def insert_att(self,lan,lav,an,res_av):
''' 如果res_av--正则表达式匹配 '''
if res_av:
thd = p_jkh.sub('',res_av[0]).strip()
if an == self.keys_digikey[3]:
''' 处理Quantity Available '''
lan.append(an)
if thd:
lav.append(thd.replace(',',''))
else:
''' 库存为0 '''
lav.append('0')
else:
lan.append(an)
lav.append(thd)
def get_one_cartprice(self,html):
''' 精确获取到了某个型号的购物车页面 此时购物车页面有且仅有一条记录 '''
one_cartprice = {}
for key,p_info in list_keys_p:
res_info = p_info.findall(html)
if res_info:
info = res_info[0]
info = p_jkh.sub('', info).strip()
if key == 'Mouser detail url':
''' 详细信息页面加上mouser域名 '''
one_cartprice[key] = 'http://cn.mouser.com' + info
else:
one_cartprice[key] = info
else:
one_cartprice[key] = ''
return one_cartprice
def get_dict_info(self,hc):
""" 详细信息页面代码中获取关键信息 """
dict_info = {}
try:
""" 一 二级分类 """
res_fsc = self.p_first_second_catetory.findall(hc)
res_fsc = change_res_shuxian(res_fsc)
""" 供应商型号 """
res_supp_partno = self.p_supp_partno.findall(hc)
res_supp_partno = change_res_shuxian(res_supp_partno)
""" 生产商型号 """
res_mfr_partno = self.p_mfr_partno.findall(hc)
res_mfr_partno = change_res_shuxian(res_mfr_partno)
""" 生产厂商 """
res_manufacturer = self.p_manufacturer.findall(hc)
res_manufacturer = change_res_shuxian(res_manufacturer)
""" 描述 """
res_description = self.p_description.findall(hc)
res_description = change_res_shuxian(res_description)
""" 寿命周期 """
res_lifecycle = self.p_lifecycle.findall(hc)
res_lifecycle = change_res_shuxian(res_lifecycle)
""" 限制信息 """
res_shiprest = self.p_shiprest.findall(hc)
res_shiprest = change_res_shuxian(res_shiprest)
""" 图片url """
res_image_url = self.p_image_url.findall(hc)
""" pdf url """
res_pdf_url = self.p_pdf_url.findall(hc)
""" 加上封装 """
res_packaging = self.p_packaging.findall(hc)
res_packaging = change_res_shuxian(res_packaging)
if res_packaging:
dict_info[keys_mouser_tt[14][1]] = res_packaging[0]
""" 加上详细信息页面url """
res_info_url = self.p_info_url.findall(hc)
if res_info_url:
dict_info[keys_mouser_tt[27][1]] = res_info_url[0]
""" 加上种类 """
res_pc = self.p_pc.findall(hc)
res_pc = change_res_shuxian(res_pc)
if res_pc:
dict_info[keys_mouser_tt[21][1]] = p_jkh.sub('',res_pc[0]).strip()
if res_fsc:
dict_info[keys_mouser_tt[22][1]] = res_fsc[0][0] + ' >> ' + res_fsc[0][1]
if res_supp_partno and res_supp_partno[0] in ['Not Assigned','未分配']:
if debug: print 'line 232 find mouser partno is invalid, so return {}'
return {}
if res_supp_partno:
dict_info[keys_mouser_tt[18][1]] = res_supp_partno[0]
if res_mfr_partno:
dict_info[keys_mouser_tt[1][1]] = p_jkh.sub('', res_mfr_partno[0])
if res_manufacturer:
dict_info[keys_mouser_tt[2][1]] = res_manufacturer[0]
if res_description:
dict_info[keys_mouser_tt[3][1]] = p_jkh.sub('', res_description[0])
if res_lifecycle:
dict_info[keys_mouser_tt[4][1]] = p_jkh.sub('',res_lifecycle[0])
if res_shiprest:
''' 匹配到页面发货限制的信息时，设置键字shiprest'''
shiprest = res_shiprest[0]
res_shiprestinfo = self.p_shiprestinfo.findall(shiprest)
''' res_shiprestinfo: [('src','alt'),()] '''
if res_shiprestinfo:
''' 每个限制信息格式: src||alt 可能有一或者多个限制信息 每种限制信息以|||隔开 '''
sr_info = [[self.url_mouser_qz + src.replace('../',''), alt] for src,alt in res_shiprestinfo]
''' [src||alt,...] '''
sr_info = ['||'.join(one) for one in sr_info]
''' src||alt|||src||alt ... '''
sr_info = '|||'.join(sr_info)
dict_info[keys_mouser_tt[13][1]] = sr_info
else:
dict_info[keys_mouser_tt[13][1]] = unicode('该产品存在发货限制，请上mouser网站查询','utf-8')
''' 设置禁运类型 EIP CCC BIG等 edit by daimingming on 2013年 03月 01日 星期五 14:38:21 CST '''
res_shiprest_type = self.p_shiprest_type.findall(shiprest)
if res_shiprest_type:
dict_info[keys_mouser_tt[30][1]] = '||'.join(res_shiprest_type)
else:
dict_info[keys_mouser_tt[30][1]] = unicode('该产品存在发货限制','utf-8')
if res_image_url:
dict_info[keys_mouser_tt[28][1]] = res_image_url[0].strip()
if res_pdf_url:
dict_info[keys_mouser_tt[23][1]] = res_pdf_url[0].strip()
""" 处理详细信息 这里特殊处理 RoHS 格式为: attname:attvalue|||... """
res_special_info = self.p_special_info.findall(hc)
if res_special_info:
list_special_info = []
for an,av in res_special_info:
if an == 'RoHS':
if 'icon_rohs.gif' in av:
dict_info[keys_mouser_tt[24][1]] = 'Yes'
else:
dict_info[keys_mouser_tt[24][1]] = 'No'
else:
av = p_jkh.sub('',av).strip().replace(':','')
list_special_info.append('%s:%s' % (an,av))
special_info = '|||'.join(list_special_info)
dict_info[keys_mouser_tt[29][1]] = special_info
""" 库存 """
res_div_avai = self.p_div_availability.findall(hc)
if res_div_avai:
div_avai = res_div_avai[0]
res_stock = self.p_stock.findall(div_avai)
res_stock = change_res_shuxian(res_stock)
res_on_order = self.p_on_order.findall(div_avai)
res_on_order = change_res_shuxian(res_on_order)
res_flt = self.p_flt.findall(div_avai)
res_flt = change_res_shuxian(res_flt)
if res_stock:
''' 为了显示的更好效果 '''
info = res_stock[0]
info = info.replace('</tr>','\n').replace(',','')
info = p_jkh.sub('',info)
info = p_nbsp.sub('',info)
info = info.replace(' ','')
if info and info[-1] == '\n':
info = info[:-1]
else:
pass
dict_info[keys_mouser_tt[17][1]] = info
res_num = p_num.findall(info)#该正则表达式不来自配置文件
if res_num:
dict_info[keys_mouser_tt[5][1]] = res_num[0]
else:
dict_info[keys_mouser_tt[5][1]] = '0'
if res_on_order:
info = p_jkh.sub('',res_on_order[0])
info = p_nbsp.sub('',info)
info = info.replace(' ','')
res_num_start = p_num_start.findall(info)
if res_num_start:
dict_info[keys_mouser_tt[6][1]] = res_num_start[0]
else:
dict_info[keys_mouser_tt[6][1]] = '0'
if res_flt:
info = p_jkh.sub('',res_flt[0])
info = p_nbsp.sub('',info)
info = info.replace(' ','')
dict_info[keys_mouser_tt[7][1]] = info
else:
pass
""" 价格 """
res_minimum = self.p_minimum.findall(hc)
res_minimum = change_res_shuxian(res_minimum)#
res_multiples = self.p_multiples.findall(hc)
res_multiples = change_res_shuxian(res_multiples)#
if res_minimum:
dict_info[keys_mouser_tt[8][1]] = int(res_minimum[0].replace(' ',''))
else:
dict_info[keys_mouser_tt[8][1]] = '0'
if res_multiples:
dict_info[keys_mouser_tt[9][1]] = int(res_multiples[0].replace(' ',''))
else:
dict_info[keys_mouser_tt[9][1]] = '0'
res_div_price = self.p_div_price.findall(hc)
if res_div_price:
div_price = res_div_price[0]
res_buy_quantity = self.p_buy_quantity.findall(div_price)
res_buy_price = self.p_buy_price.findall(div_price)
res_spe_xing = self.p_spe_xing.findall(div_price)
res_spe_xing = change_res_shuxian(res_spe_xing)#
res_spe_price = self.p_spe_price.findall(div_price)
res_reel = self.p_reel.findall(div_price)
res_more = self.p_more.findall(div_price)
res_more = change_res_shuxian(res_more)#
if res_buy_quantity and res_buy_price:
if len(res_buy_quantity) == len(res_buy_price):
""" 数量个数 与 购买价格个数 一致 """
list_price_normal = []
i = 0
while i < len(res_buy_quantity):
bq = res_buy_quantity[i].replace(',','')#'number'
bp = res_buy_price[i]
if bq and bp:
''' 防止出现有购买数量 无购买价格的情况 如页面 http://cn.mouser.com/ProductDetail/Littelfuse/0202125H/?qs=sGAEpiMZZMseCiJT91fwIpCtAz8CGq9CFANOg93eDRM%3d'''
list_price_normal.append('%s:%s' % (bq,bp))
i += 1
price_info = '|||'.join(list_price_normal)
dict_info[keys_mouser_tt[10][1]] = price_info
else:
pass
if res_buy_quantity and res_spe_price:
if len(res_buy_quantity) == len(res_spe_price) and res_spe_xing:
""" 数量个数 与 特殊价格个数 一致 """
list_price_special = []
i = 0
while i < len(res_buy_quantity):
bq = res_buy_quantity[i].replace(',','')#'number'
bp = res_spe_price[i]
if bq and bp:
list_price_special.append('%s:%s' % (bq,bp))
i += 1
price_spe_info = '|||'.join(list_price_special)
dict_info[keys_mouser_tt[16][1]] = price_spe_info
else:
pass
if res_reel:
reel = res_reel[0]
reel = p_jkh.sub('',reel)
reel = reel.replace(' ','')
dict_info[keys_mouser_tt[11][1]] = reel
if res_more:
more = res_more[0]
more = self.url_mouser_qz + more.replace('../','')
dict_info[keys_mouser_tt[12][1]] = more
else:
pass
return dict_info
except Exception,e:
if debug:print 'line 353 exception :\n',e
return {}
def get_dict_info(self,hc,**dict_args):
''' 冲详细信息页面的代码中获取数据 {} '''
fun = 'function get_dict_info of %s' % self.name
dict_info = {}
hc = filter_html(hc)
''' 此时 hc 是否为详细信息页面的代码 '''
iip = dict_args.get('is_info_page', False)
if iip:
''' 处在详细信息页面 '''
res_imgurl = p_imgurl_iip.findall(hc)
res_partno = p_partno_iip.findall(hc)
res_mfr = p_mfr_iip.findall(hc)
res_desc = p_desc_iip.findall(hc)
res_stock = p_stock_iip.findall(hc)
else:
res_imgurl = p_imgurl.findall(hc)
res_partno = p_partno.findall(hc)
res_mfr = p_mfr.findall(hc)
res_desc = p_desc.findall(hc)
res_stock = p_stock.findall(hc)
if res_imgurl:
dict_info[keys_mouser_tt[28][1]] = p_jkh.sub('',res_imgurl[0]).replace('"','').strip()
if res_partno:
dict_info[keys_mouser_tt[1][1]] = p_jkh.sub('',res_partno[0]).strip()
if res_mfr:
dict_info[keys_mouser_tt[2][1]] = p_jkh.sub('',res_mfr[0]).strip()
if res_desc:
dict_info[keys_mouser_tt[3][1]] = p_jkh.sub('',res_desc[0]).strip()
if res_stock:
dict_info[keys_mouser_tt[5][1]] = p_jkh.sub('',res_stock[0]).strip()
''' 处理区间价格 [('1-24','$82.08'),.('25 +','$61.56')] >>> ['1:$82.08','1000:$61.56'] >>> '1:$82.08|||25:$61.56' '''
if iip:
''' 详细信息页面 '''
res_priceinfo = p_priceinfo_iip.findall(hc)
pc_pp_new = ['%s:%s' % (p_invalidnum.sub('',pc).strip(), pp) for pc,pp in res_priceinfo]
pc_pp_finall = '|||'.join(pc_pp_new)
else:
''' 现在为表格页面模式 获取该<tr>对应的详细信息页面url '''
res_seemore = p_seemore.findall(hc)
res_priceinfo = []#默认设置空
if res_seemore:
''' 需要进入详细信息页面获取完整价格 '''
res_uip = p_uip.findall(hc)
if res_uip:
dict_info[keys_mouser_tt[27][1]] = res_uip[0]
hc_more = filter_html(get_html_urllib(res_uip[0], 2))
if hc_more != 'timeout':
''' 正常获取了 详细信息页面的价格信息 '''
res_priceinfo = p_priceinfo_iip.findall(hc_more)
else:
''' 只需从<tr>行字符串获取价格 即可 '''
res_priceinfo = p_priceinfo.findall(hc)
pc_pp_new = ['%s:%s' % (p_invalidnum.sub('',pc).strip(), pp) for pc,pp in res_priceinfo]
pc_pp_finall = '|||'.join(pc_pp_new)
if pc_pp_finall:dict_info[keys_mouser_tt[10][1]] = pc_pp_finall
''' 加上型号搜索页面url 详细页面url 详细页面html代码 '''
dict_info[keys_mouser_tt[19][1]] = self.url_search
return dict_info
def get_dict_info(self,hc):
''' 冲详细信息页面的代码中获取数据 {} '''
fun = 'function get_dict_info of %s' % self.name
dict_info = {}
hc = filter_html(hc)
res_mfr = p_mfr.findall(hc)
if res_mfr:
dict_info[keys_mouser_tt[2][1]] = res_mfr[0]
res_partno = p_partno.findall(hc)
if res_partno:
dict_info[keys_mouser_tt[1][1]] = res_partno[0]
res_desc = p_desc.findall(hc)
if res_desc:
dict_info[keys_mouser_tt[3][1]] = p_jkh.sub('', res_desc[0]).strip()
res_pdf = p_pdf.findall(hc)
if res_pdf:
dict_info[keys_mouser_tt[23][1]] = res_pdf[0]
res_pack = p_pack.findall(hc)
if res_pack:
dict_info[keys_mouser_tt[14][1]] = res_pack[0].strip()
res_rohs = p_rohs.findall(hc)
if res_rohs:
dict_info[keys_mouser_tt[24][1]] = res_rohs[0].strip()
res_pc_pp = p_pc_pp.findall(hc)
if res_pc_pp:
''' 处理区间价格 '''
''' [('1-24','$82.08'),.('over 1000','$61.56')] >>> ['1:$82.08','1000:$61.56'] >>> '1:$82.08|||1000:$61.56' '''
pc_pp_new = ['%s:%s' % (p_invalidnum.sub('',pc), pp) for pc,pp in res_pc_pp]
pc_pp_finall = '|||'.join(pc_pp_new)
dict_info[keys_mouser_tt[10][1]] = pc_pp_finall
res_yourcost = p_yourcost.findall(hc)
if res_yourcost:
dict_info[keys_mouser_tt[25][1]] = res_yourcost[0].strip()
res_table_lnq = p_table_lnq.findall(hc)
if res_table_lnq:
table_lnq = res_table_lnq[0]
res_tr_lnq = p_tr_lnq.findall(table_lnq)
qty = 0
for l,n,q in res_tr_lnq:
qty += int(q)
dict_info[keys_mouser_tt[5][1]] = qty
dict_info[keys_mouser_tt[26][1]] = res_tr_lnq
''' 加上型号搜索页面url 详细页面url 详细页面html代码 '''
dict_info[keys_mouser_tt[19][1]] = self.url_search
res_uip = p_uip.findall(hc)
if res_uip:
dict_info[keys_mouser_tt[20][1]] = res_uip[0]
return dict_info