Python程序下载m3u列表：Post方法无法定位结果页求助

我想用Python程序下载一份M3U列表，但通过POST方法无法找到对应的结果页面，相关页面URL为 https://playtvnow.com/shop1/order/trial-products/1，以下是我当前的代码：

from __future__ import print_function
import requests , json, re,random,string,time,warnings
from requests.packages.urllib3.exceptions import InsecureRequestWarning
warnings.simplefilter('ignore',InsecureRequestWarning)
post_url='https://playtvnow.com/shop1/modules/addons/LagomOrderForm/api/index.php/cart/registration-type/update'
post_url2='https://playtvnow.com/shop1/modules/addons/LagomOrderForm/api/index.php/cart/billing-details/update'


def get_clipmails():     
    Headers_={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:83.0) Gecko/20100101 Firefox/83.0',
              'Accept': 'application/json, text/plain, */*',
              'Accept-Language': 'fr,fr-FR;q=0.8,en-US;q=0.5,en;q=0.3',
              'Content-Type':'application/x-www-form-urlencoded',
              'Origin': 'https://playtvnow.com/',
              'Connection': 'keep-alive',
              'Referer': 'https://playtvnow.com/shop1/order/trial-products/1',
              'Accept-Encoding':'gzip'}#, deflate, br'}
    params='details[firstname]='+NAME_TARGET+'&details[lastname]='+LAST_TARGET+'&details[email]='+EMAIL_TARGET+'&details[callingCode]=1&details[phonenumber]='+PHON_TARGET+'&details[companyname]=&details[tax_id]=&details[address1]='+ADRS_TARGET+'&details[address2]='+ADRS_TARGET+'&details[city]='+CITY_TARGET+'&details[state]='+STATE_TARGET+'&details[country]=US&details[password]='+RND_PASS+'&details[password2]='+RND_PASS+'&details[postcode]='+ZIP_TARGET+'&paymentMethod=mailin&details[marketingoptin]=1&details[country-calling-code-phonenumber]=1&acceptTos=&currency=1&'
    post_data2=requests.post(post_url2,headers=Headers_,data=params).text 
    print("POST DATA2:",post_data2)
    post_data=requests.post(post_url,headers=Headers_,data=params).text 
    print("POST DATA:",post_data)

问题分析与解决步骤 #

1. 会话未保持 #

网站通常通过Cookie跟踪用户会话，当前代码每次POST都是独立请求，无法维持状态。改用requests.Session()统一管理Cookie和会话。

2. 缺少CSRF令牌验证 #

多数表单提交需要CSRF令牌，需先访问初始页面提取令牌，添加到请求头或参数中。

3. 请求顺序错误 #

需模拟浏览器操作流程：先访问目标页面，再按正确顺序调用API（通常先更新注册类型，再更新账单详情）。

4. 参数完整性与编码问题 #

手动拼接参数易出现编码错误，改用字典格式传递参数；acceptTos参数为空，需设置为1表示同意条款。

修改后的代码 #

from __future__ import print_function
import requests, re, random, string, warnings
from requests.packages.urllib3.exceptions import InsecureRequestWarning

warnings.simplefilter('ignore', InsecureRequestWarning)

BASE_URL = "https://playtvnow.com/shop1/order/trial-products/1"
POST_URL_REG = 'https://playtvnow.com/shop1/modules/addons/LagomOrderForm/api/index.php/cart/registration-type/update'
POST_URL_BILL = 'https://playtvnow.com/shop1/modules/addons/LagomOrderForm/api/index.php/cart/billing-details/update'

def get_clipmails():
    # 初始化会话，自动维护Cookie
    session = requests.Session()
    session.headers.update({
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:83.0) Gecko/20100101 Firefox/83.0',
        'Accept': 'application/json, text/plain, */*',
        'Accept-Language': 'fr,fr-FR;q=0.8,en-US;q=0.5,en;q=0.3',
        'Origin': 'https://playtvnow.com/',
        'Connection': 'keep-alive',
        'Referer': BASE_URL,
        'Accept-Encoding': 'gzip'
    })

    # 先访问初始页面，获取Cookie和CSRF令牌
    response = session.get(BASE_URL, verify=False)
    csrf_match = re.search(r'name="csrfToken" value="([^"]+)"', response.text)
    if csrf_match:
        csrf_token = csrf_match.group(1)
        session.headers.update({'X-CSRF-Token': csrf_token})

    # 字典形式传递参数，自动处理编码
    params = {
        'details[firstname]': NAME_TARGET,
        'details[lastname]': LAST_TARGET,
        'details[email]': EMAIL_TARGET,
        'details[callingCode]': '1',
        'details[phonenumber]': PHON_TARGET,
        'details[companyname]': '',
        'details[tax_id]': '',
        'details[address1]': ADRS_TARGET,
        'details[address2]': ADRS_TARGET,
        'details[city]': CITY_TARGET,
        'details[state]': STATE_TARGET,
        'details[country]': 'US',
        'details[password]': RND_PASS,
        'details[password2]': RND_PASS,
        'details[postcode]': ZIP_TARGET,
        'paymentMethod': 'mailin',
        'details[marketingoptin]': '1',
        'details[country-calling-code-phonenumber]': '1',
        'acceptTos': '1',
        'currency': '1'
    }

    # 按正确顺序请求API
    post_data_reg = session.post(POST_URL_REG, data=params, verify=False).text
    print("POST REG DATA:", post_data_reg)
    
    post_data_bill = session.post(POST_URL_BILL, data=params, verify=False).text
    print("POST BILL DATA:", post_data_bill)

    # 提取并下载M3U列表（需根据页面实际结构调整规则）
    m3u_response = session.get(BASE_URL, verify=False)
    m3u_match = re.search(r'https?://[^\s"]+\.m3u', m3u_response.text)
    if m3u_match:
        m3u_url = m3u_match.group(0)
        print("找到M3U链接:", m3u_url)
        m3u_content = session.get(m3u_url, verify=False).text
        with open('playlist.m3u', 'w') as f:
            f.write(m3u_content)
        print("M3U文件已保存")

# 定义必填变量
NAME_TARGET = "Test"
LAST_TARGET = "User"
EMAIL_TARGET = f"test_{random.randint(1000,9999)}@example.com"
PHON_TARGET = f"555{random.randint(1000000,9999999)}"
ADRS_TARGET = "123 Test St"
CITY_TARGET = "New York"
STATE_TARGET = "NY"
ZIP_TARGET = "10001"
RND_PASS = ''.join(random.choices(string.ascii_letters + string.digits, k=12))

get_clipmails()

补充说明 #

• 若页面CSRF令牌位置不同，需调整正则表达式匹配规则。
• M3U链接提取逻辑需根据实际页面结构修改，若M3U通过API返回，需跟踪浏览器后续请求。
• 确保所有变量已正确定义，避免运行报错。

内容的提问来源于stack exchange，提问作者mino31