本文实例讲述了Python基于分析Ajax请求实现抓取今日头条街拍图集功能。分享给大家供大家参考，具体如下：

代码:

import osimport reimport jsonimport timefrom hashlib import md5from multiprocessing import Poolimport requestsfrom requests.exceptions import RequestExceptionfrom pymongo import MongoClient# 配置信息OFFSET_START = 0 # 爬去页面的起始下标OFFSET_END = 20 # 爬去页面的结束下标KEYWORD = '街拍' # 搜索的关键字# mongodb相关配置MONGO_URL = 'localhost'MONGO_DB = 'toutiao' # 数据库名称MONGO_TABLE = 'jiepai' # 集合名称# 图片保存的文件夹名称IMAGE_PATH = 'images'headers = { "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'}client = MongoClient(host=MONGO_URL)db = client[MONGO_DB]jiepai_table = db[MONGO_TABLE]if not os.path.exists(IMAGE_PATH): os.mkdir(IMAGE_PATH)def get_html(url, params=None): try: response = requests.get(url, params=params, headers=headers) if response.status_code == 200: return response.text return None except RequestException as e: print("请求%s失败: " % url, e) return None# 获取索引页内容def get_index_page(offset, keyword): basic_url = 'http:///search_content/?offset={}&format=json&keyword=%E8%A1%97%E6%8B%8D&autoload=true&count=20&cur_tab=3'url = basic_url.format(0)html = requests.get(url).json()items = html['data']for item in items: title = item['media_name'] image_list = [image_detail['url'] for image_detail in item['image_detail']] print(title, image_list)

更多关于Python相关内容感兴趣的读者可查看本站专题：《Python Socket编程技巧总结》、《Python URL操作技巧总结》、《Python数据结构与算法教程》、《Python函数使用技巧总结》、《Python字符串操作技巧汇总》及《Python入门与进阶经典教程》

希望本文所述对大家Python程序设计有所帮助。