通用代码
import threading
import requests
from lxml import etree
import os
from urllib import request
from queue import Queue
class Producer(threading.Thread):
headers = {
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 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=url,headers=self.headers)
text = response.text
html = etree.HTML(text)
img_list = html.xpath('//div[@class="page-content text-center"]/div/a/img')
for img in img_list:
img_url = img.xpath('./@data-original')[0]
img_name = img.xpath('./@alt')[0]+'.jpg'
self.img_queue.put((img_url, 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:
if self.page_queue.empty() and self.img_queue.empty():
break
img_url, img_name = self.img_queue.get()
request.urlretrieve(img_url, "./imgs/" + img_name)
print(img_name + " 下载完成！")
# 定义一个主方法，该方法向处理方法中传值
def main():
page_queue = Queue(50) #存储页码链接
img_queue = Queue(100)#存储解析出来的图片链接
#想要爬取前10页的数据
for x in range(1, 11):
url = "https://www.doutula.com/photo/list/?page=%d" % x
page_queue.put(url) #将10页的页码链接加入到了page_queue
for x in range(3):
t = Producer(page_queue, img_queue)
t.start()
for x in range(3):
t = Consumer(page_queue, img_queue)
t.start()
if __name__ == '__main__':
main()
-------------------------------------------
个性签名：代码过万，键盘敲烂！！！
如果觉得这篇文章对你有小小的帮助的话，记得在右下角点个“推荐”哦，博主在此感谢！
