多线程爬取表情包

全拼

啥也不说直接上代码

[Python] 纯文本查看 复制代码

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

class Produce(threading.Thread):
    headers = {
        'User-Agent': 'Mozilla/5.0'
    }
    i = 1
    def __init__(self, page_queue, img_queue, *args, **kwargs):
        super(Produce, 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):
        r = requests.get(url, self.headers)
        r.encoding = r.apparent_encoding
        html = etree.HTML(r.text)
        imgs = html.xpath('//div[@class="random_article"]//img[@class!="gif"]')
        for img in imgs:
            # img_url = img.xpath('@data-original') 或者
            img_url = img.get('data-original')
            name = img.get('alt')
            name = re.sub(r'\?？。\.', "", name)
            if name:
                name = img.get('alt')
            else:
                name = self.i
                self.i += 1
            suddix = os.path.splitext(img_url)[1]
            filename = str(name) + suddix
            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():
                return
            img_url, filename = self.img_queue.get()
            request.urlretrieve(img_url, 'image/' + filename)
            print(filename+'下载完成')


def main():
    page_queue = Queue(500)
    img_queue = Queue(1000)
    for x in range(1,10):
        url = 'https://www.doutula.com/article/list/?page={}'.format(x)
        page_queue.put(url)

    for x in range(5):
        t = Produce(page_queue, img_queue)
        t.start()
    for x in range(5):
        t = Consumer(page_queue, img_queue)
        t.start()


if __name__ == '__main__':
    main()

顺便在这里问一下各位大佬
for x in range(1,10):url = 'https://www.doutula.com/article/list/?page={}'.format(x)
page_queue.put(url)
这段代码如果改成for x in range(1,5)，就会不进行爬取，直接结束？？也不知道是啥原因

家有葫芦仔

一共五个线程，你只给四个网站，岂不是符合了空线程的判断，那肯定会停啊