get is fetching information from other website , but not from this particular website "nseindia"
hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko)
Chrome/23.0.1271.64 Safari/537.11',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Referer': 'https://cssspritegenerator.com',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Accept-Encoding': 'none',
'Accept-Language': 'en-US,en;q=0.8',
'Connection': 'keep-alive'}
page_url = "https://www1.nseindia.com/live_market/dynaContent/live_watch/option_chain/optionKeys.jsp?symbolCode=-9999&symbol=BANKNIFTY&symbol=BANKNIFTY&instrument=OPTIDX&date=-&segmentLink=17"
d = get(page_url,headers =hdr)
Try requests:
pip install requests
import requests
from requests.exceptions import HTTPError
page_url = "https://www1.nseindia.com/live_market/dynaContent/live_watch/option_chain/optionKeys.jsp?symbolCode=-9999&symbol=BANKNIFTY&symbol=BANKNIFTY&instrument=OPTIDX&date=-&segmentLink=17"
try:
response.headers['content-type'] = '...yours header ...'
response = requests.get(page_url)
except HTTPError as http_err:
print(f'HTTP error occurred: {http_err}')
except Exception as err:
print(f'Other error occurred: {err}')
Related
On the same website here, a consistent valid response is provided for One Page(200-url/nifty) but not provided for anotherpage(401-url/oispurtscontracts).
It does provide a valid response sometimes and other times returns a 401 error.
Browser cache cleared and reloaded.
Please provide a solution.
Error :
response.status_code = 401 for https://www.nseindia.com/api/live-analysis-oi-spurts-contracts
Code:
import requests
def connRequest(url,headers):
session = requests.Session()
request = session.get(url, headers=headers)
cookies = dict(request.cookies)
# print(cookies)
print(f"response.status_code = {request.status_code} for {url}")
response = session.get(url, headers=headers, cookies=cookies).json()
print(f"response = {response}")
return response
# Working - Response Provided
def nifty_Working():
url = 'https://www.nseindia.com/api/option-chain-indices?symbol=NIFTY'
# data = requests.get(url)
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en;q=0.5',
'Accept':'application/json'
}
response = connRequest(url, headers)
# 401 Error
def oiSpurtsContracts_NotWorking():
url = 'https://www.nseindia.com/api/live-analysis-oi-spurts-contracts'
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en',
'Accept': 'application/json'
}
response = connRequest(url, headers)
def main():
# Working - Response Provided
nifty_Working()
print()
print()
print()
print()
# 401 Error
time.sleep(1)
oiSpurtsContracts_NotWorking()
main()
So this code below is working fine but when i change the url to another site it doesn't work
import requests
import re
url = "https://www.autotrader.ca/a/ram/1500/hamilton/ontario/19_12052335_/?showcpo=ShowCpo&ncse=no&ursrc=pl&urp=2&urm=8&sprx=-2"
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}
response = requests.get(url, headers=headers)
phone_number = re.findall('"phoneNumber":"([\d-]+)"', response.text)
print(phone_number)
['905-870-7127']
This code below doesn't work it gives the output [] Please tell me what am i doing wrong
import requests
import re
urls = "https://www.kijijiautos.ca/vip/22686710/","https://www.kijijiautos.ca/vip/22686710/"
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}
for url in urls:
response = requests.get(url, headers=headers)
number = re.findall('"number":"([\d-]+)"', response.text)
print(number)
[]
I think you are not getting The HTTP 200 OK success status as a response.for that cause you are unable to get the exptected ouptput. To get the HTTP 200 OK success status, I have changed the headers from inspecting http requests.
please try this
import requests
import re
import requests
headers = {
'authority': 'www.kijijiautos.ca',
'sec-ch-ua': '"Chromium";v="94", "Google Chrome";v="94", ";Not A Brand";v="99"',
'pragma': 'no-cache',
'accept-language': 'en-CA',
'sec-ch-ua-mobile': '?0',
'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36',
'content-type': 'application/json',
'accept': 'application/json',
'cache-control': 'no-cache',
'x-client-id': 'c89e7ff8-1d5a-4c2b-a095-c08dc08ccd3b',
'x-client': 'ca.move.web.app',
'sec-ch-ua-platform': '"Linux"',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://www.kijijiautos.ca/cars/hyundai/sonata/used/',
'cookie': 'mvcid=c89e7ff8-1d5a-4c2b-a095-c08dc08ccd3b; locale=en-CA; trty=e; _gcl_au=1.1.1363596757.1633936124; _ga=GA1.2.1193080228.1633936126; _gid=GA1.2.71842091.1633936126; AAMC_kijiji_0=REGION%7C3; aam_uuid=43389576784435124231935699643302941454; _fbp=fb.1.1633936286669.1508597061; __gads=ID=bb71a6fc168c1c33:T=1633936286:S=ALNI_MZk3lgy-9xgSGLPnfrkBET60uS6fA; GCLB=COyIgrWs-PWPsQE; lux_uid=163402080128473094; cto_bundle=zxCnjF95NFglMkZrTG5EZ2dzNHFSdjJ6QSUyQkJvM1BUbk5WTkpjTms0aWdZb3RxZUR3Qk1nd1BmcSUyQjZaZVFUdFdSelpua3pKQjFhTFk0U2ViTHVZbVg5ODVBNGJkZ2NqUGg1cHZJN3V0MWlwRkQwb1htcm5nNDlqJTJGUUN3bmt6ZFkzU1J0bjMzMyUyRkt5aGVqWTJ5RVJCa2ZJQUwxcFJnJTNEJTNE; _td=7f855061-c320-4570-b2d2-73c94bd22b13; rbzid=54THgSkyCRKwhVBqy+iHmjb1RG+uE6uH1XjpsXIazO5nO45GtpIXHGYii/PbJcdG3ahjIgKaBrjh0Yx2J6YCOLHEv3QYL559oz3jQaVrssH2/1Ui9buvIpuCwBOGG2xXGWW2qvcU5807PGsdubQDUvLkxmy4sor+4EzCI1OoUHMOG2asQwsgChqwzJixVvrE21E/NJdRfDLlejb5WeGEgU4B3dOYH95yYf5h+7fxV6H/XLhqbNa8e41DM3scfyeYWeqWCWmOH2VWZ7i3oQ0OXW1SkobLy0D6G+V9J5QMxb0=; rbzsessionid=ca53a07d3404ca93b3f8bc879291dc83; _uetsid=131a47702a6211ecba407d9ff6588dde; _uetvid=131b13602a6211ecacd0b56b0815e9b2',
}
response = requests.get('https://www.kijijiautos.ca/consumer/svc/a/22686710', headers=headers)
if response.status_code == 200:
# print(response.text)
numbers = re.findall(r'"number":"\+\d+"', response.text) # number one or more
print(numbers[0])
else:
print('status code is ', response.status_code)
output
# "number":"+17169905088"
I want to get the json data in the target url:
target url
To get it manually :open it in brower manually and copy,paste.I want a more samrt way--programmatically and automatically,have tried with several way,all failed.
Method 1--traditional way with wget or curl:
wget https://xueqiu.com/stock/cata/stocktypelist.json?page=1&size=300
--2021-02-09 11:55:44-- https://xueqiu.com/stock/cata/stocktypelist.json?page=1
Resolving xueqiu.com (xueqiu.com)... 39.96.249.191
Connecting to xueqiu.com (xueqiu.com)|39.96.249.191|:443... connected.
HTTP request sent, awaiting response... 403 Forbidden
2021-02-09 11:55:44 ERROR 403: Forbidden.
Method 2--scrapy with selenium:
>>> from selenium import webdriver
>>> browser = webdriver.Chrome()
>>> url="https://xueqiu.com/stock/cata/stocktypelist.json?page=1&size=300"
>>> browser.get(url)
It happen to me in the browser:
{"error_description":"遇到错误，请刷新页面或者重新登录帐号后再试","error_uri":"/stock/cata/stocktypelist.json","error_code":"400016"}
Method 3--build a mitmproxy:
mitmweb --listen-host 127.0.0.1 -p 8080
Set proxy in browser and open the target url in browser
Error info in terminal:
Web server listening at http://127.0.0.1:8081/
Opening in existing browser session.
Proxy server listening at http://127.0.0.1:8080
127.0.0.1:41268: clientconnect
127.0.0.1:41270: clientconnect
127.0.0.1:41268: HTTP/2 connection terminated by client: error code: 0, last stream id: 0, additional data: None
Error info in browser:
error_description "遇到错误，请刷新页面或者重新登录帐号后再试"
error_uri "/stock/cata/stocktypelist.json"
error_code "400016"
So powerful site to protect the data ,is there no way to get the data automatically?
You could use requests module
import json
import requests
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:77.0) Gecko/20100101 Firefox/77.0",}
import requests
cookies = {
'xq_a_token': '176b14b3953a7c8a2ae4e4fae4c848decc03a883',
'xqat': '176b14b3953a7c8a2ae4e4fae4c848decc03a883',
'xq_r_token': '2c9b0faa98159f39fa3f96606a9498edb9ddac60',
'xq_id_token': 'eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTYxMzQ0MzE3MSwiY3RtIjoxNjEyODQ5MDY2ODI3LCJjaWQiOiJkOWQwbjRBWnVwIn0.VuyNicSjIvVkp9FrCzIlRyx8487XM4HH1C3X9KsFA2FipFiilSifBhux9pMNRyziHHiEifhX-xOgccc8IG1mn8cOylOVy3b-L1YG2T5Hs8MKgx7qm4gnV5Mzm_5_G5BiNtO44aczUcmp0g53dp7-0_Bvw3RlwXzT1DTvCKTV-s_zfBsOPyFTfiqyDUxU-oBRvkz1GpgVJzJL4EmZ8zDE2PBqeW00ueLLC7qPW50WeDCsEFS4ZPAvd2SbX9JPk-lU2WzlcMck2S9iFYmpDwuTeQuPbSeSl6jt5suwTImSgJDIUP9o2TX_Z7nNRDTYxvbP8XlejSt8X0pRDPDd_zpbMQ',
'u': '661612849116563',
'device_id': '24700f9f1986800ab4fcc880530dd0ed',
'Hm_lvt_1db88642e346389874251b5a1eded6e3': '1612849123',
's': 'c111f3y1kn',
'Hm_lpvt_1db88642e346389874251b5a1eded6e3': '1612849252',
}
headers = {
'Connection': 'keep-alive',
'Cache-Control': 'no-cache',
'sec-ch-ua': '"Chromium";v="88", "Google Chrome";v="88", ";Not A Brand";v="99"',
'sec-ch-ua-mobile': '?0',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36',
'Accept': 'image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8',
'Sec-Fetch-Site': 'same-origin',
'Sec-Fetch-Mode': 'no-cors',
'Sec-Fetch-User': '?1',
'Sec-Fetch-Dest': 'image',
'Accept-Language': 'en-US,en;q=0.9',
'Pragma': 'no-cache',
'Referer': '',
}
params = (
('page', '1'),
('size', '300'),
)
response = requests.get('https://xueqiu.com/stock/cata/stocktypelist.json', headers=headers, params=params, cookies=cookies)
print(response.status_code)
json_data = response.json()
print(json_data)
You could use scrapy:
import json
import scrapy
class StockSpider(scrapy.Spider):
name = 'stock_spider'
start_urls = ['https://xueqiu.com/stock/cata/stocktypelist.json?page=1&size=300']
custom_settings = {
'DEFAULT_REQUEST_HEADERS': {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.16; rv:85.0) Gecko/20100101 Firefox/85.0',
'Host': 'xueqiu.com',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Language': 'en-US',
'Accept-Encoding': 'gzip,deflate,br',
'Connection': 'keep-alive',
'Cache-Control': 'no-cache',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'none',
'Sec-Fetch-User': '?1',
'Upgrade-Insecure-Requests': '1',
'Pragma': 'no-cache',
'Referer': '',
},
'ROBOTSTXT_OBEY': False
}
handle_httpstatus_list = [400]
def parse(self, response):
json_result = json.loads(response.body)
yield json_result
Run spider: scrapy crawl stock_spider
I m using python 3.6.5 and my os system is macOS 10.13.6.
I m learning Web Scraping and I want to catch data from this web site(https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput=)
Here is my code:
# encoding: utf-8
import requests
from lxml import etree
def parse_list_page():
url = 'https://www.lagou.com/jobs/positionAjax.json?city=%E6%B7%B1%E5%9C%B3&needAddtionalResult=false'
headers = {
'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537',
'Host':'www.lagou.com',
'Referer':'https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput=',
'X-Anit-Forge-Code':'0',
'X-Anit-Forge-Token':None,
'X-Requested-With':'XMLHttpRequest',
}
data = {
'first':'false',
'pn':1,
'kd':'python',
}
response = requests.post(url,headers=headers,data=data)
print(response.json())
def main():
parse_list_page()
if __name__ == '__main__':
main()
I m appreciate you for spending the time to answer my question.
I got the answer, here is the code below:
# encoding: utf-8
import requests
from lxml import etree
import time
def parse_list_page():
url = 'https://www.lagou.com/jobs/list_python?px=default&city=%E6%B7%B1%E5%9C%B3'
headers = {
'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537',
'Host':'www.lagou.com',
'Referer':'https://www.lagou.com/',
'Connection':'keep-alive',
'Accept-Encoding':'gzip, deflate, br',
'Accept-Language':'zh-CN,zh;q=0.9,en;q=0.8',
'Upgrade-Insecure-Requests':'1',
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Cache-Control':'no-cache',
'Pragma':'no-cache',
}
response = requests.get(url,headers=headers)
# print(response.text)
r = requests.utils.dict_from_cookiejar(response.cookies)
print(r)
print('='*30)
# r['LGUID'] = r['LGRID']
# r['user_trace_token'] = r['LGRID']
# r['LGSID'] = r['LGRID']
cookies = {
# 'X_MIDDLE_TOKEN':'df7c1d3cfdf279f0caf13df990723620',
# 'JSESSIONID':'ABAAABAAAIAACBI29FE9BDFB6838D8DD69C580E517292C9',
# '_ga':'GA1.2.820168368.1551196380',
# '_gat':'1',
# 'Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6':'1551196381',
# 'user_trace_token':'20190226235303-99bc357a-39de-11e9-921f-525400f775ce',
# 'LGSID':'20190311094827-c3bc2393-439f-11e9-a15a-525400f775ce',
# 'PRE_UTM':'',
# 'PRE_HOST':'',
# 'PRE_SITE':'',
# 'PRE_LAND':'https%3A%2F%2Fwww.lagou.com%2F',
# 'LGUID':'20190226235303-99bc3944-39de-11e9-921f-525400f775ce',
# '_gid':'GA1.2.1391680888.1552248111',
# 'index_location_city':'%E6%B7%B1%E5%9C%B3',
# 'TG-TRACK-CODE':'index_search',
# 'LGRID':'20190311100452-0ed0525c-43a2-11e9-9113-5254005c3644',
# 'Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6':'1552269893',
# 'SEARCH_ID':'aae3c38ec76545fc86cd4e23153afe44',
}
cookies.update(r)
print(r)
print('=' * 30)
print(cookies)
print('=' * 30)
headers = {
'Origin':'https://www.lagou.com',
'X-Anit-Forge-Code': '0',
'X-Anit-Forge-Token': None,
'X-Requested-With': 'XMLHttpRequest',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'h-CN,zh;q=0.9,en;q=0.8',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Referer': 'https://www.lagou.com/jobs/list_python?px=default&city=%E6%B7%B1%E5%9C%B3',
'Connection': 'keep-alive',
}
params = {
'px':'default',
'city':'深圳',
'needAddtionalResult':'false'
}
data = {
'first':'true',
'pn':1,
'kd':'python',
}
url_json = 'https://www.lagou.com/jobs/positionAjax.json'
response = requests.post(url=url_json,headers=headers,params=params,cookies=cookies,data=data)
print(response.json())
def main():
parse_list_page()
if __name__ == '__main__':
main()
The reason why I can't get the json as response is the against web scraping rules here is you need to use the first cookie when you send the request.
so when you first send the request you need to save the cookies and then update it to use your second page request. Hope it will helpful for you to do web scraping when you face this problem
When I visit 'https://baike.baidu.com/wikitag/taglist?tagId=75953' on chrome,through fiddler I find the browser sends a post request to 'https://baike.baidu.com//wikitag/api/getlemmas'.
So I'm trying to send a 'POST' request with form data to the url:'https://baike.baidu.com//wikitag/api/getlemmas' and get the JSON data from its 'response' request.
I get all the headers and form data through the Fiddler and try to send the same 'POST' request by python3 using requests package.
But even I send the 'POST' request with the same headers and form data, I get the request(status:200) with an empty body.
the same request I send by 'postman' is also all right, but by python3 I failed anyway.
# -*- coding:UTF-8 -*-
import requests
def disease_json():
host = 'https://baike.baidu.com'
target = host + '/wikitag/api/getlemmas'
cookies={
'BAIDUID':'EEE35ACB030447144E615B191397065B:FG=1;PSTM=1523192637;BIDUPSID=B34DD366905D15BB907C1667346970AE;Hm_lvt_55b574651fcae74b0a9f1cf9c8d7c93a=1522304864,1522305101,1523192946,1523253565;PSINO=2;H_PS_PSSID=1990_1438_26082_21 125_22074;BDORZ=B490B5EBF6F3CD402E515D22BCDA1598'
}
headers = {
'Accept':'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding':'gzip, deflate, br',
'Accept-Language':'zh-CN,zh;q=0.8',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
'X-Requested-With':'XMLHttpRequest',
'Content-Length':'91',
'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8',
'Referer':'https://baike.baidu.com/wikitag/taglist?tagId=75953',
'Origin':'https://baike.baidu.com',
'Connection':'keep-alive',
'Host':'baike.baidu.com',
}
forms = {
'limit': '24',
'timeout': '3000',
'filterTags':'[]',
'tagID': '75953',
'fromLemma': 'false',
'contentLength': '40',
'page': '0',
}
req=requests.post(url=target,data=forms,verify=False,headers=headers)
print(req.text)
"""
html = json.loads(req.text)
for each in html['lemmaList']:
print('lemmaCroppedTitle:',each['lemmaCroppedTitle'])
print(req.text)
"""
def main():
disease_json()
if __name__ == '__main__':
main()
Following is the correct request sent by browser:
Modified content-type and your request payload. Also added method encode_multipart_data for payload transformation to be consistent with multipart-form-data
import sys
import requests
def encode_multipart_data(fields):
boundary = '------WebKitFormBoundary7MA4YWxkTrZu0gW'
CRLF = '\r\n'
L = []
for key, value in fields.items():
L.append(boundary)
L.append('Content-Disposition: form-data; name="%s"\r\n' % key)
L.append(value)
L.append(boundary + "--")
body = CRLF.join(L)
return body
def disease_json():
host = 'https://baike.baidu.com'
target = host + '/wikitag/api/getlemmas'
headers = {
'Accept':'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding':'gzip, deflate, br',
'Accept-Language':'zh-CN,zh;q=0.8',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
'X-Requested-With':'XMLHttpRequest',
# changed content-type
'content-type': "multipart/form-data; boundary=----WebKitFormBoundary7MA4YWxkTrZu0gW",
'Referer':'https://baike.baidu.com/wikitag/taglist?tagId=75953',
'Origin':'https://baike.baidu.com',
'Connection':'keep-alive',
'Host':'baike.baidu.com'
}
forms = {
'limit': '24',
'timeout': '3000',
'filterTags': '[]',
'tagId': '75953',
'fromLemma': 'false',
'contentLength': '40',
'page': '0',
}
payload = encode_multipart_data(forms)
resp = requests.post(url=target, data=payload, headers=headers)
print(resp.text)
if __name__ == '__main__':
disease_json()
This way can also solve the problem.
import requests
import http.cookiejar
import json
url = "https://baike.baidu.com/wikitag/api/getlemmas"
payload = "limit=24&timeout=3000&filtetTags=%5B%5D&tagId=75953&fromLemma=false&contentLegth=40&page=0"
headers = {
'Content-Type': "application/x-www-form-urlencoded",
'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181\
Safari/537.36"
}
def get_cookies():
session = requests.Session()
session.cookies = http.cookiejar.LWPCookieJar("cookie")
response = session.post(url, headers=headers, data=payload, allow_redirects=False,verify=False)
session.cookies.save(ignore_discard=True, ignore_expires=True)
return response
def disease_json(times=-1):
times += 1
response = get_cookies()
if response.status_code == 302:
session = requests.session()
session.cookies = http.cookiejar.LWPCookieJar(filename='cookie')
session.cookies.load(ignore_discard=True)
url = response.headers['Location']
response = session.post(url, headers=headers, data=payload, allow_redirects=False)
json_data = response.text
print(json.loads(json_data))
print(times)
if __name__ == '__main__':
disease_json()