10 实例4：用多线程对视频的爬取

"""使用多线程爬取梨视频视频数据"""
"""https://www.cnblogs.com/zivli/p/11614103.html"""


import requests
import re
from lxml import etree
from multiprocessing.dummy import Pool

url = 'https://www.pearvideo.com/category_5'
page_text = requests.get(url=url).text

tree = etree.HTML(page_text)
# 1、获取页面中视频详情地址
li_list = tree.xpath('//ul[@id="listvideoListUl"]/li')
url_list = []
for i in li_list:
    # 2、构造出每个视频的详情地址
    detail_url = "https://www.pearvideo.com/" + i.xpath('./div/a/@href')[0]
    name = i.xpath('./div/a/div[2]/text()')[0] + '.mp4'
    # 3、向视频详情地址发起请求
    detail_page = requests.get(url=detail_url).text
    # 4、从response中解析出视频的真实地址
    ex = 'srcUrl="(.*?)",vdoUrl'
    video_url = re.findall(ex, detail_page)[0]
    dic = {
        'name': name,
        'url': video_url
    }
    url_list.append(dic)


def get_video_data(d):
    """
    向视频地址发起请求，二进制写入本地文件
    :param d:
    :return:
    """
    url = d['url']
    data = requests.get(url=url).content
    print(d['name'], "正在下载。。。")
    with open(d['name'], 'wb') as f:
        f.write(data)
        print(d['name'], "下载成功。。。")


# 使用多进程处理
pool = Pool(4)
pool.map(get_video_data, url_list)
pool.close()
pool.join()