Python实战---使用多线程爬取斗图啦表情包

使用多线程爬取斗图啦表情包

目标

爬取前一百页的表情包。

话不多说，直接上爬取结果：

只是作为练习，所以中途就把程序关掉了，可以看出来多线程爬取是真的快。

思路

1、先写出不使用多线程爬取页面的代码
2、使用多线程的生产者和消费者模式来爬取。

实现代码

'''
@Description: 爬取斗图啦的表情包
@Author: sikaozhifu
@Date: 2020-06-11 14:20:53
@LastEditTime: 2020-06-11 15:36:21
@LastEditors: Please set LastEditors
'''
import requests
from lxml import etree
import os
from urllib import request
import re
import threading
from queue import Queue


class Producer(threading.Thread):
    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.pares_url(url)

    def pares_url(self, url):
        headers = {
            'User-Agent':
            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'
        }
        response = requests.get(url, headers=headers)
        text = response.text
        html = etree.HTML(text)
        imgs = html.xpath(
            '//div[@class = "page-content text-center"]//img[@class != "gif"]')
        for img in imgs:
            img_url = img.get('data-original')
            alt = img.get('alt')
            # 要用正则表达式去掉win10下不满足命名规则的特殊符号
            alt = re.sub(r'[\?？。\.!！,，\/:\*<>|"]', '', alt)
            suffix = os.path.splitext(img_url)[1]
            filename = alt + suffix
            self.img_queue.put((img_url, filename))


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:
            if self.img_queue.empty() and self.page_queue.empty():
                break
            img_url, filename = self.img_queue.get()
            request.urlretrieve(img_url, 'images/'+filename)
            print(filename + '下载完成！')


def main():
    page_queue = Queue(100)
    img_queue = Queue(1000)
    for x in range(1, 101):
        url = 'https://www.doutula.com/photo/list/?page=%s' % x
        page_queue.put(url)
    for x in range(15):
        t = Producer(page_queue, img_queue)
        t.start()
    for x in range(64):
        t = Consumer(page_queue, img_queue)
        t.start()


if __name__ == "__main__":
    main()

也可以在控制台打印爬取的图片名字，简直快到飞起：

总结

多线程爬取就是舒服哇， i 了 i 了。