Created
May 24, 2015 13:12
-
-
Save jin/4288b140b1e0d0fb6191 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'nokogiri' | |
require 'httparty' | |
require 'concurrent' | |
require 'pp' | |
class HWZRequest | |
def initialize | |
@host = "http://forums.hardwarezone.com.sg" | |
end | |
def get_thread_paths(path) | |
doc = Nokogiri::HTML(HTTParty.get(@host + '/' + path)) | |
thread_list_xpath = '//*[contains(@id, "thread_title_")]' | |
doc.xpath(thread_list_xpath).map do |element| | |
element.attributes['href'].value | |
end | |
end | |
def get_comments(thread, page = 1, max_pages = nil, comments = []) | |
url = @host + '/' + thread | |
if page > 1 | |
splitted = url.split(".") | |
splitted.pop | |
splitted[-1] += "-#{page}" | |
url = splitted.push("html").join(".") | |
end | |
begin | |
doc = Nokogiri::HTML(HTTParty.get(url)) | |
rescue SocketError => e | |
puts "Hit with SocketError #{e}, skipping.." | |
return comments | |
end | |
max_pages = max_pages_count(doc) if max_pages.nil? | |
puts "SUCCESS: Thread: #{thread} - pulled page #{page}/#{max_pages}" | |
comments_xpath = '//*[contains(@id, "post_message_")]' | |
c = doc.xpath(comments_xpath).map do |element| | |
comment = element | |
.children | |
.first | |
.content | |
.gsub(/\r|\t|\n/, " ") | |
.gsub(/\s+/, " ") | |
.strip | |
# Remove '$username wrote: { ... }' | |
splitted = comment.split(":") | |
splitted.count > 1 ? splitted[1..-1].join(":") : splitted.first | |
end | |
comments.push(*c) | |
if page == max_pages | |
puts "comment count: #{comments.count}" | |
comments | |
else | |
get_comments(thread, page + 1, max_pages, comments) | |
end | |
end | |
private | |
def max_pages_count(doc) | |
max_pages_xpath = '//div[@class="pagination"]' | |
result = doc.xpath(max_pages_xpath).first | |
if result.nil? | |
1 | |
else | |
result | |
.children[1] | |
.children | |
.first | |
.content | |
.scan(/(\d+)[^\d]*$/)[0][0] | |
.to_i | |
end | |
end | |
end | |
class HWZScraper | |
def self.scrape_thread_paths(forum_path) | |
req = HWZRequest.new | |
resp = req.get_thread_paths(forum_path) | |
save!('threads.txt', resp) | |
resp | |
end | |
def self.scrape_thread_comments(thread_path) | |
req = HWZRequest.new | |
resp = req.get_comments(thread_path).compact.map(&:strip).uniq | |
save!('comment.txt', resp) | |
end | |
def self.save!(filepath, data) | |
File.open(filepath, 'a') do |f| | |
data.each { |e| f.puts e } | |
end | |
end | |
end | |
# forums = { | |
# edmw: 'eat-drink-man-woman-16' | |
# } | |
# threads = [] << HWZScraper.scrape_thread_paths(forums[:edmw]) | |
# 786.upto(905) do |i| | |
# HWZScraper.scrape_thread_paths(forums[:edmw] + "/index#{i}.html") | |
# p "pulled #{i}" | |
# end | |
f = File.read('unique_threads.txt') | |
threads = f.split("\n") | |
pool = Concurrent::FixedThreadPool.new(5) | |
threads.each_with_index do |t, idx| | |
puts "Posting job #{idx} to poll" | |
pool.post do | |
HWZScraper.scrape_thread_comments(t) | |
puts "SUCCESS: Thread #{idx}/#{threads.count}" | |
end | |
end | |
pool.shutdown | |
pool.wait_for_termination |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment