keyword = input("请输入关键字:")
head = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36"}
print("程序启动中... 一页30张图片")
page = int(input("需要爬取几页"))
url = 'https://image.baidu.com/search/acjson?'
p = 1
k = 0
import requests
import os
import json
import urllib
from bs4 import BeautifulSoup
try:
os.mkdir('E:/素材/'+keyword)
except:
print("目录已经存在")
for i in range(1,page+1):
param = {
'tn': 'resultjson_com',
'logid': '8846269338939606587',
'ipn': 'rj',
'ct': '201326592',
'is': '',
'fp': 'result',
'queryWord': keyword,
'cl': '2',
'lm': '-1',
'ie': 'utf-8',
'oe': 'utf-8',
'adpicid': '',
'st': '-1',
'z':'' ,
'ic':'' ,
'hd': '',
'latest': '',
'copyright': '',
'word': keyword,
's':'' ,
'se':'' ,
'tab': '',
'width': '',
'height': '',
'face': '0',
'istype': '2',
'qc': '',
'nc': '1',
'fr': '',
'expermode': '',
'force': '',
'cg': 'girl',
'pn': p,#从第几张图片开始
'rn': '30',
'gsm': '1e',
}
p = p+29
r = requests.get(url,headers=head,params=param)
r.encoding = 'utf-8'
j = json.loads(r.text, strict=False)
for i in j['data']:
try:
k = k+1
urllib.request.urlretrieve(i['thumbURL'],'E:/素材/'+keyword+"/"+str(k)+'.jpg')
except:
pass
print("处理完成")
Last modification:August 17, 2021
© Allow specification reprint