多线线程梨视频下载

要用多线程的方法下载梨视频，但是由于一直梨视频视频的数据对应的url一直拿不到，开始的时候还直接访问了某个视频的ajax返回的url，是个没用的，后来基本上完全参考了一篇博客，才踉踉跄跄的把这个小视频下载完成。

转载博客地址，在这里很感谢此博客的博主，去拿一个视频的对应的json解析出来然后构造出url这个自己目前都不知道是怎么得到的。

from lxml import etree
import requests
import os
import random
from multiprocessing.dummy import Pool

if not os.path.exists('./pearvideo/'):
    os.mkdir('./pearvideo/')

urls = []
download_urls = []
name_list = []
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 '
                  '(KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36'
}


def home_parse(url):
    home_page = requests.get(url=url, headers=headers).text

    home_tree = etree.HTML(home_page)

    li_list = home_tree.xpath('//*[@id="listvideoListUl"]/li')
    for li in li_list:
        href = 'https://www.pearvideo.com/' + li.xpath('.//@href')[0]
        urls.append(href)
        name = li.xpath('.//@vervideo-title')
        name_list.append(name)
    # print('li_href:', urls)


def get_download_urls(url_list):
    for url in url_list:
        contId = str(url.split('_')[-1])
        params = {
            'contId': contId,
            'mrd': str(random.random())
        }

        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 '
                          '(KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36',
            "Referer": "https://www.pearvideo.com/video_" + contId
        }
        url = 'https://www.pearvideo.com/videoStatus.jsp'
        rsp = requests.get(url=url, headers=headers, params=params)
        json = rsp.json()
        if 'videoInfo' in json.keys():
            srcUrl = json['videoInfo']['videos']['srcUrl']
            title = '/'.join(srcUrl.split('/')[0:-1])
            body = "/cont-" + contId + '-'
            footer = '-'.join(srcUrl.split('-')[1:])
            file_root = title + body + footer
            download_urls.append(file_root)
    print(download_urls)


def get_video(url):
    name = url.split('/')[-1]
    print('正在下载：{}'.format(name))

    data = requests.get(url=url, headers=headers).content
    with open('./pearvideo/' + name, 'wb') as f:
        f.write(data)
    print('成功下载：{}'.format(name))


# def multi_wrapper(args):
   # return get_video(*args)


def main():
    url = 'https://www.pearvideo.com/category_5'
    home_parse(url)
    get_download_urls(urls)
    pool = Pool(4)
    # url_name = list(zip(download_urls, name_list))
    # pool.map(multi_wrapper, url_name)
    # name_list传不进去，
    pool.map(get_video, download_urls)
    pool.close()
    pool.join()


if __name__ == '__main__':
    print('start')
    main()

• get_down_urls()函数中的henders的构造比较特别。
• home_parse()中不同视频的url的解析方式需要注意。