python爬取百度图片

import requests
import re
from urllib import parse
import os
from threading import Thread

def download(i,j,key,url):
    header = {'content-type': 'application/json',
             "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36",
              "Connection":"keep-alive",
              "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
              "Accept-Language":"zh-CN,zh;q=0.8"
              }
    response = requests.get(url,headers=header)

    link = re.findall(r'"objURL":"(.*?)"',response.text,re.S)
    if not os.path.exists(key):
        os.mkdir("./"+key+"/")
    for web in link:
        url = decodeurl(web)
        print(url)

        try:
            #allow_redirects=False 关闭重定向
            pic = requests.get(url,timeout=10,headers=header,allow_redirects=False)
            dirfile = "./"+key+"/" +key + '_' + str(j) + '.jpg'
            fp = open(dirfile, 'wb')
            fp.write(pic.content)
            fp.close()
            j += 1
        except requests.exceptions.ConnectionError:
            print(web,"【错误】当前图片无法下载")
            continue
        except requests.exceptions.ReadTimeout:
            print(web, "【错误】超时")
            continue
        except requests.exceptions.ChunkedEncodingError:
            print(web, "【错误】远程主机强迫关闭了一个现有的连接")
            continue

def decodeurl(url):
    str_table = {
    '_z2C$q': ':',
    '_z&e3B': '.',
    'AzdH3F': '/'
    }
    char_table = {
        'w': 'a',
        'k': 'b',
        'v': 'c',
        '': 'd',
        'j': 'e',
        'u': 'f',
        '': 'g',
        'i': 'h',
        't': 'i',
        '': 'j',
        'h': 'k',
        's': 'l',
        '': 'm',
        'g': 'n',
        '': 'o',
        'r': 'p',
        'q': 'q',
        '': 'r',
        'f': 's',
        'p': 't',
        '': 'u',
        'e': 'v',
        'o': 'w',
        '': '',
        'd': '',
        'n': '',
        '': '',
        'c': '',
        'm': '',
        '': '',
        'b': '',
        'l': '',
        'a': ''
    }
    char_table = {ord(key): ord(value) for key, value in char_table.items()}
    for key,value in str_table.items():
        url = url.replace(key,value)
    url = url.translate(char_table)
    return url

def main():
    j = 0
    key = "树叶标本"
    data = parse.quote(str(key))

    for i in range(j,2000,30):
        if j == 0:
            j +=1
        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="+data+"&z=&ic=&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=1&fr=&step_word="+data+"&pn="+str(i)+"&rn=30&gsm=3c&1527055161957="
        download(i,j,key,url)
        j += 30

if __name__ == "__main__":
    main()