百度图片 二爬

import requests
import re
import os
num=1
headers = {
     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
     "referer":"https://image.baidu.com"
    }
for i in range(1,3):
    url="http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord+=&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&word=%E6%88%90%E9%BE%99&z=&ic=&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=1&fr=&step_word=%E6%88%90%E9%BE%99&pn={}&rn=30".format(i*30)
    html=requests.get(url)
    html.encoding="utf-8"
    c=html.json()["data"]

    for i in c:
        num=num+1
        c=i.get("thumbURL")

        if c!=None:
            c=requests.get(c,headers=headers)
            print(c)
            c=c.content
            with open(r'H:/chenglong1/' + str(num) + '.jpg', 'wb') as f:
                f.write(c)
                f.close()

二爬的感觉很不一样 尤其是json还是没有处理好

表头文件referer 是判断从那个网站点击的这个链接 在爬虫中必不可少

不能一味的去只用[]来搜寻Key值 有些key值为空而get很好的解决了这个问题