datahen 0.15.11 → 0.16.0
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/lib/datahen/cli/scraper.rb +3 -0
- data/lib/datahen/cli/scraper_job.rb +1 -0
- data/lib/datahen/cli/scraper_page.rb +2 -0
- data/lib/datahen/client/job.rb +1 -0
- data/lib/datahen/client/job_page.rb +2 -0
- data/lib/datahen/client/scraper.rb +2 -0
- data/lib/datahen/client/scraper_job.rb +2 -0
- data/lib/datahen/version.rb +1 -1
- metadata +5 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 39397d5cb4e60a6d24cdec5bd979f543a23019b7c9b9dffe6140a204d330465c
|
4
|
+
data.tar.gz: 1db7c2b448179c2bc4b56e99428dfb4303cbb1451df032ec43cb5264f58935ec
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 7058506211d537c8ea3c9a521625fd339b255f41188a70341cc04683ca1abc1fa7f19ed796026b5e07679bb2fd7e57f096d319fbe8a75ae6fb7fd59a704a9824
|
7
|
+
data.tar.gz: b8b60607cd27acbd654afe0816b0b7738871ca61c370fbafa747985d3723fec64f9b07c6078b34c1192db1d7b160682522a4901a7047c3d067860bc2b745b0b0
|
data/lib/datahen/cli/scraper.rb
CHANGED
@@ -32,6 +32,7 @@ module Datahen
|
|
32
32
|
option :profile, type: :string, desc: 'Set the profiles (comma separated) to apply to the job. Default: default'
|
33
33
|
option :multiple_jobs, type: :boolean, desc: 'Set true to enable multiple jobs. Default: false'
|
34
34
|
option :max_job_count, type: :numeric, desc: 'Set a value to set max number of jobs available. Set -1 for unlimited. Default: 3'
|
35
|
+
option :max_page_size, type: :numeric, desc: 'Set a value to set max page size when fetching a page. Set a value grather than 0 to set it as limit, 0 means any size. Default: 0'
|
35
36
|
def create(scraper_name, git_repository)
|
36
37
|
# puts "options #{options}"
|
37
38
|
client = Client::Scraper.new(options)
|
@@ -57,6 +58,7 @@ module Datahen
|
|
57
58
|
option :profile, type: :string, desc: 'Set the profiles (comma separated) to apply to the job. Default: default'
|
58
59
|
option :multiple_jobs, type: :boolean, desc: 'Set true to enable multiple jobs. Default: false'
|
59
60
|
option :max_job_count, type: :numeric, desc: 'Set a value to set max number of jobs available. Set -1 for unlimited. Default: 3'
|
61
|
+
option :max_page_size, type: :numeric, desc: 'Set a value to set max page size when fetching a page. Set a value grather than 0 to set it as limit, 0 means any size. Default: 0'
|
60
62
|
def update(scraper_name)
|
61
63
|
client = Client::Scraper.new(options)
|
62
64
|
puts "#{client.update(scraper_name, options)}"
|
@@ -94,6 +96,7 @@ module Datahen
|
|
94
96
|
option :browsers, type: :numeric, desc: 'Set how many browser workers to use. Default: 0'
|
95
97
|
option :proxy_type, desc: 'Set the Proxy type. Default: standard'
|
96
98
|
option :vars, type: :string, banner: :JSON, desc: 'Set input vars. Must be in json format. i.e: [{"name":"foo", "value":"bar", "secret":false}] '
|
99
|
+
option :max_page_size, type: :numeric, desc: 'Set a value to set max page size when fetching a page. Set a value grather than 0 to set it as limit, 0 means any size. Default: 0'
|
97
100
|
def start(scraper_name)
|
98
101
|
client = Client::ScraperJob.new(options)
|
99
102
|
puts "Starting a scrape job..."
|
@@ -104,6 +104,7 @@ module Datahen
|
|
104
104
|
option :proxy_type, desc: 'Set the Proxy type. Default: standard'
|
105
105
|
option :profile, type: :string, desc: 'Set the profiles (comma separated) to apply to the job. Default: default'
|
106
106
|
option :job, :aliases => :j, type: :numeric, desc: 'Set a specific job ID'
|
107
|
+
option :max_page_size, type: :numeric, desc: 'Set a value to set max page size when fetching a page. Set a value grather than 0 to set it as limit, 0 means any size. Default: 0'
|
107
108
|
def update(scraper_name)
|
108
109
|
if options[:job]
|
109
110
|
client = Client::Job.new(options)
|
@@ -45,6 +45,7 @@ module Datahen
|
|
45
45
|
option :freshness, :aliases => :s, desc: 'Set how fresh the page cache is. Accepts timestap format.'
|
46
46
|
option :ua_type, :aliases => :u, desc: 'Set user agent type. Default: desktop'
|
47
47
|
option :no_redirect, :aliases => :n, type: :boolean, desc: 'Set true to not follow redirect. Default: false'
|
48
|
+
option :max_size, type: :numeric, desc: 'Set a value to set max page size when fetching a page. Set a value grather than 0 to set it as limit, 0 means any size. Default: 0'
|
48
49
|
def add(scraper_name, url)
|
49
50
|
begin
|
50
51
|
options[:headers] = JSON.parse(options[:headers]) if options[:headers]
|
@@ -78,6 +79,7 @@ module Datahen
|
|
78
79
|
option :page_type, :aliases => :t, desc: 'Set page type'
|
79
80
|
option :priority, type: :numeric, desc: 'Set fetch priority. The higher the value, the sooner the page gets fetched. Default: 0'
|
80
81
|
option :vars, :aliases => :v, type: :string, desc: 'Set user-defined page variables. Must be in json format. i.e: {"Foo":"bar"}'
|
82
|
+
option :max_size, type: :numeric, desc: 'Set a value to set max page size when fetching a page. Set a value grather than 0 to set it as limit, 0 means any size. Default: 0'
|
81
83
|
def update(scraper_name, gid)
|
82
84
|
begin
|
83
85
|
options[:vars] = JSON.parse(options[:vars]) if options[:vars]
|
data/lib/datahen/client/job.rb
CHANGED
@@ -21,6 +21,7 @@ module Datahen
|
|
21
21
|
body[:browser_worker_count] = opts[:browsers] if opts[:browsers]
|
22
22
|
body[:proxy_type] = opts[:proxy_type] if opts[:proxy_type]
|
23
23
|
body[:profile] = opts[:profile] if opts[:profile]
|
24
|
+
body[:max_page_size] = opts[:max_page_size] if opts[:max_page_size]
|
24
25
|
params = @options.merge({body: body.to_json})
|
25
26
|
|
26
27
|
self.class.put("/jobs/#{job_id}", params)
|
@@ -15,6 +15,7 @@ module Datahen
|
|
15
15
|
body[:page_type] = opts[:page_type] if opts[:page_type]
|
16
16
|
body[:priority] = opts[:priority] if opts[:priority]
|
17
17
|
body[:vars] = opts[:vars] if opts[:vars]
|
18
|
+
body[:max_size] = opts[:max_size] if opts[:max_size]
|
18
19
|
|
19
20
|
params = @options.merge({body: body.to_json})
|
20
21
|
|
@@ -36,6 +37,7 @@ module Datahen
|
|
36
37
|
body[:ua_type] = opts[:ua_type] if opts[:ua_type]
|
37
38
|
body[:no_redirect] = opts[:no_redirect] if opts[:no_redirect]
|
38
39
|
body[:cookie] = opts[:cookie] if opts[:cookie]
|
40
|
+
body[:max_size] = opts[:max_size] if opts[:max_size]
|
39
41
|
|
40
42
|
params = @options.merge({body: body.to_json})
|
41
43
|
|
@@ -28,6 +28,7 @@ module Datahen
|
|
28
28
|
body[:profile] = opts[:profile] if opts[:profile]
|
29
29
|
body[:multiple_jobs] = opts[:multiple_jobs] if opts[:multiple_jobs]
|
30
30
|
body[:max_job_count] = opts[:max_job_count] if opts[:max_job_count]
|
31
|
+
body[:max_page_size] = opts[:max_page_size] if opts[:max_page_size]
|
31
32
|
params = @options.merge({body: body.to_json})
|
32
33
|
self.class.post("/scrapers", params)
|
33
34
|
end
|
@@ -49,6 +50,7 @@ module Datahen
|
|
49
50
|
body[:profile] = opts[:profile] if opts[:profile]
|
50
51
|
body[:multiple_jobs] = opts[:multiple_jobs] if opts.has_key?("multiple_jobs") || opts.has_key?(:multiple_jobs)
|
51
52
|
body[:max_job_count] = opts[:max_job_count] if opts.has_key?("max_job_count") || opts.has_key?(:max_job_count)
|
53
|
+
body[:max_page_size] = opts[:max_page_size] if opts.has_key?("max_page_size") || opts.has_key?(:max_page_size)
|
52
54
|
params = @options.merge({body: body.to_json})
|
53
55
|
|
54
56
|
self.class.put("/scrapers/#{scraper_name}", params)
|
@@ -11,6 +11,7 @@ module Datahen
|
|
11
11
|
body[:standard_worker_count] = opts[:workers] if opts[:workers]
|
12
12
|
body[:browser_worker_count] = opts[:browsers] if opts[:browsers]
|
13
13
|
body[:proxy_type] = opts[:proxy_type] if opts[:proxy_type]
|
14
|
+
body[:max_page_size] = opts[:max_page_size] if opts[:max_page_size]
|
14
15
|
if opts[:vars]
|
15
16
|
if opts[:vars].is_a?(Array)
|
16
17
|
body[:vars] = opts[:vars]
|
@@ -37,6 +38,7 @@ module Datahen
|
|
37
38
|
body[:browser_worker_count] = opts[:browsers] if opts[:browsers]
|
38
39
|
body[:proxy_type] = opts[:proxy_type] if opts[:proxy_type]
|
39
40
|
body[:profile] = opts[:profile] if opts[:profile]
|
41
|
+
body[:max_page_size] = opts[:max_page_size] if opts[:max_page_size]
|
40
42
|
params = @options.merge({body: body.to_json})
|
41
43
|
|
42
44
|
self.class.put("/scrapers/#{scraper_name}/current_job", params)
|
data/lib/datahen/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: datahen
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.16.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Parama Danoesubroto
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2021-
|
11
|
+
date: 2021-07-22 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: thor
|
@@ -276,7 +276,7 @@ metadata:
|
|
276
276
|
allowed_push_host: https://rubygems.org
|
277
277
|
homepage_uri: https://datahen.com
|
278
278
|
source_code_uri: https://github.com/DataHenOfficial/datahen-ruby
|
279
|
-
post_install_message:
|
279
|
+
post_install_message:
|
280
280
|
rdoc_options: []
|
281
281
|
require_paths:
|
282
282
|
- lib
|
@@ -292,7 +292,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
292
292
|
version: '0'
|
293
293
|
requirements: []
|
294
294
|
rubygems_version: 3.0.3
|
295
|
-
signing_key:
|
295
|
+
signing_key:
|
296
296
|
specification_version: 4
|
297
297
|
summary: DataHen toolbelt for developers
|
298
298
|
test_files: []
|