使用Requests+Re库方法多线程爬取亚马逊商城商品图片，以关键词“书包”搜索页面的商品的图片，爬取0-2页面商品图片。
关键词：多线程爬虫程序、商城网站的遍历，链接的查找和访问。巩固搜索接口和翻页处理。
import requests
from fake_useragent import UserAgent
import re
from multiprocessing.dummy import Pool as ThreadPool
import time
#获取图片数据
def get_pagelist(pagenum):
url="https://www.amazon.cn/s?k=%E4%B9%A6%E5%8C%85&__mk_zh_CN=%E4%BA%9A%E9%A9%AC%E9%80%8A%E7%BD%91%E7%AB%99&crid=1RAID9NTPCARM&sprefix=%E4%B9%A6%E5%8C%85%2Caps%2C154&ref=nb_sb_noss_1"
headers={'User-Agent':UserAgent().random}
data={
'block_last_random': 'custom',
'block_custom': '54',
'action': 'list_publications',
'page': pagenum,
}
response=requests.post(url=url,data=data,headers=headers,timeout=8)
html=response.content.decode('utf-8')
datamedias=re.findall(r'<img class="s-image" src="(.*?)"',html,re.S)
#print(len(datamedias))
return datamedias
#下载图片数据
def dowm(imgurl):
imgname=imgurl.split("/")[-1]
headers = {'User-Agent': UserAgent().random}
r=requests.get(url=imgurl,headers=headers,timeout=8)
with open(f'D:\DATASET\img\{imgname}','wb') as f:
f.write(r.content)
print(f'{imgname} 图片下载成功了！')
#多线程下载图片数据
def thread_down(imgs):
pool = ThreadPool()
results = pool.map(dowm, imgs)
pool.close()
pool.join()
print("采集所有图片完成！")
#主程序
def main():
start_time = time.time()
for i in range(0,3):
print(f'正在爬取采集第 {i} 页图片数据..')
imgs=get_pagelist(i)
thread_down(imgs)
end_time = time.time()
print("time taken:",end_time - start_time, "seconds")
if __name__=='__main__':
main()