datahen 0.14.1 → 0.14.2
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_job.rb +8 -2
- data/lib/datahen/cli/scraper_page.rb +1 -1
- data/lib/datahen/scraper/executor.rb +9 -3
- data/lib/datahen/version.rb +1 -1
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 10e4e646ff403fbdb91e0be43e0a78a879c48f3686be251f26185cae961e4b4f
|
4
|
+
data.tar.gz: bc8a4f11cb3929e2cf1655d7463f02c6dd9166a1994a7cbdb69cddf327099f95
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 7d57fc498d3f3b6bcf08a31a663a48f5ace6fff5f9fdeeb1b8f396710e6d7e96f31b1a0dc460aeab312d468d19098b759cc19d6c60ecee9286a409934cfd5872
|
7
|
+
data.tar.gz: ff1585a9b3be081898c597d5e696f0927b90f54d420de3bab39451b16dbd55d622a1aa7c9b631dac22cc9f84d1c5e60b86bf5284bde1cb0abb0a24ed69a5834e
|
@@ -7,10 +7,16 @@ module Datahen
|
|
7
7
|
end
|
8
8
|
|
9
9
|
desc "show <scraper_name>", "Show a scraper's current job (Defaults to showing data from cached job)"
|
10
|
+
option :job, :aliases => :j, type: :numeric, desc: 'Set a specific job ID'
|
10
11
|
option :live, type: :boolean, desc: 'Get data from the live job, not cached job.'
|
11
12
|
def show(scraper_name)
|
12
|
-
|
13
|
-
|
13
|
+
if options[:job]
|
14
|
+
client = Client::Job.new(options)
|
15
|
+
puts "#{client.find(options[:job], options)}"
|
16
|
+
else
|
17
|
+
client = Client::ScraperJob.new(options)
|
18
|
+
puts "#{client.find(scraper_name, options)}"
|
19
|
+
end
|
14
20
|
end
|
15
21
|
|
16
22
|
|
@@ -230,7 +230,7 @@ module Datahen
|
|
230
230
|
end
|
231
231
|
end
|
232
232
|
|
233
|
-
desc "failedcontent <gid>", "Show a page's failed content in scraper's current job"
|
233
|
+
desc "failedcontent <scraper_name> <gid>", "Show a page's failed content in scraper's current job"
|
234
234
|
option :job, :aliases => :j, type: :numeric, desc: 'Set a specific job ID'
|
235
235
|
def failedcontent(scraper_name, gid)
|
236
236
|
result = nil
|
@@ -60,7 +60,12 @@ module Datahen
|
|
60
60
|
|
61
61
|
def init_global_page()
|
62
62
|
client = Client::GlobalPage.new()
|
63
|
-
client.find(gid)
|
63
|
+
global_page = client.find(gid)
|
64
|
+
unless global_page.code == 200
|
65
|
+
raise "GID #{gid} not found. Aborting execution!"
|
66
|
+
else
|
67
|
+
global_page
|
68
|
+
end
|
64
69
|
end
|
65
70
|
|
66
71
|
def get_content(job_id, gid)
|
@@ -287,11 +292,12 @@ module Datahen
|
|
287
292
|
end
|
288
293
|
|
289
294
|
# behave differently if it is a real save
|
295
|
+
save_status = status
|
290
296
|
if save
|
291
297
|
log_msg = "Saving #{log_msgs.join(' and ')}."
|
292
298
|
puts "#{log_msg}"
|
293
299
|
else
|
294
|
-
|
300
|
+
save_status = "#{status}_try"
|
295
301
|
end
|
296
302
|
|
297
303
|
# saving to server
|
@@ -300,7 +306,7 @@ module Datahen
|
|
300
306
|
gid: gid,
|
301
307
|
pages: pages_slice,
|
302
308
|
outputs: outputs_slice,
|
303
|
-
status:
|
309
|
+
status: save_status)
|
304
310
|
|
305
311
|
if response.code == 200
|
306
312
|
if save
|
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: 0.14.
|
4
|
+
version: 0.14.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Parama Danoesubroto
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-07-
|
11
|
+
date: 2020-07-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: thor
|
@@ -264,7 +264,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
264
264
|
- !ruby/object:Gem::Version
|
265
265
|
version: '0'
|
266
266
|
requirements: []
|
267
|
-
rubygems_version: 3.
|
267
|
+
rubygems_version: 3.0.3
|
268
268
|
signing_key:
|
269
269
|
specification_version: 4
|
270
270
|
summary: DataHen toolbelt for developers
|