python网络爬虫——线程池

本实例主要进行线程池创建，多线程获取、存储视频文件

梨视频：利用线程池进行视频爬取

#爬取梨视频数据
import requests
import re
from lxml import etree
from multiprocessing.dummy import Pool
import random

# 定义获取视频数据方法
def getVideoData(url): # url为列表中的视频url
    return requests.get(url=url,headers=headers).content

# 定义存储数据方法
def saveVideo(data):
    fileName = str(random.randint(0,5000))+'.mp4'
    with open(fileName,'wb') as fp:
        fp.write(data)

# 爬取数据
#实例化一个线程池对象，开启5个线程池
pool = Pool(5)

url = 'https://www.pearvideo.com/category_1'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
page_text = requests.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@id="listvideoList"]/ul/li')

video_url_list = [] # 存的是将要下载视频的url
for li in li_list:
    detail_url = 'https://www.pearvideo.com/'+li.xpath('./div/a/@href')[0]
    detail_page = requests.get(url=detail_url,headers=headers).text
    #因为视频连接不在标签汇中，而是一个js语句，所以用正则匹配
    video_url = re.findall('srcUrl="(.*?)",vdoUrl',detail_page,re.S)[0]
    video_url_list.append(video_url)
    
# map函数的应用：参数1：回调函数，参数2：列表；
#将列表中的参数赋值给回调函数的形参，让回调函数处理
video_data_list = pool.map(getVideoData,video_url_list)

pool.map(saveVideo,video_data_list)