From fc0551f7dcf2880dcbd97b0cbec0a93d1ec78fcd Mon Sep 17 00:00:00 2001
From: Aykhan <aykhan.shahs0@gmail.com>
Date: Wed, 13 Sep 2023 23:46:11 +0400
Subject: [PATCH] Added BeautifulSoup to html2text function

---
 src/app/utils/custom_functions.py |  9 +++------
 src/poetry.lock                   | 31 ++++++++++++++++++++++++++++++-
 src/pyproject.toml                |  1 +
 3 files changed, 34 insertions(+), 7 deletions(-)

diff --git a/src/app/utils/custom_functions.py b/src/app/utils/custom_functions.py
index 90832a0..51188fe 100644
--- a/src/app/utils/custom_functions.py
+++ b/src/app/utils/custom_functions.py
@@ -1,9 +1,6 @@
-import re
+from bs4 import BeautifulSoup
 
 
 def html2text(html: str) -> str:
-    return re.sub(
-            re.compile('<.*?>'),
-            '',
-            html
-        )
\ No newline at end of file
+    soup = BeautifulSoup(html, 'html.parser')
+    return soup.get_text()
\ No newline at end of file
diff --git a/src/poetry.lock b/src/poetry.lock
index 32a499d..524b1ce 100644
--- a/src/poetry.lock
+++ b/src/poetry.lock
@@ -130,6 +130,24 @@ files = [
 docs = ["Sphinx (>=5.3.0,<5.4.0)", "sphinx-rtd-theme (>=1.2.2)", "sphinxcontrib-asyncio (>=0.3.0,<0.4.0)"]
 test = ["flake8 (>=5.0,<6.0)", "uvloop (>=0.15.3)"]
 
+[[package]]
+name = "beautifulsoup4"
+version = "4.12.2"
+description = "Screen-scraping library"
+optional = false
+python-versions = ">=3.6.0"
+files = [
+    {file = "beautifulsoup4-4.12.2-py3-none-any.whl", hash = "sha256:bd2520ca0d9d7d12694a53d44ac482d181b4ec1888909b035a3dbf40d0f57d4a"},
+    {file = "beautifulsoup4-4.12.2.tar.gz", hash = "sha256:492bbc69dca35d12daac71c4db1bfff0c876c00ef4a2ffacce226d4638eb72da"},
+]
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
 [[package]]
 name = "blinker"
 version = "1.6.2"
@@ -975,6 +993,17 @@ files = [
     {file = "sniffio-1.3.0.tar.gz", hash = "sha256:e60305c5e5d314f5389259b7f22aaa33d8f7dee49763119234af3755c55b9101"},
 ]
 
+[[package]]
+name = "soupsieve"
+version = "2.5"
+description = "A modern CSS selector implementation for Beautiful Soup."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "soupsieve-2.5-py3-none-any.whl", hash = "sha256:eaa337ff55a1579b6549dc679565eac1e3d000563bcb1c8ab0d0fefbc0c2cdc7"},
+    {file = "soupsieve-2.5.tar.gz", hash = "sha256:5663d5a7b3bfaeee0bc4372e7fc48f9cff4940b3eec54a6451cc5299f1097690"},
+]
+
 [[package]]
 name = "sqlalchemy"
 version = "2.0.20"
@@ -1114,4 +1143,4 @@ standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)",
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "333a9be3573863da41b6a2615cd28aa3a6daf2e608a76da1476af72d343dae52"
+content-hash = "78fafe7f9e40a699277d899f9b66a4bc2b9d191008a5fcd6bd393462d51d473f"
diff --git a/src/pyproject.toml b/src/pyproject.toml
index cbc95aa..27e0401 100644
--- a/src/pyproject.toml
+++ b/src/pyproject.toml
@@ -23,6 +23,7 @@ pillow = "^10.0.0"
 aiofiles = "^23.2.1"
 python-jose = {extras = ["cryptography"], version = "^3.3.0"}
 fastapi-mail = "^1.4.1"
+beautifulsoup4 = "^4.12.2"
 
 
 [build-system]