#! /usr/bin/env python3
# coding=utf-8
from bs4 import BeautifulSoup
import re
from datetime import datetime
import os
import sys
import random
import string

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["title"] = url

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

		links2 = soup.find('img', class_='image')
		#new_data["img_url"] = links2['src']
		picture_url = links2['src']
		'''生产随机字符串作为图片名'''
		ran_str = ''.join(random.sample(string.ascii_letters + string.digits, 16))
		picture_str = ran_str + ".jpg"
		#print(picture_str)

		'''下载图片到指定位置并且重新命名'''
		cmd = "wget " + picture_url + " -O " + "/data/www/redis_news_code/download/%s" % (picture_str)
		res = os.system(cmd)
		if res != 0:
			print("下载失败")
			sys.exit(1)

		'''将本地网页路径写入数据库'''
		local_url = "http://redisnews.quyihuang.cn/download/" + picture_str
		new_data["img_url"] = local_url

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

		neirong = Size + "  Score:" + Score
		new_data["content"] = neirong

		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["author"] = links4[0].get_text()

		new_data["created_at"] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
		new_data["updated_at"] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')

		new_data["is_valid"] = "1"
		new_data["news_type"] = "图片"

		return new_data