清华大佬耗费三个月吐血整理的几百G的资源，免费分享！....>>>

__author__ = 'Saint'

import os
import urllib.request
import json

from html.parser import HTMLParser

# 从获取的网页内容筛选图片的内容
class MyHtmlParser(HTMLParser):
    links = []

    def handle_starttag(self, tag, attrs):
        if tag == "img":
            if len(attrs) == 0:
                pass
            else:
                for name, value in attrs:
                    if name == "src":
                        self.links.append(value)


class Down(object):

    # 总的目录
    img_path = "E:/saint"

    # 下载目录
    dir = ''

    # 采集源地址
    collect_links = ["http://dy.163.com/v2/media/articlelist/T1374483113516-1", "http://dy.163.com/v2/media/articlelist/T1420776257254-1", "http://dy.163.com/v2/media/articlelist/T1376641060407-1"]
    img_links = "http://dy.163.com/v2/article"

    def handleCollect(self):
        for collect_link in self.collect_links:
            notice = "开始从[" + collect_link + "]采集图片"
            print(notice)
            # 建立下载的目录
            dir_name = collect_link.split("/")[-1]
            self.isDirExists(dir_name)

            dict = self.getListFromSubscribe(collect_link)
            if dict == False:
                print("数据采集失败，是否继续(y/n)")
                op = input();
                if op == "y":
                    os.system("cls")
                    pass
                elif op == "n":
                    print("停止采集")
                    break
                else:
                    os.system("cls")
                    print("非法输入")
                    break
            else:
                for page in dict:
                    page_uri = self.img_links + "/" + page["tid"] + "/" + page["docid"]
                    self.getImgFromUri(page_uri)
                    print("是否继续(y/n)")
                    new_op = input();
                    if new_op == "n":
                        os.system("cls")
                        print("采集完毕")
                        break

        print("OK")



    # 从订阅源获取目录
    def getListFromSubscribe(self, uri):
        res = urllib.request.urlopen(uri)
        if res.code < 200 or res.code > 300:
            os.system("clear")
            return False
        else:
            result = res.read().decode("gbk") # 3.4版本的read()返回的是byte类型，需要decode()处理，选项是网页编码
            dict = json.loads(result)
            if dict['code'] != 1:
                print(dict['msg'])
                return False
            else:
                return dict['data']

    # 获取本期订阅的网页，并从网页中提取出来需要的图片
    def getImgFromUri(self, uri):
        html_code = urllib.request.urlopen(uri).read().decode("gbk")
        hp = MyHtmlParser()
        hp.feed(html_code)
        hp.close()

        for link in hp.links: # hp.links 是图片的下载地址的列表
            self.writeToDisk(link)

    # 检查文件目录是否存在，如果不存在，则创建目录
    def isDirExists(self, dir_name):
        self.dir = self.img_path + dir_name
        isExists = os.path.exists(self.dir)
        if not isExists:
            os.makedirs(self.dir)
            return True
        else:
            return True

    # 下载文件，并且写入磁盘
    def writeToDisk(self, url):
        os.chdir(self.dir)
        file = urllib.request.urlopen(url).read()
        file_name = url.split("/")[-1]
        open(file_name, "wb").write(file)
        return True

if __name__ == "__main__":
    down = Down()
    down.handleCollect()