Python 获取百度的预览图片

#!/usr/bin/python

import requests
from bs4 import BeautifulSoup
import sys
import re
import json

reload(sys)
sys.setdefaultencoding('utf-8')

class PicFromWeb:
    def set_url(self, url_pic):
        self.url_pic = url_pic
    print self.url_pic
    pass

def GetUrlList(url_pic_pattern, num_page, num_len):
    url_pic = re.sub('PAGE', '%d' % num_page, url_pic_pattern)
    url_pic = re.sub('LEN', '%d' % num_len, url_pic)
    r = requests.get(url_pic)
    r.encoding = 'utf-8'
    jo = json.loads(r.text)
    list_url = []
    for i in range(0, num_len):
        list_url.append(jo['data'][i]['thumbURL'])
    return list_url

if __name__ == '__main__':
    #url_pic = 'http://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gbk&word=%CD%BC%C6%AC&fr=ala&ala=1&alatpl=others&pos=0'
    url_pic_pattern = 'http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord=%E5%9B%BE%E7%89%87&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&word=%E5%9B%BE%E7%89%87&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=&fr=&pn=PAGE&rn=LEN&gsm=5e&1465654782303= HTTP/1.1'
    num_page = 0
    num_len = 30
    list_url = []
    for i in range(0, 2):
        num_page = i * 30
        list_url = GetUrlList(url_pic_pattern, num_page, num_len)
    print list_url

    for item in list_url:
        name = re.findall('u=(.*?),', item)[0] + '.jpg'

        headers = {
        'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0',
        'Referer' : 'http://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gbk&word=%CD%BC%C6%AC&fr=ala&ala=1&alatpl=others&pos=0',
        'Cache-Control' : 'max-age=0'
        }
        r = requests.get(item, headers = headers)
        #print r.content
        with open('./baidu/' + name, 'wb') as f:
            for chunk in r.iter_content(chunk_size=1024):
            if chunk:
                f.write(chunk)
            f.flush()
        f.close()