您的 R2R 期末结账与对账数据模板

import requests
import pandas as pd
import datetime
import time
import os

class=class="hl-string">"hl-comment"># --- CONFIGURATION SECTION --- #
class=class="hl-string">"hl-comment"># Replace with your BlackLine instance details
BLACKLINE_BASE_URL = class="hl-string">"https://[your-instance].blackline.com/v2" class=class="hl-string">"hl-comment"># e.g., https://api.blackline.com/v2
CLIENT_ID = os.environ.get(class="hl-string">'BLACKLINE_CLIENT_ID', class="hl-string">"YOUR_CLIENT_ID")
CLIENT_SECRET = os.environ.get(class="hl-string">'BLACKLINE_CLIENT_SECRET', class="hl-string">"YOUR_CLIENT_SECRET")
REFRESH_TOKEN = os.environ.get(class="hl-string">'BLACKLINE_REFRESH_TOKEN', class="hl-string">"YOUR_REFRESH_TOKEN")

class=class="hl-string">"hl-comment"># Date range for extraction (YYYY-MM-DD)
START_DATE = class="hl-string">"2023-01-01"
END_DATE = class="hl-string">"2023-06-30"

class=class="hl-string">"hl-comment"># API request settings
LIMIT = 100 class=class="hl-string">"hl-comment"># Records per page

class=class="hl-string">"hl-comment"># Mapping of BlackLine Task Names to ProcessMind Activity Names
class=class="hl-string">"hl-comment"># CRITICAL: Update these keys to match the exact names of tasks in your BlackLine instance.
MILESTONE_TASK_MAPPING = {
    class="hl-string">"Period Open": class="hl-string">"Period Open For Close",
    class="hl-string">"Load Source System Data": class="hl-string">"Source Data Loaded",
    class="hl-string">"Generate Preliminary Trial Balance": class="hl-string">"Trial Balance Generated",
    class="hl-string">"Generate Final Financial Statements": class="hl-string">"Financial Statements Generated",
    class="hl-string">"Close Period - Final": class="hl-string">"Period Closed"
}
class=class="hl-string">"hl-comment"># --- END CONFIGURATION --- #

def get_access_token():
    class="hl-string">"""Authenticates with BlackLine API to get an access token."""
    auth_url = fclass="hl-string">"{BLACKLINE_BASE_URL.replace('/v2', '')}/oauth/token"
    payload = {
        class="hl-string">'grant_type': class="hl-string">'refresh_token',
        class="hl-string">'refresh_token': REFRESH_TOKEN,
        class="hl-string">'client_id': CLIENT_ID,
        class="hl-string">'client_secret': CLIENT_SECRET
    }
    try:
        response = requests.post(auth_url, data=payload)
        response.raise_for_status()
        return response.json()[class="hl-string">'access_token']
    except requests.exceptions.RequestException as e:
        print(fclass="hl-string">"Error getting access token: {e}")
        return None

def fetch_paginated_data(endpoint, headers, params):
    class="hl-string">"""Fetches all data from a paginated BlackLine API endpoint."""
    all_data = []
    url = fclass="hl-string">"{BLACKLINE_BASE_URL}/{endpoint}"
    offset = 0
    while True:
        params[class="hl-string">'offset'] = offset
        try:
            response = requests.get(url, headers=headers, params=params)
            response.raise_for_status()
            data = response.json()
            records = data.get(class="hl-string">'data', [])
            all_data.extend(records)

            if len(records) < LIMIT:
                break
            offset += LIMIT
            time.sleep(0.5) class=class="hl-string">"hl-comment"># Be respectful to the API rate limits
        except requests.exceptions.RequestException as e:
            print(fclass="hl-string">"Error fetching data from {endpoint}: {e}")
            break
    return all_data

def main():
    class="hl-string">"""Main function to extract, transform, and save BlackLine data."""
    print(class="hl-string">"Starting BlackLine data extraction...")
    access_token = get_access_token()
    if not access_token:
        return

    headers = {
        class="hl-string">'Authorization': fclass="hl-string">'Bearer {access_token}',
        class="hl-string">'Content-Type': class="hl-string">'application/json'
    }

    event_log = []
    last_data_update = datetime.datetime.now().isoformat()

    class=class="hl-string">"hl-comment"># 1. Fetch and process Reconciliations
    print(class="hl-string">"Fetching reconciliations...")
    rec_params = {class="hl-string">'limit': LIMIT, class="hl-string">'updatedAfter': START_DATE, class="hl-string">'updatedBefore': END_DATE}
    reconciliations = fetch_paginated_data(class="hl-string">'reconciliations', headers, rec_params)
    for rec in reconciliations:
        common_attrs = {
            class="hl-string">'FinancialPeriod': rec.get(class="hl-string">'periodName'),
            class="hl-string">'CompanyCode': rec.get(class="hl-string">'companyCode'),
            class="hl-string">'GLAccount': rec.get(class="hl-string">'accountNumber'),
            class="hl-string">'Department': rec.get(class="hl-string">'preparer', {}).get(class="hl-string">'department'),
            class="hl-string">'SourceSystem': class="hl-string">'BlackLine',
            class="hl-string">'LastDataUpdate': last_data_update
        }
        if rec.get(class="hl-string">'preparedDate'):
            event_log.append({**common_attrs, class="hl-string">'ActivityName': class="hl-string">'Reconciliation Prepared', class="hl-string">'EventTime': rec[class="hl-string">'preparedDate'], class="hl-string">'ResponsibleUser': rec.get(class="hl-string">'preparer', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': class="hl-string">'Prepared'}) 
        if rec.get(class="hl-string">'certifiedDate'):
            event_log.append({**common_attrs, class="hl-string">'ActivityName': class="hl-string">'Reconciliation Certified', class="hl-string">'EventTime': rec[class="hl-string">'certifiedDate'], class="hl-string">'ResponsibleUser': rec.get(class="hl-string">'preparer', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': class="hl-string">'Certified'}) 
        if rec.get(class="hl-string">'reviewedDate'): class=class="hl-string">"hl-comment"># This may represent first or last review depending on config
            event_log.append({**common_attrs, class="hl-string">'ActivityName': class="hl-string">'Reconciliation Reviewed', class="hl-string">'EventTime': rec[class="hl-string">'reviewedDate'], class="hl-string">'ResponsibleUser': rec.get(class="hl-string">'reviewer', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': class="hl-string">'Reviewed'}) 
        if rec.get(class="hl-string">'rejectedDate'):
            event_log.append({**common_attrs, class="hl-string">'ActivityName': class="hl-string">'Reconciliation Rejected', class="hl-string">'EventTime': rec[class="hl-string">'rejectedDate'], class="hl-string">'ResponsibleUser': rec.get(class="hl-string">'reviewer', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': class="hl-string">'Rejected'}) 
        if rec.get(class="hl-string">'approvedDate'):
            event_log.append({**common_attrs, class="hl-string">'ActivityName': class="hl-string">'Reconciliation Approved', class="hl-string">'EventTime': rec[class="hl-string">'approvedDate'], class="hl-string">'ResponsibleUser': rec.get(class="hl-string">'approver', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': class="hl-string">'Approved'}) 

    class=class="hl-string">"hl-comment"># 2. Fetch and process Tasks
    print(class="hl-string">"Fetching tasks...")
    task_params = {class="hl-string">'limit': LIMIT, class="hl-string">'updatedAfter': START_DATE, class="hl-string">'updatedBefore': END_DATE}
    tasks = fetch_paginated_data(class="hl-string">'tasks', headers, task_params)
    today = datetime.datetime.now().isoformat()
    for task in tasks:
        common_attrs = {
            class="hl-string">'FinancialPeriod': task.get(class="hl-string">'periodName'),
            class="hl-string">'CompanyCode': task.get(class="hl-string">'companyCode'),
            class="hl-string">'GLAccount': None,
            class="hl-string">'Department': task.get(class="hl-string">'assignee', {}).get(class="hl-string">'department'),
            class="hl-string">'SourceSystem': class="hl-string">'BlackLine',
            class="hl-string">'LastDataUpdate': last_data_update
        }
        if task.get(class="hl-string">'status') == class="hl-string">'Completed' and task.get(class="hl-string">'completedDate'):
            activity_name = MILESTONE_TASK_MAPPING.get(task.get(class="hl-string">'name'), class="hl-string">'Task Completed')
            event_log.append({**common_attrs, class="hl-string">'ActivityName': activity_name, class="hl-string">'EventTime': task[class="hl-string">'completedDate'], class="hl-string">'ResponsibleUser': task.get(class="hl-string">'assignee', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': None})
        elif task.get(class="hl-string">'dueDate') and task.get(class="hl-string">'dueDate') < today and task.get(class="hl-string">'status') != class="hl-string">'Completed':
             event_log.append({**common_attrs, class="hl-string">'ActivityName': class="hl-string">'Task Delinquent', class="hl-string">'EventTime': task[class="hl-string">'dueDate'], class="hl-string">'ResponsibleUser': task.get(class="hl-string">'assignee', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': None})

    class=class="hl-string">"hl-comment"># 3. Fetch and process Journals
    print(class="hl-string">"Fetching journals...")
    journal_params = {class="hl-string">'limit': LIMIT, class="hl-string">'updatedAfter': START_DATE, class="hl-string">'updatedBefore': END_DATE}
    journals = fetch_paginated_data(class="hl-string">'journals', headers, journal_params)
    for journal in journals:
        common_attrs = {
            class="hl-string">'FinancialPeriod': journal.get(class="hl-string">'periodName'),
            class="hl-string">'CompanyCode': journal.get(class="hl-string">'companyCode'),
            class="hl-string">'GLAccount': journal.get(class="hl-string">'lines', [{}])[0].get(class="hl-string">'accountNumber'), class=class="hl-string">"hl-comment"># Get account from first line
            class="hl-string">'Department': journal.get(class="hl-string">'creator', {}).get(class="hl-string">'department'),
            class="hl-string">'SourceSystem': class="hl-string">'BlackLine',
            class="hl-string">'LastDataUpdate': last_data_update
        }
        if journal.get(class="hl-string">'createdDate'):
            event_log.append({**common_attrs, class="hl-string">'ActivityName': class="hl-string">'Adjusting Journal Created', class="hl-string">'EventTime': journal[class="hl-string">'createdDate'], class="hl-string">'ResponsibleUser': journal.get(class="hl-string">'creator', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': None})
        if journal.get(class="hl-string">'postedDate'):
            event_log.append({**common_attrs, class="hl-string">'ActivityName': class="hl-string">'Adjusting Journal Posted', class="hl-string">'EventTime': journal[class="hl-string">'postedDate'], class="hl-string">'ResponsibleUser': journal.get(class="hl-string">'poster', {}).get(class="hl-string">'username'), class="hl-string">'ReconciliationStatus': None})

    class=class="hl-string">"hl-comment"># 4. Create DataFrame and save to CSV
    if not event_log:
        print(class="hl-string">"No events found for the specified period.")
        return

    df = pd.DataFrame(event_log)
    class=class="hl-string">"hl-comment"># Add missing recommended columns with null values if they don't exist
    recommended_cols = [class="hl-string">'EventEndTime']
    for col in recommended_cols:
        if col not in df.columns:
            df[col] = None

    class=class="hl-string">"hl-comment"># Reorder columns to match ProcessMind requirements
    final_cols = [class="hl-string">'FinancialPeriod', class="hl-string">'ActivityName', class="hl-string">'EventTime', class="hl-string">'EventEndTime', class="hl-string">'SourceSystem', class="hl-string">'LastDataUpdate', class="hl-string">'ResponsibleUser', class="hl-string">'Department', class="hl-string">'ReconciliationStatus', class="hl-string">'CompanyCode', class="hl-string">'GLAccount']
    df = df[final_cols]

    output_file = class="hl-string">'blackline_event_log.csv'
    df.to_csv(output_file, index=False, date_format=class="hl-string">'%Y-%m-%dT%H:%M:%S.%f')
    print(fclass="hl-string">"Extraction complete. Event log saved to {output_file}")

if __name__ == class="hl-string">"__main__":
    main()