Crawling State Administration Drug Administration based on data related to license production of cosmetics People's Republic of China
import requests
from fake_useragent import UserAgent
ua = UserAgent(use_cache_server=False,verify_ssl=False).random
headers = {
'User-Agent':ua
}
url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList'
pageNum = 3
for page in range(3,5):
data = {
'on': 'true',
'page': str(page),
'pageSize': '15',
'productName':'',
'conditionType': '1',
'applyname':'',
'applysn':''
}
json_text = requests.post(url=url,data=data,headers=headers).JSON ()
ID = dict [ 'ID'] # for two page data acquisition
all_id_list = []
for dict in json_text['list']:
# The following information can be obtained before the two pages
# name = dict [ 'EPS_NAME']
# Product dict = [ 'PRODUCT_SN']
# = man_name dict [ 'QF_MANAGER_NAME']
# D1 = dict [ 'XC_DATE']
# = D2 dict [ 'XK_DATE']
all_id_list.append (ID)
# is the url of a post request ajax
POST_URL = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById'
for ID in all_id_list :
post_data = {
'ID': ID
}
Response = requests.post (= POST_URL URL, Data = post_data, headers = headers)
IF Response.Headers [' Content-Type '] ==' application / json;charset=UTF-8':
#Print (response.json ())
# json be resolved
json_text = response.json ()
print(json_text['businessPerson'])