Download sentry events with a query for a project. Useful for data processing.

download_sentry_data.py

"""Download sentry data.
usage:
 1. create auth token (https://sentry.io/settings/account/api/auth-tokens/).
 2. make a directory for export if not exists.
    $ mkdir data
 3. fix query (L29).
 4. install python and run pip3 install requests then execute
    $ python download_sentry_data.py <org>/<project> <auth_token>
 5. a CSV file with a name formatted as "./data/issues_YYYYmmDDHHMMSS.csv" is created.
"""

import requests
import csv
import sys
import datetime
import re


if __name__ == '__main__':
    dt_now = datetime.datetime.now()
    now = dt_now.strftime('%Y%m%d%H%M%S')
    with open('./data/issues_{0}.csv'.format(now), 'w', encoding='utf-8') as csvfile:
        fieldnames = ['id', 'title', 'permalink']
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames, extrasaction='ignore')
        writer.writeheader()
        url = f'https://app.getsentry.com/api/0/projects/{sys.argv[1]}/issues/'
        org = sys.argv[1].split('/', 1)[0]
        project = sys.argv[1].split('/', 1)[1]
        print(f'org: {org}')
        print(f'project: {project}')
        # time-range absolute date
        #params = {'query': 'event.timestamp:>=2020-04-01T00:00:00 event.timestamp:<2020-05-01T00:00:00'}
        params = {'query': 'title:"*EBenFetchError*"'}
        title_set = set()
        title_regex1 = '\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}.\d{3}Z' #timestamp
        # title_regex2 = 'org\/\d+/' #specific org
        while True:
            response = requests.get(
                url,
                params=params,
                headers={'Authorization': 'Bearer {TOKEN}'.format(TOKEN=sys.argv[2])}
                )
            data = response.json()
            for issue in data:
                id = issue['id']
                event_url = f'https://app.getsentry.com/api/0/issues/{id}/events/'
                event_response = requests.get(
                    event_url,
                    headers={'Authorization': 'Bearer {TOKEN}'.format(TOKEN=sys.argv[2])}
                )
                print({event_url})
                print({event_response})
                # tags = {item['key']: item['value'] for item in event['tags']}
                event_data = event_response.json()
                for event in event_data:
                    event_id = event['id']
                    event_title = event['title']
                    event_title = re.sub(title_regex1, '', event_title)
                    # event_title = re.sub(title_regex2, '', event_title)
                    if event_title not in title_set:
                        title_set.add(event_title)
                        event_detail_url = f'https://app.getsentry.com/api/0/projects/{org}/{project}/events/{event_id}/'
                        event_detail_response = requests.get(
                            event_detail_url,
                            headers={'Authorization': 'Bearer {TOKEN}'.format(TOKEN=sys.argv[2])}
                        )
                        event_detail_data = event_detail_response.json()
                        long_event_title = event_detail_data['metadata']['value']
                        permalink = f'https://sentry.io/organizations/{org}/issues/{id}/events/{event_id}'
                        writer.writerow({'id': event_id,'title': long_event_title, 'permalink': permalink})
            link = response.headers.get('Link')
            print(f"Last event date: {data[-1]['lastSeen']}")
            if link and 'rel="next"; results="true"' in link:
                print("Getting next page...")
                url = link.split()[4][1:-2]
            else:
                break