def parseZXMeta(self, text, id):
kv_dic = KYZhuanXian.get_k_v_dic()
result = {}
result["webSiteId"] = id
soup = BeautifulSoup(text)
soup.prettify()
table = soup.find(attrs={"id": "product_details"})
tds = table.findAll("td")
allInfo = {}
for info in tds:
key = info.fetchText(text=True)[0].strip()
if key.startswith(u"下载"):
continue
k = key.split("：")[0]
v = key.split("：")[1]
allInfo[k] = v
for k, v in allInfo.iteritems():
result[kv_dic.get(k)] = v
return result
url = "http://wl.kywmall.com/wl_pages/wl_find_line_details.aspx?id=%s" % id
try:
KYZhuanXian.objects.get(webSiteId=id)
logger.info("Zhuanxian %s already exsists" % id)
return
except:
pass
text = self.httpClient.geturlcon(url)
result = {}
try:
result = self.parseZXMeta(text, id)
except Exception, e:
logger.error(e)
if (result.get("telephoneNumber")) and (result.get("postedTo")):
source = KYZhuanXian()
try:
source.save_from_dic(result)
except Exception, e:
logger.info(traceback.format_exc())
else:
logger.info("saved")
else:
logger.error(url + " is a null page")
def getAndSaveHYFromId(self, id):
url = "http://wl.kywmall.com/wl_pages/wl_find_product_details.aspx?id=%s" % id
try:
KYHuoYuan.objects.get(webSiteId=id)
logger.info("HuoYuan %s already exsists" % id)
