案例地址：http://www.zjmazhang.gov.cn/hdjlpt/published?via=pc
我才开始一直遇到的问题如该图片所示：
一直怀疑是自己代码思路问题，我来回测验，我在控制台前后对比响应cookies和请求cookies发现不一致，后来我换了一个在线格式化工具，一对比发现一致，就是很奇怪这是一点。
第二点就是在script = re.findall("var _CSRF = '(.?)';",response.text)[0] 中，自己的太粗心，在这个地方'(.?)'少加了'',害让我一通乱找呀，
代码如下：
import re
import pprint
import requests
def get_cookie():
headers = {
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,/;q=0.8,application/signed-exchange;v=b3;q=0.7",
"Accept-Language": "zh-CN,zh;q=0.9",
"Cache-Control": "no-cache",
"Connection": "keep-alive",
"Pragma": "no-cache",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36"
}
url = "http://www.zjmazhang.gov.cn/hdjlpt/published"
params = {
"via": "pc"
}
response = requests.get(url, headers=headers, params=params, verify=False)
token = response.cookies.get('XSRF-TOKEN')
szxx_session=response.cookies.get("szxx_session")
script = re.findall("var _CSRF = '(.*?)';",response.text)[0]
return token,szxx_session,script
def get_content():
token,szxx_session,script = get_cookie()
headers1 = {
"Accept": "application/json, text/plain, /",
"Accept-Language": "zh-CN,zh;q=0.9",
"Cache-Control": "no-cache",
"Connection": "keep-alive",
"Content-Type": "application/x-www-form-urlencoded",
"Origin": "http://www.zjmazhang.gov.cn",
"Pragma": "no-cache",
"Referer": "http://www.zjmazhang.gov.cn/",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36",
"X-CSRF-TOKEN": script
}
cookies = {
"XSRF-TOKEN": token,
"szxx_session": szxx_session
}
url = "http://www.zjmazhang.gov.cn/hdjlpt/letter/pubList"
data = {
"offset": "0",
"limit": "20",
"site_id": "759010",
"time_from": "1735315200",
"time_to": "1766851199"
}
response = requests.post(url, headers=headers1, cookies=cookies, data=data)
pprint.pprint(response.text)
get_content()
