datahen 0.20.0 → 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/datahen/cli/scraper.rb +9 -6
- data/lib/datahen/cli/scraper_job.rb +3 -2
- data/lib/datahen/client/job.rb +2 -1
- data/lib/datahen/client/scraper.rb +4 -2
- data/lib/datahen/client/scraper_job.rb +4 -2
- data/lib/datahen/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: ea12b1c12b5a5db4a650b35869de91b9b2ccc8c0c5b4e35da904fc77bfee5ebc
|
4
|
+
data.tar.gz: bd96345cc669816cc281d76065cf64d150268aa8f14659e6395796d2aebd52ec
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 763c11bb6d96fdd92c8d2eb8c7965729b3812dbc0dfa9abb47151a61175f695870369d98cac0663ebdf2c644eda028833be313fb8e7924a353f82049c6430c22
|
7
|
+
data.tar.gz: 43e074b6acde5a0367fc11f74c0a3dab0c7e1aecfc781c1e927c8e55bb6e367701ec0dcec2aa90d63c988eca16af90577a63e5f8191a5c7c055e9d0fb9e5bbea
|
data/lib/datahen/cli/scraper.rb
CHANGED
@@ -24,8 +24,9 @@ module Datahen
|
|
24
24
|
option :freshness_type, :aliases => :t, desc: 'Set how fresh the page cache is. Possible values: day, week, month, year. Default: any'
|
25
25
|
option :proxy_type, desc: 'Set the Proxy type. Default: standard'
|
26
26
|
option :force_fetch, :aliases => :f, type: :boolean, desc: 'Set true to force fetch page that is not within freshness criteria. Default: false'
|
27
|
-
option :
|
28
|
-
option :
|
27
|
+
option :parsers, :aliases => :pw, type: :numeric, desc: 'Set how many parser workers to use. Default: 1'
|
28
|
+
option :fetchers, :aliases => :fw, type: :numeric, desc: 'Set how many fetcher workers to use. Default: 1'
|
29
|
+
option :browsers, :aliases => :bw, type: :numeric, desc: 'Set how many browser workers to use. Default: 0'
|
29
30
|
option :disable_scheduler, type: :boolean, desc: 'Set true to disable scheduler. Default: false'
|
30
31
|
option :cancel_current_job, type: :boolean, desc: 'Set true to cancel currently active job if scheduler starts. Default: false'
|
31
32
|
option :schedule, type: :string, desc: 'Set the schedule of the scraper to run. Must be in CRON format.'
|
@@ -52,8 +53,9 @@ module Datahen
|
|
52
53
|
option :freshness_type, :aliases => :t, desc: 'Set how fresh the page cache is. Possible values: day, week, month, year. Default: any'
|
53
54
|
option :proxy_type, desc: 'Set the Proxy type. Default: standard'
|
54
55
|
option :force_fetch, :aliases => :f, type: :boolean, desc: 'Set true to force fetch page that is not within freshness criteria. Default: false'
|
55
|
-
option :
|
56
|
-
option :
|
56
|
+
option :parsers, :aliases => :pw, type: :numeric, desc: 'Set how many parser workers to use. Default: 1'
|
57
|
+
option :fetchers, :aliases => :fw, type: :numeric, desc: 'Set how many fetcher workers to use. Default: 1'
|
58
|
+
option :browsers, :aliases => :bw, type: :numeric, desc: 'Set how many browser workers to use. Default: 0'
|
57
59
|
option :disable_scheduler, type: :boolean, desc: 'Set true to disable scheduler. Default: false'
|
58
60
|
option :cancel_current_job, type: :boolean, desc: 'Set true to cancel currently active job if scheduler starts. Default: false'
|
59
61
|
option :schedule, type: :string, desc: 'Set the schedule of the scraper to run. Must be in CRON format.'
|
@@ -97,8 +99,9 @@ module Datahen
|
|
97
99
|
long_desc <<-LONGDESC
|
98
100
|
Starts a scraper by creating an active scrape job\x5
|
99
101
|
LONGDESC
|
100
|
-
option :
|
101
|
-
option :
|
102
|
+
option :parsers, :aliases => :pw, type: :numeric, desc: 'Set how many parser workers to use. Default: 1'
|
103
|
+
option :fetchers, :aliases => :fw, type: :numeric, desc: 'Set how many fetcher workers to use. Default: 1'
|
104
|
+
option :browsers, :aliases => :bw, type: :numeric, desc: 'Set how many browser workers to use. Default: 0'
|
102
105
|
option :proxy_type, desc: 'Set the Proxy type. Default: standard'
|
103
106
|
option :vars, type: :string, banner: :JSON, desc: 'Set input vars. Must be in json format. i.e: [{"name":"foo", "value":"bar", "secret":false}] '
|
104
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'
|
@@ -99,8 +99,9 @@ module Datahen
|
|
99
99
|
long_desc <<-LONGDESC
|
100
100
|
Updates a scraper's current job.
|
101
101
|
LONGDESC
|
102
|
-
option :
|
103
|
-
option :
|
102
|
+
option :parsers, :aliases => :pw, type: :numeric, desc: 'Set how many parser workers to use. Scraper job must be restarted (paused then resumed) for it to take effect. Default: 1. '
|
103
|
+
option :fetchers, :aliases => :fw, type: :numeric, desc: 'Set how many fetcher workers to use. Scraper job must be restarted (paused then resumed) for it to take effect. Default: 1. '
|
104
|
+
option :browsers, :aliases => :bw, type: :numeric, desc: 'Set how many browser workers to use. Scraper job must be restarted (paused then resumed) for it to take effect. Default: 0. '
|
104
105
|
option :proxy_type, desc: 'Set the Proxy type. Default: standard'
|
105
106
|
option :profile, type: :string, desc: 'Set the profiles (comma separated) to apply to the job. Default: default'
|
106
107
|
option :job, :aliases => :j, type: :numeric, desc: 'Set a specific job ID'
|
data/lib/datahen/client/job.rb
CHANGED
@@ -17,7 +17,8 @@ module Datahen
|
|
17
17
|
def update(job_id, opts={})
|
18
18
|
body = {}
|
19
19
|
body[:status] = opts[:status] if opts[:status]
|
20
|
-
body[:
|
20
|
+
body[:parser_worker_count] = opts[:parsers] if opts[:parsers]
|
21
|
+
body[:fetcher_worker_count] = opts[:fetchers] if opts[:fetchers]
|
21
22
|
body[:browser_worker_count] = opts[:browsers] if opts[:browsers]
|
22
23
|
body[:proxy_type] = opts[:proxy_type] if opts[:proxy_type]
|
23
24
|
body[:profile] = opts[:profile] if opts[:profile]
|
@@ -18,7 +18,8 @@ module Datahen
|
|
18
18
|
body[:git_branch] = opts[:branch] || opts[:git_branch] || "master" if opts[:branch] || opts[:git_branch]
|
19
19
|
body[:freshness_type] = opts[:freshness_type] if opts[:freshness_type]
|
20
20
|
body[:force_fetch] = opts[:force_fetch] if opts[:force_fetch]
|
21
|
-
body[:
|
21
|
+
body[:parser_worker_count] = opts[:parsers] || opts[:parser_worker_count] if opts[:parsers] || opts[:parser_worker_count]
|
22
|
+
body[:fetcher_worker_count] = opts[:fetchers] || opts[:fetcher_worker_count] if opts[:fetchers] || opts[:fetcher_worker_count]
|
22
23
|
body[:browser_worker_count] = opts[:browsers] || opts[:browser_worker_count] if opts[:browsers] || opts[:browser_worker_count]
|
23
24
|
body[:proxy_type] = opts[:proxy_type] if opts[:proxy_type]
|
24
25
|
body[:disable_scheduler] = opts[:disable_scheduler] if opts[:disable_scheduler]
|
@@ -42,7 +43,8 @@ module Datahen
|
|
42
43
|
body[:git_branch] = opts[:branch] || opts[:git_branch] if opts[:branch] || opts[:git_branch]
|
43
44
|
body[:freshness_type] = opts[:freshness_type] if opts[:freshness_type]
|
44
45
|
body[:force_fetch] = opts[:force_fetch] if opts.has_key?("force_fetch") || opts.has_key?(:force_fetch)
|
45
|
-
body[:
|
46
|
+
body[:parser_worker_count] = opts[:parsers] || opts[:parser_worker_count] if opts[:parsers] || opts[:parser_worker_count]
|
47
|
+
body[:fetcher_worker_count] = opts[:fetchers] || opts[:fetcher_worker_count] if opts[:fetchers] || opts[:fetcher_worker_count]
|
46
48
|
body[:browser_worker_count] = opts[:browsers] || opts[:browser_worker_count] if opts[:browsers] || opts[:browser_worker_count]
|
47
49
|
body[:proxy_type] = opts[:proxy_type] if opts[:proxy_type]
|
48
50
|
body[:disable_scheduler] = opts[:disable_scheduler] if opts.has_key?("disable_scheduler") || opts.has_key?(:disable_scheduler)
|
@@ -8,7 +8,8 @@ module Datahen
|
|
8
8
|
|
9
9
|
def create(scraper_name, opts={})
|
10
10
|
body = {}
|
11
|
-
body[:
|
11
|
+
body[:parser_worker_count] = opts[:parsers] if opts[:parsers]
|
12
|
+
body[:fetcher_worker_count] = opts[:fetchers] if opts[:fetchers]
|
12
13
|
body[:browser_worker_count] = opts[:browsers] if opts[:browsers]
|
13
14
|
body[:proxy_type] = opts[:proxy_type] if opts[:proxy_type]
|
14
15
|
body[:max_page_size] = opts[:max_page_size] if opts[:max_page_size]
|
@@ -36,7 +37,8 @@ module Datahen
|
|
36
37
|
def update(scraper_name, opts={})
|
37
38
|
body = {}
|
38
39
|
body[:status] = opts[:status] if opts[:status]
|
39
|
-
body[:
|
40
|
+
body[:parser_worker_count] = opts[:parsers] if opts[:parsers]
|
41
|
+
body[:fetcher_worker_count] = opts[:fetchers] if opts[:fetchers]
|
40
42
|
body[:browser_worker_count] = opts[:browsers] if opts[:browsers]
|
41
43
|
body[:proxy_type] = opts[:proxy_type] if opts[:proxy_type]
|
42
44
|
body[:profile] = opts[:profile] if opts[:profile]
|
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: 1.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Parama Danoesubroto
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2022-06-03 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: thor
|