(我用的谷歌浏览器,在tb登录页面,按F12键进入检查模式,点击Network,勾选Preserve log,点击登陆,这样就记录下了登陆需要提交的所有参数)
-- coding: utf-8 --
import scrapy
import re
import json
import time
from tao_bao_data.items import TaoBaoDataItem
class TaobaodataSpider(scrapy.Spider):
# 爬虫名
name = ‘TaoBaoData’
# 爬虫允许的域名
allowed_domains = [“taobao.com”, “passport.alibaba.com”]
# 爬虫进行模拟登录的url
login_url = ‘https://login.taobao.com/member/login.jhtml’
# 爬虫要抓取数据的url
crawl_urls = ‘https://buyertrade.taobao.com/trade/itemlist/list_bought_items.htm’
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:35.0) Gecko/20100101 Firefox/35.0',
'Content-Type': 'application/x-www-form-urlencoded',
'Connection': 'Keep-Alive'
}
# 模拟登录需要提交的用户名
username = '(此处是自己的淘宝用户名或者店铺名)'
# 构建模拟登录需要提交的表单数据
post_data = {
'TPL_username': username,
'TPL_password': '',
'ncoSig': '',
'ncoSessionid': '',
'ncoToken': 'd801d3c69349',
'slideCodeShow': 'false',
'useMobile': 'false',
'lang': 'zh_CN',
'loginsite': '0',
'newlogin': '0',
'TPL_redirect_url': 'http://buyertra