from bs4 import BeautifulSoup
import re

class Jiexi():
	def get_data(self, url, htm):
		soup = BeautifulSoup(htm, "html.parser", from_encoding="utf-8")
		new_data = self._get_new_data(url, soup)

		return  new_data

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

		new_data["url"] = 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('img', class_='image')
		new_data["Img"] = links2['src']

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

		links4 = soup.find("div", class_ = "vote-container").find_all("a", target = re.compile(r"_blank"))
		if links4 is None or len(links4) == 0:
			return
		new_data["Source_html"] = (links4[0])["href"]
		new_data["Source_name"] = links4[0].get_text()

		return new_data