Extract HTTP Requests From an HAR File

extract_http_requests.py

import json

# Path to your HAR file
har_file = "example.har"

# Load HAR file
with open(har_file, "r", encoding="utf-8") as f:
    har_data = json.load(f)

# HAR files store entries under log.entries
entries = har_data.get("log", {}).get("entries", [])

requests_data = []
for entry in entries:
    request = entry.get("request", {})
    url = request.get("url", "")

    # Skip requests to sentry.rightsense.ai, https://www.google-analytics.com
    if url.startswith("https://sentry.rightsense.ai") or url.startswith(
        "https://www.google-analytics.com"
    ):
        continue

    requests_data.append(
        {
            "method": request.get("method"),
            "url": request.get("url"),
            "headers": request.get("headers"),
            "queryString": request.get("queryString"),
            "postData": (
                request.get("postData", {}).get("text")
                if request.get("postData")
                else None
            ),
        }
    )

# Print all requests
for req in requests_data:
    print(f"{req['method']} {req['url']}")
    if req["postData"]:
        print("Body:", req["postData"])
    print("-" * 80)