A python script for adding MVP blog activities from blog sitemap

activity.py

from xml.etree import ElementTree as ET
import datetime
import requests
import time

# Load and parse the XML file
file_path = '[PATH]' # Replace [PATH] with the actual path
userProfileId = '[USER_PROFILE_ID]' # Replace [USER_PROFILE_ID] with the actual user profile ID
token = 'Bearer [TOKEN]' # Replace [TOKEN] with the actual token
lastRenewalDate = "2022-10-01"
technologyFocusArea = "Cloud Native"

tree = ET.parse(file_path)
root = tree.getroot()

# Define the target date for comparison
target_date = datetime.datetime.strptime(lastRenewalDate, '%Y-%m-%d').replace(tzinfo=datetime.timezone(datetime.timedelta(hours=8)))

# Extract articles with pubDate after October 1, 2022
extracted_articles = []
for item in root.findall('.//item'):
    # Extracting necessary details
    title = item.find('title').text if item.find('title') is not None else 'No Title'
    link = item.find('link').text if item.find('link') is not None else 'No Link'
    description = item.find('description').text if item.find('description') is not None else 'No Description'
    pub_date_str = item.find('pubDate').text if item.find('pubDate') is not None else ''

    # Converting pubDate to datetime object
    try:
        pub_date = datetime.datetime.strptime(pub_date_str, '%a, %d %b %Y %H:%M:%S %z')
    except ValueError:
        continue  # Skip the article if the date format is incorrect or missing

    # Check if the publication date is after the target date
    if pub_date > target_date:
        extracted_articles.append({
            'title': title,
            'link': link,
            'date': pub_date_str,
            'description': description
        })

# Define the request body

url = 'https://mavenapi-prod.azurewebsites.net/api/Activities/'
data = {
    "activity": {
        "id": 0,
        "activityTypeName": "Blog",
        "typeName": "Blog",
        # "date": "2023-11-15T16:00:00.000Z",
        # "description": "快速探索 Tetragon：基于 eBPF 的安全可观察性和执行工具",
        # "privateDescription": "快速探索 Tetragon：基于 eBPF 的安全可观察性和执行工具",
        "isPrivate": False,
        "targetAudience": ["Developer"],
        "tenant": "MVP",
        # "title": "快速探索 Tetragon：基于 eBPF 的安全可观察性和执行工具",
        # "url": "https://atbug.com/explore-tetragon-security-observability-and-enforcement-tool-based-on-ebpf/",
        "userProfileId": userProfileId,
        "reach": 200,
        "quantity": 1,
        "role": "Author",
        "technologyFocusArea": technologyFocusArea,
        "additionalTechnologyAreas": [],
        "imageUrl": ""
    }
}

headers = {
    'Content-Type': 'application/json',
    'Pragma': 'no-cache',
    'Accept': '*/*',
    'Authorization': token, 
    'Sec-Fetch-Site': 'cross-site',
    'Accept-Language': 'en-US,en;q=0.9',
    'Cache-Control': 'no-cache',
    'Sec-Fetch-Mode': 'cors',
    'Accept-Encoding': 'gzip, deflate, br',
    'Origin': 'https://mvp.microsoft.com',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Safari/605.1.15',
    'Referer': 'https://mvp.microsoft.com/',
    'Connection': 'keep-alive',
    'Host': 'mavenapi-prod.azurewebsites.net',
    'Sec-Fetch-Dest': 'empty'
}

print(f'Number of articles published after {target_date}: {len(extracted_articles)}')

for article in extracted_articles[:1]:
    data['activity']['date'] = article['date']
    data['activity']['description'] = article['description'][:1000] # Limit the description to 1000 characters
    data['activity']['privateDescription'] = 'a blog post'
    data['activity']['title'] = article['title']
    data['activity']['url'] = article['link']

    response = requests.post(url, headers=headers, json=data)
    print(response.text)
    time.sleep(2)