前言

“ 相信各位爬虫小伙伴在工作中，肯定遇到过写了大半天才出来的爬虫，好不容易运行起来，结果跑的贼慢，反正我是遇到过的。如今是大数据的时代，光会写爬虫根本没有什么竞争力，所以要学会对爬虫代码进行优化，优化爬虫的健壮性或者爬取速度等等，这些都能提高自己的竞争力！”

本文爬虫以糗事百科为例，以普通爬虫和多线程爬虫运行时间相比，相信大家都能领略到多线程的厉害之处！

多线程表情包分类爬取实战，话不多说，开干！

1、普通爬虫

import requests
from lxml import etree
import time
import sys

headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36"
}

#爬取
def Crawl(response):
    e = etree.HTML(response.text)
   #根据class值定位
    span_text = e.xpath("//div[@class='content']/span[1]")
    with open("duanzi.txt", "a", encoding="utf-8") as f:
        for span in span_text:
            info = span.xpath("string(.)")
            f.write(info)


#main
if __name__ == '__main__':
  //记下开始时间
    start = time.time()
    base_url = "https://www.qiushibaike.com/text/page/{}"
    for i in range(1, 14):
      #打印当前爬取的页数
        print("正在爬取第{}页".format(i))
        new_url = base_url.format(i)
        #发送get请求
        response = requests.get(new_url,headers=headers)
        Crawl(response)
  
  #记下结束时间
    end = time.time()
    #相减获取运行时间
    print(end - start)

2、多线程爬虫

import requests
from lxml import etree
#Queue队列，先进先出
from queue import Queue
from threading import Thread
import time

#请求头
headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36"
}

#数据获取
#继承Thread
class CrawlInfo(Thread):
    #重写init函数
    def __init__(self,url_queue,html_queue):
        Thread.__init__(self)

        self.url_queue = url_queue
        self.html_queue = html_queue

    # 重写run方法
    def run(self):
        while self.url_queue.empty()== False:
            url = self.url_queue.get()
            response = requests.get(url,headers=headers)
            if response.status_code == 200:
              #将数据放到队列中
                self.html_queue.put(response.text)

#数据解析、保存
#继承Thread
class ParseInfo(Thread):
    def __init__(self,html_queue):
        Thread.__init__(self)
        self.html_queue = html_queue

    def run(self):
      #判断队列是否为空。不为空则继续遍历
        while self.html_queue.empty() == False:
          #从队列中取最后一个数据
            e = etree.HTML(self.html_queue.get())
            span_text = e.xpath("//div[@class='content']/span[1]")
            with open("duanzi.txt", "a", encoding="utf-8") as f:
                for span in span_text:
                    info = span.xpath("string(.)")
                    f.write(info)


#开始
if __name__ == '__main__':
    start = time.time()
    #实例化
    url_queue = Queue()
    html_queue = Queue()
    
    base_url = "https://www.qiushibaike.com/text/page/{}"
    for i in range(1,14):
        print("正在爬取第{}页".format(i))
        new_url = base_url.format(i)
        url_queue.put(new_url)

    crawl_list = []
    for i in range(3):
        Crawl = CrawlInfo(url_queue,html_queue)
        crawl_list.append(Crawl)
        Crawl.start()

    for crawl in crawl_list:
      #join()等到队列为空，再执行别的操作
        crawl.join()

    parse_list = []
    for i in range(3):
        parse = ParseInfo(html_queue)
        parse_list.append(parse)
        parse.start()

    for parse in parse_list:
        parse.join()

    end = time.time()
    print(end - start)

3、对比运行

普通爬虫

多线程爬虫

可能还有些小伙伴觉得这几秒钟的时间没什么大不了的，还是那句话，现在是大数据时代，动不动都是上百万、上千万的数据量，在采集总量中会有很大的区别。如有不足之处或更多技巧，欢迎指教补充。愿本文的分享对您之后多线程有所帮助。谢谢～