link_thumbnailer 3.1.2 → 3.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +13 -0
- data/lib/generators/templates/initializer.rb +6 -2
- data/lib/link_thumbnailer/configuration.rb +3 -1
- data/lib/link_thumbnailer/scraper.rb +2 -8
- data/lib/link_thumbnailer/version.rb +1 -1
- data/spec/scraper_spec.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: 9799bede3f23e3369ddafa4ddeb36c9436d7ee5d
|
4
|
+
data.tar.gz: 484c6c008967be9cd3d813bac81dffde02c18bd7
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 3c6a25faef22554a54a84a2ffbf0ee85babb1b088b5ed79d08e6550504f9e9853fa177cd730856cd1c3cb3d285dc1bf6a727cd89a85d410f00cf89023668d1de
|
7
|
+
data.tar.gz: 10216dc920ce54195179337fc4034ba14413c833369a2e566e2b7aa5d118a5c7599df4673564ff7a57bc3558be3fa8d826e0c8f35058aba64e9544a13bc1d09d
|
data/CHANGELOG.md
CHANGED
@@ -1,3 +1,16 @@
|
|
1
|
+
# 3.2.0
|
2
|
+
|
3
|
+
Makes scrapers configurable by allowing to set the scraping strategy:
|
4
|
+
|
5
|
+
```ruby
|
6
|
+
LinkThumbnailer.configure do |config|
|
7
|
+
config.scrapers = [:opengraph, :default]
|
8
|
+
end
|
9
|
+
```
|
10
|
+
|
11
|
+
`opengraph` use the [Open Graph Protocol](http://ogp.me/).
|
12
|
+
`default` use a homemade algorithm
|
13
|
+
|
1
14
|
# 3.1.2
|
2
15
|
|
3
16
|
Allows to customize ideal description length
|
@@ -67,13 +67,17 @@ LinkThumbnailer.configure do |config|
|
|
67
67
|
# does not have to fetch its size and type.
|
68
68
|
#
|
69
69
|
# config.image_stats = true
|
70
|
-
|
70
|
+
|
71
71
|
# Whether you want LinkThumbnailer to raise an exception if the Content-Type of the HTTP request
|
72
72
|
# is not an html or xml.
|
73
73
|
#
|
74
74
|
# config.raise_on_invalid_format = false
|
75
|
-
|
75
|
+
|
76
76
|
# Sets number of concurrent http connections that can be opened to fetch images informations such as size and type.
|
77
77
|
#
|
78
78
|
# config.max_concurrency = 20
|
79
|
+
|
80
|
+
# Defines the strategies to use to scrap the website. See the [Open Graph Protocol](http://ogp.me/) for more information.
|
81
|
+
#
|
82
|
+
# config.scrapers = [:opengraph, :default]
|
79
83
|
end
|
@@ -25,7 +25,8 @@ module LinkThumbnailer
|
|
25
25
|
attr_accessor :redirect_limit, :blacklist_urls, :user_agent,
|
26
26
|
:verify_ssl, :http_open_timeout, :http_read_timeout, :attributes,
|
27
27
|
:graders, :description_min_length, :positive_regex, :negative_regex,
|
28
|
-
:image_limit, :image_stats, :raise_on_invalid_format, :max_concurrency
|
28
|
+
:image_limit, :image_stats, :raise_on_invalid_format, :max_concurrency,
|
29
|
+
:scrapers
|
29
30
|
|
30
31
|
alias_method :http_timeout, :http_open_timeout
|
31
32
|
alias_method :http_timeout=, :http_open_timeout=
|
@@ -60,6 +61,7 @@ module LinkThumbnailer
|
|
60
61
|
@image_stats = true
|
61
62
|
@raise_on_invalid_format = false
|
62
63
|
@max_concurrency = 20
|
64
|
+
@scrapers = [:opengraph, :default]
|
63
65
|
end
|
64
66
|
|
65
67
|
end
|
@@ -33,7 +33,7 @@ module LinkThumbnailer
|
|
33
33
|
|
34
34
|
def call
|
35
35
|
config.attributes.each do |name|
|
36
|
-
scrapers.each do |scraper_prefix|
|
36
|
+
config.scrapers.each do |scraper_prefix|
|
37
37
|
scraper_class(scraper_prefix, name).new(document, website).call(name.to_s)
|
38
38
|
break unless website.send(name).blank?
|
39
39
|
end
|
@@ -44,14 +44,8 @@ module LinkThumbnailer
|
|
44
44
|
|
45
45
|
private
|
46
46
|
|
47
|
-
def scrapers
|
48
|
-
[
|
49
|
-
'::LinkThumbnailer::Scrapers::Opengraph',
|
50
|
-
'::LinkThumbnailer::Scrapers::Default'
|
51
|
-
]
|
52
|
-
end
|
53
|
-
|
54
47
|
def scraper_class(prefix, name)
|
48
|
+
prefix = "::LinkThumbnailer::Scrapers::#{prefix.to_s.camelize}"
|
55
49
|
name = name.to_s.camelize
|
56
50
|
"#{prefix}::#{name}".constantize
|
57
51
|
rescue NameError
|
data/spec/scraper_spec.rb
CHANGED
@@ -25,7 +25,7 @@ describe LinkThumbnailer::Scraper do
|
|
25
25
|
|
26
26
|
before do
|
27
27
|
instance.stub_chain(:config, :attributes).and_return(attributes)
|
28
|
-
instance.
|
28
|
+
instance.stub_chain(:config, :scrapers).and_return(scrapers)
|
29
29
|
end
|
30
30
|
|
31
31
|
context 'when first one return a result' do
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: link_thumbnailer
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 3.
|
4
|
+
version: 3.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Pierre-Louis Gottfrois
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-
|
11
|
+
date: 2016-05-15 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activesupport
|