爬虫之线程池的应用

恰当的使用线程池可以很大程度上的提升爬去速率，下面介绍一个使用线程池的案例

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

#实例化一个线程池对象
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 = []
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
    video_url = re.findall('srcUrl="(.*?)",vdoUrl',detail_page,re.S)[0]
    video_url_list.append(video_url)
    
video_data_list = pool.map(getVideoData,video_url_list)

pool.map(saveVideo,video_data_list)

def getVideoData(url):
    return requests.get(url=url,headers=headers).content

def saveVideo(data):
    fileName = str(random.randint(0,5000))+'.mp4'
    with open(fileName,'wb') as fp:
        fp.write(data)