环境
操作系统:Windows 7
Python版本:2.7.9
过程
- 打开谷歌浏览器;
- 打开1元夺宝商品列表页面;
- 随便点击一个商品,按F12调用开发者工具,选择“Network”标签,筛选“XHR”,再单击页面上的“夺宝参与记录”;
- 观察开发者工具,找到返回JSON格式数据的URL,如下图:
- 从上图的URL返回的JSON格式数据我们可以得知参与夺宝的用户数(totalCnt),每个用户的头像链接前缀(avatarPrefix);
- 随便点击一个用户,从开发者工具中可以得知用户头像的URL是由头像链接前缀和“160.jpeg”组成的。
代码
# -*- coding: utf-8 -*- import sys reload(sys) sys.setdefaultencoding('utf-8') ''' 作者:昨夜星辰 ''' import re import os import requests from bs4 import BeautifulSoup # 创建一个用于存放头像的文件夹 folder = u'头像' os.mkdir(folder) # 用于存放用户的cid cidList = [] # 用于头像计数 picCnt = 1 url = 'http://1.163.com/list.html' bs = BeautifulSoup(requests.get(url).text, 'lxml') for div in bs('div', 'w-goods w-goods-l w-goods-ing'): gid = div['data-gid'] period = div['data-period'] url = 'http://1.163.com/record/getDuobaoRecord.do?pageNum=1&pageSize=50&totalCnt=0&gid=%s&period=%s' % (gid, period) json = requests.get(url).json() totalCnt = json['result']['totalCnt'] for pageNum in range(1, totalCnt / 50 + 1): url = 'http://1.163.com/record/getDuobaoRecord.do?pageNum=%d&pageSize=50&totalCnt=%d&gid=%s&period=%s' % (pageNum, totalCnt, gid, period) json = requests.get(url).json() for _list in json['result']['list']: cid = _list['user']['cid'] if cid in cidList: continue cidList.append(cid) avatarPrefix = _list['user']['avatarPrefix'] if avatarPrefix: url = avatarPrefix + '160.jpeg' filename = folder + '\' + re.search(r'.*/(.*)', url).group(1) print u'正在保存第%d个头像...' % picCnt picCnt += 1 with open(filename, 'wb') as f: f.write(requests.get(url).content)