at site root stage" #if debug
|
511
|
+
|
512
|
+
# abort if we doubled blog i.e. /blog/blog/ in the url
|
513
|
+
next if rssurl =~ /blog\/blog/
|
514
|
+
next if failed_probes.include?(rssurl)
|
515
|
+
|
516
|
+
status, url = UrlCommon.check_for_404(rssurl, true)
|
517
|
+
return rssurl if status == :ok
|
518
|
+
failed_probes << rssurl
|
519
|
+
end
|
520
|
+
|
521
|
+
|
522
|
+
#
|
523
|
+
# Stage 4 - parse the html
|
524
|
+
#
|
525
|
+
rssurl = UrlCommon.parse_html_for_rssurl_from_head(site_url, nil, true)
|
526
|
+
return rssurl if rssurl
|
527
|
+
|
528
|
+
#
|
529
|
+
# Stage 5 - fall over to feedback
|
530
|
+
#
|
531
|
+
results = Feedbag.find(site_url)
|
532
|
+
# checked_results = []
|
533
|
+
# results.each do |result|
|
534
|
+
# struct = UrlCommon.check_for_404(result)
|
535
|
+
# checked_results << result if struct.status == 200
|
536
|
+
# end
|
537
|
+
|
538
|
+
#
|
539
|
+
# Stage 6 - cache failures to redis so don't look for them again
|
540
|
+
#
|
541
|
+
#$redis.
|
542
|
+
|
543
|
+
return UrlCommon.select_best_rssurl_from_rssurls(results)
|
544
|
+
end
|
545
|
+
|
269
546
|
end
|
data/url_common.gemspec
CHANGED
@@ -26,4 +26,8 @@ Gem::Specification.new do |spec|
|
|
26
26
|
spec.bindir = "exe"
|
27
27
|
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
28
28
|
spec.require_paths = ["lib"]
|
29
|
+
|
30
|
+
spec.add_dependency 'fuzzyurl', '~> 0.9.0'
|
31
|
+
spec.add_dependency 'mechanize', '~> 2.6'
|
32
|
+
|
29
33
|
end
|
metadata
CHANGED
@@ -1,15 +1,43 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: url_common
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Scott Johnson
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
12
|
-
dependencies:
|
11
|
+
date: 2022-07-02 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: fuzzyurl
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.9.0
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.9.0
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: mechanize
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '2.6'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '2.6'
|
13
41
|
description: This is a class library for common url manipulation and crawling tasks. It
|
14
42
|
is based on a career focused on the practical side of working with the Internet
|
15
43
|
using Ruby.
|
@@ -24,6 +52,7 @@ files:
|
|
24
52
|
- ".travis.yml"
|
25
53
|
- CODE_OF_CONDUCT.md
|
26
54
|
- Gemfile
|
55
|
+
- Gemfile.lock
|
27
56
|
- LICENSE.txt
|
28
57
|
- README.md
|
29
58
|
- Rakefile
|
@@ -55,7 +84,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
55
84
|
- !ruby/object:Gem::Version
|
56
85
|
version: '0'
|
57
86
|
requirements: []
|
58
|
-
rubygems_version: 3.
|
87
|
+
rubygems_version: 3.3.7
|
59
88
|
signing_key:
|
60
89
|
specification_version: 4
|
61
90
|
summary: This is a class library designed for common url manipulation and crawling
|