rss_searcher 0.1.1
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 +7 -0
- data/LICENSE +22 -0
- data/README.md +1 -0
- data/lib/file_reader.rb +28 -0
- data/lib/rss_keyword_finder.rb +80 -0
- data/lib/rss_reader.rb +21 -0
- data/lib/rss_searcher.rb +26 -0
- data/lib/send_text.rb +24 -0
- metadata +51 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 6a748b23904a57481f5838d40aacfff1b6a26dca
|
4
|
+
data.tar.gz: 23358084b8f1f4c19e8f11243abd22c4253fef25
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 228bd90ed5b24259db12d4df5e589e9181f1dfa30d09654b217139b94c2f6341427b4a431d6fbafb6edc497976783de33c3d1541596f8f067ece3de19bb16fa7
|
7
|
+
data.tar.gz: 5a93943e8bae27326cb80843e81f6381448d39c6dec9cc9f71aa550322078186e4498df27992f2215a2a2d10438a019157539234fd14551e2640a7b6a9c8a7ef
|
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 Gregory White
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in all
|
13
|
+
copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
21
|
+
SOFTWARE.
|
22
|
+
|
data/README.md
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
# rss_searcher
|
data/lib/file_reader.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
class File_Reader
|
2
|
+
|
3
|
+
URL_REGEX = "((http|ftp|https):\/{2})+([0-9a-z_-]+\.)+[a-z]+"
|
4
|
+
|
5
|
+
def self.get_lines(input)
|
6
|
+
if input.is_a? Array
|
7
|
+
return input
|
8
|
+
else
|
9
|
+
return File_Reader.get_lines_from_file(input)
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
# assumes file has one line to one url ratio
|
14
|
+
def self.get_lines_from_file(filename)
|
15
|
+
return null if !filename
|
16
|
+
begin
|
17
|
+
return File.readlines(filename).each_with_object(Array.new) do |line, urls|
|
18
|
+
if( line =~ /#{URL_REGEX}/)
|
19
|
+
urls.push line.chomp
|
20
|
+
end
|
21
|
+
end
|
22
|
+
rescue
|
23
|
+
puts "failed to open file #{filename}"
|
24
|
+
return nil
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
end
|
@@ -0,0 +1,80 @@
|
|
1
|
+
require_relative "rss_reader.rb"
|
2
|
+
require 'date'
|
3
|
+
|
4
|
+
INTEREST_LEVEL_ALL = "ALL"
|
5
|
+
INTEREST_LEVEL_ONE_OR_MORE = "ONE_OR_MORE"
|
6
|
+
|
7
|
+
class RSS_Keyword_Searcher
|
8
|
+
|
9
|
+
def initialize(feed_urls, keywords, match_level, minimum_publish_date=Date.today)
|
10
|
+
@reader = RSS_Reader.new(feed_urls)
|
11
|
+
@news_items = @reader.get_news_items
|
12
|
+
@keywords = keywords
|
13
|
+
@match_level = match_level
|
14
|
+
@minimum_publish_date = minimum_publish_date
|
15
|
+
raise ArgumentError, "no valid feed urls given" unless @news_items
|
16
|
+
raise ArgumentError, "no keywords given" unless keywords.is_a?(Array) && keywords.length > 0
|
17
|
+
raise ArgumentError, "invalid match_level" unless self.valid_match_level(match_level)
|
18
|
+
end
|
19
|
+
|
20
|
+
def get_links_of_interest(links_of_interest=Array.new)
|
21
|
+
@news_items.each do |item|
|
22
|
+
content = self.content_from_item(item)
|
23
|
+
next if self.out_of_date(item)
|
24
|
+
links_of_interest.push(item.link) if self.is_of_interest(content)
|
25
|
+
end
|
26
|
+
return links_of_interest
|
27
|
+
end
|
28
|
+
|
29
|
+
def is_of_interest(content)
|
30
|
+
if(@match_level === INTEREST_LEVEL_ALL)
|
31
|
+
regex_string = @keywords.inject("") {|ret, keyword| ret+"(?=.*#{keyword.downcase})"}
|
32
|
+
return content =~ /#{regex_string}/
|
33
|
+
elsif(@match_level === INTEREST_LEVEL_ONE_OR_MORE)
|
34
|
+
regex_string = @keywords.map(&:downcase).join("|")
|
35
|
+
return content =~ /#{regex_string}/
|
36
|
+
elsif(@match_level.is_a?(Integer) && @match_level > 1 && @match_level < 100 )
|
37
|
+
match_percentage = self.get_keyword_match_percentage(content)
|
38
|
+
(match_percentage*100) > @match_level ? (return true) : (return false)
|
39
|
+
else
|
40
|
+
return false
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
def event_triggered?(flag=false)
|
45
|
+
@news_items.each do |item|
|
46
|
+
content = self.content_from_item(item)
|
47
|
+
flag = self.is_of_interest(content)
|
48
|
+
return flag if flag
|
49
|
+
end
|
50
|
+
return flag
|
51
|
+
end
|
52
|
+
|
53
|
+
def get_keyword_match_percentage(content)
|
54
|
+
match_count = 0
|
55
|
+
@keywords.each do |keyword|
|
56
|
+
if content.include?(keyword.downcase)
|
57
|
+
match_count += 1
|
58
|
+
end
|
59
|
+
end
|
60
|
+
return (match_count * 1.0) / @keywords.length
|
61
|
+
end
|
62
|
+
|
63
|
+
def out_of_date(news_item)
|
64
|
+
pub_date_string = news_item.pubDate.to_s
|
65
|
+
pub_date = Date.parse(pub_date_string)
|
66
|
+
return pub_date < @minimum_publish_date
|
67
|
+
end
|
68
|
+
|
69
|
+
def content_from_item(item)
|
70
|
+
content_string = item.categories.each_with_object("") do |category, string|
|
71
|
+
string.concat category.content
|
72
|
+
end
|
73
|
+
return (content_string+item.description+item.title).downcase
|
74
|
+
end
|
75
|
+
|
76
|
+
def valid_match_level(match_level)
|
77
|
+
return (match_level === INTEREST_LEVEL_ALL || match_level === INTEREST_LEVEL_ONE_OR_MORE || (match_level.is_a?(Integer) && match_level > 1 && match_level < 100))
|
78
|
+
end
|
79
|
+
|
80
|
+
end
|
data/lib/rss_reader.rb
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'rss'
|
2
|
+
require 'open-uri'
|
3
|
+
|
4
|
+
class RSS_Reader
|
5
|
+
|
6
|
+
def initialize(feed_urls)
|
7
|
+
@feed_urls = feed_urls
|
8
|
+
end
|
9
|
+
|
10
|
+
# returns an array of rss items
|
11
|
+
def get_news_items
|
12
|
+
news_items = @feed_urls.each_with_object(Array.new) do |url, items|
|
13
|
+
open(url) do |rss|
|
14
|
+
feed = RSS::Parser.parse(rss)
|
15
|
+
items.concat feed.items
|
16
|
+
end
|
17
|
+
end
|
18
|
+
return news_items.empty? ? nil : news_items
|
19
|
+
end
|
20
|
+
|
21
|
+
end
|
data/lib/rss_searcher.rb
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
require_relative "rss_keyword_finder.rb"
|
2
|
+
require_relative "file_reader.rb"
|
3
|
+
|
4
|
+
class RSS_Searcher
|
5
|
+
|
6
|
+
def get_links_of_interest(feeds, keywords, match_level="ONE_OR_MORE", minimum_publish_date=Date.today)
|
7
|
+
self.set_relevant_params(feeds, keywords, minimum_publish_date)
|
8
|
+
return Array.new unless @feed_urls && @keywords && @minimum_publish_date
|
9
|
+
links_of_interest = Array.new
|
10
|
+
begin
|
11
|
+
searcher = RSS_Keyword_Searcher.new(@feed_urls, @keywords, match_level, @minimum_publish_date)
|
12
|
+
links_of_interest = searcher.get_links_of_interest
|
13
|
+
rescue ArgumentError => ae
|
14
|
+
puts ae.message
|
15
|
+
links_of_interest = Array.new
|
16
|
+
end
|
17
|
+
return links_of_interest
|
18
|
+
end
|
19
|
+
|
20
|
+
def set_relevant_params(feeds, keywords, minimum_publish_date)
|
21
|
+
@feed_urls = File_Reader::get_lines(feeds)
|
22
|
+
@keywords = File_Reader::get_lines(keywords)
|
23
|
+
@minimum_publish_date = minimum_publish_date
|
24
|
+
end
|
25
|
+
|
26
|
+
end
|
data/lib/send_text.rb
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'twilio-ruby'
|
2
|
+
|
3
|
+
account_sid = 'ACa2d607218147d7fefd923c2b1a8f9d11'
|
4
|
+
auth_token = '38ea477a666c1975c9d3dacbc4b2dfe5'
|
5
|
+
@client = Twilio::REST::Client.new account_sid, auth_token
|
6
|
+
|
7
|
+
args = Hash[*ARGV]
|
8
|
+
|
9
|
+
|
10
|
+
|
11
|
+
content = args.has_key?("-m") ? args["-m"] : nil
|
12
|
+
|
13
|
+
if content
|
14
|
+
puts "Your message was #{content}"
|
15
|
+
|
16
|
+
message = @client.account.messages.create(
|
17
|
+
:body => content,
|
18
|
+
:to => "+15038413886",
|
19
|
+
:from => "+19712051238")
|
20
|
+
puts message.to
|
21
|
+
|
22
|
+
else
|
23
|
+
puts "No message given, no action taken"
|
24
|
+
end
|
metadata
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rss_searcher
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Greg White
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-05-03 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: A simple rss feed curator based on keyword matches
|
14
|
+
email: gwhite@dayspring-tech.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- LICENSE
|
20
|
+
- README.md
|
21
|
+
- lib/file_reader.rb
|
22
|
+
- lib/rss_keyword_finder.rb
|
23
|
+
- lib/rss_reader.rb
|
24
|
+
- lib/rss_searcher.rb
|
25
|
+
- lib/send_text.rb
|
26
|
+
homepage:
|
27
|
+
licenses:
|
28
|
+
- MIT
|
29
|
+
metadata: {}
|
30
|
+
post_install_message:
|
31
|
+
rdoc_options: []
|
32
|
+
require_paths:
|
33
|
+
- lib
|
34
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
35
|
+
requirements:
|
36
|
+
- - '>='
|
37
|
+
- !ruby/object:Gem::Version
|
38
|
+
version: '0'
|
39
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
40
|
+
requirements:
|
41
|
+
- - '>='
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: '0'
|
44
|
+
requirements: []
|
45
|
+
rubyforge_project:
|
46
|
+
rubygems_version: 2.2.2
|
47
|
+
signing_key:
|
48
|
+
specification_version: 4
|
49
|
+
summary: This gem reads rss feeds and then searches them for keywords returning only
|
50
|
+
stories of interest
|
51
|
+
test_files: []
|