爬虫实战之多线程下载表情包

一般下载 

import requests
from lxml import etree
import os
import re
from urllib.request import urlretrieve
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36',
    'reference':'https://www.doutula.com/photo/list/',
    'cookie':'Hm_lvt_2fc12699c699441729d4b335ce117f40=1615008627; BAIDU_SSP_lcr=https://www.baidu.com/link?url=UQoesURrEsUM4NvE5ZacHkR-o392OBjm7Vf1Kmexgz6f1t95skqOdvaJhf-yr-ST&wd=&eqid=d489b93900083bf50000000560431370; _agep=1615008629; _agfp=71fff58d61b1da1742311be98d81dade; _agtk=c790afa4b042c24f31f6047911d8f716; Hm_lpvt_2fc12699c699441729d4b335ce117f40=1615008678'

}
def parse_page(url):
    response = requests.get(url, headers=headers)
    text = response.text
    html = etree.HTML(text)
    print(html)
    #imgs = html.xpath("//div[@class='page-content text-center']//a//img")
    imgs=html.xpath('//div[@class="page-content text-center"]//img[@class!="gif"]')
    i = 0

    for img in imgs:
        #print(etree.tostring(img,encoding='utf-8').decode('utf-8'))
        img_url = img.xpath(".//@data-original")[0]
        suffix = os.path.splitext(img_url)[1]
        alt = img.xpath(".//@alt")[0]
        alt= re.sub(r'[，。？?,/\\·]', '', alt)
        if alt=='':

            i=i+1
            alt='image%d'%i
        img_name = alt + suffix
        urlretrieve(img_url, 'images/'+img_name)
def spider():
    for x in range(1, 2):
        url = "http://www.doutula.com/photo/list/?page=%d" % x
        parse_page(url)

if __name__ == '__main__':
    spider()

多线程下载图片

import threading
import requests
from lxml import etree
from urllib import request
import os
import re
from queue import Queue
i = 0
class Producer(threading.Thread):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36'
    }
    def __init__(self,page_queue,img_queue,*args,**kwargs):
        super(Producer, self).__init__(*args,**kwargs)
        self.page_queue = page_queue
        self.img_queue = img_queue
    def run(self):
        while True:
            if self.page_queue.empty():
                break
            url = self.page_queue.get()
            self.parse_page(url)

    def parse_page(self,url):
        response = requests.get(url, headers=self.headers)
        text = response.text
        html = etree.HTML(text)
        imgs = html.xpath('//div[@class="page-content text-center"]//img[@class!="gif"]')
        global i
        for img in imgs:
            # print(etree.tostring(img,encoding='utf-8').decode('utf-8'))
            img_url = img.xpath(".//@data-original")[0]
            suffix = os.path.splitext(img_url)[1]
            alt = img.xpath(".//@alt")[0]
            alt = re.sub(r'[，。？?,/\\·]', '', alt)
            if alt == '':
                i = i + 1
                alt = 'image%d' % i
            img_name = alt + suffix
            #print(img_name)
            self.img_queue.put((img_url, img_name))
            # request.urlretrieve(img_url, 'images/'+img_name)

class Consumer(threading.Thread):
    def __init__(self,page_queue,img_queue,*args,**kwargs):
        super(Consumer, self).__init__(*args,**kwargs)
        self.page_queue = page_queue
        self.img_queue = img_queue
    def run(self):
        while True:
            print("xiaofeiz")
            if self.img_queue.empty():
                if self.page_queue.empty():
                    return
            img = self.img_queue.get(block=True)
            url,filename = img
            #request.urlretrieve(url,'images/'+filename)
            print(filename+'  下载完成！')

def spider():
    page_queue = Queue(5)#队列数目一定要和你爬取页数一样否则可能出错
    img_queue = Queue(40)
    for x in range(1, 6):
        url = "http://www.doutula.com/photo/list/?page=%d" % x
        page_queue.put(url)
    for x in range(4):
        t = Producer(page_queue,img_queue)
        t.start()

    for x in range(4):
        t = Consumer(page_queue,img_queue)
        t.start()
if __name__ == '__main__':
    spider()

对于消费者跳出还存在一些问题，网上很多代码设置的页数比较大还是存下这个问题，

待解决，如果你有好方法欢迎留言