爬虫-获取百度图片壁纸保存至本地

# ！/user/bin/python3
# -*- coding:utf-8 -*-

import requests
import os
import re  # 使用正则表达式

def getManyPages(keyword, pages):
    params=[]
    # 分页请求地址拼接 每页显示60个图片
    for i in range(0, 30*pages+30, 30):
        params.append({
            'tn': 'resultjson_com',
            'ipn': 'rj',
            'ct': 201326592,
            'is': '',
            'fp': 'result',
            'queryWord': keyword,
            'cl': 2,
            'lm': -1,
            'ie': 'utf-8',
            'oe': 'utf-8',
            'adpicid': '',
            'st': -1,
            'z': '',
            'ic': 0,
            'word': keyword,
            's': '',
            'se': '',
            'tab': '',
            'width': '',
            'height': '',
            'face': 0,
            'istype': 2,
            'qc': '',
            'nc': 1,
            'fr': '',
            'pn': i,
            'rn': 30,
            'gsm': '1e',
            '1488942260214': ''
        })
    url = 'https://image.baidu.com/search/acjson'
    urls = []
    # 获取图片加密地址列表
    for i in params:
        urls.append(requests.get(url, params=i).json().get('data'))
    return urls

# 百度图片地址解密方法
def  baidtu_uncomplie(url):
    res = ''
    c = ['_z2C$q', '_z&e3B', 'AzdH3F']
    d= {'w':'a', 'k':'b', 'v':'c', '1':'d', 'j':'e', 'u':'f', '2':'g', 'i':'h', 't':'i', '3':'j', 'h':'k', 's':'l', '4':'m', 'g':'n', '5':'o', 'r':'p', 'q':'q', '6':'r', 'f':'s', 'p':'t', '7':'u', 'e':'v', 'o':'w', '8':'1', 'd':'2', 'n':'3', '9':'4', 'c':'5', 'm':'6', '0':'7', 'b':'8', 'l':'9', 'a':'0', '_z2C$q':':', '_z&e3B':'.', 'AzdH3F':'/'}
    if(url==None or 'http' in url):
        return url
    else:
        j= url
        for m in c:
            j=j.replace(m,d[m])
        for char in j:
            if re.match('^[a-w\d]+$',char):
                char = d[char]
            res= res+char
        return res

# 根据路径和图片地址列表下载图到本地
def getImg(dataList, localPath):

    if not os.path.exists(localPath):  # 新建文件夹
        os.mkdir(localPath)
    x = 1
    for list in dataList:
        for i in list:
            if i.get('objURL') != None:
                print('正在下载：%s' % baidtu_uncomplie(i.get('objURL')))
                try:
                    ir = requests.get(baidtu_uncomplie(i.get('objURL')))
                    open(localPath + '%d.jpg' % x, 'wb').write(ir.content)
                    x += 1
                except Exception as e:
                    print(e)
            else:
                print('图片链接不存在')

if __name__ == '__main__':
    # 参数1:关键字，参数2:要下载的页数
    dataList = getManyPages('小清新壁纸', 1)
    print(dataList)
    # 参数2:指定保存的路径
    getImg(dataList, 'D:/a/')