upload week5 exercise: personal knowledge assistant with local file, Gmail, outlook and Google Workspace files
This commit is contained in:
Zhufeng-Qiu
@@ -0,0 +1,154 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "35177005-196a-48b3-bf92-fa37d84693f4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Gmail API Credential Guide"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7bcad9ee-cd11-4b12-834d-9f1ddcefb190",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Use Gmail API to Read Your Emails\n",
|
||||
"1. Set up a Google Cloud Project\n",
|
||||
"\n",
|
||||
" Go to Google Cloud Platform(GCP) Console\n",
|
||||
"\n",
|
||||
" Create a new project\n",
|
||||
"\n",
|
||||
"2. Enable the Gmail API for that project\n",
|
||||
"\n",
|
||||
" Select the created project and go to \"APIs & services\" page\n",
|
||||
"\n",
|
||||
" Click \"+ Enable APIs and services\" button, search \"Gmail API\" and enable it\n",
|
||||
"\n",
|
||||
"3. Go to \"OAuth Consent Screen\" and configure:\n",
|
||||
"\n",
|
||||
" Choose External and Fill in app name, dedveloper email, etc.\n",
|
||||
"\n",
|
||||
"4. Create OAuth Credentials\n",
|
||||
"\n",
|
||||
" Go to APIs & Services > Credentials\n",
|
||||
"\n",
|
||||
" Click \"+ Create Credentials\" > \"OAuth client ID\"\n",
|
||||
"\n",
|
||||
" Choose Desktop App\n",
|
||||
"\n",
|
||||
" Download the generated credentials.json\n",
|
||||
"\n",
|
||||
" Sometimes, GCP will navigate you to \"Google Auth Platform\" > \"Clients\", and you can click \"+ Create client\" here to create the OAuth Credentials\n",
|
||||
"\n",
|
||||
" \n",
|
||||
"5. Add Test Users for Gmail API OAuth Access\n",
|
||||
" \n",
|
||||
" Go to \"APIs & Services\" > \"OAuth consent screen\" > \"Audience\" > \"Test Users\"\n",
|
||||
"\n",
|
||||
" Add the email account from which you want to extract email content.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"6. Create 'credentials' folders to store gmail credential and user tokens"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bc86bec0-bda8-4e9e-9c85-423179a99981",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4270e52e-378c-4127-bd52-1d082e9834e0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from __future__ import print_function\n",
|
||||
"import os.path\n",
|
||||
"import base64\n",
|
||||
"import re\n",
|
||||
"from email import message_from_bytes\n",
|
||||
"from google.oauth2.credentials import Credentials\n",
|
||||
"from google_auth_oauthlib.flow import InstalledAppFlow\n",
|
||||
"from googleapiclient.discovery import build\n",
|
||||
"\n",
|
||||
"# If modifying these SCOPES, delete the token.json\n",
|
||||
"SCOPES = ['https://www.googleapis.com/auth/gmail.readonly']\n",
|
||||
"PORT = 18000\n",
|
||||
"\n",
|
||||
"def main():\n",
|
||||
" creds = None\n",
|
||||
" # token.json stores the user's access and refresh tokens\n",
|
||||
" if os.path.exists('token.json'):\n",
|
||||
" creds = Credentials.from_authorized_user_file('token.json', SCOPES)\n",
|
||||
" else:\n",
|
||||
" flow = InstalledAppFlow.from_client_secrets_file('credentials/gmail_credentials.json', SCOPES)\n",
|
||||
" creds = flow.run_local_server(port=PORT)\n",
|
||||
" with open('token.json', 'w') as token:\n",
|
||||
" token.write(creds.to_json())\n",
|
||||
"\n",
|
||||
" service = build('gmail', 'v1', credentials=creds)\n",
|
||||
"\n",
|
||||
" # Get the latest message\n",
|
||||
" results = service.users().messages().list(userId='me', maxResults=1).execute()\n",
|
||||
" messages = results.get('messages', [])\n",
|
||||
"\n",
|
||||
" if not messages:\n",
|
||||
" print(\"No messages found.\")\n",
|
||||
" return\n",
|
||||
"\n",
|
||||
" msg = service.users().messages().get(userId='me', id=messages[0]['id'], format='raw').execute()\n",
|
||||
" raw_msg = base64.urlsafe_b64decode(msg['raw'].encode('ASCII'))\n",
|
||||
" email_message = message_from_bytes(raw_msg)\n",
|
||||
"\n",
|
||||
" subject = email_message['Subject']\n",
|
||||
" print(\"Subject:\", subject)\n",
|
||||
"\n",
|
||||
" # Extract text/plain body\n",
|
||||
" for part in email_message.walk():\n",
|
||||
" if part.get_content_type() == 'text/plain':\n",
|
||||
" print(\"Body:\")\n",
|
||||
" print(part.get_payload(decode=True).decode('utf-8'))\n",
|
||||
"\n",
|
||||
"if __name__ == '__main__':\n",
|
||||
" main()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5ff68e06-3cfb-48ae-9dad-fa431d0d548a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,294 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "35177005-196a-48b3-bf92-fa37d84693f4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Workspace API Credential Guide"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7bcad9ee-cd11-4b12-834d-9f1ddcefb190",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Use Google Drive API to Read files in Google Workspace \n",
|
||||
"1. Set up a Google Cloud Project\n",
|
||||
"\n",
|
||||
" Go to Google Cloud Platform(GCP) Console\n",
|
||||
"\n",
|
||||
" Create a new project\n",
|
||||
"\n",
|
||||
"2. Enable the Gmail API for that project\n",
|
||||
"\n",
|
||||
" Select the created project and go to \"APIs & services\" page\n",
|
||||
"\n",
|
||||
" Click \"+ Enable APIs and services\" button, enable these APIs: Google Drive API, Google Docs API, Google Sheets API, and Google Slides API \n",
|
||||
"\n",
|
||||
"3. Go to \"OAuth Consent Screen\" and configure:\n",
|
||||
"\n",
|
||||
" Choose External and Fill in app name, dedveloper email, etc.\n",
|
||||
"\n",
|
||||
"4. Create OAuth Credentials\n",
|
||||
"\n",
|
||||
" Go to APIs & Services > Credentials\n",
|
||||
"\n",
|
||||
" Click \"+ Create Credentials\" > \"OAuth client ID\"\n",
|
||||
"\n",
|
||||
" Choose Desktop App\n",
|
||||
"\n",
|
||||
" Download the generated credentials.json\n",
|
||||
"\n",
|
||||
" Sometimes, GCP will navigate you to \"Google Auth Platform\" > \"Clients\", and you can click \"+ Create client\" here to create the OAuth Credentials\n",
|
||||
"\n",
|
||||
" \n",
|
||||
"5. Add Test Users for Gmail API OAuth Access\n",
|
||||
" \n",
|
||||
" Go to \"APIs & Services\" > \"OAuth consent screen\" > \"Audience\" > \"Test Users\"\n",
|
||||
"\n",
|
||||
" Add the email account from which you want to extract email content.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"6. Create 'credentials' folders to store google workspace credential and user tokens"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bc86bec0-bda8-4e9e-9c85-423179a99981",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install PyPDF2\n",
|
||||
"# !pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4270e52e-378c-4127-bd52-1d082e9834e0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5ff68e06-3cfb-48ae-9dad-fa431d0d548a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "69c20f2d-2f49-408c-8700-f12d6745efd3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google_auth_oauthlib.flow import InstalledAppFlow\n",
|
||||
"from googleapiclient.discovery import build\n",
|
||||
"from google.oauth2.credentials import Credentials\n",
|
||||
"from googleapiclient.http import MediaIoBaseDownload\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"import io\n",
|
||||
"from PyPDF2 import PdfReader\n",
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"from langchain.embeddings import OpenAIEmbeddings\n",
|
||||
"from langchain.schema import Document\n",
|
||||
"\n",
|
||||
"GOOGLE_WORKSPACE_SCOPES = [\"https://www.googleapis.com/auth/drive.readonly\",\n",
|
||||
" 'https://www.googleapis.com/auth/documents.readonly',\n",
|
||||
" 'https://www.googleapis.com/auth/spreadsheets.readonly',\n",
|
||||
" 'https://www.googleapis.com/auth/presentations.readonly'\n",
|
||||
" ]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "7164903b-be81-46b2-8c04-886397599c27",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def extract_google_doc(docs_service, file_id):\n",
|
||||
" doc = docs_service.documents().get(documentId=file_id).execute()\n",
|
||||
" content = \"\"\n",
|
||||
" for elem in doc.get(\"body\", {}).get(\"content\", []):\n",
|
||||
" if \"paragraph\" in elem:\n",
|
||||
" for run in elem[\"paragraph\"][\"elements\"]:\n",
|
||||
" content += run.get(\"textRun\", {}).get(\"content\", \"\")\n",
|
||||
" return content.strip()\n",
|
||||
"\n",
|
||||
"def extract_google_sheet(service, file_id):\n",
|
||||
" # Get spreadsheet metadata\n",
|
||||
" spreadsheet = service.spreadsheets().get(spreadsheetId=file_id).execute()\n",
|
||||
" all_text = \"\"\n",
|
||||
"\n",
|
||||
" # Loop through each sheet\n",
|
||||
" for sheet in spreadsheet.get(\"sheets\", []):\n",
|
||||
" title = sheet[\"properties\"][\"title\"]\n",
|
||||
" result = service.spreadsheets().values().get(\n",
|
||||
" spreadsheetId=file_id,\n",
|
||||
" range=title\n",
|
||||
" ).execute()\n",
|
||||
"\n",
|
||||
" values = result.get(\"values\", [])\n",
|
||||
" sheet_text = f\"### Sheet: {title} ###\\n\"\n",
|
||||
" sheet_text += \"\\n\".join([\", \".join(row) for row in values])\n",
|
||||
" all_text += sheet_text + \"\\n\\n\"\n",
|
||||
"\n",
|
||||
" return all_text.strip()\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def extract_google_slide(slides_service, file_id):\n",
|
||||
" pres = slides_service.presentations().get(presentationId=file_id).execute()\n",
|
||||
" text = \"\"\n",
|
||||
" for slide in pres.get(\"slides\", []):\n",
|
||||
" for element in slide.get(\"pageElements\", []):\n",
|
||||
" shape = element.get(\"shape\")\n",
|
||||
" if shape:\n",
|
||||
" for p in shape.get(\"text\", {}).get(\"textElements\", []):\n",
|
||||
" if \"textRun\" in p:\n",
|
||||
" text += p[\"textRun\"][\"content\"]\n",
|
||||
" return text.strip()\n",
|
||||
"\n",
|
||||
"def extract_pdf_from_drive(drive_service, file_id, filename='downloaded.pdf'):\n",
|
||||
" request = drive_service.files().get_media(fileId=file_id)\n",
|
||||
" fh = io.BytesIO()\n",
|
||||
" downloader = MediaIoBaseDownload(fh, request)\n",
|
||||
" done = False\n",
|
||||
" while not done:\n",
|
||||
" _, done = downloader.next_chunk()\n",
|
||||
" fh.seek(0)\n",
|
||||
" reader = PdfReader(fh)\n",
|
||||
" return \"\\n\".join([page.extract_text() for page in reader.pages if page.extract_text()])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5f2edc68-f9f8-4cba-810e-159bea4fe4ac",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_creds():\n",
|
||||
" if os.path.exists(\"token.json\"):\n",
|
||||
" creds = Credentials.from_authorized_user_file(\"token.json\", SCOPES)\n",
|
||||
" else:\n",
|
||||
" flow = InstalledAppFlow.from_client_secrets_file(\"credentials/google_drive_workspace_credentials.json\", SCOPES)\n",
|
||||
" creds = flow.run_local_server(port=0)\n",
|
||||
" with open(\"token.json\", \"w\") as token:\n",
|
||||
" token.write(creds.to_json())\n",
|
||||
" return creds\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"def get_folder_id_by_name(drive_service, folder_name):\n",
|
||||
" query = f\"mimeType='application/vnd.google-apps.folder' and name='{folder_name}' and trashed=false\"\n",
|
||||
" results = drive_service.files().list(\n",
|
||||
" q=query,\n",
|
||||
" fields=\"files(id, name)\",\n",
|
||||
" pageSize=1\n",
|
||||
" ).execute()\n",
|
||||
"\n",
|
||||
" folders = results.get(\"files\", [])\n",
|
||||
" if not folders:\n",
|
||||
" raise ValueError(f\"❌ Folder named '{folder_name}' not found.\")\n",
|
||||
" return folders[0]['id']\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def extract_docs_from_google_workspace(folder_name):\n",
|
||||
" info = \"\"\n",
|
||||
" \n",
|
||||
" creds = get_creds()\n",
|
||||
"\n",
|
||||
" file_types = {\n",
|
||||
" 'application/vnd.google-apps.document': lambda fid: extract_google_doc(docs_service, fid),\n",
|
||||
" 'application/vnd.google-apps.spreadsheet': lambda fid: extract_google_sheet(sheets_service, fid),\n",
|
||||
" 'application/vnd.google-apps.presentation': lambda fid: extract_google_slide(slides_service, fid),\n",
|
||||
" 'application/pdf': lambda fid: extract_pdf_from_drive(drive_service, fid),\n",
|
||||
" }\n",
|
||||
" \n",
|
||||
" drive_service = build(\"drive\", \"v3\", credentials=creds)\n",
|
||||
" docs_service = build('docs', 'v1', credentials=creds)\n",
|
||||
" sheets_service = build('sheets', 'v4', credentials=creds)\n",
|
||||
" slides_service = build('slides', 'v1', credentials=creds)\n",
|
||||
"\n",
|
||||
" folder_id = get_folder_id_by_name(drive_service, folder_name)\n",
|
||||
" info += f\"Collection files from folder: {folder_name}\\n\"\n",
|
||||
" \n",
|
||||
" query = (\n",
|
||||
" f\"'{folder_id}' in parents and (\"\n",
|
||||
" 'mimeType=\"application/vnd.google-apps.document\" or '\n",
|
||||
" 'mimeType=\"application/vnd.google-apps.spreadsheet\" or '\n",
|
||||
" 'mimeType=\"application/vnd.google-apps.presentation\" or '\n",
|
||||
" 'mimeType=\"application/pdf\")'\n",
|
||||
" )\n",
|
||||
" \n",
|
||||
" results = drive_service.files().list(\n",
|
||||
" q=query,\n",
|
||||
" fields=\"files(id, name, mimeType)\",\n",
|
||||
" pageSize=20\n",
|
||||
" ).execute()\n",
|
||||
"\n",
|
||||
" docs = []\n",
|
||||
" summary_info = {\n",
|
||||
" 'application/vnd.google-apps.document': {'file_type': 'Google Doc', 'count': 0},\n",
|
||||
" 'application/vnd.google-apps.spreadsheet': {'file_type': 'Google Sheet', 'count': 0},\n",
|
||||
" 'application/vnd.google-apps.presentation': {'file_type': 'Google Silde', 'count': 0},\n",
|
||||
" 'application/pdf': {'file_type': 'PDF', 'count': 0}\n",
|
||||
" }\n",
|
||||
" for file in results.get(\"files\", []):\n",
|
||||
" extractor = file_types.get(file['mimeType'])\n",
|
||||
" if extractor:\n",
|
||||
" try:\n",
|
||||
" content = extractor(file[\"id\"])\n",
|
||||
" if content:\n",
|
||||
" docs.append(Document(page_content=content, metadata={\"source\": file[\"name\"]}))\n",
|
||||
" summary_info[file['mimeType']]['count'] += 1\n",
|
||||
" except Exception as e:\n",
|
||||
" print(f\"❌ Error processing {file['name']}: {e}\")\n",
|
||||
" \n",
|
||||
" total = 0;\n",
|
||||
" for file_type, element in summary_info.items():\n",
|
||||
" total += element['count']\n",
|
||||
" info += f\"Found {element['count']} {element['file_type']} files\\n\"\n",
|
||||
" info += f\"Total documents loaded: {total}\"\n",
|
||||
" return docs, info"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8a9da5c9-415c-4856-973a-627a1790f38d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs, info = extract_docs_from_google_workspace(\"google_workspace_knowledge_base\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,178 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "35177005-196a-48b3-bf92-fa37d84693f4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Outlook API Credential Guide"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7bcad9ee-cd11-4b12-834d-9f1ddcefb190",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Extract Outlook Emails via Microsoft Graph API\n",
|
||||
"\n",
|
||||
"1. Register Your App on Azure Portal\n",
|
||||
"\n",
|
||||
" Go to Azure Portal > Azure Active Directory > App registrations\n",
|
||||
"\n",
|
||||
" Click “New registration”\n",
|
||||
"\n",
|
||||
" Choose Mobole/Desktop app\n",
|
||||
" \n",
|
||||
" After creation, note the Application (client) ID\n",
|
||||
"\n",
|
||||
"2. API Permissions\n",
|
||||
"\n",
|
||||
" Go to API permissions tab\n",
|
||||
"\n",
|
||||
" Click Add permission > Microsoft Graph > Delegated\n",
|
||||
"\n",
|
||||
" Choose: Mail.Read\n",
|
||||
"\n",
|
||||
" Click Grant admin consent\n",
|
||||
"\n",
|
||||
"3. Allow public client flows\n",
|
||||
"\n",
|
||||
" Navigate to: Azure Active Directory > App registrations > Your App\n",
|
||||
"\n",
|
||||
" Go to Authentication tab\n",
|
||||
"\n",
|
||||
" Under \"Advanced settings\" → \"Allow public client flows\", set to \"Yes\"\n",
|
||||
"\n",
|
||||
" Save changes"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bc86bec0-bda8-4e9e-9c85-423179a99981",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install msal requests"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4270e52e-378c-4127-bd52-1d082e9834e0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from msal import PublicClientApplication\n",
|
||||
"import os\n",
|
||||
"from dotenv import load_dotenv\n",
|
||||
"import requests"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5ff68e06-3cfb-48ae-9dad-fa431d0d548a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"load_dotenv()\n",
|
||||
"\n",
|
||||
"CLIENT_ID = os.getenv(\"AZURE_CLIENT_ID\")\n",
|
||||
"AUTHORITY = \"https://login.microsoftonline.com/common\" \n",
|
||||
"SCOPES = [\"Mail.Read\"]\n",
|
||||
"\n",
|
||||
"app = PublicClientApplication(CLIENT_ID, authority=AUTHORITY)\n",
|
||||
"\n",
|
||||
"flow = app.initiate_device_flow(scopes=SCOPES)\n",
|
||||
"print(\"Go to:\", flow[\"verification_uri\"])\n",
|
||||
"print(\"Enter code:\", flow[\"user_code\"])\n",
|
||||
"\n",
|
||||
"result = app.acquire_token_by_device_flow(flow)\n",
|
||||
"\n",
|
||||
"if \"access_token\" not in result:\n",
|
||||
" raise Exception(\"Failed to authenticate:\", result)\n",
|
||||
"\n",
|
||||
"access_token = result[\"access_token\"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9c7f97da-68cc-4923-b280-1ddf7e5b7aa3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"Granted scopes:\", result.get(\"scope\"))\n",
|
||||
"\n",
|
||||
"headers = {\n",
|
||||
" \"Authorization\": f\"Bearer {access_token}\",\n",
|
||||
" \"Prefer\": \"outlook.body-content-type='text'\"\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"query = (\n",
|
||||
" \"https://graph.microsoft.com/v1.0/me/messages\"\n",
|
||||
" \"?$top=1\"\n",
|
||||
" \"&$select=id,subject,receivedDateTime,body\"\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"all_emails = []\n",
|
||||
"\n",
|
||||
"while query:\n",
|
||||
" response = requests.get(query, headers=headers)\n",
|
||||
"\n",
|
||||
" if not response.ok:\n",
|
||||
" print(response.text)\n",
|
||||
" print(f\"❌ HTTP {response.status_code}: {response.text}\")\n",
|
||||
" break\n",
|
||||
"\n",
|
||||
" try:\n",
|
||||
" res = response.json()\n",
|
||||
" except ValueError:\n",
|
||||
" print(\"❌ Invalid JSON:\", response.text)\n",
|
||||
" break\n",
|
||||
"\n",
|
||||
" for msg in res.get(\"value\", []):\n",
|
||||
" all_emails.append({\n",
|
||||
" \"id\": msg.get(\"id\"),\n",
|
||||
" \"subject\": msg.get(\"subject\", \"\"),\n",
|
||||
" \"body\": msg.get(\"body\", {}).get(\"content\", \"\"),\n",
|
||||
" \"date\": msg.get(\"receivedDateTime\", \"\")\n",
|
||||
" })\n",
|
||||
"\n",
|
||||
" query = res.get(\"@odata.nextLink\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e29493b6-0a9e-4106-93c9-e58ff6aa0f97",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"all_emails"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
// delete key
|
||||
|
||||
{"installed":{"client_id":"196620306719-vr5i30l44mqmkmnp7j96iavjfqsfl41f.apps.googleusercontent.com","project_id":"llms-personal-knowledge","auth_uri":"https://accounts.google.com/o/oauth2/auth","token_uri":"https://oauth2.googleapis.com/token","auth_provider_x509_cert_url":"https://www.googleapis.com/oauth2/v1/certs","redirect_uris":["http://localhost"]}}
|
||||
@@ -0,0 +1,3 @@
|
||||
// delete key
|
||||
|
||||
{"installed":{"client_id":"196620306719-7qvdhd86sau3ngmrrlcb1314us9nuli4.apps.googleusercontent.com","project_id":"llms-personal-knowledge","auth_uri":"https://accounts.google.com/o/oauth2/auth","token_uri":"https://oauth2.googleapis.com/token","auth_provider_x509_cert_url":"https://www.googleapis.com/oauth2/v1/certs","redirect_uris":["http://localhost"]}}
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 11 KiB |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,9 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<title>My First Web Page</title>
|
||||
</head>
|
||||
<body>
|
||||
<h1>Zephyr won ZHTML award</h1>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1 @@
|
||||
Zephyr won ZMD award
|
||||
Binary file not shown.
@@ -0,0 +1 @@
|
||||
Zephyr won ZTXT award
|
||||
Reference in New Issue
Block a user