jsonify: Support tweets.csv
Allow official archive tweets.csv as input to create Ebooks::Archive compatible JSON archive
This commit is contained in:
parent
db453600be
commit
74fd9c1e2e
1 changed files with 17 additions and 9 deletions
26
bin/ebooks
26
bin/ebooks
|
@ -2,6 +2,7 @@
|
|||
# encoding: utf-8
|
||||
|
||||
require 'twitter_ebooks'
|
||||
require 'csv'
|
||||
|
||||
$debug = true
|
||||
|
||||
|
@ -154,16 +155,23 @@ STR
|
|||
|
||||
tweets = []
|
||||
id = nil
|
||||
File.read(path).split("\n").each do |l|
|
||||
if l.start_with?('# ')
|
||||
id = l.split('# ')[-1]
|
||||
else
|
||||
tweet = { text: l }
|
||||
if id
|
||||
tweet[:id] = id
|
||||
id = nil
|
||||
if path.split('.')[-1] == "csv" #from twitter archive
|
||||
csv_archive = CSV.read(path, :headers=>:first_row)
|
||||
tweets = csv_archive.map do |tweet|
|
||||
{ text: tweet['text'], id: tweet['tweet_id'] }
|
||||
end
|
||||
else
|
||||
File.read(path).split("\n").each do |l|
|
||||
if l.start_with?('# ')
|
||||
id = l.split('# ')[-1]
|
||||
else
|
||||
tweet = { text: l }
|
||||
if id
|
||||
tweet[:id] = id
|
||||
id = nil
|
||||
end
|
||||
tweets << tweet
|
||||
end
|
||||
tweets << tweet
|
||||
end
|
||||
end
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue