#-*- coding:utf8 -*-
import requests
import bs4
from bs4 import BeautifulSoup
import xlwt
import json
import re
import urllib

def text_replace(text):
    return text.getText().replace('\n', '').replace('\r', '').strip()


def url_content(url, header, proxies=False):
    if proxies:
        res_sub = requests.get(url, proxies={'http': proxies}, headers=header)
        list_txt = BeautifulSoup(res_sub.text, 'html.parser')
    else:
        res_sub = requests.get(url, headers=header)
        list_txt = BeautifulSoup(res_sub.text, 'html.parser')
    return list_txt

def postData(value):
    res_sub = requests.post('http://api.myfristweb.com/default/beike', value)
    res_sub.encoding = 'utf-8'
    print(res_sub)
    res_sub = json.loads(res_sub.text)
    print(res_sub)
    if res_sub['code'] == 200:
        return True
    else:
        return False


def download_videofile(video_links):
    root='./'
    for link in video_links:
        file_name = link.split('/')[-1]
        print("文件下载:%s" % file_name)
        r = requests.get(link, stream=True)
        with open(root+file_name, 'wb') as f:
            for chunk in r.iter_content(chunk_size=1024 * 1024):
                print(chunk)
                if chunk:
                    f.write(chunk)

        print("%s 下载完成!\n" % file_name)
    print("所有视频下载完成!")
    return

header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'}
url = 'http://mskt.hner.cn/index.html'
html = requests.get(url, headers=header).text

hrefs = re.findall(r'"href": "(.*?)"',html)
for one in hrefs:
    if one != '#':
        arr = one.split("/")
        name = arr[3].split(".")
        mp4Urls = 'http://mskt.hner.cn/vhtml/' + arr[2] + '/' + arr[3]
        print(mp4Urls)
        detail = url_content(mp4Urls,header)
        mp4Url = detail.find("video")['src']
        file_name = name[0] + '.mp4'
        print(mp4Url)
        r = requests.get(mp4Url, stream=True,headers=header)
        with open('./'+file_name, 'wb') as f:
            for chunk in r.iter_content(chunk_size=1024 * 1024):
                if chunk:
                    f.write(chunk)
        print("%s 下载完成!\n" % file_name)
    print(one)
    exit()