textract 0.0.15 → 0.0.16
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/textract.rb +7 -2
- data/lib/textract/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6df62961d3d6f6fb6fb88d189bc657111ea04f65
|
4
|
+
data.tar.gz: 400fe86f14b624c7d280719d66b705ac5cea6b41
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e3797cea30cc5ddc90e672c75b4c700a900c6bbe23bb916b504b2ea2e5ecaef1bc5619d90293c9574b85dea2fc8769d8585b13ae2615ac2bbb9806ffdfab13c5
|
7
|
+
data.tar.gz: b3aa7a586c9ab8a679f2d89e0fef6e9847612ab8c945420388e6dec8769ed0dd993158321cb470f9e99e6750f0bab17201795765da1d17c57e72fe5e9c1acdb3
|
data/lib/textract.rb
CHANGED
@@ -78,9 +78,14 @@ module Textract
|
|
78
78
|
twitter_meta.attribute('content').value unless twitter_meta.empty?
|
79
79
|
end
|
80
80
|
|
81
|
-
def self.build_site(html)
|
81
|
+
def self.build_site(url, html)
|
82
82
|
site_twitter = Nokogiri::HTML(html).search('meta[name="twitter:site"]')
|
83
83
|
site_name = Nokogiri::HTML(html).search('meta[property="og:site_name"]')
|
84
|
+
if site_name.empty?
|
85
|
+
site = url.match(/(http|ftp)s?:\/\/((\w+\.)?(\w+\.)(\w+))\//)
|
86
|
+
site = site[2] unless site[2].nil?
|
87
|
+
site = site.sub(/^www\./, '').capitalize!
|
88
|
+
end
|
84
89
|
{
|
85
90
|
name: site_name.empty? ? nil : site_name.attribute('content').value,
|
86
91
|
twitter: site_twitter.empty? ? nil : site_twitter.attribute('content').value,
|
@@ -131,7 +136,7 @@ module Textract
|
|
131
136
|
end
|
132
137
|
@md5 = Textract.generate_hash @text
|
133
138
|
@author = Textract.build_author @article, @html
|
134
|
-
@site = Textract.build_site @html
|
139
|
+
@site = Textract.build_site @url, @html
|
135
140
|
@title = @tags.title || Textract.get_page_title(@html)
|
136
141
|
if @url.match(/\/robots.txt$/) and @title = @text
|
137
142
|
@title = @url
|
data/lib/textract/version.rb
CHANGED