Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
C
crawler
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
backend
crawler
Commits
5758f2df
Commit
5758f2df
authored
Jul 20, 2021
by
李小芳
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add
parent
00066ad7
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
199 additions
and
0 deletions
+199
-0
app_soyoung.py
dev/xinyang_ask_tag/app_soyoung.py
+199
-0
No files found.
dev/xinyang_ask_tag/app_soyoung.py
0 → 100644
View file @
5758f2df
import
json
import
logging
import
smtplib
import
socket
import
time
import
traceback
import
datetime
import
os
import
sys
from
email.mime.application
import
MIMEApplication
from
email.mime.multipart
import
MIMEMultipart
from
email.mime.text
import
MIMEText
from
email.utils
import
formataddr
import
pandas
as
pd
import
requests
from
lxml
import
etree
logger
=
logging
.
getLogger
(
__name__
)
def
send_email_tome
():
try
:
from_addrs
=
'lixiaofang@igengmei.com'
password
=
'EzJzSRyEG4Jibuy9'
toaddrs
=
"lixiaofang@igengmei.com"
content
=
'爬取新氧热搜前100的词召回的商品,内容详见表格'
text_apart
=
MIMEText
(
content
,
'plain'
,
"utf-8"
)
zip_file_week
=
'result1.csv'
zip_apart_week
=
MIMEApplication
(
open
(
zip_file_week
,
'rb'
)
.
read
())
zip_apart_week
.
add_header
(
'Content-Disposition'
,
'attachment'
,
filename
=
zip_file_week
)
m
=
MIMEMultipart
()
m
.
attach
(
text_apart
)
m
.
attach
(
zip_apart_week
)
m
[
'From'
]
=
formataddr
((
"李小芳"
,
from_addrs
))
m
[
"To"
]
=
formataddr
((
"李小芳"
,
toaddrs
))
m
[
'Subject'
]
=
'新氧商品信息'
try
:
server
=
smtplib
.
SMTP_SSL
(
'smtp.exmail.qq.com'
,
465
)
server
.
login
(
from_addrs
,
password
)
server
.
sendmail
(
from_addrs
,
[
toaddrs
],
m
.
as_string
())
print
(
'success'
)
server
.
quit
()
except
smtplib
.
SMTPException
as
e
:
print
(
'error'
,
e
)
except
Exception
as
e
:
print
(
str
(
e
))
logger
.
error
(
"catch exception,main:
%
s"
%
traceback
.
format_exc
())
def
get_service_info
(
city_id
=-
1
,
keyword
=
""
,
city_name
=
""
,
all_skuids
=
[]):
print
(
"get_service_info"
)
service_info_list
=
[]
url
=
'https://api.soyoung.com/v8/superList/index'
for
page
in
range
(
1
,
1000
):
data
=
{
'_time'
:
'1626769752'
,
'ab_id'
:
'C521C79519A5D544390E60FEA08B32DB'
,
"app_id"
:
42
,
"area_belong"
:
4
,
"channel"
:
1
,
"cityId"
:
str
(
city_id
),
"device_id"
:
196374256
,
"device_model"
:
"iPhone12,1"
,
'device_version'
:
'13.6.1'
,
"event"
:
"--Boundary+D46DCD61FE6FA268"
,
"filter"
:
{},
"from_site"
:
1
,
"gps_city_id"
:
1
,
"idfa"
:
"057F28DF-20B8-488F-A285-931367FCC110"
,
"is_tf"
:
0
,
"item_id"
:
"--Boundary+D46DCD61FE6FA268"
,
"keyword"
:
str
(
keyword
),
"list_name"
:
"sy_app_superlist_search_page"
,
"lver"
:
"8.28.2"
,
# "menu1_id": "--Boundary+D46DCD61FE6FA268",
# "menu2_id": "--Boundary+D46DCD61FE6FA268",
"page"
:
page
,
"page_size"
:
20
,
"push_app_id"
:
42
,
"request_id"
:
"14d1e2b53ca644242ec7ccd7316a0aa2"
,
"s_mei_device_id"
:
"20200317131719d8bcbc37c54be511421dc3ebf7f1d0a801036b566bd47092"
,
"s_meng_device_id"
:
"D2VCzq4o472Ur7QtdVY6RlcjO6h3455JlJ+OC39JcQC7sX6a"
,
"schemecard"
:
"--Boundary+D46DCD61FE6FA268"
,
# "sub_tab": "--Boundary+D46DCD61FE6FA268",
"sys"
:
1
,
"tab"
:
"mix"
,
"uid"
:
"48804194"
,
"vistor_uid"
:
""
,
"xy_device_token"
:
"33fa06111dea535c88cc07521f2e466c91"
,
'xy_sign'
:
"Z1VfaYFXrpWBPeizj2VGeQ
%3
D
%3
D"
,
"xy_token"
:
"ad970db3d79f0833d1d25d3942068585"
}
response_res
=
requests
.
post
(
url
,
data
,
verify
=
False
)
print
(
response_res
,
response_res
.
text
)
if
response_res
.
status_code
==
200
and
response_res
.
text
:
response
=
json
.
loads
(
response_res
.
text
)
responseData
=
response
.
get
(
"responseData"
,
{})
.
get
(
"data"
)
for
item
in
responseData
:
if
item
.
get
(
"type"
)
==
"feed_area"
:
if
item
.
get
(
"items"
,
{})
.
get
(
"feed_list"
,
[]):
for
data
in
item
.
get
(
"items"
,
{})
.
get
(
"feed_list"
,
[]):
if
data
.
get
(
"type"
)
==
"feed_shop_diallel"
:
for
service
in
data
.
get
(
"items"
,
[]):
service_data
=
service
.
get
(
"data"
)
if
str
(
service_data
.
get
(
"district_2"
))
==
str
(
city_id
):
service_info
=
dict
()
service_info
[
'skuid'
]
=
service_data
.
get
(
"pid"
)
service_info
[
'美购id'
]
=
service_data
.
get
(
"spu_id"
)
# service_info['医生名'] = service_data.get("doctor_name")
service_info
[
'医院名称'
]
=
service_data
.
get
(
"hospital_name"
)
service_info
[
'sku原价'
]
=
service_data
.
get
(
"price_origin"
)
service_info
[
'sku活动价'
]
=
service_data
.
get
(
"price_online"
)
service_info
[
'机构等级'
]
=
service_data
.
get
(
"avg_score"
)
service_info
[
'美购名称'
]
=
service_data
.
get
(
"title"
)
service_info
[
'销量'
]
=
service_data
.
get
(
"order_cnt"
)
icon_data
=
service_data
.
get
(
"icons"
,
[])
service_info
[
'可用尾款券'
]
=
service_data
.
get
(
"wei_kuan_list"
,
[])
service_info
[
'可领取预约金优惠券'
]
=
[
service_data
.
get
(
"new_user_text"
,
""
)]
if
service_data
.
get
(
"new_user_text"
,
""
)
else
[]
for
item
in
icon_data
:
if
"预约金满"
in
item
:
service_info
[
'可领取预约金优惠券'
]
.
append
(
item
)
elif
"尾款满"
in
item
:
service_info
[
'可用尾款券'
]
.
append
(
item
)
service_info
[
'query词'
]
=
keyword
service_info
[
'城市'
]
=
city_name
service_info
[
'平台'
]
=
"新氧"
service_info
[
'链接'
]
=
"https://y.soyoung.com/cp{}"
.
format
(
service_info
[
'skuid'
])
print
(
service_info
)
if
service_data
.
get
(
"pid"
)
not
in
all_skuids
:
service_info_list
.
append
(
service_info
)
else
:
print
(
"break"
)
return
service_info_list
else
:
# if response_res
print
(
city_id
,
keyword
,
"fail or end"
)
return
service_info_list
if
__name__
==
'__main__'
:
begin
=
time
.
time
()
nowday
=
datetime
.
datetime
.
now
()
today
=
str
(
nowday
)
.
split
()[
0
]
file_name
=
"save_data_"
+
str
(
today
)
+
".txt"
get_data_file
=
open
(
file_name
,
"a+"
,
encoding
=
"utf-8"
)
cityIdMapping
=
{
'北京'
:
'1'
,
'上海'
:
'9'
,
'重庆'
:
'22'
,
'广州市'
:
'289'
,
'深圳市'
:
'291'
,
'郑州市'
:
'240'
,
'武汉市'
:
'258'
,
'长沙市'
:
'275'
,
'南京市'
:
'162'
,
'成都市'
:
'385'
,
'西安市'
:
'438'
,
'杭州市'
:
'175'
}
keywords
=
[
'瘦脸针'
,
'双眼皮'
,
'光子嫩肤'
,
'吸脂'
,
'水光针'
,
'玻尿酸'
,
'热玛吉'
,
'脱毛'
,
'瘦腿针'
,
'鼻综合'
,
'瘦肩针'
,
'下颌角'
,
'线雕'
,
'超声刀'
,
'美白针'
,
'眼综合'
,
'隆鼻'
,
'菲洛嘉'
,
'下巴'
,
'热拉提'
,
'点阵激光'
,
'面部吸脂'
,
'开内眼角'
,
'嗨体'
,
'牙齿矫正'
,
'皮秒'
,
'超皮秒'
,
'植发'
,
'黄金微针'
,
'隆胸'
,
'微针'
,
'光子嫩肤'
,
'祛斑'
,
'小气泡'
,
'嗨体熊猫针'
,
'熊猫针'
,
'果酸焕肤'
,
'自体脂肪隆胸'
,
'7D聚拉提'
,
'瘦脸'
,
'埋线双眼皮'
,
'菲洛嘉水光针'
,
'双眼皮修复'
,
'欧洲之星'
,
'脂肪填充'
,
'溶脂针'
,
'法令纹'
,
'鼻基底'
,
'全切双眼皮'
,
'颧骨内推'
,
'鼻子'
,
'光子嫩肤m22'
,
'下颌缘提升'
,
'm22'
,
'鼻翼缩小'
,
'欧洲之星fotona4d'
,
'自体脂肪全面部填充'
,
'玻尿酸丰唇'
,
'水光'
,
'嗨体祛颈纹'
,
'假体隆胸'
,
'英诺小棕瓶'
,
'黄金微雕'
,
'眼袋'
,
'乔雅登'
,
'除皱'
,
'颧骨'
,
'艾莉薇'
,
'抽脂'
,
'瘦腿'
,
'玻尿酸丰下巴'
,
'纹眉'
,
'伊肤泉微针'
,
'美白'
,
'厚唇改薄'
,
'面部线雕'
,
'祛疤'
,
'伊婉V'
,
'超皮秒祛斑'
,
'除皱针'
,
'开眼角'
,
'海菲秀'
,
'假体下巴'
,
'刷酸'
,
'泪沟'
,
'拉皮'
,
'全身吸脂'
,
'缩鼻翼'
]
city_list
=
[
"北京"
,
"上海"
,
"广州市"
,
"深圳市"
,
"杭州市"
,
"成都市"
,
"重庆"
,
"南京市"
,
"武汉市"
,
"长沙市"
,
"郑州市"
,
"西安市"
]
all_skuids
=
[]
for
city_name
in
city_list
:
city_id
=
cityIdMapping
.
get
(
city_name
)
for
word
in
keywords
:
service_info_list
=
get_service_info
(
city_id
=
city_id
,
keyword
=
word
,
city_name
=
city_name
,
all_skuids
=
all_skuids
)
for
data
in
service_info_list
:
get_data_file
.
write
(
json
.
dumps
(
data
))
get_data_file
.
write
(
"
\n
"
)
get_data_file
.
close
()
all_data
=
[]
if
os
.
path
.
exists
(
file_name
):
open_file
=
open
(
file_name
,
"r"
,
encoding
=
"utf-8"
)
for
item
in
open_file
.
readlines
():
all_data
.
append
(
json
.
loads
(
item
))
open_file
.
close
()
res
=
pd
.
DataFrame
(
all_data
)
res
.
to_csv
(
"result1.csv"
,
encoding
=
"gb18030"
)
send_email_tome
()
print
(
time
.
time
()
-
begin
)
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment