python抓取制定产品图片及简介代码实现

python抓取制定产品图片及简介代码实现

# coding:utf-8     设置编码格式
import requests   #引入requests
from bs4 import BeautifulSoup
import re   #引入正则
import lxml
import os  
#图片下载函数
def download_image(url, image_name=None):  
    response = requests.get(url, stream=True)  
    # 检查请求是否成功  
    if response.status_code == 200:  
        # 如果未指定图片名称，则生成一个随机名称  
        if image_name is None:  
            import uuid  
            image_name = str(uuid.uuid4()) + '.jpg'  
  
        # 打开一个文件以保存图片  
        with open(image_name, 'wb') as f:  
            f.write(response.content)  
  
        print(f"图片已保存为：{image_name}")  
    else:  
        print(f"请求失败，HTTP状态码为：{response.status_code}") 
		

#抓取产品链接  https://www.aimitoy.com/products/roating-king-white
#循环执行，执行完一次后，重新开始
while True:
	url = input("请输入url：")
	#print('请输入url')
	html=requests.get(url)
	html.encoding = "utf-8"  #修改文件编码格式  解决乱码问题
	content=html.text        #保存请求到的网页源码
	soup = BeautifulSoup(content,'lxml')   #将网页源码构造成BeautifulSoup对象，方便操作
	#print(soup)
	#a_list=soup.find_all('a',class_="full-unstyled-link") #获取网页中的所有a标签对象
	#a_list=soup.select('.card__heading .h5> .full-unstyled-link') #获取网页中的所有a标签对象
	a_list=soup.select('ul[id="Slider-Thumbnails-template--14450556207192__main"] li img')
	#title=soup.find('h1').contents[0]  #获取h1标题里的文本内容
	title=soup.find_all('h1')
	mulu=title[0].string#获取h1标题里的文本内容
	os.makedirs(mulu,exist_ok=True) #创建目录

	#获取产品标题
	# productTitle=soup.select('span[id="productTitle"]')[0].string
	# #print(productTitle)
	# with open(mulu+'/content.txt', "a") as f:
	# 	f.write('==========pro title=========='+'\n')
	# 	f.write(productTitle)
	print(mulu+'产品文档建立完成')	
	#获取简介
	#productcontent=soup.select('div[class="product__description rte quick-add-hidden"]').get_text()
	productcontent=soup.find('div', attrs={'class': 'product__description rte quick-add-hidden'}).get_text()
	#print(productcontent)
	with open(mulu+'/content.txt', "a",encoding='utf-8') as f:
		f.write('\n'+'==========pro detail======='+'\n')
		f.write(productcontent)
	#下载简介图片
	con_pic=soup.select('div[class="product__description rte quick-add-hidden"] img')
	num=1
	for p in con_pic:
		#print(p.get('src'))
		savename1=mulu+'/con_pic'+str(num)+'.jpg'
		download_image(p.get('src'),savename1)
		#print(savename)
		num += 1

	#下载图片
	#print(a_list[0].get('src'))
	#print(len(a_list))
	#保存产品图片
	id = 1
	for img in a_list:
		imgurl='https:'+img.get('src').split('?')[0]
		name='/pic'+str(id)+'.jpg'
		savename=mulu+name
		download_image(imgurl,savename)
		id += 1 
	print('采集完成')


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81