-
Notifications
You must be signed in to change notification settings - Fork 4
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Refactor code and update Zoom authentication process #3
Open
skywinder
wants to merge
6
commits into
gsamat:main
Choose a base branch
from
skywinder:refactor
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
6 commits
Select commit
Hold shift + click to select a range
9f0672d
WIP: trying to update new auth process see
skywinder 08ab04e
refactor code - fix getting zoom access token, fetch recordings by mo…
idealatom f95dcbb
update readme, fix auth method, remove unused mentod
skywinder 3d7651a
Merge branch 'refactor'
skywinder d3252bf
Refactor file processing in zoom-importer.py
skywinder 388c565
Merge branch 'main' into refactor
skywinder File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,2 +1,5 @@ | ||
| .DS_Store | ||
| .env | ||
| .env | ||
| *.mp4 | ||
|
|
||
| .python-version |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,133 +1,199 @@ | ||
| import requests | ||
| import json | ||
| from slugify import slugify | ||
| from datetime import date, timedelta | ||
| import b2sdk.v2 as b2 | ||
| import b2sdk | ||
| import base64 | ||
| import os | ||
| import time | ||
| from environs import Env | ||
| import urllib | ||
| from datetime import date, timedelta | ||
|
|
||
| import b2sdk | ||
| import b2sdk.v2 as b2 | ||
| import requests | ||
| from environs import Env | ||
| from slugify import slugify | ||
|
|
||
|
|
||
| def download_file(url, filename): | ||
| response = requests.get( | ||
| url=url, | ||
| headers={ | ||
| "Authorization": f"Bearer {ZOOM_KEY}", | ||
| }, | ||
| ) | ||
| with open(filename, 'wb') as f: | ||
| f.write(response.content) | ||
| response = requests.get( | ||
| url=url, | ||
| headers={ | ||
| "Authorization": f"Bearer {ZOOM_KEY}", | ||
| }, | ||
| ) | ||
| with open(filename, 'wb') as f: | ||
| f.write(response.content) | ||
|
|
||
|
|
||
| def b2_file_size(file): | ||
| try: | ||
| return b.get_file_info_by_name(file).content_length | ||
| return bucket.get_file_info_by_name(file).content_length | ||
| except (b2sdk.exception.FileNotPresent): | ||
| return 0 | ||
|
|
||
| def delete_recordings(uuid): | ||
|
|
||
| def delete_recording(uuid): | ||
| try: | ||
| uuid = urllib.parse.quote(urllib.parse.quote(uuid, safe='')) | ||
| response = requests.delete( | ||
| url=f"https://api.zoom.us/v2/meetings/{uuid}/recordings", | ||
| headers={ | ||
| "Authorization": f"Bearer {ZOOM_KEY}", | ||
| }, | ||
| ) | ||
| except requests.exceptions.RequestException: | ||
| print(f"delete failed for {uuid}") | ||
|
|
||
|
|
||
| def process_file(file, name): | ||
| filename = slugify(name) + '.' + file['file_extension'].lower() | ||
| size_zoom = file['file_size'] | ||
| size_bb = b2_file_size(filename) | ||
| try: | ||
| uuid = urllib.parse.quote(urllib.parse.quote(uuid, safe = '')) | ||
| response = requests.delete( | ||
| url=f"https://api.zoom.us/v2/meetings/{uuid}/recordings", | ||
| headers={ | ||
| "Authorization": f"Bearer {ZOOM_KEY}", | ||
| }, | ||
| ) | ||
| except requests.exceptions.RequestException: | ||
| print(f"delete failed for {uuid}") | ||
|
|
||
| def send_request(date_from, date_to): | ||
| size_local = os.path.getsize(filename) | ||
| except FileNotFoundError: | ||
| size_local = 0 | ||
| if size_zoom > size_bb: | ||
| if size_zoom > size_local: | ||
| file_url = file['download_url'] | ||
| print(' start download: ' + filename) | ||
| download_file(file_url, filename) | ||
| # Check if the file was downloaded successfully | ||
| if not os.path.exists(filename): | ||
| print(f"Failed to download file: {filename}") | ||
| return | ||
| print(' start upload: ' + filename) | ||
| # Check if the file exists and is accessible before upload | ||
| if os.path.exists(filename) and os.access(filename, os.R_OK): | ||
| bucket.upload_local_file(filename, filename) | ||
| else: | ||
| print(f"File {filename} doesn't exist or isn't accessible") | ||
| return | ||
|
|
||
| try: | ||
| response = requests.get( | ||
| url="https://api.zoom.us/v2/users/me/recordings", | ||
| params={ | ||
| "from": date_from, | ||
| "to": date_to | ||
| }, | ||
| headers={ | ||
| "Authorization": f"Bearer {ZOOM_KEY}", | ||
| }, | ||
| ) | ||
| meetings = response.json()["meetings"] | ||
| for meeting in meetings: | ||
| name = meeting['start_time'] + '-' + meeting['topic'] | ||
| print(' ' + name) | ||
| if meeting['recording_count'] > 0: | ||
| files = meeting['recording_files'] | ||
| sizes = [x['file_size'] for x in files] | ||
| global processed_storage | ||
| processed_storage = processed_storage + sum(sizes) | ||
| types = [x['recording_type'] for x in files] | ||
| wanted_types = ['audio_only', 'chat_file'] | ||
| if 'shared_screen_with_gallery_view' in types: | ||
| wanted_types.append('shared_screen_with_gallery_view') | ||
| elif 'gallery_view' in types: | ||
| wanted_types.append('gallery_view') | ||
| elif 'shared_screen_with_speaker_view' in types: | ||
| wanted_types.append('shared_screen_with_speaker_view') | ||
| elif 'speaker_view' in types: | ||
| wanted_types.append('speaker_view') | ||
| elif 'shared_screen' in types: | ||
| wanted_types.append('shared_screen') | ||
| print(f" {wanted_types}") | ||
| for file in files: | ||
| if file['recording_type'] in wanted_types: | ||
| filename = slugify(name) + '.' + file['file_extension'].lower() | ||
| size_zoom = file['file_size'] | ||
| size_bb = b2_file_size(filename) | ||
| try: | ||
| size_local = os.path.getsize(filename) | ||
| except FileNotFoundError: | ||
| size_local = 0 | ||
| if size_zoom > size_bb: | ||
| if size_zoom > size_local: | ||
| file_url = file['download_url'] | ||
| print(' start download: ' + filename) | ||
| download_file(file_url, filename) | ||
| print(' start upload: ' + filename) | ||
| b.upload_local_file(filename, filename) | ||
| try: | ||
| os.remove(filename) | ||
| except FileNotFoundError: | ||
| pass | ||
| delete_recordings(meeting['uuid']) | ||
| time_elapsed = time.time() - time_start | ||
| speed = processed_storage / (time_elapsed/60) | ||
| print(f"total processed {processed_storage:,} bytes, elapsed {time_elapsed:,.0f} sec, {speed:,.0f} bytes per minute") | ||
| except requests.exceptions.RequestException: | ||
| print('HTTP Request failed') | ||
|
|
||
| def daterange(start_date, end_date): | ||
| if start_date < end_date: | ||
| raise RuntimeError('start date should be > than end_date!') | ||
| for n in range(int((start_date - end_date).days)): | ||
| yield start_date - timedelta(n) | ||
| os.remove(filename) | ||
| except FileNotFoundError: | ||
| pass | ||
|
|
||
| def process_meeting(meeting): | ||
| print(f" {meeting['start_time']} {meeting['topic']}") | ||
| if meeting['recording_count'] > 0: | ||
| files = meeting['recording_files'] | ||
| global processed_storage | ||
| sizes = [x['file_size'] for x in files] | ||
|
|
||
| processed_storage = processed_storage + sum(sizes) | ||
| types = [x['recording_type'] for x in files] | ||
| wanted_types = ['audio_only', 'chat_file'] | ||
| extra_wanted_types = [ | ||
| 'shared_screen_with_gallery_view', | ||
| 'gallery_view', | ||
| 'shared_screen_with_speaker_view', | ||
| 'speaker_view', | ||
| 'shared_screen', | ||
| ] | ||
| for t in extra_wanted_types: | ||
| if t in types: | ||
| wanted_types.append(t) | ||
| break | ||
| print(f" {wanted_types}") | ||
| for file in files: | ||
| if file['recording_type'] in wanted_types: | ||
| name = meeting['start_time'] + '-' + meeting['topic'] | ||
| process_file(file, name) | ||
| delete_recording(meeting['uuid']) | ||
| time_elapsed = time.time() - time_start | ||
| speed = processed_storage / (time_elapsed / 60) | ||
| print( | ||
| f"total processed {processed_storage:,} bytes, elapsed {time_elapsed:,.0f} sec, {speed:,.0f} bytes per minute") | ||
|
|
||
|
|
||
| def get_recordings(date_from, date_to): | ||
| # The maximum date range for this endpoing can be a month | ||
| print(f"getting recordings from {date_from} to {date_to}...") | ||
| response = requests.get( | ||
| url="https://api.zoom.us/v2/users/me/recordings", | ||
| params={ | ||
| "from": date_from.strftime("%Y-%m-%d"), | ||
| "to": date_to.strftime("%Y-%m-%d"), | ||
| 'page_size': 300, | ||
| }, | ||
| headers={ | ||
| "Authorization": f"Bearer {ZOOM_KEY}", | ||
| }, | ||
| ) | ||
| meetings = response.json()['meetings'] | ||
| return meetings | ||
|
|
||
|
|
||
| def date_span(date_start, date_end, delta=timedelta(days=30)): | ||
| if date_start > date_end: | ||
| raise RuntimeError('start date should be lower than end date!') | ||
|
|
||
| current_date = date_start | ||
| while current_date < date_end: | ||
| yield (current_date, min(current_date + delta, date_end)) | ||
| current_date += delta | ||
|
|
||
|
|
||
| # Get Zoom access token using Server-to-Server OAuth app | ||
| def get_zoom_access_token(): | ||
| print('getting Zoom access token...') | ||
| params = { | ||
| 'grant_type': 'account_credentials', | ||
| 'account_id': env('ACCOUNT_ID'), | ||
| } | ||
| credentials = base64.b64encode(f"{env('CLIENT_ID')}:{env('CLIENT_SECRET')}".encode()).decode() | ||
| headers = { | ||
| "Authorization": f"Basic {credentials}", | ||
| 'Content-Type': 'application/x-www-form-urlencoded', | ||
| } | ||
| response = requests.post( | ||
| "https://zoom.us/oauth/token", | ||
| params=params, | ||
| headers=headers, | ||
| ) | ||
| data = response.json() | ||
| if not 'access_token' in data: | ||
| raise Exception(data) | ||
| return data['access_token'] | ||
|
|
||
|
|
||
| def get_cloud_bucket(): | ||
| print('preparing B2 bucket...') | ||
| info = b2.InMemoryAccountInfo() | ||
| b2_api = b2.B2Api(info) | ||
| b2_api.authorize_account("production", env('B2_KEY_ID'), env('B2_KEY')) | ||
| return b2_api.get_bucket_by_name(env('BUCKET')) | ||
|
|
||
|
|
||
| env = Env() | ||
| env.read_env() | ||
| B2_KEY_ID = env('B2_KEY_ID') | ||
| B2_KEY = env('B2_KEY') | ||
| BUCKET = env('BUCKET') | ||
| ZOOM_KEY = env('ZOOM_KEY') | ||
| DATE_FROM_Y = env.int('DATE_FROM_Y') | ||
| DATE_FROM_M = env.int('DATE_FROM_M') | ||
| DATE_FROM_D = env.int('DATE_FROM_D') | ||
| DATE_TO_Y = env.int('DATE_TO_Y') | ||
| DATE_TO_M = env.int('DATE_TO_M') | ||
| DATE_TO_D = env.int('DATE_TO_D') | ||
|
|
||
|
|
||
| info = b2.InMemoryAccountInfo() | ||
| b2_api = b2.B2Api(info) | ||
| b2_api.authorize_account("production", B2_KEY_ID, B2_KEY) | ||
| b = b2_api.get_bucket_by_name(BUCKET) | ||
|
|
||
| bucket = get_cloud_bucket() | ||
| processed_storage = 0 | ||
| time_start = time.time() | ||
|
|
||
| if __name__ == "__main__": | ||
| start_date = date(DATE_FROM_Y, DATE_FROM_M, DATE_FROM_D) | ||
| end_date = date(DATE_TO_Y, DATE_TO_M, DATE_TO_D) | ||
| for single_date in daterange(start_date, end_date): | ||
| print(f"{single_date.strftime('%Y-%m-%d')}") | ||
| send_request(single_date.strftime("%Y-%m-%d"), single_date.strftime("%Y-%m-%d")) | ||
| date_start = date( | ||
| env.int('DATE_FROM_Y'), | ||
| env.int('DATE_FROM_M'), | ||
| env.int('DATE_FROM_D') | ||
| ) | ||
| date_end = date( | ||
| env.int('DATE_TO_Y'), | ||
| env.int('DATE_TO_M'), | ||
| env.int('DATE_TO_D'), | ||
| ) | ||
|
|
||
| ZOOM_KEY = get_zoom_access_token() | ||
|
|
||
| meetings = [] | ||
| for period_start, period_end in date_span(date_start, date_end): | ||
| period_meetings = get_recordings(period_start, period_end) | ||
| meetings.extend(period_meetings) | ||
| if period_end > date.today(): | ||
| break | ||
| meetings.sort(key=lambda x: x['start_time']) | ||
|
|
||
| print(f'Total meetings in cloud: {len(meetings)}') | ||
| for i, meeting in enumerate(meetings): | ||
| print(i, meeting['start_time'], meeting['topic']) | ||
| process_meeting(meeting) | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
here is key changes with auth