#! /usr/bin/env python3
# coding=utf-8
from bs4 import BeautifulSoup
import re

class Parse():
	# new_urls, new_data = self.parse.Parser(new_url, html)
	def Parser(self, new_url, html):
		soup = BeautifulSoup(html, "html.parser", from_encoding="utf-8")
		new_urls = self._get_new_urls(soup)
		#new_data = self._get_new_data(new_url, soup)

		return new_urls

	def _get_new_urls(self, soup):
		new_urls = set()

		links = soup.find_all("span", class_="plid")
		for link in links:
			new_urls.add(((link.get_text()).split())[1])

		return new_urls

'''
	def _get_new_data(self, new_url, soup):
		new_data = {}

		new_data["url"] = new_url

		links1 = soup.find("div", class_="vote-container").find_all("li", text=re.compile(r"Size"))
		new_data["Size"] = links1[0].get_text()

		links2 = soup.find("div", class_="vote-container").find_all("a", target=re.compile(r"_blank"))
		if len(links2) != 0:
			new_data["Source_html"]= (links2[0])["href"]
			new_data["Source_text"]= links2[0].get_text()

		links3 = soup.find("div", class_="vote-container").find_all("span", id = re.compile(r"post"))
		new_data["Score"] = links3[0].get_text()

		return new_data
'''