【python爬虫】使用线程池来爬取数据

简介

• 在爬虫的过程中，难免会遇到阻塞的情况，这样子效率就会大大的降低，所以在爬虫时一般都需要使用到，线程池，来实现并发的爬虫，来提高效率

具体操作

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

#进行UA伪装
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36'
}
#url路径
url = 'https://sc.chinaz.com/tupian/meinvtupian.html'
#将页面实例化，并且对其进行解析，以便于获取每一个图片的url
page_text = requests.get(url=url, headers=headers).text
tree = etree.HTML(page_text)
#获取一个存储所有li的集合
li_list = tree.xpath('//*[@id="container"]/div')
urls = []
for li in li_list:
    img_url = 'http:' + li.xpath('./div/a/@href')[0]
    img_name = li.xpath('./div/a/@alt')[0] + '.rar'
    img_name = img_name.encode('iso-8859-1').decode('utf-8')
    # print(img_name,img_url)
    detail_page_text = requests.get(url=img_url, headers=headers).text
    # print(detail_page_text)
    tree = etree.HTML(detail_page_text)
    detail_url = tree.xpath('//*[@class="downbody"]/div[3]/a[4]/@href')[0]
    #用字典来存储图片名及其url
    dic = {
        'name': img_name,
        'url': detail_url
    }
    urls.append(dic)
def get_vi_data(url):
    url = dic['url']
    print(dic['name'], '正在下载.....')
    data = requests.get(url=url, headers=headers).content
    # 持久化存储的操作
    with open('./resource/' + dic['name'], 'wb') as fp:
        fp.write(data)
        print(dic['name'], '下载成功')

#设置一个线程池，他的容量为5
pool = Pool(5)
#因为在get_vi_data方法中会发生阻塞，因此将这个方法放入线程池中来提高爬取的效率
pool.map(get_vi_data, urls)
#关闭线程池
pool.close()
pool.join()