wayfarer 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +8 -0
- data/.rbenv-gemsets +1 -0
- data/.rspec +3 -0
- data/.rubocop.yml +21 -0
- data/.ruby-version +1 -0
- data/.travis.yml +5 -0
- data/.yardopts +3 -0
- data/Changelog.md +10 -0
- data/Gemfile +11 -0
- data/LICENSE +19 -0
- data/README.md +21 -0
- data/Rakefile +114 -0
- data/benchmark/frontiers.rb +143 -0
- data/bin/wayfarer +116 -0
- data/docs/.gitignore +2 -0
- data/docs/_config.yml +15 -0
- data/docs/_includes/base.html +7 -0
- data/docs/_includes/head.html +10 -0
- data/docs/_includes/navigation.html +187 -0
- data/docs/_layouts/default.html +42 -0
- data/docs/_sass/base.scss +439 -0
- data/docs/_sass/variables.scss +24 -0
- data/docs/_sass/vendor/bourbon/_bourbon-deprecate.scss +19 -0
- data/docs/_sass/vendor/bourbon/_bourbon-deprecated-upcoming.scss +425 -0
- data/docs/_sass/vendor/bourbon/_bourbon.scss +90 -0
- data/docs/_sass/vendor/bourbon/addons/_border-color.scss +29 -0
- data/docs/_sass/vendor/bourbon/addons/_border-radius.scss +48 -0
- data/docs/_sass/vendor/bourbon/addons/_border-style.scss +28 -0
- data/docs/_sass/vendor/bourbon/addons/_border-width.scss +28 -0
- data/docs/_sass/vendor/bourbon/addons/_buttons.scss +69 -0
- data/docs/_sass/vendor/bourbon/addons/_clearfix.scss +25 -0
- data/docs/_sass/vendor/bourbon/addons/_ellipsis.scss +30 -0
- data/docs/_sass/vendor/bourbon/addons/_font-stacks.scss +31 -0
- data/docs/_sass/vendor/bourbon/addons/_hide-text.scss +27 -0
- data/docs/_sass/vendor/bourbon/addons/_margin.scss +29 -0
- data/docs/_sass/vendor/bourbon/addons/_padding.scss +29 -0
- data/docs/_sass/vendor/bourbon/addons/_position.scss +51 -0
- data/docs/_sass/vendor/bourbon/addons/_prefixer.scss +66 -0
- data/docs/_sass/vendor/bourbon/addons/_retina-image.scss +27 -0
- data/docs/_sass/vendor/bourbon/addons/_size.scss +56 -0
- data/docs/_sass/vendor/bourbon/addons/_text-inputs.scss +118 -0
- data/docs/_sass/vendor/bourbon/addons/_timing-functions.scss +34 -0
- data/docs/_sass/vendor/bourbon/addons/_triangle.scss +63 -0
- data/docs/_sass/vendor/bourbon/addons/_word-wrap.scss +29 -0
- data/docs/_sass/vendor/bourbon/css3/_animation.scss +61 -0
- data/docs/_sass/vendor/bourbon/css3/_appearance.scss +5 -0
- data/docs/_sass/vendor/bourbon/css3/_backface-visibility.scss +5 -0
- data/docs/_sass/vendor/bourbon/css3/_background-image.scss +44 -0
- data/docs/_sass/vendor/bourbon/css3/_background.scss +57 -0
- data/docs/_sass/vendor/bourbon/css3/_border-image.scss +61 -0
- data/docs/_sass/vendor/bourbon/css3/_calc.scss +6 -0
- data/docs/_sass/vendor/bourbon/css3/_columns.scss +67 -0
- data/docs/_sass/vendor/bourbon/css3/_filter.scss +6 -0
- data/docs/_sass/vendor/bourbon/css3/_flex-box.scss +327 -0
- data/docs/_sass/vendor/bourbon/css3/_font-face.scss +29 -0
- data/docs/_sass/vendor/bourbon/css3/_font-feature-settings.scss +6 -0
- data/docs/_sass/vendor/bourbon/css3/_hidpi-media-query.scss +12 -0
- data/docs/_sass/vendor/bourbon/css3/_hyphens.scss +6 -0
- data/docs/_sass/vendor/bourbon/css3/_image-rendering.scss +15 -0
- data/docs/_sass/vendor/bourbon/css3/_keyframes.scss +38 -0
- data/docs/_sass/vendor/bourbon/css3/_linear-gradient.scss +40 -0
- data/docs/_sass/vendor/bourbon/css3/_perspective.scss +12 -0
- data/docs/_sass/vendor/bourbon/css3/_placeholder.scss +10 -0
- data/docs/_sass/vendor/bourbon/css3/_radial-gradient.scss +40 -0
- data/docs/_sass/vendor/bourbon/css3/_selection.scss +44 -0
- data/docs/_sass/vendor/bourbon/css3/_text-decoration.scss +27 -0
- data/docs/_sass/vendor/bourbon/css3/_transform.scss +21 -0
- data/docs/_sass/vendor/bourbon/css3/_transition.scss +81 -0
- data/docs/_sass/vendor/bourbon/css3/_user-select.scss +5 -0
- data/docs/_sass/vendor/bourbon/functions/_assign-inputs.scss +16 -0
- data/docs/_sass/vendor/bourbon/functions/_contains-falsy.scss +25 -0
- data/docs/_sass/vendor/bourbon/functions/_contains.scss +31 -0
- data/docs/_sass/vendor/bourbon/functions/_is-length.scss +16 -0
- data/docs/_sass/vendor/bourbon/functions/_is-light.scss +26 -0
- data/docs/_sass/vendor/bourbon/functions/_is-number.scss +16 -0
- data/docs/_sass/vendor/bourbon/functions/_is-size.scss +23 -0
- data/docs/_sass/vendor/bourbon/functions/_modular-scale.scss +74 -0
- data/docs/_sass/vendor/bourbon/functions/_px-to-em.scss +24 -0
- data/docs/_sass/vendor/bourbon/functions/_px-to-rem.scss +26 -0
- data/docs/_sass/vendor/bourbon/functions/_shade.scss +24 -0
- data/docs/_sass/vendor/bourbon/functions/_strip-units.scss +22 -0
- data/docs/_sass/vendor/bourbon/functions/_tint.scss +24 -0
- data/docs/_sass/vendor/bourbon/functions/_transition-property-name.scss +37 -0
- data/docs/_sass/vendor/bourbon/functions/_unpack.scss +32 -0
- data/docs/_sass/vendor/bourbon/helpers/_convert-units.scss +26 -0
- data/docs/_sass/vendor/bourbon/helpers/_directional-values.scss +108 -0
- data/docs/_sass/vendor/bourbon/helpers/_font-source-declaration.scss +53 -0
- data/docs/_sass/vendor/bourbon/helpers/_gradient-positions-parser.scss +24 -0
- data/docs/_sass/vendor/bourbon/helpers/_linear-angle-parser.scss +35 -0
- data/docs/_sass/vendor/bourbon/helpers/_linear-gradient-parser.scss +51 -0
- data/docs/_sass/vendor/bourbon/helpers/_linear-positions-parser.scss +77 -0
- data/docs/_sass/vendor/bourbon/helpers/_linear-side-corner-parser.scss +41 -0
- data/docs/_sass/vendor/bourbon/helpers/_radial-arg-parser.scss +74 -0
- data/docs/_sass/vendor/bourbon/helpers/_radial-gradient-parser.scss +55 -0
- data/docs/_sass/vendor/bourbon/helpers/_radial-positions-parser.scss +28 -0
- data/docs/_sass/vendor/bourbon/helpers/_render-gradients.scss +31 -0
- data/docs/_sass/vendor/bourbon/helpers/_shape-size-stripper.scss +15 -0
- data/docs/_sass/vendor/bourbon/helpers/_str-to-num.scss +55 -0
- data/docs/_sass/vendor/bourbon/settings/_asset-pipeline.scss +7 -0
- data/docs/_sass/vendor/bourbon/settings/_deprecation-warnings.scss +8 -0
- data/docs/_sass/vendor/bourbon/settings/_prefixer.scss +9 -0
- data/docs/_sass/vendor/bourbon/settings/_px-to-em.scss +1 -0
- data/docs/_sass/vendor/neat/_neat-helpers.scss +11 -0
- data/docs/_sass/vendor/neat/_neat.scss +23 -0
- data/docs/_sass/vendor/neat/functions/_new-breakpoint.scss +49 -0
- data/docs/_sass/vendor/neat/functions/_private.scss +114 -0
- data/docs/_sass/vendor/neat/grid/_box-sizing.scss +15 -0
- data/docs/_sass/vendor/neat/grid/_direction-context.scss +33 -0
- data/docs/_sass/vendor/neat/grid/_display-context.scss +28 -0
- data/docs/_sass/vendor/neat/grid/_fill-parent.scss +22 -0
- data/docs/_sass/vendor/neat/grid/_media.scss +92 -0
- data/docs/_sass/vendor/neat/grid/_omega.scss +87 -0
- data/docs/_sass/vendor/neat/grid/_outer-container.scss +34 -0
- data/docs/_sass/vendor/neat/grid/_pad.scss +25 -0
- data/docs/_sass/vendor/neat/grid/_private.scss +35 -0
- data/docs/_sass/vendor/neat/grid/_row.scss +52 -0
- data/docs/_sass/vendor/neat/grid/_shift.scss +50 -0
- data/docs/_sass/vendor/neat/grid/_span-columns.scss +94 -0
- data/docs/_sass/vendor/neat/grid/_to-deprecate.scss +97 -0
- data/docs/_sass/vendor/neat/grid/_visual-grid.scss +42 -0
- data/docs/_sass/vendor/neat/mixins/_clearfix.scss +25 -0
- data/docs/_sass/vendor/neat/settings/_disable-warnings.scss +13 -0
- data/docs/_sass/vendor/neat/settings/_grid.scss +51 -0
- data/docs/_sass/vendor/neat/settings/_visual-grid.scss +27 -0
- data/docs/_sass/vendor/normalize-3.0.2.scss +427 -0
- data/docs/_sass/vendor/pygments.scss +356 -0
- data/docs/automating_browsers/capybara.md +70 -0
- data/docs/css/screen.scss +7 -0
- data/docs/guides/callbacks.md +45 -0
- data/docs/guides/cli.md +52 -0
- data/docs/guides/configuration.md +184 -0
- data/docs/guides/error_handling.md +46 -0
- data/docs/guides/frontiers.md +93 -0
- data/docs/guides/halting.md +23 -0
- data/docs/guides/job_queues.md +26 -0
- data/docs/guides/locals.md +36 -0
- data/docs/guides/logging.md +22 -0
- data/docs/guides/page_objects.md +67 -0
- data/docs/guides/peeking.md +46 -0
- data/docs/guides/selenium_capybara.md +100 -0
- data/docs/guides/tutorial.md +452 -0
- data/docs/index.md +82 -0
- data/docs/js/navigation.js +11 -0
- data/docs/misc/contributing.md +20 -0
- data/docs/misc/testing.md +11 -0
- data/docs/recipes/authentication.md +23 -0
- data/docs/recipes/csv.md +29 -0
- data/docs/recipes/javascript.md +20 -0
- data/docs/recipes/multiple_uris.md +18 -0
- data/docs/recipes/screenshots.md +20 -0
- data/docs/routing/custom_rules.md +16 -0
- data/docs/routing/filetypes_rules.md +21 -0
- data/docs/routing/host_rules.md +24 -0
- data/docs/routing/path_rules.md +33 -0
- data/docs/routing/protocol_rules.md +17 -0
- data/docs/routing/query_rules.md +69 -0
- data/docs/routing/routes.md +96 -0
- data/docs/routing/uri_rules.md +18 -0
- data/examples/collect_github_issues.rb +65 -0
- data/examples/find_foobar_on_wikipedia.rb +23 -0
- data/lib/wayfarer/configuration.rb +86 -0
- data/lib/wayfarer/crawl.rb +79 -0
- data/lib/wayfarer/crawl_observer.rb +103 -0
- data/lib/wayfarer/dispatcher.rb +104 -0
- data/lib/wayfarer/finders.rb +61 -0
- data/lib/wayfarer/frontiers/frontier.rb +79 -0
- data/lib/wayfarer/frontiers/memory_bloomfilter.rb +32 -0
- data/lib/wayfarer/frontiers/memory_frontier.rb +76 -0
- data/lib/wayfarer/frontiers/memory_trie_frontier.rb +39 -0
- data/lib/wayfarer/frontiers/normalize_uris.rb +48 -0
- data/lib/wayfarer/frontiers/redis_bloomfilter.rb +34 -0
- data/lib/wayfarer/frontiers/redis_frontier.rb +83 -0
- data/lib/wayfarer/http_adapters/adapter_pool.rb +62 -0
- data/lib/wayfarer/http_adapters/net_http_adapter.rb +77 -0
- data/lib/wayfarer/http_adapters/selenium_adapter.rb +80 -0
- data/lib/wayfarer/job.rb +211 -0
- data/lib/wayfarer/locals.rb +40 -0
- data/lib/wayfarer/page.rb +94 -0
- data/lib/wayfarer/parsers/json_parser.rb +20 -0
- data/lib/wayfarer/parsers/xml_parser.rb +27 -0
- data/lib/wayfarer/processor.rb +103 -0
- data/lib/wayfarer/routing/custom_rule.rb +21 -0
- data/lib/wayfarer/routing/filetypes_rule.rb +20 -0
- data/lib/wayfarer/routing/host_rule.rb +19 -0
- data/lib/wayfarer/routing/path_rule.rb +54 -0
- data/lib/wayfarer/routing/protocol_rule.rb +21 -0
- data/lib/wayfarer/routing/query_rule.rb +59 -0
- data/lib/wayfarer/routing/router.rb +71 -0
- data/lib/wayfarer/routing/rule.rb +114 -0
- data/lib/wayfarer/routing/uri_rule.rb +21 -0
- data/lib/wayfarer.rb +68 -0
- data/spec/configuration_spec.rb +26 -0
- data/spec/crawl_spec.rb +48 -0
- data/spec/finders_spec.rb +49 -0
- data/spec/frontiers/memory_bloomfilter_spec.rb +6 -0
- data/spec/frontiers/memory_frontier_spec.rb +6 -0
- data/spec/frontiers/memory_trie_frontier_spec.rb +6 -0
- data/spec/frontiers/normalize_uris_spec.rb +59 -0
- data/spec/frontiers/redis_bloomfilter_spec.rb +6 -0
- data/spec/frontiers/redis_frontier_spec.rb +6 -0
- data/spec/http_adapters/adapter_pool_spec.rb +33 -0
- data/spec/http_adapters/net_http_adapter_spec.rb +83 -0
- data/spec/http_adapters/selenium_adapter_spec.rb +53 -0
- data/spec/integration/callbacks_spec.rb +42 -0
- data/spec/integration/locals_spec.rb +106 -0
- data/spec/integration/peeking_spec.rb +61 -0
- data/spec/job_spec.rb +122 -0
- data/spec/page_spec.rb +38 -0
- data/spec/parsers/json_parser_spec.rb +30 -0
- data/spec/parsers/xml_parser_spec.rb +24 -0
- data/spec/processor_spec.rb +31 -0
- data/spec/routing/custom_rule_spec.rb +26 -0
- data/spec/routing/filetypes_rule_spec.rb +40 -0
- data/spec/routing/host_rule_spec.rb +48 -0
- data/spec/routing/path_rule_spec.rb +66 -0
- data/spec/routing/protocol_rule_spec.rb +26 -0
- data/spec/routing/query_rule_spec.rb +124 -0
- data/spec/routing/router_spec.rb +67 -0
- data/spec/routing/rule_spec.rb +251 -0
- data/spec/routing/uri_rule_spec.rb +24 -0
- data/spec/shared/frontier.rb +96 -0
- data/spec/spec_helpers.rb +62 -0
- data/spec/wayfarer_spec.rb +24 -0
- data/support/static/finders.html +38 -0
- data/support/static/graph/details/a.html +10 -0
- data/support/static/graph/details/b.html +10 -0
- data/support/static/graph/index.html +20 -0
- data/support/static/json/dummy.json +13 -0
- data/support/static/links/links.html +28 -0
- data/support/static/xml/dummy.xml +120 -0
- data/support/test_app.rb +45 -0
- data/wayfarer-jruby.gemspec +49 -0
- data/wayfarer.gemspec +53 -0
- metadata +697 -0
@@ -0,0 +1,16 @@
|
|
1
|
+
---
|
2
|
+
layout: default
|
3
|
+
title: Custom rules
|
4
|
+
---
|
5
|
+
|
6
|
+
# Custom rules
|
7
|
+
|
8
|
+
Custom rules take a block that gets yielded the URI or an object that responds to `#call(uri)`. If the block or the delegate return a truthy value, the rule matches.
|
9
|
+
|
10
|
+
{% highlight ruby %}
|
11
|
+
class DummyJob < Wayfarer::Job
|
12
|
+
route.if -> (uri) { uri.host == uri.host.reverse }
|
13
|
+
end
|
14
|
+
{% endhighlight %}
|
15
|
+
|
16
|
+
* Matches only URIs with palindrome hosts
|
@@ -0,0 +1,21 @@
|
|
1
|
+
---
|
2
|
+
layout: default
|
3
|
+
title: Filetypes rules
|
4
|
+
---
|
5
|
+
|
6
|
+
# Filetypes rules
|
7
|
+
|
8
|
+
Filetypes rules match against the URI path's file extension.
|
9
|
+
|
10
|
+
{% highlight ruby %}
|
11
|
+
class DummyJob < Wayfarer::Job
|
12
|
+
route.filetypes [:png, :jpg], to: :image
|
13
|
+
route.forbid.filetypes [:php, :js]
|
14
|
+
end
|
15
|
+
{% endhighlight %}
|
16
|
+
|
17
|
+
Matches:
|
18
|
+
|
19
|
+
* `http://example.com/foo.png`
|
20
|
+
* `http://example.com/foo.jpg`
|
21
|
+
* `https://example.com/qux/bar.jpg`
|
@@ -0,0 +1,24 @@
|
|
1
|
+
---
|
2
|
+
layout: default
|
3
|
+
title: Host rules
|
4
|
+
---
|
5
|
+
|
6
|
+
# Host rules
|
7
|
+
|
8
|
+
Host rules match against a host string or RegExp.
|
9
|
+
|
10
|
+
{% highlight ruby %}
|
11
|
+
class DummyJob < Wayfarer::Job
|
12
|
+
route.host "example.com"
|
13
|
+
route.host /example/
|
14
|
+
end
|
15
|
+
{% endhighlight %}
|
16
|
+
|
17
|
+
Matches:
|
18
|
+
|
19
|
+
* All URIs hosted on `"example.com"`.
|
20
|
+
* All URIs that contain `"example"`.
|
21
|
+
|
22
|
+
<aside class="note">
|
23
|
+
<code>"www.host.net"</code> and <code>"host.net"</code> are not considered equal. You have to specify the exact host when using strings. Consider using <code>/host.net/</code> instead.
|
24
|
+
</aside>
|
@@ -0,0 +1,33 @@
|
|
1
|
+
---
|
2
|
+
layout: default
|
3
|
+
title: Path rules
|
4
|
+
---
|
5
|
+
|
6
|
+
# Path rules
|
7
|
+
|
8
|
+
Path rules match against the path of a URI. Both strings and RegExps are accepted, and path segment pattern matching and RegExp captures are supported.
|
9
|
+
|
10
|
+
{% highlight ruby %}
|
11
|
+
class DummyJob < Wayfarer::Job
|
12
|
+
route.path "/:alpha/:beta", to: :foo
|
13
|
+
route.path /^foobar\/(.+)/, to: :bar
|
14
|
+
|
15
|
+
def foo
|
16
|
+
params[:alpha]
|
17
|
+
params[:beta]
|
18
|
+
end
|
19
|
+
|
20
|
+
def foo
|
21
|
+
params["0"]
|
22
|
+
end
|
23
|
+
end
|
24
|
+
{% endhighlight %}
|
25
|
+
|
26
|
+
Matches:
|
27
|
+
|
28
|
+
* All URIs with path segments matching `/:alpha/:beta`, e.g. `https://example.com/foo/bar`
|
29
|
+
* All URIs starting with `"/foobar/"`.
|
30
|
+
|
31
|
+
<aside class="note">
|
32
|
+
<code>/:alpha/:beta</code> and <code>:alpha/:beta</code> are not considered equal. Note the opening slash.
|
33
|
+
</aside>
|
@@ -0,0 +1,17 @@
|
|
1
|
+
---
|
2
|
+
layout: default
|
3
|
+
title: Protocol rules
|
4
|
+
---
|
5
|
+
|
6
|
+
# Protocol rules
|
7
|
+
|
8
|
+
Protocol rules match against symbols/strings.
|
9
|
+
|
10
|
+
{% highlight ruby %}
|
11
|
+
class DummyJob < Wayfarer::Job
|
12
|
+
route.protocol :https
|
13
|
+
end
|
14
|
+
{% endhighlight %}
|
15
|
+
|
16
|
+
* Matches `https://example.com`.
|
17
|
+
* Does not match `http://example.com`.
|
@@ -0,0 +1,69 @@
|
|
1
|
+
---
|
2
|
+
layout: default
|
3
|
+
title: Query rules
|
4
|
+
---
|
5
|
+
|
6
|
+
# Query rules
|
7
|
+
|
8
|
+
Query rules impose constraints on key-value query parameters. Strings, integers, RegExps and ranges are supported.
|
9
|
+
|
10
|
+
## String constraints
|
11
|
+
|
12
|
+
{% highlight ruby %}
|
13
|
+
class DummyJob < Wayfarer::Job
|
14
|
+
route.query arg: "foo"
|
15
|
+
end
|
16
|
+
{% endhighlight %}
|
17
|
+
|
18
|
+
* Matches `https://example.com?arg=foo`.
|
19
|
+
|
20
|
+
## Integer constraints
|
21
|
+
|
22
|
+
{% highlight ruby %}
|
23
|
+
class DummyJob < Wayfarer::Job
|
24
|
+
route.query arg: 42
|
25
|
+
end
|
26
|
+
{% endhighlight %}
|
27
|
+
|
28
|
+
* Matches `https://example.com?arg=42`.
|
29
|
+
|
30
|
+
---
|
31
|
+
|
32
|
+
## RegExp constraints
|
33
|
+
|
34
|
+
{% highlight ruby %}
|
35
|
+
class DummyJob < Wayfarer::Job
|
36
|
+
route.query arg: /foo/
|
37
|
+
end
|
38
|
+
{% endhighlight %}
|
39
|
+
|
40
|
+
* Matches `https://example.com?arg=foo`.
|
41
|
+
* Matches `https://example.com?arg=foobar`.
|
42
|
+
|
43
|
+
---
|
44
|
+
|
45
|
+
## Range constraints
|
46
|
+
|
47
|
+
{% highlight ruby %}
|
48
|
+
class DummyJob < Wayfarer::Job
|
49
|
+
route.query arg: 1..10
|
50
|
+
end
|
51
|
+
{% endhighlight %}
|
52
|
+
|
53
|
+
* Matches `https://example.com?arg=1`.
|
54
|
+
* Matches […]
|
55
|
+
* Matches `https://example.com?arg=10`.
|
56
|
+
|
57
|
+
---
|
58
|
+
|
59
|
+
## Compound constraints
|
60
|
+
|
61
|
+
{% highlight ruby %}
|
62
|
+
class DummyJob < Wayfarer::Job
|
63
|
+
route.query foo: 1..5, bar: /baz/, qux: "zot", toto: 2
|
64
|
+
end
|
65
|
+
{% endhighlight %}
|
66
|
+
|
67
|
+
* Matches `https://example.com?foo=4&bar=bazqux&qux=zot&toto=2`.
|
68
|
+
|
69
|
+
---
|
@@ -0,0 +1,96 @@
|
|
1
|
+
---
|
2
|
+
layout: default
|
3
|
+
title: Routes
|
4
|
+
categories: [Routing]
|
5
|
+
---
|
6
|
+
|
7
|
+
# Routes
|
8
|
+
|
9
|
+
* Routes are filters for interesting URIs.
|
10
|
+
* Routes put constraints on URIs that should get processed.
|
11
|
+
* Routes map URIs to instance methods (actions).
|
12
|
+
* Routes are tree nodes and thus nestable.
|
13
|
+
|
14
|
+
Currently, the following rules are available:
|
15
|
+
|
16
|
+
* [URI rules](uri_rules.html) match URIs against a string.
|
17
|
+
* [Host rules](/routing/host_rules.html) match hosts against strings and RegExps.
|
18
|
+
* [Path rules](/routing/path_rules.html) match paths against pattern strings and RegExps. They support path segment capturing.
|
19
|
+
* [Query rules](/routing/query_rules.html) match key-value pairs of query parameters against strings, integers, RegExps and ranges.
|
20
|
+
|
21
|
+
Routes can be fordidden. URIs that match forbidden rules are never processed.
|
22
|
+
|
23
|
+
## Route declaration
|
24
|
+
|
25
|
+
### Declaration order matching
|
26
|
+
|
27
|
+
{% highlight ruby %}
|
28
|
+
class DummyJob < Wayfarer::Job
|
29
|
+
route.host "example.com", to: :foo
|
30
|
+
route.path "/foo", to: :bar
|
31
|
+
|
32
|
+
# Is equivalent to:
|
33
|
+
#
|
34
|
+
# routes do
|
35
|
+
# host "example.com", to: :foo
|
36
|
+
# path "/foo", to: :bar
|
37
|
+
# end
|
38
|
+
end
|
39
|
+
{% endhighlight %}
|
40
|
+
|
41
|
+
* Dispatches `https://example.com/foo` to `:foo`.
|
42
|
+
* Dispatches `https://example.com` to `:foo`.
|
43
|
+
* Dispatches `https://yahoo.com/foo` to `:bar`.
|
44
|
+
|
45
|
+
---
|
46
|
+
|
47
|
+
### Nesting routes (child rules)
|
48
|
+
|
49
|
+
A route matches if it has a child rule that matches. This applies recursively.
|
50
|
+
|
51
|
+
{% highlight ruby %}
|
52
|
+
class DummyJob < Wayfarer::Job
|
53
|
+
route.host "example.com", to: :foo do
|
54
|
+
path "/foo"
|
55
|
+
end
|
56
|
+
|
57
|
+
# Is equivalent to:
|
58
|
+
#
|
59
|
+
# route.host "example.com", path: "/foo", to: :foo
|
60
|
+
# route.path "/foo", host: "example.com", to: :foo
|
61
|
+
end
|
62
|
+
{% endhighlight %}
|
63
|
+
|
64
|
+
* Dispatches `https://example.com/foo` to `:foo`.
|
65
|
+
* Does not dispatch `https://example.com`.
|
66
|
+
* Does not dispatch `https://yahoo.com/foo`.
|
67
|
+
|
68
|
+
---
|
69
|
+
|
70
|
+
### Deepest routes override actions
|
71
|
+
|
72
|
+
{% highlight ruby %}
|
73
|
+
class DummyJob < Wayfarer::Job
|
74
|
+
route.host "example.com", to: :foo do
|
75
|
+
path "/foo", to: :bar
|
76
|
+
end
|
77
|
+
end
|
78
|
+
{% endhighlight %}
|
79
|
+
|
80
|
+
* Dispatches `https://example.com/foo` to `:bar`.
|
81
|
+
* Does not dispatch `https://example.com`.
|
82
|
+
* Does not dispatch `https://yahoo.com/foo`.
|
83
|
+
|
84
|
+
---
|
85
|
+
|
86
|
+
### Forbidding rules
|
87
|
+
|
88
|
+
{% highlight ruby %}
|
89
|
+
class DummyJob < Wayfarer::Job
|
90
|
+
route.forbid.path "/foo"
|
91
|
+
route.host "example.com", to: :foo
|
92
|
+
end
|
93
|
+
{% endhighlight %}
|
94
|
+
|
95
|
+
* Dispatches `https://example.com` to `:bar`.
|
96
|
+
* Does not dispatch `https://example.com/foo`.
|
@@ -0,0 +1,18 @@
|
|
1
|
+
---
|
2
|
+
layout: default
|
3
|
+
title: URI Rules
|
4
|
+
---
|
5
|
+
|
6
|
+
# URI rules
|
7
|
+
|
8
|
+
URI rules match against a string.
|
9
|
+
|
10
|
+
{% highlight ruby %}
|
11
|
+
class DummyJob < Wayfarer::Job
|
12
|
+
route.uri "https://example.com"
|
13
|
+
end
|
14
|
+
{% endhighlight %}
|
15
|
+
|
16
|
+
Matches:
|
17
|
+
|
18
|
+
* Only `https://example.com`
|
@@ -0,0 +1,65 @@
|
|
1
|
+
require_relative "../lib/wayfarer"
|
2
|
+
|
3
|
+
class CollectGithubIssues < Wayfarer::Job
|
4
|
+
config.connection_count = 4
|
5
|
+
config.logger.level = :fatal
|
6
|
+
|
7
|
+
let(:records) { [] }
|
8
|
+
|
9
|
+
routes do
|
10
|
+
host "github.com" do
|
11
|
+
path "/:user/:repo", to: :repository
|
12
|
+
path "/:user/:repo/issues", to: :index
|
13
|
+
path "/:user/:repo/issues/:id", to: :show
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
after_crawl do
|
18
|
+
records.each do |issue|
|
19
|
+
# Save them somewhere?
|
20
|
+
puts issue
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def repository
|
25
|
+
stage navigation_links
|
26
|
+
end
|
27
|
+
|
28
|
+
def index
|
29
|
+
stage issue_listing_links, next_page
|
30
|
+
end
|
31
|
+
|
32
|
+
def show
|
33
|
+
return halt if records.count > 30
|
34
|
+
|
35
|
+
records << {
|
36
|
+
id: params[:id],
|
37
|
+
title: issue_title,
|
38
|
+
author: issue_author
|
39
|
+
}
|
40
|
+
end
|
41
|
+
|
42
|
+
private
|
43
|
+
|
44
|
+
def issue_title
|
45
|
+
doc.css(".js-issue-title").text.strip
|
46
|
+
end
|
47
|
+
|
48
|
+
def issue_author
|
49
|
+
doc.css(".TableObject-item .author").text.strip
|
50
|
+
end
|
51
|
+
|
52
|
+
def navigation_links
|
53
|
+
page.links ".reponav-item"
|
54
|
+
end
|
55
|
+
|
56
|
+
def issue_listing_links
|
57
|
+
page.links ".issues-listing"
|
58
|
+
end
|
59
|
+
|
60
|
+
def next_page
|
61
|
+
page.links ".next_page"
|
62
|
+
end
|
63
|
+
end
|
64
|
+
|
65
|
+
CollectGithubIssues.perform_now("https://github.com/rails/rails")
|
@@ -0,0 +1,23 @@
|
|
1
|
+
require_relative "../lib/wayfarer"
|
2
|
+
|
3
|
+
class FindFoobarOnWikipedia < Wayfarer::Job
|
4
|
+
config.http_adapter = :selenium
|
5
|
+
config.selenium_argv = [:chrome]
|
6
|
+
config.connection_count = 4
|
7
|
+
|
8
|
+
let(:keywords) { [] }
|
9
|
+
|
10
|
+
route.host "en.wikipedia.org", to: :article
|
11
|
+
|
12
|
+
def article
|
13
|
+
if page.body =~ /Foobar/
|
14
|
+
driver.save_screenshot("/tmp/foobar.png")
|
15
|
+
return halt
|
16
|
+
end
|
17
|
+
|
18
|
+
keywords << page.keywords
|
19
|
+
stage page.links
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
FindFoobarOnWikipedia.perform_now("https://en.wikipedia.org/wiki/Special:Random")
|
@@ -0,0 +1,86 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "ostruct"
|
4
|
+
require "securerandom"
|
5
|
+
require "forwardable"
|
6
|
+
|
7
|
+
module Wayfarer
|
8
|
+
class Configuration < OpenStruct
|
9
|
+
extend Forwardable
|
10
|
+
|
11
|
+
DEFAULTS = {
|
12
|
+
# Print full stacktraces?
|
13
|
+
print_stacktraces: true,
|
14
|
+
|
15
|
+
# Crash when encountering unhandled exceptions?
|
16
|
+
reraise_exceptions: false,
|
17
|
+
|
18
|
+
# Allow processing URIs multiple times?
|
19
|
+
allow_circulation: false,
|
20
|
+
|
21
|
+
# How many HTTP connections/Selenium drivers to use
|
22
|
+
# 1:1 correspondence with spawned threads
|
23
|
+
connection_count: 1,
|
24
|
+
|
25
|
+
# Which HTTP adapter to use. Supported are :net_http and :selenium
|
26
|
+
http_adapter: :net_http,
|
27
|
+
|
28
|
+
# Which frontier to use.
|
29
|
+
frontier: :memory,
|
30
|
+
|
31
|
+
# How long a thread may hold an HTTP adapter.
|
32
|
+
# Threads that exceed this limit fail with an exception.
|
33
|
+
connection_timeout: Float::INFINITY,
|
34
|
+
|
35
|
+
# How many 3xx redirects to follow. Has no effect when using Selenium
|
36
|
+
max_http_redirects: 3,
|
37
|
+
|
38
|
+
# Argument vector for instantiating Selenium drivers
|
39
|
+
selenium_argv: [:firefox],
|
40
|
+
|
41
|
+
# Argument vector for instantiating a Redis connection
|
42
|
+
redis_opts: {
|
43
|
+
host: "localhost",
|
44
|
+
port: 6379
|
45
|
+
}.freeze,
|
46
|
+
|
47
|
+
# Size of browser windows
|
48
|
+
window_size: [1024, 768],
|
49
|
+
|
50
|
+
# Which Mustermann pattern type to use when matching URI paths
|
51
|
+
# TODO: Mention in docs
|
52
|
+
mustermann_type: :sinatra,
|
53
|
+
|
54
|
+
# Options for instantiating Bloomfilters
|
55
|
+
bloomfilter_opts: {
|
56
|
+
size: 100,
|
57
|
+
hashes: 2,
|
58
|
+
seed: 1,
|
59
|
+
bucket: 3,
|
60
|
+
raise: false
|
61
|
+
},
|
62
|
+
|
63
|
+
# Whether to normalize URIs
|
64
|
+
normalize_uris: true,
|
65
|
+
|
66
|
+
# URI normalization options
|
67
|
+
# See: https://github.com/rwz/normalize_url
|
68
|
+
normalize_uri_options: {}
|
69
|
+
}.freeze
|
70
|
+
|
71
|
+
attr_reader :uuid
|
72
|
+
|
73
|
+
def initialize(overrides = {})
|
74
|
+
super(DEFAULTS.merge(overrides))
|
75
|
+
@uuid = SecureRandom.uuid
|
76
|
+
end
|
77
|
+
|
78
|
+
def logger
|
79
|
+
@logger ||= Wayfarer.logger.dup
|
80
|
+
end
|
81
|
+
|
82
|
+
def reset!
|
83
|
+
DEFAULTS.each { |key, val| self[key] = val }
|
84
|
+
end
|
85
|
+
end
|
86
|
+
end
|
@@ -0,0 +1,79 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "observer"
|
4
|
+
require "normalize_url"
|
5
|
+
|
6
|
+
module Wayfarer
|
7
|
+
class Crawl
|
8
|
+
extend Forwardable
|
9
|
+
include Observable
|
10
|
+
|
11
|
+
# The prepared job.
|
12
|
+
# @!attribute [r] job
|
13
|
+
attr_reader :job
|
14
|
+
|
15
|
+
# @!attribute [r] dispatcher
|
16
|
+
attr_reader :dispatcher
|
17
|
+
|
18
|
+
delegate config: :job
|
19
|
+
delegate logger: :config
|
20
|
+
|
21
|
+
def initialize(job, *uris)
|
22
|
+
@job = job.prepare
|
23
|
+
@uris = uris
|
24
|
+
@dispatcher = Dispatcher.new(@job)
|
25
|
+
@processor = Processor.new(@job, frontier, @dispatcher)
|
26
|
+
end
|
27
|
+
|
28
|
+
def execute
|
29
|
+
trap_signals
|
30
|
+
|
31
|
+
CrawlObserver.new(@processor, @dispatcher, config.logger)
|
32
|
+
|
33
|
+
@job.run_hook(:before_crawl)
|
34
|
+
@processor.run(*@uris)
|
35
|
+
@job.run_hook(:after_crawl)
|
36
|
+
ensure
|
37
|
+
untrap_signals
|
38
|
+
end
|
39
|
+
|
40
|
+
# A frontier with initially pre-staged URIs.
|
41
|
+
# @return [Frontier]
|
42
|
+
def frontier
|
43
|
+
return @frontier if @frontier
|
44
|
+
|
45
|
+
@frontier = case config.frontier
|
46
|
+
when :memory_trie
|
47
|
+
Frontiers::MemoryTrieFrontier.new(config)
|
48
|
+
when :redis
|
49
|
+
Frontiers::RedisFrontier.new(config)
|
50
|
+
when :memory_bloom
|
51
|
+
Frontiers::MemoryBloomfilter.new(config)
|
52
|
+
when :redis_bloom
|
53
|
+
Frontiers::RedisBloomfilter.new(config)
|
54
|
+
else
|
55
|
+
Frontiers::MemoryFrontier.new(config)
|
56
|
+
end
|
57
|
+
|
58
|
+
@frontier.extend(Frontiers::NormalizeURIs) if config.normalize_uris
|
59
|
+
|
60
|
+
@frontier.stage(*@uris) # TODO: Test
|
61
|
+
|
62
|
+
@frontier
|
63
|
+
end
|
64
|
+
|
65
|
+
private
|
66
|
+
|
67
|
+
def trap_signals
|
68
|
+
@cached_sigint_handler = trap(:INT) {
|
69
|
+
halt!
|
70
|
+
@cached_sigint_handler.try(:call)
|
71
|
+
exit(-1)
|
72
|
+
}
|
73
|
+
end
|
74
|
+
|
75
|
+
def untrap_signals
|
76
|
+
trap(:INT) { @cached_sigint_handler.try(:call) }
|
77
|
+
end
|
78
|
+
end
|
79
|
+
end
|
@@ -0,0 +1,103 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
class CrawlObserver
|
5
|
+
module Events
|
6
|
+
FirstCycle = Struct.new(:frontier)
|
7
|
+
NewCycle = Struct.new(:current_uris_count)
|
8
|
+
DispatchedURI = Struct.new(:action, :uri)
|
9
|
+
CycleFinished = Class.new
|
10
|
+
Peeking = Struct.new(:uri)
|
11
|
+
AboutToCycle = Struct.new(:staged_uris_count)
|
12
|
+
MismatchedURI = Struct.new(:uri)
|
13
|
+
HaltInitiated = Struct.new(:action, :uri)
|
14
|
+
StagingURIs = Struct.new(:staged_uris_count)
|
15
|
+
UnhandledError = Struct.new(:exception)
|
16
|
+
end
|
17
|
+
|
18
|
+
module ObservableShortcuts
|
19
|
+
def notify_observers!(*argv)
|
20
|
+
changed
|
21
|
+
notify_observers(*argv)
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
extend Forwardable
|
26
|
+
|
27
|
+
attr_reader :logger
|
28
|
+
|
29
|
+
def initialize(*observables, logger)
|
30
|
+
@logger = logger
|
31
|
+
observables.each { |obsv| obsv.add_observer(self) }
|
32
|
+
end
|
33
|
+
|
34
|
+
def update(event)
|
35
|
+
case event
|
36
|
+
when Events::FirstCycle then first_cycle(event)
|
37
|
+
when Events::NewCycle then new_cycle(event)
|
38
|
+
when Events::DispatchedURI then dispatched_uri(event)
|
39
|
+
when Events::CycleFinished then cycle_finished
|
40
|
+
when Events::Peeking then peeking(event)
|
41
|
+
when Events::AboutToCycle then about_to_cycle(event)
|
42
|
+
when Events::MismatchedURI then mismatched_uri(event)
|
43
|
+
when Events::HaltInitiated then halt_initiated(event)
|
44
|
+
when Events::StagingURIs then staging_uris(event)
|
45
|
+
when Events::UnhandledError then unhandled_error(event)
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
private
|
50
|
+
|
51
|
+
def first_cycle(event)
|
52
|
+
logger.info("First cycle")
|
53
|
+
logger.info("Frontier: #{event.frontier}")
|
54
|
+
end
|
55
|
+
|
56
|
+
def new_cycle(event)
|
57
|
+
logger.info("Current cycle contains #{event.current_uris_count} URI(s)")
|
58
|
+
end
|
59
|
+
|
60
|
+
def dispatched_uri(event)
|
61
|
+
logger.info("Dispatched to \##{event.action}: #{event.uri}")
|
62
|
+
end
|
63
|
+
|
64
|
+
def cycle_finished
|
65
|
+
logger.info("No URIs left in current cycle")
|
66
|
+
end
|
67
|
+
|
68
|
+
def peeking(event)
|
69
|
+
logger.info("Peeking into: #{event.uri}")
|
70
|
+
end
|
71
|
+
|
72
|
+
def about_to_cycle(event)
|
73
|
+
logger.info("About to cycle. #{event.staged_uris_count} staged URI(s)")
|
74
|
+
end
|
75
|
+
|
76
|
+
def mismatched_uri(event)
|
77
|
+
logger.debug("No matching route for: #{event.uri}")
|
78
|
+
end
|
79
|
+
|
80
|
+
def halt_initiated(event)
|
81
|
+
logger.info("Halt initiated from \##{event.action} at: #{event.uri}")
|
82
|
+
end
|
83
|
+
|
84
|
+
def staging_uris(event)
|
85
|
+
logger.info("Staging #{event.staged_uris_count} URI(s)")
|
86
|
+
end
|
87
|
+
|
88
|
+
def unhandled_error(event)
|
89
|
+
level = config.reraise_exceptions ? :fatal : :error
|
90
|
+
|
91
|
+
if config.print_stacktraces
|
92
|
+
logger.public_send level, <<~LOGGER
|
93
|
+
Unhandled exception in an action: #{event.exception.class.inspect}
|
94
|
+
#{event.exception.backtrace.map(&:to_s).join("\n* ")}
|
95
|
+
LOGGER
|
96
|
+
else
|
97
|
+
logger.public_send level, <<~LOGGER
|
98
|
+
Unhandled exception in an action: #{event.exception.class.inspect}
|
99
|
+
LOGGER
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|
103
|
+
end
|