爬取今日头条Ajax请求

import requestsimport osfrom urllib.parse import urlencodefrom hashlib import md5from multiprocessing.pool import Poolfrom requests import codesdef get_page(offset):  params = {    "offset":offset,    "format":"json",    "keyword":"街拍",    "autoload":"true",    "count":"20",    "cur_tab":"1",    "from":"search_tab"  }  url = 'https://www.toutiao.com/search_content/?'+urlencode(params)  try:    response = requests.get(url)    if response.status_code == 200:      # print(url)      return response.json()  except requests.ConnectionError:    return None# get_page(0)def get_images(json):  if json.get('data'):    for item in json.get('data'):      if item.get('cell_type') is not None:        continue      title = item.get('title')      images = item.get('image_list')      for image in images:        yield {          'title':title,          'image':'https:' + image.get('url'),        }def save_image(item):  #os.path.sep  路径分隔符‘//'  img_path = 'img' + os.path.sep + item.get('title')  if not os.path.exists(img_path):    os.makedirs(img_path)  try:    resp = requests.get(item.get('image'))    # print(type(resp))    if codes.ok == resp.status_code:      file_path = img_path + os.path.sep + '{file_name}.{file_suffix}'.format(        file_name=md5(resp.content).hexdigest(),#md5是一种加密算法获取图片的二进制数据，以二进制形式写入文件        file_suffix='jpg')      if not os.path.exists(file_path):        with open(file_path,'wb')as f:          f.write(resp.content)          print('Downladed image path is %s' % file_path)      else:        print('Already Downloaded',file_path)  except requests.ConnectionError:    print('Failed to Save Image,item %s' % item)def main(offset):  json = get_page(offset)  for item in get_images(json):    print(item)    save_image(item)GROUP = 0GROUP_END = 2if __name__ == '__main__':  pool = Pool()  groups = ([x*20 for x in range(GROUP,GROUP_END)])  pool.map(main,groups)  #将groups一个个调出来传给main函数  pool.close()  pool.join()   #保证子进程结束后再向下执行 pool.join(1) 等待一秒