"""
#该代码仅供交流与测试，禁止非法盈利
#作者:yhkdw
"""
import json
import urllib.request
import time
from lxml import etree
headers = {
#请求头根据自己的浏览器定制
#不同的浏览器请求头不同
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'accept-language': 'zh-CN,zh;q=0.9,en-GB;q=0.8,en-US;q=0.7,en;q=0.6',
'cache-control': 'max-age=0',
'cookie': '有用的cookie',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
'sec-fetch-dest': 'document',
'sec-fetch-mode': 'navigate',
'sec-fetch-site': 'same-origin',
'sec-fetch-user': '?1',
'upgrade-insecure-requests': '1',
'user-agent': '有用的ua',
}
# url='https://www.xiaohongshu.com/explore/6149f62f000000000102d0cd'
# 输入下载链接
url = input('请输入你要下载的图片链接')
request = urllib.request.Request(url=url, headers=headers)
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
# print(content)
# 找到起始和结束的url
begin = content.find('imageList') + 11
new_content = content[begin::]
new_end = new_content.find('],"')
# end=content.find('],"')
# json_img=content[begin:end+1]
# 转成json
json_img = new_content[:new_end + 1:]
# print(json_img)
try:
image_json = json.loads(json_img)
i = 1
for image in image_json:
if image.get('url') and image.get('traceId'):
print('正在下载' + str(i) + '图片')
img_url = image['url'][:30] + image['traceId']
urllib.request.urlretrieve(img_url, 'F://redbook//' + image['traceId'] + '.webp')
time.sleep(1)
i += 1
except:
print('服务器在升级')
标签：img,小红书,image,30,content,url,json,sec,2023 From： https://www.cnblogs.com/yhkdw/p/17274718.html