tanakai 1.6.0 → 1.7.0
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 +4 -4
- data/.gitignore +1 -0
- data/CHANGELOG.md +15 -5
- data/README.md +6 -0
- data/lib/tanakai/base.rb +5 -5
- data/lib/tanakai/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a544dd8c9d448beccd646a4a536a5597bd9e6348717c4f8103f708798fbc21c5
|
4
|
+
data.tar.gz: '093f88b3185e3999f4bed6b6c9df472a1d7c32c4f1e95e044bd313ec4e444f50'
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0bf1db16739720f015902830f588a3a463331b6d36d241fdd0d397bd1d8cb2e8ef921bf8d10a552016b7b2e43e415f938b974001e63a347a8feec9bb8b9b270f
|
7
|
+
data.tar.gz: c080531acf9b98fb00c94ca994c3e32281c5eada7a38d15175a481f55e4b8cbe11b707950a9674fdfd09909b6ded2ece608f753b5fb5fb919ae79b6810c97547
|
data/.gitignore
CHANGED
data/CHANGELOG.md
CHANGED
@@ -1,18 +1,28 @@
|
|
1
1
|
# CHANGELOG
|
2
2
|
|
3
|
+
## Next
|
4
|
+
* Your contribution here
|
5
|
+
|
6
|
+
## 1.7.0
|
7
|
+
### New
|
8
|
+
* Allow passing `data:` to `crawl!` - [glaucocustodio](https://github.com/glaucocustodio)
|
9
|
+
|
10
|
+
### Fixes
|
11
|
+
* [#4](https://github.com/glaucocustodio/tanakai/pull/4): Fix keyword args on `crawl!` - [milk1000cc](https://github.com/milk1000cc)
|
12
|
+
|
3
13
|
## 1.6.0
|
4
14
|
### New
|
5
|
-
* Add support to Ruby 3
|
15
|
+
* Add support to Ruby 3 - [glaucocustodio](https://github.com/glaucocustodio)
|
6
16
|
|
7
17
|
## 1.5.1
|
8
18
|
### New
|
9
|
-
* Add `response_type` to `in_parallel`
|
19
|
+
* Add `response_type` to `in_parallel` - [glaucocustodio](https://github.com/glaucocustodio)
|
10
20
|
|
11
21
|
## 1.5.0
|
12
22
|
### New
|
13
|
-
* First release as Tanakai
|
14
|
-
* Add support to [Apparition](https://github.com/twalpole/apparition)
|
15
|
-
* Add support to [Cuprite](https://github.com/rubycdp/cuprite)
|
23
|
+
* First release as Tanakai - [glaucocustodio](https://github.com/glaucocustodio)
|
24
|
+
* Add support to [Apparition](https://github.com/twalpole/apparition) - [glaucocustodio](https://github.com/glaucocustodio)
|
25
|
+
* Add support to [Cuprite](https://github.com/rubycdp/cuprite) - [glaucocustodio](https://github.com/glaucocustodio)
|
16
26
|
|
17
27
|
## 1.4.0
|
18
28
|
### New
|
data/README.md
CHANGED
@@ -1355,6 +1355,12 @@ end # =>
|
|
1355
1355
|
# {:spider_name=>"example_spider", :status=>:completed, :environment=>"development", :start_time=>2018-08-22 18:49:22 +0400, :stop_time=>2018-08-22 18:49:23 +0400, :running_time=>0.801, :visits=>{:requests=>1, :responses=>1}, :items=>{:sent=>0, :processed=>0}, :error=>nil}
|
1356
1356
|
```
|
1357
1357
|
|
1358
|
+
You can also pass `data` to `crawl!`:
|
1359
|
+
|
1360
|
+
```ruby
|
1361
|
+
ExampleSpider.crawl!(data: { foo: "bar" })
|
1362
|
+
```
|
1363
|
+
|
1358
1364
|
So what if you're don't care about stats and just want to process request to a particular spider method and get the returning value from this method? Use `.parse!` instead:
|
1359
1365
|
|
1360
1366
|
#### `.parse!(:method_name, url:)` method
|
data/lib/tanakai/base.rb
CHANGED
@@ -100,7 +100,7 @@ module Tanakai
|
|
100
100
|
end
|
101
101
|
end
|
102
102
|
|
103
|
-
def self.crawl!(exception_on_fail: true)
|
103
|
+
def self.crawl!(exception_on_fail: true, data: {})
|
104
104
|
logger.error "Spider: already running: #{name}" and return false if running?
|
105
105
|
|
106
106
|
@storage = Storage.new
|
@@ -124,13 +124,13 @@ module Tanakai
|
|
124
124
|
if start_urls
|
125
125
|
start_urls.each do |start_url|
|
126
126
|
if start_url.class == Hash
|
127
|
-
spider.request_to(:parse, start_url)
|
127
|
+
spider.request_to(:parse, url: start_url, data: data)
|
128
128
|
else
|
129
|
-
spider.request_to(:parse, url: start_url)
|
129
|
+
spider.request_to(:parse, url: start_url, data: data)
|
130
130
|
end
|
131
131
|
end
|
132
132
|
else
|
133
|
-
spider.parse
|
133
|
+
spider.parse(data: data)
|
134
134
|
end
|
135
135
|
rescue StandardError, SignalException, SystemExit => e
|
136
136
|
@run_info.merge!(status: :failed, error: e.inspect)
|
@@ -160,7 +160,7 @@ module Tanakai
|
|
160
160
|
if args.present?
|
161
161
|
spider.public_send(handler, *args)
|
162
162
|
elsif request.present?
|
163
|
-
spider.request_to(handler, request)
|
163
|
+
spider.request_to(handler, **request)
|
164
164
|
else
|
165
165
|
spider.public_send(handler)
|
166
166
|
end
|
data/lib/tanakai/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: tanakai
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.7.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Victor Afanasev
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: exe
|
11
11
|
cert_chain: []
|
12
|
-
date: 2023-
|
12
|
+
date: 2023-10-25 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: thor
|