python花瓣图_【爬虫】花瓣图片爬虫，Python图片采集下载源码

#https://huaban.com/search/?q=纹理&category=industrial_design

#by 微信：huguo00289

# -*- coding: UTF-8 -*-

import requests,json,time

from fake_useragent import UserAgent

def ua():

ua=UserAgent()

headers={"User-Agent":ua.random,}

return headers

def get_pins():

img_urls=[]

headers={

'Accept': 'application/json',

'Accept-Encoding': 'gzip, deflate, br',

'Accept-Language': 'zh-CN,zh;q=0.9',

'Connection': 'keep-alive',

'Cookie': 'UM_distinctid=170c29e8d8f84f-0b44fc835bc8e3-43450521-1fa400-170c29e8d903de; _uab_collina=158415646085953266966037; __auc=30586f3f170d7154a5593583b24; __gads=ID=28115786a916a7a1:T=1584156505:S=ALNI_MbtohAUwMbbd5Yoa5OBBaSO0tSJkw; sid=s%3AkwSz9iaMxZf-XtcJX9rrY4ltNDbqkeYs.bc8fvfAq6DLGxsRQ6LF9%2FmHcjOGIhRSZC0RkuKyHd7w; CNZZDATA1256914954=1367860536-1583810242-null%7C1587376670; _hmt=1; CNZZDATA1256903590=1599552095-1584151635-https%253A%252F%252Fwww.baidu.com%252F%7C1588756694; referer=https%3A%2F%2Fwww.baidu.com%2Flink%3Furl%3DT3iVFqKfv0ZIY9RMrXTlhcNC2fDPWtr_IXajsAGNAP3%26wd%3D%26eqid%3Dab659ef1000000cb000000065eb28dfc; uid=29417717; _f=iVBORw0KGgoAAAANSUhEUgAAADIAAAAUCAYAAADPym6aAAABJ0lEQVRYR%2B1VuxHCMAyVFqKjomEjVgkb0VDRMQgrmJMdBcUn2VbAXDiSJpb9%2FHl6%2BiCEEAAAAiL9AJP5sgHSQuMXAOIB6NxXO354DOlhxodMhB8vicQxjgxrN4l1IrMRMRzmVkSeQ4pMIUdRp4RNaU4LsRzPNt9rKekmooWWDJVvjqVTuxKJeTWqJL1vkV2CZzJdifRWZ5EitfJrxbI2r6nEj8rxs5w08pAwLkXUgrGg%2FDoqdTN0IzK5ylAkXG6pgx%2F3sfPntuZqxsh9JUkk%2Fry7FtWbdXZvaNFFkgiPLRJyXe5txZfIbEQ4nMjLNe9K7FS9hJqrUeTnibQm%2BeoV0R5olZZctZqKGr5bsnuISPXy8muRssrv6X6AnNRbVau5LX8A%2BDed%2FQkRsJAorSTxBAAAAABJRU5ErkJggg%3D%3D%2CWin32.1920.1080.24; Hm_lvt_d4a0e7c3cd16eb58a65472f40e7ee543=1586168768,1586940578,1588755090,1588760062; __asc=73b5c1ee171e97aa8742174584b; _cnzz_CV1256903590=is-logon%7Clogged-in%7C1588760083771%26urlname%7Cxpmvxxfddh%7C1588760083771; Hm_lpvt_d4a0e7c3cd16eb58a65472f40e7ee543=1588760083',

'Host': 'huaban.com',

'Referer': 'https: // huaban.com / search /?q =% E7 % BA % B9% E7 % 90 % 86 & category = industrial_design',

'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',

'X-Request': 'JSON',

'X-Requested-With': 'XMLHttpRequest',

}

for i in range(1,25):

url=f"https://huaban.com/search/?q=%E7%BA%B9%E7%90%86&category=industrial_design&k9v6qdc9&page={i}&per_page=20&wfl=1"

response = requests.get(url,headers=headers,timeout=6).content.decode('utf-8')

time.sleep(2)

response_dict=json.loads(response)

print(response_dict)

pins=response_dict['pins']

print(len(pins))

for pin in pins:

key=pin['file']['key']

key =f'https://hbimg.huabanimg.com/{key}'

img_urls.append(key)

print(len(img_urls))

return img_urls

def tp(img_urls):

i=1

for img_url in img_urls:

r = requests.get(img_url,headers=ua(),timeout=6)

time.sleep(1)

with open(f'{i}.jpg','wb')as f:

f.write(r.content)

print("下载图片成功")

i=i+1

if __name__ == '__main__':

img_urls=get_pins()

tp(img_urls)