website_information 0.4.4 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: e1f3b31146d3da07c6be7952cbe78e6121da9e86
|
4
|
+
data.tar.gz: b165e9c3c14503ca4efc03ead798179324b306d0
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: bdee9b5cd2efe9da8b0e011e6a13024ab0ccf1fb68fb08d7e55d3eb39e98dc956209f2d20586e9952c505d97de85320d00c8d68ec1b24113feba8d1c76002919
|
7
|
+
data.tar.gz: 32811dc8836e78dd65b175f14adf7338d0d81e8256ea970d923405f2d90b46104f86f035e6729f70fa59bee7151bafaa85995934267c5fd4c5cc4cfca2e8ce24
|
data/README.md
CHANGED
@@ -34,9 +34,26 @@ Please install web driver if you want to use site capture.
|
|
34
34
|
scraped_params = WebsiteInformation::Website.new('scraping_url(ex. https://www.google.com)').scraped_params
|
35
35
|
|
36
36
|
# ex) get website title
|
37
|
-
scraped_params.title
|
37
|
+
scraped_params.title # => Google
|
38
|
+
|
38
39
|
```
|
39
40
|
|
41
|
+
### Output
|
42
|
+
The list of allowed get `params` values.
|
43
|
+
|
44
|
+
* ```.title``` — ```<title>``` tag value
|
45
|
+
* ```.meta.description``` — ```<meta name="description" >``` tag content
|
46
|
+
* ```.meta.keyword``` — ```<meta name="keyword" >``` tag content
|
47
|
+
* ```.og.site_name``` — ```<meta property="og:site_name" >``` tag content
|
48
|
+
* ```.og.description``` — ```<meta property="og:description" >``` tag content
|
49
|
+
* ```.og.url``` — ```<meta property="og:url" >``` tag content
|
50
|
+
* ```.og.type``` — ```<meta property="og:type" >``` tag content
|
51
|
+
* ```.og.image``` — ```<meta property="og:image" >``` tag content
|
52
|
+
* ```.feed``` — ```<link rel="alternate" >``` tag href application/atom+xml or application/rss+xml type
|
53
|
+
* ```.sns.facebook``` — Facebook page plugin (https://developers.facebook.com/docs/plugins/page-plugin/) from data-href
|
54
|
+
* ```.sns.twitter``` — Twitter embedded timelines (https://dev.twitter.com/web/embedded-timelines/list) from href
|
55
|
+
|
56
|
+
|
40
57
|
## Contributing
|
41
58
|
|
42
59
|
Bug reports and pull requests are welcome on GitHub at https://github.com/miraoto/website_information. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
@@ -1,3 +1,5 @@
|
|
1
|
+
require 'watir'
|
2
|
+
|
1
3
|
module WebsiteInformation
|
2
4
|
module Params
|
3
5
|
class Site
|
@@ -7,6 +9,7 @@ module WebsiteInformation
|
|
7
9
|
@url = url
|
8
10
|
@meta = WebsiteInformation::Params::Meta.new
|
9
11
|
@og = WebsiteInformation::Params::Og.new
|
12
|
+
@sns = WebsiteInformation::Params::Sns.new
|
10
13
|
end
|
11
14
|
|
12
15
|
def meta
|
@@ -17,6 +20,10 @@ module WebsiteInformation
|
|
17
20
|
@og
|
18
21
|
end
|
19
22
|
|
23
|
+
def sns
|
24
|
+
@sns
|
25
|
+
end
|
26
|
+
|
20
27
|
def capture
|
21
28
|
if @capture.nil?
|
22
29
|
browser = Watir::Browser.new
|
@@ -1,5 +1,4 @@
|
|
1
1
|
require 'nokogiri'
|
2
|
-
require 'watir'
|
3
2
|
|
4
3
|
module WebsiteInformation
|
5
4
|
class Website
|
@@ -26,11 +25,19 @@ module WebsiteInformation
|
|
26
25
|
@params.og.type = doc.css('//meta[property="og:type"]/@content').to_s
|
27
26
|
@params.og.image = doc.css('//meta[property="og:image"]/@content').to_s
|
28
27
|
feed(doc)
|
28
|
+
sns(doc)
|
29
29
|
end
|
30
30
|
|
31
31
|
def feed(doc)
|
32
32
|
@params.feed = doc.css('//link[@rel="alternate"][@type="application/atom+xml"]/@href')[0].to_s
|
33
33
|
@params.feed = doc.css('//link[@rel="alternate"][@type="application/rss+xml"]/@href')[0].to_s if @params.feed.empty?
|
34
34
|
end
|
35
|
+
|
36
|
+
def sns(doc)
|
37
|
+
# scrape facebook url from page plugin (https://developers.facebook.com/docs/plugins/page-plugin/)
|
38
|
+
@params.sns.facebook = doc.css('//div[class$="fb-page"]/@data-href')[0].to_s
|
39
|
+
# scrape twitter url from embedded timelines (https://dev.twitter.com/web/embedded-timelines/list)
|
40
|
+
@params.sns.twitter = doc.css('//a[class$="twitter-timeline"]/@href')[0].to_s
|
41
|
+
end
|
35
42
|
end
|
36
43
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: website_information
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.5.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- miraoto
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-10-
|
11
|
+
date: 2017-10-03 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -117,6 +117,7 @@ files:
|
|
117
117
|
- lib/website_information/params/meta.rb
|
118
118
|
- lib/website_information/params/og.rb
|
119
119
|
- lib/website_information/params/site.rb
|
120
|
+
- lib/website_information/params/sns.rb
|
120
121
|
- lib/website_information/version.rb
|
121
122
|
- lib/website_information/website.rb
|
122
123
|
- website_information.gemspec
|