textract 0.0.1 → 0.0.2
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/textract.rb +5 -3
- data/lib/textract/version.rb +1 -1
- data/textract.gemspec +1 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6c0f4e826cede5d69f4c35d74129c33ffe6fd59a
|
4
|
+
data.tar.gz: 8884dac18c1ddf501ccabbfbde7d5f50c24e37d3
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 43d1097a7252e581849883b43c4581757b029e9a8f2e8cca754c396a1ff519cd92e538d984fd163c7733b5a8fdeb1211465cc24a29bffd34918c06d9bce68ce7
|
7
|
+
data.tar.gz: 8658b5de346c5e47214bcc294627c9d9c2d0bf40446af26192836e8925429dd029c9a91cd75c54d2d3be62db32417d05a85a11c05b0786e80d8c868006b57bbb
|
data/lib/textract.rb
CHANGED
@@ -1,5 +1,5 @@
|
|
1
1
|
require "textract/version"
|
2
|
-
require '
|
2
|
+
require 'mechanize'
|
3
3
|
require 'nokogiri'
|
4
4
|
require 'opengraph_parser'
|
5
5
|
require 'reverse_markdown'
|
@@ -21,6 +21,7 @@ module Textract
|
|
21
21
|
if selectors.nil?
|
22
22
|
article = doc.search('article')
|
23
23
|
else
|
24
|
+
require 'pry'; binding.pry
|
24
25
|
article = doc.search(selectors)
|
25
26
|
end
|
26
27
|
if article.count == 1
|
@@ -30,7 +31,6 @@ module Textract
|
|
30
31
|
i = 1
|
31
32
|
until els.count < 2
|
32
33
|
search_text = description.split(" ")[0..i].join(" ")
|
33
|
-
puts search_text
|
34
34
|
els = doc.search "[text()*='#{search_text}']"
|
35
35
|
i += 1
|
36
36
|
end
|
@@ -66,7 +66,9 @@ module Textract
|
|
66
66
|
|
67
67
|
def initialize(url, selectors)
|
68
68
|
@url = url
|
69
|
-
|
69
|
+
agent = Mechanize.new
|
70
|
+
agent.user_agent_alias = 'Mac Safari'
|
71
|
+
@html = agent.get(url).content
|
70
72
|
@tags = Textract.get_og_tags(@html)
|
71
73
|
if @tags.nil? or @tags.description.nil?
|
72
74
|
# use readability method
|
data/lib/textract/version.rb
CHANGED
data/textract.gemspec
CHANGED
@@ -19,9 +19,9 @@ Gem::Specification.new do |spec|
|
|
19
19
|
spec.require_paths = ["lib"]
|
20
20
|
|
21
21
|
spec.add_dependency "opengraph_parser"
|
22
|
-
spec.add_dependency "httparty"
|
23
22
|
spec.add_dependency "reverse_markdown"
|
24
23
|
spec.add_dependency "ruby-readability"
|
24
|
+
spec.add_dependency "mechanize"
|
25
25
|
|
26
26
|
spec.add_development_dependency "bundler", "~> 1.7"
|
27
27
|
spec.add_development_dependency "rake", "~> 10.0"
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: textract
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Adam Pash
|
@@ -25,7 +25,7 @@ dependencies:
|
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
|
-
name:
|
28
|
+
name: reverse_markdown
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
31
|
- - ">="
|
@@ -39,7 +39,7 @@ dependencies:
|
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
|
-
name:
|
42
|
+
name: ruby-readability
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
45
|
- - ">="
|
@@ -53,7 +53,7 @@ dependencies:
|
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
56
|
+
name: mechanize
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
59
|
- - ">="
|