import urllib
import datetime
import re
import requests
from sqlHelper import SqlHelper
from scrabHelper import ScrabHelper
from dateHelper import DateHelper
from selenium import webdriver
import time
dmId = 1
searchArr = ['小黑瓶', '兰蔻小黑瓶', '兰蔻 小黑瓶']
searchStr = searchArr[0]
count = SqlHelper.ExecuteScalar(
"select count(*) from jimi_radar_index where dm_id=%d and keyword='%s'" %
(dmId, searchStr))
if count == 0:
SqlHelper.ExecuteScalar(
"insert into jimi_radar_index (dm_id,keyword,ctime) values (%d,'%s','%s')"
% (dmId, searchStr, DateHelper.getDateNowStr()))
id = SqlHelper.ExecuteScalar(
"select id from jimi_radar_index where dm_id=%d and keyword='%s'" %
(dmId, searchStr))
def numMinusComma(num):
return ''.join(num.split(','))
resultDictionary[wordEncode] += matchLength
jsonStr = json.dumps(resultDictionary,
ensure_ascii=False,
encoding='UTF-8')
sql = "update jimi_radar_dimensionmode set %s ='%s' where id=%d" % (
fieldName, jsonStr, dmId)
insertNum = SqlHelper.ExecuteNonQuery(sql)
print jsonStr
print sql
print insertNum
# 得到当前dm爬取了哪些网站
scrab_json = SqlHelper.ExecuteScalar(
"select scrab_json from jimi_radar_dimensionmode where id=" + str(dmId))
# {"data": [{"scrabId": 1,
# "clue": 'http://cosme.pclady.com.cn/product/29669.html'
# }, {
# "scrabId": 2,
# "clue": 'http://product.kimiss.com/product/80696/'
# }]}
scrab_json = json.loads(scrab_json)
scrabArray = scrab_json['data']
# 得到字典对象数组
dtDict = SqlHelper.ExecuteDataTable(
"select cate_json from jimi_radar_dict_cate where id<10 order by id")
# 字典关键字数组 {"data":["浓稠", "粘稠", "有点稠", "稠稠", "粘粘", "黏腻", "黏黏", "厚实", "厚重", "比较厚", "丰盈"]}
dictKeyWordArray = []