Download recordings from Zoom... Only for archive use.

download-zoom-recordings.py

#!/usr/bin/env python3

from datetime import date, datetime
import json
from pathlib import Path
import os
import sys

from urllib.request import Request, urlopen, urlretrieve

ZOOM_BASE_URL = "https://api.zoom.us/v2/"
zoom_user_id = os.environ.get("ZOOM_USER_ID") # User Id or email address

zoom_token = os.environ.get("ZOOM_TOKEN")
if not zoom_user_id or not zoom_token:
  print("ZOOM_USER_ID or ZOOM_TOKEN not set.")
  sys.exit(1)

recording_file_extensions = {
  "MP4": "mp4",
  "M4A": "m4a",
  "TIMELINE": "json",
  "TRANSCRIPT": "vtt",
  "CHAT": "txt",
  "CC": "vtt",
  "CSV": "csv",
}

today = date.today()
year = today.year
month = today.month

meetings = []
while year >= 2018:
  recording_start = date(year, month, 1)
  next_month = month + 1
  next_year = year
  if next_month == 13:
    next_month = 1
    next_year = year + 1
  recording_end = date(next_year, next_month, 1)
  
  url = f"{ZOOM_BASE_URL}users/{zoom_user_id}/recordings?page_size=300&from={recording_start}&to={recording_end}"

  print(f"Requesting recordings from {recording_start} to {recording_end}...")
  req = Request(url, headers={
    "content-type": "application/json",
    "authorization": "Bearer " + zoom_token
  })
  with urlopen(req) as response:
    meeting_list = response.read()
    meetings_data = json.loads(meeting_list)
    for meeting_info in meetings_data["meetings"]:
      meeting_recordings = []
      for recording_info in meeting_info["recording_files"]:
        if recording_info["file_type"] == "M4A":
          continue
        meeting_recordings.append(recording_info)
      meeting_info["recordings"] = meeting_recordings
      del meeting_info["recording_files"]
      meetings.append(meeting_info)

  month -= 1
  if month == 0:
    year -= 1
    month = 12

print(f"Found {len(meetings)} recordings...")

download_path =  Path("Recordings")
download_path.mkdir(exist_ok=True)
print("Beginning to download recordings")
for meeting in meetings:
  if meeting["topic"].startswith("Peer Interview"):
    print(f"Skipping {meeting['topic']}")
    continue

  print(f"Processing meeting {meeting['topic']}")
  meeting_date = datetime.strptime(meeting["start_time"], "%Y-%m-%dT%H:%M:%SZ").strftime("%Y-%m-%d")
  path_safe_uuid = "".join(x for x in meeting['uuid'] if x.isalnum())
  meeting_path = download_path / f"{meeting_date} - {meeting['topic']} - {path_safe_uuid}"
  meeting_path.mkdir(exist_ok=True)
  for recording in meeting["recordings"]:
    file_name = f"{meeting['topic']} - {recording['recording_type']} - {meeting_date}.{recording_file_extensions[recording['file_type']]}"
    recording_path = meeting_path / file_name
    if recording_path.exists() and recording_path.stat().st_size == recording["file_size"]:
      print(f"We already have the recording {file_name}. Skipping...")
      continue

    download_url = recording["download_url"] + "?access_token=" + zoom_token
    print(f"Downloading {file_name} from {download_url} ({recording['file_size']} bytes)...")
    urlretrieve(download_url, recording_path)