Commit d7763103 authored by rico.liu's avatar rico.liu

add deal crawl pic

parent add0f18a
...@@ -392,6 +392,14 @@ def GetParamsinfoAndPic(df): ...@@ -392,6 +392,14 @@ def GetParamsinfoAndPic(df):
response = requests.request("POST", request_url, data=payload) response = requests.request("POST", request_url, data=payload)
res = eval(response.text) res = eval(response.text)
#处理未爬取到的数据
for element in res:
if element:
pass
else:
res.remove(element)
res.append({'img_list':[],'class_list':{},'url':''})
df['url_pic'] = [str(element['img_list']) for element in res] df['url_pic'] = [str(element['img_list']) for element in res]
crawl_params_list = [str(element['class_list']).replace("'': ''","").replace(", ,",",").replace("{,","{").replace(" ","") for element in res] crawl_params_list = [str(element['class_list']).replace("'': ''","").replace(", ,",",").replace("{,","{").replace(" ","") for element in res]
url_params_list = [] url_params_list = []
...@@ -1978,8 +1986,8 @@ path = '/Users/rico/project/模板建库v2/历史数据/20201202/路桥建库模 ...@@ -1978,8 +1986,8 @@ path = '/Users/rico/project/模板建库v2/历史数据/20201202/路桥建库模
#初始化数据 #初始化数据
InitializeData(path) InitializeData(path)
#初始化参数 #初始化参数
channel_alias = 'CL-MBJK' channel_alias = 'TJX-MBJK'
batch = '2020-12-02' batch = '2020-12-25'
#加载数据 #加载数据
df = LoadData(batch,channel_alias,'deal') df = LoadData(batch,channel_alias,'deal')
......
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