Scraper

01_naver_scraper.pl

#!/usr/bin/env perl
use strict;
use LWP::Simple;
binmode(STDOUT, ":utf8");
 
my $url = "http://www.naver.com";
my $content = get($url);
die "Couldn't get it!" unless defined $content;
 
if ($content =~ m/<ol.*?id="realrank"(.*?)<\/ol>/gsmi){
  my $list = $1;
  while ($list =~ m/<li value="(\d+)".*?><a href.*?title="(.*?)">.*?<\/a>.*?<\/li>/gsmi){
    print "$1\t$2\n";
  }
}

02_daum_scraper.pl

#!/usr/bin/env perl
use strict;
use LWP::Simple;
binmode(STDOUT, ":utf8");
 
my $url = "http://movie.daum.net/movieinfo/now/movieinfoReleased.do?modeType=all&order=recently";
my $content = get($url);
die "Couldn't get it!" unless defined $content;
 
while ($content =~ m/<strong><a[\s]href\=\"http:\/\/movie\.daum\.net\/moviedetail\/moviedetailMain.do\?movieId=[\d]{1,6}\"[\s]title=\".*?\">(.*?)<\/a><\/strong>/gsmi){
  my $list = $1;
  print $list . "\n";
}

03_daum_scraper.py

#!/usr/bin/env python
 
from lxml.cssselect import CSSSelector
import lxml.html
import httplib2
 
h = httplib2.Http(".cache")
resp, content = h.request("http://movie.daum.net/movieinfo/now/movieinfoReleased.do?modeType=all&order=recently", "GET")
 
doc = lxml.html.fromstring(content);
sel = CSSSelector('#div_nowMovieTab_1 dl dt strong a')
for e in sel(doc):
  print e.get('title');

04_daum_scraper.rb

#!/usr/bin/env ruby
require 'rubygems'
require 'nokogiri'
require 'open-uri'
 
page = Nokogiri::HTML(open("http://movie.daum.net/movieinfo/now/movieinfoReleased.do?modeType=all&order=recently"))
page.css("#div_nowMovieTab_1 dl dt strong a").each{|link| puts link["title"]}

05_movikr.rb

#!/usr/bin/env ruby
require 'rubygems'
require 'nokogiri'
require 'open-uri'
 
page = Nokogiri::HTML(open("http://movie.daum.net/movieinfo/now/movieinfoReleased.do?modeType=all&order=recently"))
page.css("#div_nowMovieTab_1 dl dt strong a").each do |link|
  movie_info = Nokogiri::HTML(open(link["href"]))
  puts movie_info.css("#movieinfoDetail strong.title_kor").text
  puts movie_info.css("#movieinfoDetail span.eng").text
  puts movie_info.css("#movieinfoDetail p.poster img").attribute('src').to_s.gsub(/C[\d]{2,3}x[\d]{2,3}/, "R678x0")
end