Changeset 19698 for lang/ruby

Show
Ignore:
Timestamp:
09/22/08 02:06:34 (2 months ago)
Author:
mtv
Message:

modified for new web design of twitter.com

Files:
1 modified

Legend:

Unmodified
Added
Removed
  • lang/ruby/robot-twitter/trunk/robot-twitter.rb

    r19026 r19698  
    2929statuses = "" 
    3030 
    31 for i in 1..10 
     31for i in 1..30 
    3232  puts "scraping ... Page " + i.to_s + "\n" 
    3333  page = agent.get('http://twitter.com/home/?page=' + i.to_s) 
    3434  page.body = page.body.toutf8 
    35   page.search('td.content').each do |entry| 
     35 
     36  page.search('div.status-body').each do |entry| 
    3637    name = entry.search('a').first.inner_text 
    3738    content = CGI.unescapeHTML(entry.search('span.entry-content').first.inner_html).gsub(/^\s+/, '') 
     
    4445 
    4546    meta = entry.search('a[@class="entry-date"]').first 
    46     time = meta.search('abbr.published').first.inner_text 
     47    time = meta.search('span.published').first.inner_text 
    4748    statuses = meta["href"] 
    4849