lesson1Title

lesson2Title

lesson3Title

lesson4Title

automationIntroApplicationChapter3Title

lesson5Title

lesson6Title

lesson7Title

lesson8Title

lesson9Title

automationIntroApplicationChapter1Title

automationIntroApplicationChapter2Title

automationIntroApplicationChapter4Title

import pandas as pd
import requests
from bs4 import BeautifulSoup
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
from email.mime.base import MIMEBase
from email import encoders
import smtplib
import io

# Load excel file
df = pd.read_excel('input_file.xlsx')

# Wikipedia base URL
base_url = 'https://en.wikipedia.org/wiki/'

# Function to extract date from Wikipedia page
def extract_date(event_name):
    # Wikipedia page URL
    url = base_url + event_name

    # Web page request
    response = requests.get(url)

    # If request is successful
    if response.status_code == 200:

        # Parse HTML
        soup = BeautifulSoup(response.content, 'html.parser')

        # Assume date information is usually in the infobox
        infobox = soup.find('table', {'class': 'infobox'})

        # Look for 'Date' field in infobox
        if infobox:
            # Check if 'Date' field exists
            date_tag = infobox.find('th', string='Date')

            # If 'Date' field exists
            if date_tag:
                # Extract date information from the sibling tag
                date_value = date_tag.find_next_sibling('td')

                # If date information exists
                if date_value:
                    # Return date information
                    return date_value.text.strip()
        # If no date information is found
        return 'No date information'
    else:
        # If web page request fails
        return 'Page error'

# Apply date extraction function to each historical event
df['Date'] = df['HistoricalEvent'].apply(extract_date)

# Save to memory as CSV
csv_buffer = io.StringIO()

# Save as CSV file
df[['HistoricalEvent', 'Date']].to_csv(csv_buffer, index=False)

# Reset memory pointer
csv_buffer.seek(0)  

# Receiver email address
receiver_email = "youremail@example.com"

# Email sender settings
sender_email = "admin_email"
sender_password = "admin_password"
smtp_server = "smtp.gmail.com"
port = 587

# Create email body
def create_email_body():
    return """
    <html>
    <body>
        <h1>Historical Event Date Information</h1>
        <p>Hello, This is CodeFriends.</p>
        <p>Please check the attached CSV file for the historical events and their dates.</p>
    </body>
    </html>
    """

# Function to send email
def send_email(to_email, subject, body, attachment_data, attachment_name):
    msg = MIMEMultipart()
    msg['Subject'] = subject
    msg['From'] = sender_email
    msg['To'] = to_email

    # Attach email body
    msg.attach(MIMEText(body, 'html'))

    # Attach file
    part = MIMEBase('application', 'octet-stream')
    part.set_payload(attachment_data.getvalue().encode('utf-8'))
    encoders.encode_base64(part)
    part.add_header(
        'Content-Disposition',
        f'attachment; filename={attachment_name}',
    )
    msg.attach(part)

    # Send email through SMTP server
    server = smtplib.SMTP(smtp_server, port)
    server.starttls()
    server.login(sender_email, sender_password)
    server.sendmail(sender_email, to_email, msg.as_string())
    server.quit()

# Create email body
email_body = create_email_body()

# Send email
send_email(receiver_email, "[CodeFriends] Historical Event Date Information", email_body, csv_buffer, 'historical_events_dates.csv')

print("Email has been sent successfully.")

# Sending Data Scraped from Wikipedia via Email

In this session, we'll learn how to send a `CSV file of date information` gathered from web crawling historical events as an email attachment.

<br />

### 1. Import Required Libraries

- *email*, *smtplib*: Libraries for creating and sending emails.

- *io*: Handles data processing using the computer's memory.

<br />

### 2. Save CSV File in Memory

```python title="Save CSV File in Computer Memory"
# Save as CSV format in memory
csv_buffer = io.StringIO()

# Save as CSV file
df[['Historical Event', 'Date']].to_csv(csv_buffer, index=False)

# Reset the memory pointer to the start
csv_buffer.seek(0)
```

Using the `io.StringIO` object, we store data in memory and then convert it to a `CSV` file.

This CSV file contains information on *Historical Events* and *Dates*.

<br />

### 3. Compose and Send Email

```python title="Compose and Send Email"
# Create email body
def create_email_body():
    return """
    <html>
    <body>
        <h1>Historical Events Date Information</h1>
        <p>Hello, CodeFriends here.</p>
        <p>Please check the historical events and date information in the attached CSV file.</p>
    </body>
    </html>
    """

# Function to send email
def send_email(to_email, subject, body, attachment_data, attachment_name):
    msg = MIMEMultipart()
    msg['Subject'] = subject
    ...(truncated)...

# Send email
send_email(receiver_email, "[CodeFriends] Historical Events Date Information", create_email_body(), csv_buffer, 'historical_events_dates.csv')
```

Compose the email body and attach the CSV file, then send the email using `smtplib`.

<br />

By combining web crawling with email sending, you can create a seamless workflow to collect and deliver data. Customize the sample code and Excel file to suit your needs, and create a practical program you can apply immediately in your job. 🙂