免责声明:仅供学习
from pprint import pprint
import re
import requests
from requests.packages import urllib3
urllib3.disable_warnings()
INDEX_URL = "http://www.zjmazhang.gov.cn/hdjlpt/published?via=pc"
POST_URL = "http://www.zjmazhang.gov.cn/hdjlpt/letter/pubList"
response = requests.get(url=INDEX_URL)
cookies = response.cookies
session = cookies["szxx_session"]
# pprint(session)
# var _CSRF = 'Z2miF39qVvSRJU1hlQiXQsD3vun0gKAbynoMt7R3';
# 这个参数网页里面有,直接正则获取
csrf = re.search("_CSRF = \'(.*?)\';", response.text).group(1)
# print(response.text)
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36",
"Cookie": f"szxx_session={session}",
"X-CSRF-TOKEN": f"{csrf}"
}
# print(headers)
data = {
"offset": 0,
"limit": 20,
"site_id": "759010"
}
res = requests.post(url=POST_URL, data=data, headers=headers)
pprint(res.json())