Skip to content

C
checkData
Commit 36e2d265 authored by rico.liu's avatar rico.liu
Browse files
Options

update

parent 6f9d10e5
Show whitespace changes
Inline Side-by-side
Showing with 232 additions and 118 deletions
checkData.py
View file @ 36e2d265
......@@ -11,7 +11,7 @@ import re
import requests
import json
def get_reponse(session,url,headers):
def get_response(session,url,headers):
'''
deal timeout request
'''
......@@ -47,6 +47,7 @@ def checkData(check_data):
name_list = []
url_list = []
source_list = []
price_list = []
for i in range(len(check_data)):
df = check_data.loc[i]
......@@ -55,10 +56,32 @@ def checkData(check_data):
name = df['name']
main_url = df['url'].strip()
source = df['source']
price = df['price']
print(main_url)
if "jd" in str(main_url):
r = get_reponse(session,main_url,headers)
try:
sku = main_url.split('/')[-1].split('.')[0]
#获取价格
url = "https://p.3.cn/prices/mgets?skuIds=" + str(sku)
r = get_response(session,url,headers).json()
jd_price = r[0]['p']
if len(jd_price) == 0:
jd_price = price
if jd_price == '-1.00':
jd_price = price
price_list.append(jd_price)
result.append("无货，请按要求提供在销渠道证明")
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
price_list.append(jd_price)
#获取其他信息
main_url_ = "https://item.jd.com/" + sku + ".html"
r = get_response(session,main_url_,headers)
html = etree.HTML(r.text)
ziying = html.xpath(
"//div[@class='name goodshop EDropdown']/em/text()")
......@@ -73,6 +96,47 @@ def checkData(check_data):
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
#获取库存信息
url = "https://c0.3.cn/stock?skuId="+str(sku)+"&area=1_2901_2906_0&cat=9987,653,655"
r = get_response(session,url,headers)
if r == -1:
print("通过")
result.append("通过")
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
r.encoding='gbk'
is_purchase = json.loads(r.text)
try:
if "无货" in is_purchase['stock']['stockDesc'] or "无货" in is_purchase['stock']['StockStateName']:
print("无货，请按要求提供在销渠道证明")
result.append("无货，请按要求提供在销渠道证明")
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
print("通过")
result.append("通过")
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
except:
if "无货" in is_purchase['StockStateName']:
print("无货，请按要求提供在销渠道证明")
result.append("无货，请按要求提供在销渠道证明")
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
print("通过")
result.append("通过")
......@@ -89,15 +153,26 @@ def checkData(check_data):
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
except:
print("链接有误，请按要求提供在销渠道证明")
result.append("链接有误，请按要求提供在销渠道证明")
price_list.append(price)
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
elif "gome" in str(main_url):
#try_ = session.get(main_url,headers=headers)
try:
main_url_1 = re.findall(".cn/(.*?).html",main_url)[0]
main_url_ = 'https://item.gome.com.cn/' + main_url_1 + '.html'
r = get_reponse(session,main_url_,headers)
r = get_response(session,main_url_,headers)
html = etree.HTML(r.text)
#content = html.xpath("//script[contains(text(),'gomePrice')]/text()")[0]
content = html.xpath("//script[contains(text(),'gomePrice')]/text()")[0]
gm_price = content.split('gomePrice:"')[1:][0].split('"')[0]
price_list.append(gm_price)
ziying = html.xpath(
"//span[@class='identify']/text()")
if len(ziying) == 1:
......@@ -111,7 +186,23 @@ def checkData(check_data):
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
#获取库存信息
sku = main_url_.split('.html')[0].split('/')[-1].replace('-','/')
url = "https://ss.gome.com.cn/item/v1/d/m/store/unite/"+str(sku)+"/N/11010200/110102002/1/null/flag/item/allStores?callback=allStores"
r = get_response(session,url,headers)
content = r.text.replace('allStores(','')
content = content.replace(')','')
content = json.loads(content)
wuhuo = content['result']['stock']['status']
if wuhuo == False:
print("无货，请按要求提供在销渠道证明")
result.append("无货，请按要求提供在销渠道证明")
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
print("通过")
result.append("通过")
......@@ -128,94 +219,117 @@ def checkData(check_data):
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
except:
print("链接有误，请按要求提供在销渠道证明")
result.append("链接有误，请按要求提供在销渠道证明")
price_list.append(price)
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
elif "suning" in str(main_url):
#sku = main_url.split('.html')[0].split('/')[-1].replace('-','/')
#main_url_ = 'http://product.suning.com/0000000000/10115687173.html'
#main_url = 'http://product.suning.com/0000000000/10530903341.html'
r = get_reponse(session,main_url,headers)
try:
sku = re.findall(".com/(.*?).html",main_url)[0]
main_url_ = 'https://product.suning.com/' + sku + '.html'
r = get_response(session,main_url_,headers)
html = etree.HTML(r.text)
#daaa = r.text
#sn_price = df.价格
#sn_price = '58.00-558.00'
daaa = r.text
sn_price = price
str2 = html.xpath("//input[@id='curPartNumber']/@value")[0]
ziying1 = html.xpath("//div[@class='proinfo-title']/h1/span/i/text()")
ziying2 = html.xpath("//h1[@id='itemDisplayName']/span/text()")
#youhuo_ = re.findall("id=\"ie7_onsale\" >(.*?)<i",daaa)
youhuo_ = re.findall("id=\"ie7_onsale\" >(.*?)<i",daaa)
if "自营" in ziying1 or "自营" in ziying2:
#daohuo = html.xpath("//a[@id='tellMe']/span/text()")
url_json = f'https://product.suning.com/pds-web/ajax/itemUniqueInfo_{str(str2)}_0000000000.html'
response_json = get_reponse(session,url_json,headers)
response_json = get_response(session,url_json,headers)
json_data = json.loads(response_json.text)
itemDetail = json_data["itemDetail"]
try:
isPublished = itemDetail["isPublished"]
except:
isPublished = '0'
try:
product_name = itemDetail["cmmdtyTitle"]
except:
product_name = '满足要求名称'
if isPublished == '1':
if '此款有货' in str(youhuo_) :
if ("定制"in str(product_name)) or ("防弹"in str(product_name)) or ("射击"in str(product_name)) \
or ("订制"in str(product_name)) or ("卫星"in str(product_name)) \
or ("靶"in str(product_name)) or ("企业定制"in str(product_name)) \
or ("军迷"in str(product_name)) or ("携行具"in str(product_name)):
print("定制/专用类产品暂不通过")
result.append("定制/专用类产品暂不通过")
price_list.append(sn_price)
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
id_all.append(date_id)
else:
str11 = html.xpath("//input[@id='curPartNumber']/@value")[0]
str22 = html.xpath("//input[@id='shop_code']/@value")[0]
str33 = html.xpath("//input[@name='procateCode']/@value")[0]
#默认收货地址为北京市丰台区
real_url = f'https://pas.suning.com/nspcsale_0_{str11}_{str11}_{str22}_10_010_0100100_157122_1000000_9017_10106_Z001___{str33}.html?callback=pcData'
price_response = requests.get(real_url)
sn_price = re.findall('"promotionPrice":"(.*?)",', price_response.text)[0]
if len(sn_price) != 0:
try:
print('通过')
sn_price = float(sn_price)
#price.append(sn_price)
result. append('通过')
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
except:
print('该链接无法定位到唯一商品')
result. append('该链接无法定位到唯一商品')
str11 = html.xpath("//input[@id='curPartNumber']/@value")[0]
str22 = html.xpath("//input[@id='shop_code']/@value")[0]
str33 = html.xpath("//input[@name='procateCode']/@value")[0]
real_url = f'https://pas.suning.com/nspcsale_0_{str11}_{str11}_{str22}_10_010_0100100_157122_1000000_9017_10106_Z001___{str33}.html?callback=pcData'
price_response = requests.get(real_url)
sn_price = re.findall('"promotionPrice":"(.*?)",', price_response.text)[0]
if len(sn_price) != 0:
price_list.append(sn_price)
else:
sn_price = price
price_list.append(sn_price)
else:
print('无货，请按要求提供在销渠道证明')
sn_price = price
result. append('无货，请按要求提供在销渠道证明')
price_list.append(sn_price)
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
print('无货，请按要求提供在销渠道证明')
sn_price = price
result. append('无货，请按要求提供在销渠道证明')
price_list.append(sn_price)
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
print('非自营，请按要求提供在销渠道证明')
result. append('非自营，请按要求提供在销渠道证明')
price_list.append(price)
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
except:
print("链接有误，请按要求提供在销渠道证明")
result.append("链接有误，请按要求提供在销渠道证明")
price_list.append(price)
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
url_list.append(main_url)
source_list.append(source)
else:
print("非自营，请按要求提供在销渠道证明")
result.append("非自营，请按要求提供在销渠道证明")
print("非三大电商，请按要求提供在销渠道证明")
result.append("非三大电商，请按要求提供在销渠道证明")
price_list.append(price)
id_all.append(date_id)
sku_list.append(sku)
name_list.append(name)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment