Update app.py
Browse files
app.py
CHANGED
|
@@ -26,6 +26,7 @@ from bs4 import BeautifulSoup
|
|
| 26 |
import smtplib
|
| 27 |
from email.mime.multipart import MIMEMultipart
|
| 28 |
from email.mime.text import MIMEText
|
|
|
|
| 29 |
|
| 30 |
# Initialize logging and load environment variables
|
| 31 |
logging.basicConfig(level=logging.INFO)
|
|
@@ -146,52 +147,8 @@ def send_feedback_via_email(name, email, feedback):
|
|
| 146 |
|
| 147 |
|
| 148 |
def clean_text(text):
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
# Convert <a> tags to Markdown links
|
| 153 |
-
for a in soup.find_all('a'):
|
| 154 |
-
a.replace_with(f"[{a.get_text()}]({a['href']})")
|
| 155 |
-
|
| 156 |
-
# Convert <b> and <strong> tags to Markdown bold
|
| 157 |
-
for tag in ['b', 'strong']:
|
| 158 |
-
for element in soup.find_all(tag):
|
| 159 |
-
element.insert_before('**')
|
| 160 |
-
element.insert_after('**')
|
| 161 |
-
element.unwrap()
|
| 162 |
-
|
| 163 |
-
# Convert <i> and <em> tags to Markdown italic
|
| 164 |
-
for tag in ['i', 'em']:
|
| 165 |
-
for element in soup.find_all(tag):
|
| 166 |
-
element.insert_before('*')
|
| 167 |
-
element.insert_after('*')
|
| 168 |
-
element.unwrap()
|
| 169 |
-
|
| 170 |
-
# Preserve <h1> to <h6> tags as Markdown headings
|
| 171 |
-
for level in range(1, 7):
|
| 172 |
-
for heading in soup.find_all(f'h{level}'):
|
| 173 |
-
heading.insert_before('#' * level + ' ')
|
| 174 |
-
heading.insert_after('\n')
|
| 175 |
-
heading.unwrap()
|
| 176 |
-
|
| 177 |
-
# Convert <u> tags to Markdown underline (if needed)
|
| 178 |
-
# Markdown does not support underline, so we'll remove the tags
|
| 179 |
-
for tag in ['u']:
|
| 180 |
-
for element in soup.find_all(tag):
|
| 181 |
-
element.unwrap()
|
| 182 |
-
|
| 183 |
-
# Get the cleaned text
|
| 184 |
-
cleaned_text = soup.get_text()
|
| 185 |
-
|
| 186 |
-
# Handle extra whitespace and preserve spacing
|
| 187 |
-
# Maintain paragraph breaks
|
| 188 |
-
cleaned_text = re.sub(r'\n\s*\n', '\n\n', cleaned_text)
|
| 189 |
-
# Replace multiple spaces with a single space
|
| 190 |
-
cleaned_text = re.sub(r'\s+', ' ', cleaned_text)
|
| 191 |
-
# Strip leading/trailing spaces
|
| 192 |
-
cleaned_text = cleaned_text.strip()
|
| 193 |
-
|
| 194 |
-
return cleaned_text
|
| 195 |
|
| 196 |
def side():
|
| 197 |
with st.sidebar.form(key='feedback_form'):
|
|
@@ -616,7 +573,7 @@ if prompt :
|
|
| 616 |
suggestion = random.choice(suggestions)
|
| 617 |
cleaned_text += f"\n\n**Trust Tip**: {trust_tip} \n\n **Suggestion**: {suggestion}"
|
| 618 |
|
| 619 |
-
st.
|
| 620 |
|
| 621 |
|
| 622 |
|
|
|
|
| 26 |
import smtplib
|
| 27 |
from email.mime.multipart import MIMEMultipart
|
| 28 |
from email.mime.text import MIMEText
|
| 29 |
+
from markdownify import markdownify
|
| 30 |
|
| 31 |
# Initialize logging and load environment variables
|
| 32 |
logging.basicConfig(level=logging.INFO)
|
|
|
|
| 147 |
|
| 148 |
|
| 149 |
def clean_text(text):
|
| 150 |
+
"""Converts HTML content to Markdown format using markdownify."""
|
| 151 |
+
return markdownify(html_content, strip=['img', 'video'])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 152 |
|
| 153 |
def side():
|
| 154 |
with st.sidebar.form(key='feedback_form'):
|
|
|
|
| 573 |
suggestion = random.choice(suggestions)
|
| 574 |
cleaned_text += f"\n\n**Trust Tip**: {trust_tip} \n\n **Suggestion**: {suggestion}"
|
| 575 |
|
| 576 |
+
st.markdown(cleaned_text)
|
| 577 |
|
| 578 |
|
| 579 |
|