-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
28 additions
and
13 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -2,9 +2,18 @@ | |
| "cells": [ | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 8, | ||
| "execution_count": 1, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "outputs": [ | ||
| { | ||
| "name": "stderr", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "c:\\Users\\Felix\\miniconda3\\envs\\mailcom\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", | ||
| " from .autonotebook import tqdm as notebook_tqdm\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "import mailcom.inout\n", | ||
| "import mailcom.parse\n", | ||
|
|
@@ -13,7 +22,7 @@ | |
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 6, | ||
| "execution_count": 2, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
|
|
@@ -40,7 +49,7 @@ | |
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 11, | ||
| "execution_count": 3, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
|
|
@@ -59,22 +68,22 @@ | |
| "out_list = []\n", | ||
| "for file in io.email_list:\n", | ||
| " print(\"Parsing input file {}\".format(file))\n", | ||
| " # creating dict\n", | ||
| " email_dict = {}\n", | ||
| " text = io.get_text(file)\n", | ||
| " # after this function was called, the email metadata can be accessed via io.email_content\n", | ||
| " # the dict already has the entries content, date, attachments, attachment type\n", | ||
| " email_dict = io.email_content.copy()\n", | ||
| " text = io.get_html_text(text)\n", | ||
| " if not text:\n", | ||
| " continue\n", | ||
| " # Test functionality of Pseudonymize class\n", | ||
| " output_text = ps.pseudonymize(text)\n", | ||
| " email_dict[\"content\"] = text\n", | ||
| " email_dict[\"pseudo_content\"] = output_text\n", | ||
| " out_list.append(email_dict)\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 12, | ||
| "execution_count": 4, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
|
|
@@ -83,15 +92,21 @@ | |
| "text": [ | ||
| " content \\\n", | ||
| "0 J'espère que tu vas bien! Je voulais partager ... \n", | ||
| "1 \\nOlá Lino,Espero que este e-mail te encontre ... \n", | ||
| "2 From : [email protected] : \"Alejandr... \n", | ||
| "3 From : [email protected] : \"Alejand... \n", | ||
| "1 <html><head></head><body><div class=\"ydp9a5bdb... \n", | ||
| "2 <div style=\"font-size: 10pt; font-family: Verd... \n", | ||
| "3 <div style=\"font-size: 10pt; font-family: Verd... \n", | ||
| "\n", | ||
| " date attachment attachement type \\\n", | ||
| "0 2024-04-17 15:13:56+00:00 2 [jpg, jpg] \n", | ||
| "1 2024-04-17 15:39:49+00:00 1 [png] \n", | ||
| "2 1970-01-01 00:00:00+00:00 0 [] \n", | ||
| "3 1970-01-01 00:00:00+00:00 0 [] \n", | ||
| "\n", | ||
| " pseudo_content \n", | ||
| "0 J'espère que tu vas bien! Je voulais partager ... \n", | ||
| "1 \\n Olá Claude,Espero que este e-mail te encont... \n", | ||
| "2 From : [email protected] : \"Claud... \n", | ||
| "3 From : [email protected] : \" Clau... \n" | ||
| "2 From : [email] : \"Claude\"< [email] : mié. , [n... \n", | ||
| "3 From : [email] : \" Claude\"< [email] Dominique\"... \n" | ||
| ] | ||
| } | ||
| ], | ||
|
|
||