WhatsApp Scraper: Efficient WhatsApp Contact and Community Data Collection

import json
from datetime import datetime

def parse_whatsapp_chat(file_path):
records = []

with open(file_path, "r", encoding="utf-8") as chat_file:
for line in chat_file:
try:
# Example format: [12/05/2026, 10:45] John Doe: Hello everyone
if "]" in line and ":" in line:
meta, message = line.split("]", 1)
timestamp_part = meta.replace("[", "").strip()
sender, text = message.split(":", 1)

record = {
"sender_name": sender.strip(),
"message_text": text.strip(),
"message_time": datetime.strptime(timestamp_part, "%d/%m/%Y, %H:%M"),
}

records.append(record)
except Exception:
continue

return records


def save_chat_data(records, output_file="whatsapp_chat_data.json"):
formatted = [
{
"Sender": r["sender_name"],
"Message": r["message_text"],
"Timestamp": r["message_time"].strftime("%Y-%m-%d %H:%M")
}
for r in records
]

with open(output_file, "w", encoding="utf-8") as f:
json.dump(formatted, f, indent=4)