#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Project: GetBaiduImage
# File : main.py
# Author : Long.Xu <fangkailove@yeah.net>
# http://gnolux.blog.csdn.net
#
# Time : 2023/5/16 19:38
# Copyright 2023 Long.Xu All rights Reserved.
import json
import requests
def decode_url(url):
if url.startswith("http"):
return url
table = {'w': "a", 'k': "b", 'v': "c", '1': "d", 'j': "e", 'u': "f", '2': "g", 'i': "h",
't': "i", '3': "j", 'h': "k", 's': "l", '4': "m", 'g': "n", '5': "o", 'r': "p",
'q': "q", '6': "r", 'f': "s", 'p': "t", '7': "u", 'e': "v", 'o': "w", '8': "1",
'd': "2", 'n': "3", '9': "4", 'c': "5", 'm': "6", '0': "7", 'b': "8", 'l': "9", 'a': "0"
}
url=url.replace('_z2C$q', ":").replace("_z&e3B", ".").replace('AzdH3F', "/")
return ''.join([table[c] if c in table.keys() else c for c in url])
def DownImage(SearchWord,PageNo=0):
url = 'https://image.baidu.com/search/acjson'
params = {
'tn': 'resultjson_com',
'logid': '5280191307193676757',
'ipn': 'rj',
# 'ct': '201326592',
'ct': '201326592',
'fp': 'result',
'queryWord': SearchWord,
'cl': '2',
'lm': '-1',
'ie': 'utf-8',
'oe': 'utf-8',
'st': '-1',
'ic': '0',
'word': SearchWord,
'face': '0',
'istype': '2',
'nc': '1',
'pn': PageNo*30, # 这里可以构造翻页
'rn': '30',
'gsm': 'b4'
}
headers = {
#参考网友构造的cookie
'Cookie': 'BDqhfp=%E5%8F%B2%E5%8A%AA%E6%AF%94%26%260-10-1undefined%26%263746%26%264; BIDUPSID=5A04241009FD166564DACF4050551F2D; PSTM=1611376447; __yjs_duid=1_2de46e288096c13a7edea3d05a5204421620544039468; BAIDUID=F163DBC1DF098AF604AE753E72659BAA:FG=1; BDUSS=Tczc3RnamRhaUhicm5rfm83V3pkMTBySUd1Z0V4Q25mbXhYdElRemJHdVktVnRoRVFBQUFBJCQAAAAAAQAAAAEAAACR090iR3JpZmZleTUxMQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJhsNGGYbDRhN; BDUSS_BFESS=Tczc3RnamRhaUhicm5rfm83V3pkMTBySUd1Z0V4Q25mbXhYdElRemJHdVktVnRoRVFBQUFBJCQAAAAAAQAAAAEAAACR090iR3JpZmZleTUxMQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJhsNGGYbDRhN; BAIDUID_BFESS=F163DBC1DF098AF604AE753E72659BAA:FG=1; BDORZ=AE84CDB3A529C0F8A2B9DCDD1D18B695; userFrom=cn.bing.com; IMG_WH=573_756; H_WISE_SIDS=110085_178384_179349_181588_182531_183327_183611_183750_184578_185029_185517_185653_185750_186317_186411_187020_187195_187206_187292_187450_187663_187670_187928_8000097_8000100_8000126_8000140_8000150_8000169_8000177_8000185; BDRCVFR[X_XKQks0S63]=mk3SLVN4HKm; firstShowTip=1; cleanHistoryStatus=0; indexPageSugList=%5B%22%E5%8F%B2%E5%8A%AA%E6%AF%94%22%2C%22%E6%B5%B7%E8%B4%BC%E7%8E%8B%22%2C%22%E8%8A%B1%E6%9C%B5%22%2C%22undertale%22%2C%22python%22%2C%22%E8%8A%B1%E7%AE%80%E7%AC%94%E7%94%BB%22%2C%22%E5%90%8C%E5%9E%8B%E4%B8%96%E4%BB%A3%E4%BA%A4%E6%9B%BF%22%2C%22%E6%A8%9F%E7%A7%91%E8%8A%B1%22%2C%22%E6%A8%9F%E7%A7%91%E8%8A%B1%E7%9A%84%E8%A7%A3%E5%89%96%22%5D; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm; ab_sr=1.0.1_MTY1OTI2YjEyMzViNzQyYWVhZjdhZWQxNzc0YjE1NzA2NGEyZmMwZGEwNzRmMWVjZGM3N2IzMDlkYjViZWVlOGYyNTllZDMzZjgwZGMxZWZhOWFiMmEyYjg0NjgyYzgwYjk0Y2QxYWVmM2E1ZTFiZjkyYTNlOGYzMDg1MWVjNjUyODViYzMyZjc2Mjk2OGFmZmZjZTkwNjg3OWI4NjhjZjdiNzJmNTY3NTIyZjg2ODVjMzUzNTExYjhiMjkxZjEx; BDRCVFR[-pGxjrCMryR]=mk3SLVN4HKm',
'Referer': 'https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=index&fr=&hs=0&xthttps=111110&sf=1&fmq=&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word=%E5%8F%B2%E5%8A%AA%E6%AF%94&oq=%E5%8F%B2%E5%8A%AA%E6%AF%94&rsp=-1',
'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Mobile Safari/537.36 Edg/93.0.961.52'
}
html = requests.get(url, params=params, headers=headers)
txt = html.text
j = json.loads(txt)
nindex = PageNo*30
for d in j['data']:
pic_url=d.get('objURL')
if pic_url:
pic_url=decode_url(pic_url)
nindex = nindex + 1
oname = "./%s_%s.jpg"%(SearchWord,nindex)
print(pic_url,oname)
continue
try:
rp = requests.get(pic_url,headers=headers)
if rp.status_code == 200:
with open(oname, 'ab') as f:
print(rp.status_code)
f.write(rp.content)
except Exception as e:
print(e)
DownImage("美女",0)
