Psing login

# Use Apify base image with Python and Playwright
FROM apify/actor-python-playwright

# Copy all source code to the default working directory
COPY ./src /app

# Install Python dependencies
RUN pip install requests

# Run the actor script
CMD ["python", "/app/main.py"]

{
  "name": "my-actor",
  "version": "0.1",
  "description": "This is my Apify actor for login automation.",
  "actorSpecification": 1,
  "input": "./input_schema.json",
  "main": "src/main.py"
}

{
    "schemaVersion": 1,
    "title": "My Actor Input Schema",
    "type": "object",
    "properties": {
        "start_url": {
            "type": "string",
            "title": "Start URL",
            "description": "The URL to start the scraping process.",
            "editor": "textfield" 
        },
        "company_id": {
        "type": "string",
        "title": "Company ID",
        "description": "ID of the company.",
        "editor": "textfield"
        },
        "username": {
            "type": "string",
            "title": "Username",
            "description": "Username for login.",
            "editor": "textfield"  
        },
        "password": {
            "type": "string",
            "title": "Password",
            "description": "Password for login.",
            "editor": "textfield"  
        },
        "patient_id": {
            "type": "string",
            "title": "Patient ID",
            "description": "ID of the patient.",
            "editor": "textfield"
        },
        "type_id": {
            "type": "string",
            "title": "Type ID",
            "description": "ID for the appointment type.",
            "editor": "textfield"
        },
        "user_id": {
            "type": "string",
            "title": "User ID",
            "description": "ID of the user making the appointment.",
            "editor": "textfield"
        },
        "reason": {
            "type": "string",
            "title": "Reason",
            "description": "Reason for the appointment.",
            "editor": "textfield"
        },
        "room": {
            "type": "string",
            "title": "Room",
            "description": "Room number for the appointment.",
            "editor": "textfield"
        },
        "appointment_date": {
            "type": "string",
            "title": "Appointment Date",
            "description": "Date of the appointment.",
            "editor": "datepicker"
        },
        "time": {
            "type": "string",
            "title": "Appointment Start Time",
            "description": "Start time of the appointment.",
            "editor": "textfield"
        },
        "time_end": {
            "type": "string",
            "title": "Appointment End Time",
            "description": "End time of the appointment.",
            "editor": "textfield"
        },
        "useRealEndTime": {
            "type": "boolean",
            "title": "Use Real End Time",
            "description": "Whether to use the real end time for the appointment.",
            "editor": "checkbox",
            "default": true
        }
    },
    "required": ["start_url", "username", "password", "patient_id", "type_id", "user_id", "reason", "room", "appointment_date", "time", "time_end", "useRealEndTime"]
}

1import asyncio
2from .main import main
3
4# Execute the Actor entry point
5asyncio.run(main())

1import logging
2import json
3import asyncio
4import requests
5from playwright.async_api import async_playwright
6from apify import Actor  # Import the Actor module
7
8logging.basicConfig(level=logging.INFO)
9
10async def main():
11    # Initialize the actor
12    await Actor.init()
13
14    # Load input parameters from Apify input
15    actor_input = await Actor.get_input() or {}
16
17    # Log the input data for debugging
18    logging.info(f'Input data: {actor_input}')
19    
20    # Extract input parameters from the input JSON
21    start_url = actor_input.get('start_url')
22    company_id = actor_input.get('company_id')
23    username = actor_input.get('username')
24    password = actor_input.get('password')
25    appointment_details = {
26        'patient_id': actor_input.get('patient_id'),
27        'type_id': actor_input.get('type_id'),
28        'user_id': actor_input.get('user_id'),
29        'reason': actor_input.get('reason'),
30        'room': actor_input.get('room'),
31        'appointment_date': actor_input.get('appointment_date'),
32        'time': actor_input.get('time'),
33        'time_end': actor_input.get('time_end'),
34        'useRealEndTime': actor_input.get('useRealEndTime')
35    }
36
37    # Log extracted appointment details
38    logging.info(f'Appointment Details: {appointment_details}')
39
40    # Ensure all input fields have values, raise an error if any critical field is missing
41    if not all([start_url, company_id, username, password, appointment_details['patient_id'], 
42                appointment_details['type_id'], appointment_details['user_id'], 
43                appointment_details['reason'], appointment_details['room'], 
44                appointment_details['appointment_date'], appointment_details['time'], 
45                appointment_details['time_end']]):
46        logging.error("Missing required input fields!")
47        return
48
49    async with async_playwright() as p:
50        browser = await p.chromium.launch(headless=True)
51        context = await browser.new_context()
52        page = await context.new_page()
53
54        # Initialize variables to hold request headers
55        sec_ch_ua = None
56        sec_ch_ua_mobile = None
57
58        # Capture request headers when a request is made
59        def extract_headers(headers):
60            nonlocal sec_ch_ua, sec_ch_ua_mobile
61            sec_ch_ua = headers.get('sec-ch-ua')
62            sec_ch_ua_mobile = headers.get('sec-ch-ua-mobile')
63
64        page.on('request', lambda request: extract_headers(request.headers))
65
66        logging.info(f'Navigating to {start_url}...')
67        await page.goto(start_url)
68
69        # Fill in the login form
70        await page.fill('#company_id', company_id)
71        await page.fill('#username', username)
72        await page.fill('#password', password)
73        await page.click('#btnLogin')
74
75        # Wait for navigation to the dashboard
76        await page.wait_for_url('**/dashboard', timeout=15000)
77        logging.info('Login successful! On the dashboard page.')
78
79        # Extract cookies
80        cookies = await context.cookies()
81        logging.info(f'Cookies: {cookies}')
82        cookie_string = "; ".join([f"{cookie['name']}={cookie['value']}" for cookie in cookies])
83        logging.info(f'Cookie String: {cookie_string}')
84
85        # Extract XSRF token
86        xsrf_token = next((cookie['value'] for cookie in cookies if cookie['name'] == 'XSRF-TOKEN'), None)
87        logging.info(f'XSRF Token: {xsrf_token}')
88
89        # Extract user agent
90        user_agent = await page.evaluate("() => navigator.userAgent")
91        logging.info(f'User Agent: {user_agent}')
92
93        # Log sec-ch-ua and sec-ch-ua-mobile
94        logging.info(f'SEC-CH-UA: {sec_ch_ua}')
95        logging.info(f'SEC-CH-UA-Mobile: {sec_ch_ua_mobile}')
96
97        # Prepare the request headers dynamically
98        request_url = 'https://us.idexxneo.com/appointments/create'
99        headers = {
100            'accept': 'application/json, text/plain, */*',
101            'accept-encoding': 'gzip, deflate, br, zstd',
102            'accept-language': 'en-GB,en;q=0.9',
103            'cookie': cookie_string,
104            'origin': 'https://us.idexxneo.com',
105            'referer': 'https://us.idexxneo.com/schedule/appointments/new?date=' + appointment_details['appointment_date'] + '&time=' + appointment_details['time'],
106            'sec-ch-ua': sec_ch_ua if sec_ch_ua else '',
107            'sec-ch-ua-mobile': sec_ch_ua_mobile if sec_ch_ua_mobile else '',
108            'sec-fetch-dest': 'empty',
109            'sec-fetch-mode': 'cors',
110            'sec-fetch-site': 'same-origin',
111            'sec-gpc': '1',
112            'user-agent': user_agent,
113            'x-neo-core-version': '87.0.0',
114            'x-xsrf-token': xsrf_token
115        }
116
117        # Adjust form data to use 'files' for multipart data
118        files = {
119            'patient_id': (None, appointment_details['patient_id']),
120            'type_id': (None, appointment_details['type_id']),
121            'user_id': (None, appointment_details['user_id']),
122            'reason': (None, appointment_details['reason']),
123            'room': (None, appointment_details['room']),
124            'appointment_date': (None, appointment_details['appointment_date']),
125            'time': (None, appointment_details['time']),
126            'time_end': (None, appointment_details['time_end']),
127            'useRealEndTime': (None, str(appointment_details['useRealEndTime']).lower())
128        }
129
130        # Send the POST request
131        response = requests.post(request_url, headers=headers, files=files)
132
133        # Print the response
134        logging.info(f'Status Code: {response.status_code}')
135        logging.info(f'Response: {response.text}')
136
137        await browser.close()
138
139if __name__ == '__main__':
140    asyncio.run(main())

.git
.mise.toml
.nvim.lua
storage

# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore

# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# PyInstaller
#  Usually these files are written by a python script from a template
#  before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec

# Installer logs
pip-log.txt
pip-delete-this-directory.txt

# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/

# Translations
*.mo
*.pot

# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal

# Flask stuff:
instance/
.webassets-cache

# Scrapy stuff:
.scrapy

# Sphinx documentation
docs/_build/

# PyBuilder
.pybuilder/
target/

# Jupyter Notebook
.ipynb_checkpoints

# IPython
profile_default/
ipython_config.py

# pyenv
#   For a library or package, you might want to ignore these files since the code is
#   intended to run in multiple environments; otherwise, check them in:
.python-version

# pdm
#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
#   in version control.
#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
.pdm.toml
.pdm-python
.pdm-build/

# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/

# Celery stuff
celerybeat-schedule
celerybeat.pid

# SageMath parsed files
*.sage.py

# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/

# Spyder project settings
.spyderproject
.spyproject

# Rope project settings
.ropeproject

# mkdocs documentation
/site

# mypy
.mypy_cache/
.dmypy.json
dmypy.json

# Pyre type checker
.pyre/

# pytype static type analyzer
.pytype/

# Cython debug symbols
cython_debug/

# PyCharm
#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
#  and can be added to the global gitignore or merged into this file.  For a more nuclear
#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
.idea/

.mise.toml
.nvim.lua
storage

# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore

# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# PyInstaller
#  Usually these files are written by a python script from a template
#  before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec

# Installer logs
pip-log.txt
pip-delete-this-directory.txt

# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/

# Translations
*.mo
*.pot

# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal

# Flask stuff:
instance/
.webassets-cache

# Scrapy stuff:
.scrapy

# Sphinx documentation
docs/_build/

# PyBuilder
.pybuilder/
target/

# Jupyter Notebook
.ipynb_checkpoints

# IPython
profile_default/
ipython_config.py

# pyenv
#   For a library or package, you might want to ignore these files since the code is
#   intended to run in multiple environments; otherwise, check them in:
.python-version

# pdm
#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
#   in version control.
#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
.pdm.toml
.pdm-python
.pdm-build/

# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/

# Celery stuff
celerybeat-schedule
celerybeat.pid

# SageMath parsed files
*.sage.py

# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/

# Spyder project settings
.spyderproject
.spyproject

# Rope project settings
.ropeproject

# mkdocs documentation
/site

# mypy
.mypy_cache/
.dmypy.json
dmypy.json

# Pyre type checker
.pyre/

# pytype static type analyzer
.pytype/

# Cython debug symbols
cython_debug/

# PyCharm
#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
#  and can be added to the global gitignore or merged into this file.  For a more nuclear
#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
.idea/

1from apify import Actor
2from crawlee.playwright_crawler import PlaywrightCrawler, PlaywrightCrawlingContext
3
4async def main() -> None:
5    """Main entry point for the Apify Actor."""
6    async with Actor:
7        actor_input = await Actor.get_input() or {}
8        start_urls = [url.get('url') for url in actor_input.get('start_urls', [{'url': 'https://us.idexxneo.com/login?'}])]
9
10        if not start_urls:
11            Actor.log.info('No start URLs specified in Actor input, exiting...')
12            await Actor.exit()
13
14        crawler = PlaywrightCrawler(
15            max_requests_per_crawl=1,  # We only need to handle one request for the login
16            headless=True,
17        )
18
19        @crawler.router.default_handler
20        async def request_handler(context: PlaywrightCrawlingContext) -> None:
21            url = context.request.url
22            Actor.log.info(f'Navigating to {url}...')
23
24            # Navigate to the login page
25            await context.page.goto(url)
26
27            # Perform login actions
28            await context.page.fill('//*[@id="company_id"]', '7880')
29            await context.page.fill('//*[@id="username"]', 'PSingh')
30            await context.page.fill('//*[@id="password"]', 'Temppass1234!')
31
32            # Click the login button
33            await context.page.click('//*[@id="btnLogin"]')
34
35            # Wait for the page to load after login
36            await context.page.wait_for_load_state('networkidle')  # Wait until there are no more network connections for at least 500 ms
37
38            # After logging in, you can extract data or navigate further
39            Actor.log.info('Login successful!')
40
41            # Example: Extracting data after login (you can customize this)
42            data = {
43                'url': context.request.url,
44                'title': await context.page.title(),
45            }
46            await context.push_data(data)
47
48        await crawler.run(start_urls)
49
50if __name__ == '__main__':
51    import asyncio
52    asyncio.run(main())

1# Feel free to add your Python dependencies below. For formatting guidelines, see:
2# https://pip.pypa.io/en/latest/reference/requirements-file-format/
3
4apify == 2.0.0
5crawlee[playwright]