grubby 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.travis.yml +5 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +127 -0
- data/Rakefile +26 -0
- data/grubby.gemspec +35 -0
- data/lib/grubby.rb +169 -0
- data/lib/grubby/core_ext/string.rb +12 -0
- data/lib/grubby/core_ext/uri.rb +12 -0
- data/lib/grubby/json_parser.rb +45 -0
- data/lib/grubby/json_scraper.rb +13 -0
- data/lib/grubby/log.rb +5 -0
- data/lib/grubby/mechanize/download.rb +8 -0
- data/lib/grubby/mechanize/fetch_with_retry.rb +39 -0
- data/lib/grubby/mechanize/file.rb +8 -0
- data/lib/grubby/mechanize/link.rb +20 -0
- data/lib/grubby/mechanize/page.rb +17 -0
- data/lib/grubby/nokogiri/searchable.rb +27 -0
- data/lib/grubby/page_scraper.rb +13 -0
- data/lib/grubby/scraper.rb +99 -0
- data/lib/grubby/version.rb +3 -0
- metadata +220 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 88c8ecc06ffba254ee9e9de3d42f868c0692b244
|
4
|
+
data.tar.gz: 8cd3445f33c9f7db05550947d686293ceee620c1
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: d9dc7435763425d54d82f4930935c913cd67eb15a1250c58c7ccf3b0e419eeb6ceb87289ed3c22386faa96e3ae3584a9f39cf8e671af8b56b52bb3e2c8257e4d
|
7
|
+
data.tar.gz: 2c5c96993c8a673274a4acc34c3f82a8719fbea508c1dffb5ce8cff1d4a13cd90c9fcbf8a3c743500a31f08419c687c24adf5f2aee464a8a4f1935b2b302b184
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2017 Jonathan Hefner
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,127 @@
|
|
1
|
+
# grubby
|
2
|
+
|
3
|
+
[Fail-fast] web scraping. *grubby* adds a layer of utility and
|
4
|
+
error-checking atop the marvelous [Mechanize gem]. See API summary
|
5
|
+
below, or browse the [full documentation].
|
6
|
+
|
7
|
+
[Fail-fast]: https://en.wikipedia.org/wiki/Fail-fast
|
8
|
+
[Mechanize gem]: https://rubygems.org/gems/mechanize
|
9
|
+
[full documentation]: http://www.rubydoc.info/gems/grubby/
|
10
|
+
|
11
|
+
|
12
|
+
## Examples
|
13
|
+
|
14
|
+
The following example scrapes the [Hacker News] front page:
|
15
|
+
|
16
|
+
```ruby
|
17
|
+
require "grubby"
|
18
|
+
|
19
|
+
class HackerNews < Grubby::PageScraper
|
20
|
+
|
21
|
+
scrapes(:items) do
|
22
|
+
page.search!(".athing").map{|item| HackerNewsItem.new(item) }
|
23
|
+
end
|
24
|
+
|
25
|
+
end
|
26
|
+
|
27
|
+
class HackerNewsItem < Grubby::Scraper
|
28
|
+
|
29
|
+
scrapes(:title) { @row1.at!(".storylink").text }
|
30
|
+
scrapes(:submitter) { @row2.at!(".hnuser").text }
|
31
|
+
scrapes(:story_uri) { URI.join(@base_uri, @row1.at!(".storylink")["href"]) }
|
32
|
+
scrapes(:comments_uri) { URI.join(@base_uri, @row2.at!(".age a")["href"]) }
|
33
|
+
|
34
|
+
def initialize(source)
|
35
|
+
@row1 = source
|
36
|
+
@row2 = source.next_sibling
|
37
|
+
@base_uri = source.document.url
|
38
|
+
super
|
39
|
+
end
|
40
|
+
|
41
|
+
end
|
42
|
+
|
43
|
+
grubby = Grubby.new
|
44
|
+
|
45
|
+
# The following line will raise an exception if anything goes wrong
|
46
|
+
# during the scraping process. For example, if the structure of the
|
47
|
+
# HTML does not match expectations, either due to a bad assumption or
|
48
|
+
# due to a site-wide change, the script will terminate immediately with
|
49
|
+
# a relevant error message. This prevents bad values from propogating
|
50
|
+
# and causing hard-to-trace errors.
|
51
|
+
hn = HackerNews.new(grubby.get("https://news.ycombinator.com/news"))
|
52
|
+
|
53
|
+
puts hn.items.take(10).map(&:title) # your scraping logic goes here
|
54
|
+
```
|
55
|
+
|
56
|
+
[Hacker News]: https://news.ycombinator.com/news
|
57
|
+
|
58
|
+
|
59
|
+
## Core API
|
60
|
+
|
61
|
+
- [Grubby](http://www.rubydoc.info/gems/grubby/Grubby)
|
62
|
+
- [#get_mirrored](http://www.rubydoc.info/gems/grubby/Grubby:get_mirrored)
|
63
|
+
- [#singleton](http://www.rubydoc.info/gems/grubby/Grubby:singleton)
|
64
|
+
- [#time_between_requests](http://www.rubydoc.info/gems/grubby/Grubby:time_between_requests)
|
65
|
+
- [Scraper](http://www.rubydoc.info/gems/grubby/Grubby/Scraper)
|
66
|
+
- [.fields](http://www.rubydoc.info/gems/grubby/Grubby/Scraper.fields)
|
67
|
+
- [.scrapes](http://www.rubydoc.info/gems/grubby/Grubby/Scraper.scrapes)
|
68
|
+
- [#[]](http://www.rubydoc.info/gems/grubby/Grubby/Scraper:[])
|
69
|
+
- [#source](http://www.rubydoc.info/gems/grubby/Grubby/Scraper:source)
|
70
|
+
- [#to_h](http://www.rubydoc.info/gems/grubby/Grubby/Scraper:to_h)
|
71
|
+
- [PageScraper](http://www.rubydoc.info/gems/grubby/Grubby/PageScraper)
|
72
|
+
- [#page](http://www.rubydoc.info/gems/grubby/Grubby/PageScraper:page)
|
73
|
+
- [JsonScraper](http://www.rubydoc.info/gems/grubby/Grubby/JsonScraper)
|
74
|
+
- [#json](http://www.rubydoc.info/gems/grubby/Grubby/JsonScraper:json)
|
75
|
+
- Nokogiri::XML::Searchable
|
76
|
+
- [#at!](http://www.rubydoc.info/gems/grubby/Nokogiri/XML/Searchable:at%21)
|
77
|
+
- [#search!](http://www.rubydoc.info/gems/grubby/Nokogiri/XML/Searchable:search%21)
|
78
|
+
- Mechanize::Page
|
79
|
+
- [#at!](http://www.rubydoc.info/gems/grubby/Mechanize/Page:at%21)
|
80
|
+
- [#search!](http://www.rubydoc.info/gems/grubby/Mechanize/Page:search%21)
|
81
|
+
- Mechanize::Page::Link
|
82
|
+
- [#to_absolute_uri](http://www.rubydoc.info/gems/grubby/Mechanize/Page/Link#to_absolute_uri)
|
83
|
+
|
84
|
+
|
85
|
+
## Supplemental API
|
86
|
+
|
87
|
+
*grubby* uses several gems which extend core Ruby objects with
|
88
|
+
convenience methods. When you import *grubby* you automatically make
|
89
|
+
these methods available. See each gem below for its specific API
|
90
|
+
documentation:
|
91
|
+
|
92
|
+
- [Active Support](https://rubygems.org/gems/activesupport)
|
93
|
+
([docs](http://www.rubydoc.info/gems/activesupport/))
|
94
|
+
- [casual_support](https://rubygems.org/gems/casual_support)
|
95
|
+
([docs](http://www.rubydoc.info/gems/casual_support/))
|
96
|
+
- [gorge](https://rubygems.org/gems/gorge)
|
97
|
+
([docs](http://www.rubydoc.info/gems/gorge/))
|
98
|
+
- [mini_sanity](https://rubygems.org/gems/mini_sanity)
|
99
|
+
([docs](http://www.rubydoc.info/gems/mini_sanity/))
|
100
|
+
- [pleasant_path](https://rubygems.org/gems/pleasant_path)
|
101
|
+
([docs](http://www.rubydoc.info/gems/pleasant_path/))
|
102
|
+
|
103
|
+
|
104
|
+
## Installation
|
105
|
+
|
106
|
+
Install from [Ruby Gems](https://rubygems.org/gems/grubby):
|
107
|
+
|
108
|
+
```bash
|
109
|
+
$ gem install grubby
|
110
|
+
```
|
111
|
+
|
112
|
+
Then require in your Ruby script:
|
113
|
+
|
114
|
+
```ruby
|
115
|
+
require "grubby"
|
116
|
+
```
|
117
|
+
|
118
|
+
|
119
|
+
## Contributing
|
120
|
+
|
121
|
+
Run `rake test` to run the tests. You can also run `rake irb` for an
|
122
|
+
interactive prompt that pre-loads the project code.
|
123
|
+
|
124
|
+
|
125
|
+
## License
|
126
|
+
|
127
|
+
[MIT License](https://opensource.org/licenses/MIT)
|
data/Rakefile
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
2
|
+
require "rake/testtask"
|
3
|
+
require "yard"
|
4
|
+
|
5
|
+
|
6
|
+
YARD::Rake::YardocTask.new(:doc) do |t|
|
7
|
+
end
|
8
|
+
|
9
|
+
desc "Launch IRB with this gem pre-loaded"
|
10
|
+
task :irb do
|
11
|
+
# HACK because lib/grubby/version is prematurely loaded by bundler/gem_tasks
|
12
|
+
Object.send(:remove_const, :Grubby)
|
13
|
+
|
14
|
+
require "grubby"
|
15
|
+
require "irb"
|
16
|
+
ARGV.clear
|
17
|
+
IRB.start
|
18
|
+
end
|
19
|
+
|
20
|
+
Rake::TestTask.new(:test) do |t|
|
21
|
+
t.libs << "test"
|
22
|
+
t.libs << "lib"
|
23
|
+
t.test_files = FileList["test/**/*_test.rb"]
|
24
|
+
end
|
25
|
+
|
26
|
+
task :default => :test
|
data/grubby.gemspec
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "grubby/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "grubby"
|
8
|
+
spec.version = Grubby::VERSION
|
9
|
+
spec.authors = ["Jonathan Hefner"]
|
10
|
+
spec.email = ["jonathan.hefner@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Fail-fast web scraping}
|
13
|
+
spec.homepage = "https://github.com/jonathanhefner/grubby"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
17
|
+
f.match(%r{^(test|spec|features)/})
|
18
|
+
end
|
19
|
+
spec.bindir = "exe"
|
20
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
21
|
+
spec.require_paths = ["lib"]
|
22
|
+
|
23
|
+
spec.add_runtime_dependency "activesupport", "~> 5.0"
|
24
|
+
spec.add_runtime_dependency "casual_support", "~> 3.0"
|
25
|
+
spec.add_runtime_dependency "dumb_delimited", "~> 1.0"
|
26
|
+
spec.add_runtime_dependency "gorge", "~> 1.0"
|
27
|
+
spec.add_runtime_dependency "mechanize", "~> 2.7"
|
28
|
+
spec.add_runtime_dependency "mini_sanity", "~> 1.0"
|
29
|
+
spec.add_runtime_dependency "pleasant_path", "~> 1.1"
|
30
|
+
|
31
|
+
spec.add_development_dependency "bundler", "~> 1.15"
|
32
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
33
|
+
spec.add_development_dependency "minitest", "~> 5.0"
|
34
|
+
spec.add_development_dependency "yard", "~> 0.9"
|
35
|
+
end
|
data/lib/grubby.rb
ADDED
@@ -0,0 +1,169 @@
|
|
1
|
+
require "active_support/all"
|
2
|
+
require "casual_support"
|
3
|
+
require "dumb_delimited"
|
4
|
+
require "gorge"
|
5
|
+
require "mechanize"
|
6
|
+
require "mini_sanity"
|
7
|
+
require "pleasant_path"
|
8
|
+
|
9
|
+
require_relative "grubby/log"
|
10
|
+
|
11
|
+
require_relative "grubby/core_ext/string"
|
12
|
+
require_relative "grubby/core_ext/uri"
|
13
|
+
require_relative "grubby/mechanize/fetch_with_retry"
|
14
|
+
require_relative "grubby/mechanize/download"
|
15
|
+
require_relative "grubby/mechanize/file"
|
16
|
+
require_relative "grubby/mechanize/link"
|
17
|
+
require_relative "grubby/mechanize/page"
|
18
|
+
require_relative "grubby/nokogiri/searchable"
|
19
|
+
|
20
|
+
|
21
|
+
class Grubby < Mechanize
|
22
|
+
|
23
|
+
# @return [Integer, Float, Range<Integer>, Range<Float>]
|
24
|
+
# The enforced minimum amount of time to wait between requests, in
|
25
|
+
# seconds. If the value is a Range, a random number within the
|
26
|
+
# Range is chosen for each request.
|
27
|
+
attr_accessor :time_between_requests
|
28
|
+
|
29
|
+
# @param singleton_journal [Pathname, String]
|
30
|
+
# Optional journal file to persist the list of resources processed
|
31
|
+
# by {singleton}. Useful to ensure only-once processing across
|
32
|
+
# multiple program runs.
|
33
|
+
def initialize(singleton_journal = nil)
|
34
|
+
super()
|
35
|
+
|
36
|
+
# Prevent "memory leaks", and prevent mistakenly blank urls from
|
37
|
+
# resolving. (Blank urls resolve as a path relative to the last
|
38
|
+
# history entry. Without this setting, an erroneous `agent.get("")`
|
39
|
+
# could sometimes successfully fetch a page.)
|
40
|
+
self.max_history = 0
|
41
|
+
|
42
|
+
# Prevent files of unforeseen content type from being buffered into
|
43
|
+
# memory by default, in case they are very large. However, increase
|
44
|
+
# the threshold for what is considered "large", to prevent
|
45
|
+
# unnecessary writes to disk.
|
46
|
+
#
|
47
|
+
# References:
|
48
|
+
# - http://docs.seattlerb.org/mechanize/Mechanize/PluggableParser.html
|
49
|
+
# - http://docs.seattlerb.org/mechanize/Mechanize/Download.html
|
50
|
+
# - http://docs.seattlerb.org/mechanize/Mechanize/File.html
|
51
|
+
self.max_file_buffer = 1_000_000 # only applies to Mechanize::Download
|
52
|
+
self.pluggable_parser.default = Mechanize::Download
|
53
|
+
self.pluggable_parser["text/plain"] = Mechanize::File
|
54
|
+
self.pluggable_parser["application/json"] = Grubby::JsonParser
|
55
|
+
|
56
|
+
# Set up configurable rate limiting, and choose a reasonable default
|
57
|
+
# rate limit.
|
58
|
+
self.pre_connect_hooks << Proc.new{ self.send(:sleep_between_requests) }
|
59
|
+
self.time_between_requests = 1.0
|
60
|
+
|
61
|
+
@journal = singleton_journal ?
|
62
|
+
singleton_journal.to_pathname.touch_file : Pathname::NULL
|
63
|
+
@seen = SingletonKey.parse_file(@journal).
|
64
|
+
group_by(&:purpose).transform_values{|sks| sks.map(&:key).index_to{ true } }
|
65
|
+
end
|
66
|
+
|
67
|
+
# Calls +#get+ with each of +mirror_uris+ until a successful
|
68
|
+
# ("200 OK") response is recieved, and returns that +#get+ result.
|
69
|
+
# Rescues and logs +Mechanize::ResponseCodeError+ failures for all but
|
70
|
+
# the last mirror.
|
71
|
+
#
|
72
|
+
# @param mirror_uris [Array<String>]
|
73
|
+
# @return [Mechanize::Page, Mechanize::File, Mechanize::Download, ...]
|
74
|
+
# @raise [Mechanize::ResponseCodeError]
|
75
|
+
# if all +mirror_uris+ fail
|
76
|
+
def get_mirrored(mirror_uris, parameters = [], referer = nil, headers = {})
|
77
|
+
i = 0
|
78
|
+
begin
|
79
|
+
get(mirror_uris[i], parameters, referer, headers)
|
80
|
+
rescue Mechanize::ResponseCodeError => e
|
81
|
+
i += 1
|
82
|
+
if i >= mirror_uris.length
|
83
|
+
raise
|
84
|
+
else
|
85
|
+
$log.info("Mirror failed with response code #{e.response_code}: #{mirror_uris[i - 1]}")
|
86
|
+
$log.debug("Trying next mirror: #{mirror_uris[i]}")
|
87
|
+
retry
|
88
|
+
end
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
# Ensures only-once processing of the resource indicated by +target+
|
93
|
+
# for the specified +purpose+. A list of previously-processed
|
94
|
+
# resource URIs and content hashes is maintained in the Grubby
|
95
|
+
# instance. The given block is called with the fetched resource only
|
96
|
+
# if the resource's URI and the resource's content hash have not been
|
97
|
+
# previously processed under the specified +purpose+.
|
98
|
+
#
|
99
|
+
# @param target [URI, String, Mechanize::Page::Link, #to_absolute_uri]
|
100
|
+
# designates the resource to fetch
|
101
|
+
# @param purpose [String]
|
102
|
+
# the purpose of processing the resource
|
103
|
+
# @yield [resource]
|
104
|
+
# processes the resource
|
105
|
+
# @yieldparam resource [Mechanize::Page, Mechanize::File, Mechanize::Download, ...]
|
106
|
+
# the fetched resource
|
107
|
+
# @return [Boolean]
|
108
|
+
# whether the given block was called
|
109
|
+
# @raise [Mechanize::ResponseCodeError]
|
110
|
+
# if fetching the resource results in error (see +Mechanize#get+)
|
111
|
+
def singleton(target, purpose = "")
|
112
|
+
series = []
|
113
|
+
|
114
|
+
original_url = target.to_absolute_uri
|
115
|
+
return if skip_singleton?(purpose, original_url.to_s, series)
|
116
|
+
|
117
|
+
url = normalize_url(original_url)
|
118
|
+
return if skip_singleton?(purpose, url.to_s, series)
|
119
|
+
|
120
|
+
$log.info("Fetching #{url}")
|
121
|
+
resource = get(url)
|
122
|
+
skip = skip_singleton?(purpose, resource.uri.to_s, series) |
|
123
|
+
skip_singleton?(purpose, "content hash: #{resource.content_hash}", series)
|
124
|
+
|
125
|
+
yield resource unless skip
|
126
|
+
|
127
|
+
series.map{|k| SingletonKey.new(purpose, k) }.append_to_file(@journal)
|
128
|
+
|
129
|
+
!skip
|
130
|
+
end
|
131
|
+
|
132
|
+
|
133
|
+
private
|
134
|
+
|
135
|
+
SingletonKey = DumbDelimited[:purpose, :key]
|
136
|
+
|
137
|
+
def skip_singleton?(purpose, key, series)
|
138
|
+
return false if series.include?(key)
|
139
|
+
series << key
|
140
|
+
already = (@seen[purpose.to_s] ||= {}).displace(key, true)
|
141
|
+
$log.info("Skipping #{series.first} (already seen #{series.last})") if already
|
142
|
+
already
|
143
|
+
end
|
144
|
+
|
145
|
+
def normalize_url(url)
|
146
|
+
url = url.dup
|
147
|
+
$log.warn("Discarding fragment in URL: #{url}") if url.fragment
|
148
|
+
url.fragment = nil
|
149
|
+
url.path = url.path.chomp("/")
|
150
|
+
url
|
151
|
+
end
|
152
|
+
|
153
|
+
def sleep_between_requests
|
154
|
+
@last_request_at ||= 0.0
|
155
|
+
delay_duration = @time_between_requests.is_a?(Range) ?
|
156
|
+
rand(@time_between_requests) : @time_between_requests
|
157
|
+
sleep_duration = @last_request_at + delay_duration - Time.now.to_f
|
158
|
+
sleep(sleep_duration) if sleep_duration > 0
|
159
|
+
@last_request_at = Time.now.to_f
|
160
|
+
end
|
161
|
+
|
162
|
+
end
|
163
|
+
|
164
|
+
|
165
|
+
require_relative "grubby/version"
|
166
|
+
require_relative "grubby/json_parser"
|
167
|
+
require_relative "grubby/scraper"
|
168
|
+
require_relative "grubby/page_scraper"
|
169
|
+
require_relative "grubby/json_scraper"
|
@@ -0,0 +1,12 @@
|
|
1
|
+
class String
|
2
|
+
|
3
|
+
# Constructs a URI from the String. Raises an exception if the String
|
4
|
+
# does not denote an absolute URI.
|
5
|
+
#
|
6
|
+
# @return [URI]
|
7
|
+
# @raise [RuntimeError] if the String does not denote an absolute URI
|
8
|
+
def to_absolute_uri
|
9
|
+
URI(self).to_absolute_uri
|
10
|
+
end
|
11
|
+
|
12
|
+
end
|
@@ -0,0 +1,45 @@
|
|
1
|
+
class Grubby::JsonParser < Mechanize::File
|
2
|
+
|
3
|
+
# Returns the options to use when parsing JSON. The returned options
|
4
|
+
# Hash is not +dup+ed and can be modified directly. Any modifications
|
5
|
+
# will be applied to all future parsing.
|
6
|
+
#
|
7
|
+
# For information about available options, see
|
8
|
+
# {http://ruby-doc.org/stdlib/libdoc/json/rdoc/JSON.html#method-i-parse
|
9
|
+
# +JSON.parse+}.
|
10
|
+
#
|
11
|
+
# @return [Hash]
|
12
|
+
def self.json_parse_options
|
13
|
+
@json_parse_options ||= {
|
14
|
+
max_nesting: false,
|
15
|
+
allow_nan: false,
|
16
|
+
symbolize_names: false,
|
17
|
+
create_additions: false,
|
18
|
+
object_class: Hash,
|
19
|
+
array_class: Array,
|
20
|
+
}
|
21
|
+
end
|
22
|
+
|
23
|
+
# Sets the options to use when parsing JSON. The entire options Hash
|
24
|
+
# is replaced, and the new value will be applied to all future
|
25
|
+
# parsing. To set options individually, see {json_parse_options}.
|
26
|
+
#
|
27
|
+
# For information about available options, see
|
28
|
+
# {http://ruby-doc.org/stdlib/libdoc/json/rdoc/JSON.html#method-i-parse
|
29
|
+
# +JSON.parse+}.
|
30
|
+
#
|
31
|
+
# @param options [Hash]
|
32
|
+
def self.json_parse_options=(options)
|
33
|
+
@json_parse_options = options
|
34
|
+
end
|
35
|
+
|
36
|
+
# @return [Hash, Array]
|
37
|
+
# The parsed JSON data.
|
38
|
+
attr_reader :json
|
39
|
+
|
40
|
+
def initialize(uri = nil, response = nil, body = nil, code = nil)
|
41
|
+
@json = body && JSON.parse(body, self.class.json_parse_options)
|
42
|
+
super
|
43
|
+
end
|
44
|
+
|
45
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
class Grubby::JsonScraper < Grubby::Scraper
|
2
|
+
|
3
|
+
# @return [Hash, Array]
|
4
|
+
# The parsed JSON data being scraped.
|
5
|
+
attr_reader :json
|
6
|
+
|
7
|
+
# @param source [Grubby::JsonParser]
|
8
|
+
def initialize(source)
|
9
|
+
@json = source.assert_kind_of!(Grubby::JsonParser).json
|
10
|
+
super
|
11
|
+
end
|
12
|
+
|
13
|
+
end
|
data/lib/grubby/log.rb
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
# This monkey patch attempts to fix the insidious "too many connection
|
2
|
+
# resets" bug described here: https://github.com/sparklemotion/mechanize/issues/123
|
3
|
+
#
|
4
|
+
# The code is taken and modified from this helpful blog article:
|
5
|
+
# http://scottwb.com/blog/2013/11/09/defeating-the-infamous-mechanize-too-many-connection-resets-bug/
|
6
|
+
class Mechanize::HTTP::Agent
|
7
|
+
|
8
|
+
MAX_CONNECTION_RESET_RETRIES = 9
|
9
|
+
IDEMPOTENT_HTTP_METHODS = [:get, :head, :options, :delete]
|
10
|
+
|
11
|
+
# Replacement for +Mechanize::HTTP::Agent#fetch+. When a "too many
|
12
|
+
# connection resets" error is encountered, this method shuts down the
|
13
|
+
# persistent HTTP connection, and then retries the request (upto
|
14
|
+
# {MAX_CONNECTION_RESET_RETRIES} times).
|
15
|
+
def fetch_with_retry(uri, http_method = :get, headers = {}, params = [], referer = current_page, redirects = 0)
|
16
|
+
retry_count = 0
|
17
|
+
begin
|
18
|
+
fetch_without_retry(uri, http_method, headers, params, referer, redirects)
|
19
|
+
rescue Net::HTTP::Persistent::Error => e
|
20
|
+
# raise if different type of error
|
21
|
+
raise unless e.message.include?("too many connection resets")
|
22
|
+
# raise if non-idempotent http method
|
23
|
+
raise unless IDEMPOTENT_HTTP_METHODS.include?(http_method)
|
24
|
+
# raise if we've tried too many times
|
25
|
+
raise if retry_count >= MAX_CONNECTION_RESET_RETRIES
|
26
|
+
|
27
|
+
# otherwise, shutdown the persistent HTTP connection and try again
|
28
|
+
retry_count += 1
|
29
|
+
$log.warn("Possible connection reset bug. Retry(#{retry_count}) #{http_method.to_s.upcase} #{uri}")
|
30
|
+
self.http.shutdown
|
31
|
+
sleep(retry_count) # incremental backoff in case problem is with server
|
32
|
+
retry
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
alias_method :fetch_without_retry, :fetch
|
37
|
+
alias_method :fetch, :fetch_with_retry
|
38
|
+
|
39
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
class Mechanize::Page::Link
|
2
|
+
|
3
|
+
# Returns the URI represented by the Link, in absolute form. If the
|
4
|
+
# href attribute of the Link is expressed in relative form, the URI of
|
5
|
+
# the Link's Page is used to convert to absolute form.
|
6
|
+
#
|
7
|
+
# @return [URI]
|
8
|
+
def to_absolute_uri
|
9
|
+
# Via the W3 spec: "If the a element has no href attribute, then the
|
10
|
+
# element represents a placeholder for where a link might otherwise
|
11
|
+
# have been placed, if it had been relevant, consisting of just the
|
12
|
+
# element's contents."[1] So, we assume a link with no href
|
13
|
+
# attribute (i.e. `uri == nil`) should be treated the same as an
|
14
|
+
# intra-page link.
|
15
|
+
#
|
16
|
+
# [1]: https://www.w3.org/TR/2016/REC-html51-20161101/textlevel-semantics.html#the-a-element
|
17
|
+
URI.join(self.page.uri, self.uri || "#").to_absolute_uri
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
class Mechanize::Page
|
2
|
+
|
3
|
+
# @!method search!(*queries)
|
4
|
+
# See {::Nokogiri::XML::Searchable#search!}.
|
5
|
+
#
|
6
|
+
# @param queries [Array<String>]
|
7
|
+
# @return [Array<Nokogiri::XML::Element>]
|
8
|
+
def_delegators :parser, :search!
|
9
|
+
|
10
|
+
# @!method at!(*queries)
|
11
|
+
# See {::Nokogiri::XML::Searchable#at!}.
|
12
|
+
#
|
13
|
+
# @param queries [Array<String>]
|
14
|
+
# @return [Nokogiri::XML::Element]
|
15
|
+
def_delegators :parser, :at!
|
16
|
+
|
17
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module Nokogiri::XML::Searchable
|
2
|
+
|
3
|
+
# Searches the node using the given XPath or CSS queries, and returns
|
4
|
+
# the results. Raises an exception if there are no results. See also
|
5
|
+
# +#search+.
|
6
|
+
#
|
7
|
+
# @param queries [Array<String>]
|
8
|
+
# @return [Array<Nokogiri::XML::Element>]
|
9
|
+
# @raise [RuntimeError] if queries yield no results
|
10
|
+
def search!(*queries)
|
11
|
+
results = search(*queries)
|
12
|
+
raise "No elements matching #{queries.map(&:inspect).join(" OR ")}" if results.empty?
|
13
|
+
results
|
14
|
+
end
|
15
|
+
|
16
|
+
# Searches the node using the given XPath or CSS queries, and returns
|
17
|
+
# only the first result. Raises an exception if there are no results.
|
18
|
+
# See also +#at+.
|
19
|
+
#
|
20
|
+
# @param queries [Array<String>]
|
21
|
+
# @return [Nokogiri::XML::Element]
|
22
|
+
# @raise [RuntimeError] if queries yield no results
|
23
|
+
def at!(*queries)
|
24
|
+
search!(*queries).first
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
class Grubby::PageScraper < Grubby::Scraper
|
2
|
+
|
3
|
+
# @return [Mechanize::Page]
|
4
|
+
# The Page being scraped.
|
5
|
+
attr_reader :page
|
6
|
+
|
7
|
+
# @param source [Mechanize::Page]
|
8
|
+
def initialize(source)
|
9
|
+
@page = source.assert_kind_of!(Mechanize::Page)
|
10
|
+
super
|
11
|
+
end
|
12
|
+
|
13
|
+
end
|
@@ -0,0 +1,99 @@
|
|
1
|
+
class Grubby::Scraper
|
2
|
+
|
3
|
+
class Error < RuntimeError
|
4
|
+
end
|
5
|
+
|
6
|
+
# Defines an attribute reader method named by +field+. During
|
7
|
+
# +initialize+, the given block is called, and the attribute is set to
|
8
|
+
# the block's return value. By default, if the block's return value
|
9
|
+
# is nil, an exception will be raised. To prevent this behavior, set
|
10
|
+
# +optional+ to true.
|
11
|
+
#
|
12
|
+
# @param field [Symbol, String]
|
13
|
+
# name of the scraped value
|
14
|
+
# @param optional [Boolean]
|
15
|
+
# whether to permit a nil scraped value
|
16
|
+
# @yield []
|
17
|
+
# scrapes the value
|
18
|
+
# @yieldreturn [Object]
|
19
|
+
# scraped value
|
20
|
+
def self.scrapes(field, optional: false, &block)
|
21
|
+
field = field.to_sym
|
22
|
+
self.fields << field
|
23
|
+
|
24
|
+
define_method(field) do
|
25
|
+
return @scraped[field] if @scraped.key?(field)
|
26
|
+
|
27
|
+
unless @errors.key?(field)
|
28
|
+
begin
|
29
|
+
value = instance_eval(&block)
|
30
|
+
if value.nil?
|
31
|
+
raise "`#{field}` cannot be nil" unless optional
|
32
|
+
$log.debug("Scraped nil value for #{self.class}##{field}")
|
33
|
+
end
|
34
|
+
@scraped[field] = value
|
35
|
+
rescue RuntimeError => e
|
36
|
+
@errors[field] = e
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
raise "`#{field}` raised a #{@errors[field].class}" if @errors.key?(field)
|
41
|
+
|
42
|
+
@scraped[field]
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
# @return [Array<Symbol>]
|
47
|
+
# The names of all scraped values, as defined by {scrapes}.
|
48
|
+
def self.fields
|
49
|
+
@fields ||= []
|
50
|
+
end
|
51
|
+
|
52
|
+
# @return [Object]
|
53
|
+
# The source being scraped. Typically a Mechanize pluggable parser
|
54
|
+
# such as +Mechanize::Page+.
|
55
|
+
attr_reader :source
|
56
|
+
|
57
|
+
# @param source
|
58
|
+
# @raise [Grubby::Scraper::Error]
|
59
|
+
# if any scraped values result in error
|
60
|
+
def initialize(source)
|
61
|
+
@source = source
|
62
|
+
@scraped = {}
|
63
|
+
@errors = {}
|
64
|
+
|
65
|
+
self.class.fields.each do |field|
|
66
|
+
begin
|
67
|
+
self.send(field)
|
68
|
+
rescue RuntimeError
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
unless @errors.empty?
|
73
|
+
listing = @errors.map do |field, error|
|
74
|
+
error_class = " (#{error.class})" unless error.class == RuntimeError
|
75
|
+
error_trace = error.backtrace.join("\n").indent(2)
|
76
|
+
"* #{field} -- #{error.message}#{error_class}\n#{error_trace}"
|
77
|
+
end
|
78
|
+
raise Error.new("Failed to scrape the following fields:\n#{listing.join("\n")}")
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
# Returns the scraped value named by +field+.
|
83
|
+
#
|
84
|
+
# @param field [Symbol, String]
|
85
|
+
# @return [Object]
|
86
|
+
# @raise [RuntimeError]
|
87
|
+
# if +field+ is not a valid name
|
88
|
+
def [](field)
|
89
|
+
@scraped.fetch(field.to_sym)
|
90
|
+
end
|
91
|
+
|
92
|
+
# Returns all scraped values as a Hash.
|
93
|
+
#
|
94
|
+
# @return [Hash<Symbol, Object>]
|
95
|
+
def to_h
|
96
|
+
@scraped.dup
|
97
|
+
end
|
98
|
+
|
99
|
+
end
|
metadata
ADDED
@@ -0,0 +1,220 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: grubby
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Jonathan Hefner
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-09-05 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: activesupport
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '5.0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '5.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: casual_support
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '3.0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '3.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: dumb_delimited
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: gorge
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: mechanize
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '2.7'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '2.7'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: mini_sanity
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '1.0'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '1.0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: pleasant_path
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '1.1'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '1.1'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: bundler
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '1.15'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '1.15'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: rake
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - "~>"
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '10.0'
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - "~>"
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '10.0'
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: minitest
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - "~>"
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '5.0'
|
146
|
+
type: :development
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - "~>"
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '5.0'
|
153
|
+
- !ruby/object:Gem::Dependency
|
154
|
+
name: yard
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
156
|
+
requirements:
|
157
|
+
- - "~>"
|
158
|
+
- !ruby/object:Gem::Version
|
159
|
+
version: '0.9'
|
160
|
+
type: :development
|
161
|
+
prerelease: false
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
163
|
+
requirements:
|
164
|
+
- - "~>"
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
version: '0.9'
|
167
|
+
description:
|
168
|
+
email:
|
169
|
+
- jonathan.hefner@gmail.com
|
170
|
+
executables: []
|
171
|
+
extensions: []
|
172
|
+
extra_rdoc_files: []
|
173
|
+
files:
|
174
|
+
- ".gitignore"
|
175
|
+
- ".travis.yml"
|
176
|
+
- Gemfile
|
177
|
+
- LICENSE.txt
|
178
|
+
- README.md
|
179
|
+
- Rakefile
|
180
|
+
- grubby.gemspec
|
181
|
+
- lib/grubby.rb
|
182
|
+
- lib/grubby/core_ext/string.rb
|
183
|
+
- lib/grubby/core_ext/uri.rb
|
184
|
+
- lib/grubby/json_parser.rb
|
185
|
+
- lib/grubby/json_scraper.rb
|
186
|
+
- lib/grubby/log.rb
|
187
|
+
- lib/grubby/mechanize/download.rb
|
188
|
+
- lib/grubby/mechanize/fetch_with_retry.rb
|
189
|
+
- lib/grubby/mechanize/file.rb
|
190
|
+
- lib/grubby/mechanize/link.rb
|
191
|
+
- lib/grubby/mechanize/page.rb
|
192
|
+
- lib/grubby/nokogiri/searchable.rb
|
193
|
+
- lib/grubby/page_scraper.rb
|
194
|
+
- lib/grubby/scraper.rb
|
195
|
+
- lib/grubby/version.rb
|
196
|
+
homepage: https://github.com/jonathanhefner/grubby
|
197
|
+
licenses:
|
198
|
+
- MIT
|
199
|
+
metadata: {}
|
200
|
+
post_install_message:
|
201
|
+
rdoc_options: []
|
202
|
+
require_paths:
|
203
|
+
- lib
|
204
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
205
|
+
requirements:
|
206
|
+
- - ">="
|
207
|
+
- !ruby/object:Gem::Version
|
208
|
+
version: '0'
|
209
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
210
|
+
requirements:
|
211
|
+
- - ">="
|
212
|
+
- !ruby/object:Gem::Version
|
213
|
+
version: '0'
|
214
|
+
requirements: []
|
215
|
+
rubyforge_project:
|
216
|
+
rubygems_version: 2.6.13
|
217
|
+
signing_key:
|
218
|
+
specification_version: 4
|
219
|
+
summary: Fail-fast web scraping
|
220
|
+
test_files: []
|