Get Messages data related to a domain from signal-spam.fr

getSignalSpamHeaders.py

# -*- coding: utf-8 -*-

import time
import sys
import requests
import json
import re
from decouple import config
import urllib.parse
import pyperclip


# Sometimes I receive spam from AWS SES, that I record on signal-spam.fr
# but at the end of each month I send the email headers + data of all email related to this domain to email-abuse@amazon.com and ec2-abuse@amazon.com

# This script needs a .env file (python-decouple) with user=yoursignalspamuser and password=yourpassword, then line 64, the domain must be adapted to yours.
# All the header + data will be retrieved from signal-spam and will be copied in the copyclip (pyperclip), then you just have to prepare a mail to AWS (or other web service provider) and paste it

def connect(s, user, password):
    s.get('https://signalants.signal-spam.fr/')
    token = s.get('https://signalants.signal-spam.fr/login')
    m = re.search('<input type="hidden" name="authenticity_token" value="([^"]+)"', token.text)
    if m:
        headers = {'Content-Type': "application/x-www-form-urlencoded"}
        time.sleep(8)
        payload = "utf8=✓&authenticity_token={}&user[email_or_login]={}&user[password]={}&user[remember_me]=0&button=".format(m.group(1), user, password)
        cookie = s.post('https://signalants.signal-spam.fr/login', headers = headers, allow_redirects = True, data=payload.encode('utf-8'))
        if cookie.status_code == 302 or "Mon activité" in cookie.text:
            time.sleep(1)
            req = s.get('https://signalants.signal-spam.fr/', headers = {'Connection': 'keep-alive', 'Accept': '*/*', 'Accept-Encoding': 'gzip, deflate, br'}, allow_redirects = False)
            time.sleep(1)
            return "OK"
    print ("unable to connect")
    return None

def getPage(s, domain, page = 1):
    req = s.get("https://signalants.signal-spam.fr/reportings?page={}".format(page))
    fa = re.findall('<tr><td class="checkbox-table">.*?&lt;(.*?)&gt;</td><td>.*?href="(/reportings/\d+)">Détail</a></td></tr>', req.text)
    lst = []
    if fa:
        for f in fa:
            if domain in f[0]:
                lst.append(getHeader(s, f[1]))
    else:
        return None
    return lst

def getHeader(s, url):
    content = s.get('https://signalants.signal-spam.fr'+url)
    m = re.search('<pre class="message">(.+)</pre>', content.text, re.M | re.S )
    if m:
        return m.group(1)
    return None

user = config('User', default='no')
password = config('Password', default='no')
s = requests.Session()
s.headers['User-Agent'] = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.80 Safari/537.36"

if connect(s, user,password) == 'OK':
    i = 1
    cp = ""
    while True:
        lst = getPage(s, 'booklet-elites.online', i)
        if lst is None:
            break
        for l in lst:
            cp += l + '\n\n=================================================================\n\n'
        i += 1
    pyperclip.copy(cp)