Changeset 19026 for lang/ruby

Show
Ignore:
Timestamp:
09/09/08 02:09:23 (2 months ago)
Author:
drry
Message:
  • fixed regexps.
Files:
1 modified

Legend:

Unmodified
Added
Removed

  • lang/ruby/robot-twitter/trunk/robot-twitter.rb

    r18535 r19026  
    3535  page.search('td.content').each do |entry| 
    3636    name = entry.search('a').first.inner_text 
    37     content = CGI.unescapeHTML(entry.search('span.entry-content').first.inner_html).gsub(/^\s*/, '') 
     37    content = CGI.unescapeHTML(entry.search('span.entry-content').first.inner_html).gsub(/^\s+/, '') 
    3838 
    3939    # リンクは ... で省略されるので url に置き換える 
    40     content = content.gsub(/<a href="(\S*)"\s*rel="\S*".*>.*<\/a>/, '\1') 
     40    content = content.gsub(%r{<a\s+href="([^"]*)"\s+rel="[^"]*"[^>]*>.*</a>}m, '\1') 
    4141 
    4242    # @username のリンクを外す 
    43     content = content.gsub(/<a href="\S*".*>(.*)<\/a>/, '\1') 
     43    content = content.gsub(%r{<a\s+href="[^"]*"[^>]*>(.*)</a>}m, '\1') 
    4444 
    4545    meta = entry.search('a[@class="entry-date"]').first