Python实例之抓取淘宝商品数据（json型数据）并保存为TXT

import requests
import re
import json
from urllib.parse import urlencode
from bs4 import BeautifulSoup
finalstr = ‘‘
count = 0                   #初始化页码对应参数，0为首页
test = 0                    #初始化数据总条数
for j in range(0,100):           #共搜索100页数据
    count = 44*j                  #每跳一页参数值增加44
    data = {
        ‘q‘:‘python‘,
        ‘imgfile‘:‘‘,
        ‘js‘:‘1‘,
        ‘stats_click‘:‘search_radio_all:1‘,
        ‘initiative_id‘:‘staobaoz_20170529‘,
        ‘ie‘:‘utf8‘,
        ‘bcoffset‘:‘4‘,
        ‘ntoffest‘:‘4‘,
        ‘p4ppushleft‘:‘1,48‘,
        ‘s‘:count                 
    }                               #浏览器地址的get参数，只有‘s‘会随着页码改变而改变
    url = ‘https://s.taobao.com/search?‘ + urlencode(data)         #浏览器地址
    req = requests.get(url)
    pattern = re.compile(‘g_page_config = (.*?);\n    g_srp_loadCss()‘)    #正则表达式匹配数据
    result = pattern.search(req.text)
    # result.group(1)
    jsres = json.loads(result.group(1))       #匹配后获得的json数据深度比较大，需要层层剖析
    sedata = jsres[‘mods‘][ ‘itemlist‘][‘data‘][‘auctions‘]     #经过剖析后的json数据
    for i in range(0,len(sedata)):
        rt = ‘标题：‘+sedata[i][‘raw_title‘]+‘\n‘
        finalstr += rt
        rp = ‘价格：‘+sedata[i][‘view_price‘]+‘\n‘
        finalstr += rp
        rn = ‘卖家：‘+sedata[i][‘nick‘]+‘\n‘
        finalstr += rn
        rd = ‘地址：‘+sedata[i][‘item_loc‘]+‘\n\n‘
        finalstr += rd
        print(‘当前正在读取第‘+str(j+1)+"页的第"+str(i+1)+‘条数据...‘)
        test += 1
f = open(‘淘宝搜索python时的商品数据，共‘+str(test)+‘条.txt‘,‘w‘,1,‘UTF-8‘)    #保存数据到TXT
f.write(finalstr)
print(‘正在保存。。。‘)
f.close()
print(‘保存完毕！共‘+str(test)+‘条数据‘)