rubyscholar 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG.md +6 -0
- data/README.md +7 -0
- data/bin/rubyscholar +35 -6
- data/lib/rubyscholar/version.rb +1 -1
- metadata +2 -2
- data/config.yml +0 -49
data/CHANGELOG.md
ADDED
data/README.md
CHANGED
@@ -13,6 +13,13 @@ Some features:
|
|
13
13
|
|
14
14
|
# How to use:
|
15
15
|
|
16
|
+
### As a Ruby Gem:
|
17
|
+
1. Install the gem using: `[sudo] gem install rubyscholar`
|
18
|
+
2. Create and configure a `config.yml` file.
|
19
|
+
3. Run as `rubyscholar scrape`.
|
20
|
+
4. A `scholar.html` file is created.
|
21
|
+
5. Done!
|
22
|
+
|
16
23
|
### As a ruby script:
|
17
24
|
1. Configure "config.yml"
|
18
25
|
If you want DOI retreival to work (including Altmetrics), you need to be
|
data/bin/rubyscholar
CHANGED
@@ -22,10 +22,9 @@ command :scrape do |c|
|
|
22
22
|
c.option '--out [Output File]', 'File to output the scrapes to'
|
23
23
|
|
24
24
|
c.action do |args, options|
|
25
|
-
options.default
|
26
|
-
|
27
|
-
|
28
|
-
config = YAML.load_file('config.yml')
|
25
|
+
options.default :config => "config.yml", :out => "scholar.html"
|
26
|
+
configFile= "#{options.config}"
|
27
|
+
config = YAML.load_file(configFile)
|
29
28
|
parsed = Rubyscholar::Parser.new(config["url"],
|
30
29
|
config["email"])
|
31
30
|
formatter = Rubyscholar::Formatter.new(parsed,
|
@@ -38,10 +37,40 @@ command :scrape do |c|
|
|
38
37
|
config["italicize"].each do |term|
|
39
38
|
html.gsub!( term , '<em>' + term + '</em>')
|
40
39
|
end
|
41
|
-
|
42
|
-
f= File.open(
|
40
|
+
outFile="#{options.out}"
|
41
|
+
f= File.open(outFile,'w')
|
43
42
|
f.write html
|
44
43
|
f.close()
|
45
44
|
end
|
46
45
|
end
|
47
46
|
|
47
|
+
command :init do |c|
|
48
|
+
c.syntax = 'rubyscholar init'
|
49
|
+
c.description = 'Creates a sample config.yml file for Scraping.'
|
50
|
+
c.action do |args, options|
|
51
|
+
say '# Intialising a configuration file for Rubyscholar.'
|
52
|
+
if File.exist?("config.yml")
|
53
|
+
abort("Initialisation aborted!") if ask("config.yml already exists. Do you want to overwrite?", ['y', 'n']) == 'n'
|
54
|
+
end
|
55
|
+
puts "# Creating config.yml."
|
56
|
+
open("config.yml", 'w') do |page|
|
57
|
+
page.puts "# Google Scholar page (you can choose how you sort it)"
|
58
|
+
page.puts "url: "
|
59
|
+
page.puts "\n\n# Name to highlight (withing \" and \")"
|
60
|
+
page.puts "highlight: "
|
61
|
+
page.puts "\n\n# Need an Email address that has been registered with CrossRef to obtain DOIs using their OpenURL service. "
|
62
|
+
page.puts "# e.g. the following should provide an XML file: "
|
63
|
+
page.puts "# http://www.crossref.org/openurl?redirect=false&pid=YOUR@EMAIL>COM&aulast=Wurm&atitle=Behavioral%20Genomics:%20A,%20Bee,%20C,%20G,%20T"
|
64
|
+
page.puts "email: your@email.com"
|
65
|
+
page.puts "\n\n# Show \"[Cited Nx]\" if N > the following number"
|
66
|
+
page.puts "minCitations: 5 "
|
67
|
+
page.puts "\n\n# Words to italicize (emphasize). These will have \"<em>\" around them. "
|
68
|
+
page.puts "italicize: "
|
69
|
+
page.puts "\n\n# DOIs of articles for which we should show altmetric.org badges. "
|
70
|
+
page.puts "altmetricDOIs: "
|
71
|
+
page.puts "\n\n# Article titles for which we have urls to PDFs in \"name\" : \"url\" format"
|
72
|
+
page.puts "pdfs:"
|
73
|
+
end
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
data/lib/rubyscholar/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: rubyscholar
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.4
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -55,13 +55,13 @@ extensions: []
|
|
55
55
|
extra_rdoc_files: []
|
56
56
|
files:
|
57
57
|
- .gitignore
|
58
|
+
- CHANGELOG.md
|
58
59
|
- Gemfile
|
59
60
|
- LICENSE.txt
|
60
61
|
- README.md
|
61
62
|
- Rakefile
|
62
63
|
- bin/rubyscholar
|
63
64
|
- bin/scrape.rb
|
64
|
-
- config.yml
|
65
65
|
- lib/rubyscholar.rb
|
66
66
|
- lib/rubyscholar/version.rb
|
67
67
|
- rubyscholar.gemspec
|
data/config.yml
DELETED
@@ -1,49 +0,0 @@
|
|
1
|
-
# Google Scholar page (you can choose how you sort it)
|
2
|
-
url: "http://scholar.google.com/citations?sortby=pubdate&hl=en&user=k6y0EGsAAAAJ&view_op=list_works"
|
3
|
-
|
4
|
-
# Name to highlight
|
5
|
-
highlight: "Y Wurm"
|
6
|
-
|
7
|
-
|
8
|
-
# Need an Email address that has been registered with CrossRef to obtain DOIs
|
9
|
-
# using their OpenURL service.
|
10
|
-
# e.g. the following should provide an XML file:
|
11
|
-
# http://www.crossref.org/openurl?redirect=false&pid=YOUR@EMAIL>COM&aulast=Wurm&atitle=Behavioral%20Genomics:%20A,%20Bee,%20C,%20G,%20T
|
12
|
-
email: your@email.com
|
13
|
-
|
14
|
-
|
15
|
-
# Show "[Cited Nx]" if N > the following number
|
16
|
-
minCitations: 5
|
17
|
-
|
18
|
-
# Words to italicize (emphasize). These will have "<em>" around them.
|
19
|
-
italicize:
|
20
|
-
- Solenopsis invicta
|
21
|
-
- Acromyrmex echinatior
|
22
|
-
- de novo
|
23
|
-
|
24
|
-
# DOIs of articles for which we should show altmetric.org badges.
|
25
|
-
altmetricDOIs:
|
26
|
-
- "10.1038/nature11832"
|
27
|
-
- "10.1101/gr.121392.111"
|
28
|
-
- "10.1073/pnas.1009690108"
|
29
|
-
- "10.1073/pnas.1104825108"
|
30
|
-
|
31
|
-
# Article titles for which we have urls to PDFs
|
32
|
-
pdfs:
|
33
|
-
"A Y-like social chromosome causes alternative colony organization in fire ants" : "/publications/wangwurm2013socialChromosome.pdf"
|
34
|
-
"Duplication and concerted evolution in a master sex determiner under balancing selection" : "/publications/procb2013.pdf"
|
35
|
-
"Comparative genomics of chemosensory protein genes reveals rapid evolution and positive selection in ant-specific duplicates" : "/publications/hdy2012122a.pdf"
|
36
|
-
"The Molecular Clockwork of the Fire Ant Solenopsis invicta" : "/publications/ingram2012-fireAntClockGenes.pdf"
|
37
|
-
"Epigenetics: The Making of Ant Castes" : "/publications/2012CurrBiolAntepigenetics.pdf"
|
38
|
-
"Visualization and quality assessment of de novo genome assemblies" : "/publications/Bioinformatics-2011-Riba-Grognuz-3425-6"
|
39
|
-
"The genomic impact of 100 million years of social evolution in seven ant species" : "/publications/TiG2011.pdf"
|
40
|
-
"Relaxed selection is a precursor to the evolution of phenotypic plasticity" : "/publications/hunt2011phenotypicPlasticity.pdf"
|
41
|
-
"The genome of the leaf-cutting ant Acromyrmex echinatior suggests key adaptations to advanced social life and fungus farming" : "/publications/nygaard2011-acromyrmex-genome.pdf"
|
42
|
-
"Behind the Scenes of an Ant Genome Project" : "/publications/wurm2011antGenomeBehindTheScenes.pdf"
|
43
|
-
"The genome of the fire ant Solenopsis invicta" : "/publications/wurm2011fireAntGenome.pdf"
|
44
|
-
"Odorant Binding Proteins of the Red Imported Fire Ant, Solenopsis invicta: An Example of the Problems Facing the Analysis of Widely Divergent Proteins" : "/publications/gotzek2011obps.pdf"
|
45
|
-
"Parasitoid Wasps: From Natural History to Genomic Studies" : "/publications/wurm2010wasps.pdf"
|
46
|
-
"Changes in reproductive roles are associated with changes in gene expression in fire ant queens" : "/publications/wurm2010fireAntQueenDealationExpression.pdf"
|
47
|
-
"Fourmidable: a database for ant genomics" : "/publications/wurm2009antDatabase.pdf"
|
48
|
-
"Behavioral Genomics: A, Bee, C, G, T" : "/publications/wurm2007bees.pdf"
|
49
|
-
"An annotated cDNA library and microarray for large-scale gene-expression studies in the ant Solenopsis invicta" : "/publications/wang2007fireAntMicroarrays.pdf"
|