学习进度12

import requests
from lxml import html
from urllib import request
import os
import re
import threading
from queue import Queue

etree = html.etree


class P(threading.Thread):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400'
    }

    def __init__(self, page_queue, img_queue, *args, **kwargs):
        super(P, 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):
        resp = requests.get(url, headers=self.headers)
        text = resp.text
        html = etree.HTML(text)
        imgs = html.xpath("//div[@class='page-content text-center']//img[@class!='gif']")
        for img in imgs:
            # 获取图片属性
            img_url = img.get('data-original')
            img_name = img.get('alt')
            img_name = re.sub(r'[\?？\.，。!！\*]', '', img_name)
            # 分隔 提取文件后缀
            suffix = os.path.splitext(img_url)[1]
            # 组成文件名
            filename = img_name + suffix
            print(filename)
            self.img_queue.put((img_url, filename))


class C(threading.Thread):
    def __init__(self, page_queue, img_queue, *args, **kwargs):
        super(C, 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()
            # 下载到本地
            request.urlretrieve(img_url, 'imgs/' + filename)


def main():
    page_queue = Queue(100)
    img_queue = Queue(500)
    for x in range(1, 100):
        url = 'http://www.doutula.com/photo/list/?page=%d' % x
        page_queue.put(url)

    for x in range(5):
        t = P(page_queue, img_queue)
        t.start()
    for x in range(5):
        t = C(page_queue, img_queue)
        t.start()


if __name__ == '__main__':
    main()

多线程下载图片