news2kindle 0.1.5 → 0.2.0
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/Gemfile.lock +2 -2
- data/bin/test-generator +1 -0
- data/lib/news2kindle/dup_checker.rb +1 -1
- data/lib/news2kindle/generator/nikkei-paid.rb +14 -17
- data/lib/news2kindle/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b6359f3d5bd815e2288ae183bdf574a429f64318
|
4
|
+
data.tar.gz: 746ab24028ae050952b3b84a58d78ec8b0e7230c
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 45d90ea6ee619e73aad9c61ad2cdcca1ecd5ef3493553618bb8ba79e534dc5582b5a6bd62f9c39e20a6420345537a886b1f16025b0dfa01162cce7875998d5ef
|
7
|
+
data.tar.gz: 4a5fc8651f8163b566191c048fe49387599db5b6e6e5c381d68762fb5ed26a6137bb368a52dd5d5eadfc6adb6bedf5d6c151958d5900073a96f4b34273dfd676
|
data/Gemfile.lock
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
news2kindle (0.
|
4
|
+
news2kindle (0.2.0)
|
5
5
|
dropbox_api
|
6
6
|
kindlegen
|
7
7
|
mail
|
@@ -55,7 +55,7 @@ GEM
|
|
55
55
|
mime-types (3.1)
|
56
56
|
mime-types-data (~> 3.2015)
|
57
57
|
mime-types-data (3.2016.0521)
|
58
|
-
mini_mime (0.
|
58
|
+
mini_mime (1.0.0)
|
59
59
|
mini_portile2 (2.3.0)
|
60
60
|
minitest (5.10.3)
|
61
61
|
mongo (2.4.3)
|
data/bin/test-generator
CHANGED
@@ -55,28 +55,25 @@ module News2Kindle
|
|
55
55
|
# scraping top news
|
56
56
|
#
|
57
57
|
toc_top = ['TOP NEWS']
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
toc_top << [canonical( a.text.strip ), uri]
|
63
|
-
end
|
58
|
+
(agent.page / '#JSID_baseRefreshNxTop2 h3 a').each do |a|
|
59
|
+
uri = a.attr('href')
|
60
|
+
next if News2Kindle::DupChecker.dup?(uri)
|
61
|
+
toc_top << [canonical(a.text.strip), uri]
|
64
62
|
end
|
65
63
|
toc << toc_top
|
66
64
|
|
67
65
|
#
|
68
66
|
# scraping all categories
|
69
67
|
#
|
70
|
-
(agent.page / 'div.
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
end
|
68
|
+
(agent.page / 'div.m-miM11_box').each do |genre|
|
69
|
+
headline = genre / 'div.m-headline h3'
|
70
|
+
toc_cat = [headline.text]
|
71
|
+
agent.get((headline / 'a').attr('href'))
|
72
|
+
(agent.page / '#CONTENTS_MAIN h3 a').each do |article|
|
73
|
+
uri = article.attr('href')
|
74
|
+
next unless article.attr('href') =~ %r|^/article/|
|
75
|
+
next if News2Kindle::DupChecker.dup?(uri)
|
76
|
+
toc_cat << [canonical(article.text), uri]
|
80
77
|
end
|
81
78
|
toc << toc_cat
|
82
79
|
end
|
@@ -150,7 +147,7 @@ module News2Kindle
|
|
150
147
|
begin
|
151
148
|
#puts "getting html #{aid}#{sub}"
|
152
149
|
retry_loop( 5 ) do
|
153
|
-
agent.get(
|
150
|
+
agent.get("#{TOP}/news/print-article/?ng=#{aid}")
|
154
151
|
html = agent.page.root
|
155
152
|
sleep 1
|
156
153
|
end
|
data/lib/news2kindle/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: news2kindle
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- TADA Tadashi
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-11-
|
11
|
+
date: 2017-11-14 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: kindlegen
|