def genBrandList_Yesky():
src = requestByProxy('http://product.yesky.com/washingmachine/')
d = pq(src)
frames = d.find('.updonwlist a')
produListEnglish = [pq(item).attr('href').split('/')[-2] for item in frames]
produListChinese = frames.my_text()
urlList = ['http://product.yesky.com/list/brand/' + item + '/' for item in produListEnglish]
# productList=zip(produListChinese,produListEnglish)
result = []
for url in urlList:
src = requestByProxy(url)
d = pq(src)
temp_1 = d.find('.rmpp>ul>li>a').my_text() if d.find('.rmpp>ul>li>a').my_text() else []
temp_2 = d.find('.rmpp>dl>dd>a').my_text() if d.find('.rmpp>dl>dd>a').my_text() else []
temp = temp_1 + temp_2
nameEnglist = url.split('/')[-2]
nameChinese = produListChinese[produListEnglish.index(nameEnglist)]
res = []
for item in temp:
res.append([nameChinese, item])
result += res
# 数据写入csv文件
title = ['category', 'brand']
writer = My_Csv.Write_Csv(path=dirCheck.dirGen('d:/spider'), name='brandList_for_xiaoju', title=title,
result=result)
writer.add_title_data()
def dataSaved(result):
import My_Csv, dirCheck
title = []
writer = My_Csv.Write_Csv(path=dirCheck.dirGen('d:/operationAnalysis'), name='temp',title=title, result=result)
writer.add_title_data()