Login with Selenium

# First, specify the base Docker image.
# You can see the Docker images from Apify at https://hub.docker.com/r/apify/.
# You can also use any other image from Docker Hub.
FROM apify/actor-python-selenium:3.13

# Second, copy just requirements.txt into the Actor image,
# since it should be the only file that affects the dependency install in the next step,
# in order to speed up the build
COPY requirements.txt ./

# Install the packages specified in requirements.txt,
# Print the installed Python version, pip version
# and all installed packages with their versions for debugging
RUN echo "Python version:" \
 && python --version \
 && echo "Pip version:" \
 && pip --version \
 && echo "Installing dependencies:" \
 && pip install -r requirements.txt \
 && echo "All installed Python packages:" \
 && pip freeze

# Next, copy the remaining files and directories with the source code.
# Since we do this after installing the dependencies, quick build will be really fast
# for most source file changes.
COPY . ./

# Use compileall to ensure the runnability of the Actor Python code.
RUN python3 -m compileall -q .

# Specify how to launch the source code of your Actor.
# By default, the "python3 -m src" command is run
CMD ["python3", "-m", "src"]

{
    "actorSpecification": 1,
    "name": "my-actor",
    "title": "Getting started with Python and Selenium",
    "description": "Scrapes titles of websites using Selenium.",
    "version": "0.0",
    "buildTag": "latest",
    "meta": {
        "templateId": "python-selenium"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

{
    "title": "Python Selenium Scraper",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "start_urls": {
            "title": "Start URLs",
            "type": "array",
            "description": "URLs to start with",
            "prefill": [
                { "url": "https://apify.com" }
            ],
            "editor": "requestListSources"
        },
        "max_depth": {
            "title": "Maximum depth",
            "type": "integer",
            "description": "Depth to which to scrape to",
            "default": 1
        }
    },
    "required": ["start_urls"]
}

1

1import asyncio
2
3from .main import main
4
5# Execute the Actor entry point.
6asyncio.run(main())

1"""This module defines the main entry point for the Apify Actor.
2
3Feel free to modify this file to suit your specific needs.
4
5To build Apify Actors, utilize the Apify SDK toolkit, read more at the official documentation:
6https://docs.apify.com/sdk/python
7"""
8
9import asyncio
10from urllib.parse import urljoin
11
12from time import sleep
13
14from apify import Actor, Request
15from selenium import webdriver
16from selenium.webdriver.chrome.service import Service
17from selenium.webdriver.chrome.options import Options
18from selenium.webdriver.common.by import By
19from selenium.webdriver.common.keys import Keys
20from selenium.webdriver.support.ui import WebDriverWait
21from selenium.webdriver.support import expected_conditions as EC
22from webdriver_manager.chrome import ChromeDriverManager
23
24# To run this Actor locally, you need to have the Selenium Chromedriver installed.
25# Follow the installation guide at:
26# https://www.selenium.dev/documentation/webdriver/getting_started/install_drivers/
27# When running on the Apify platform, the Chromedriver is already included
28# in the Actor's Docker image.
29
30
31async def main() -> None:
32    """
33
34    Returns cookies for a given site, after login
35
36    This coroutine is executed using `asyncio.run()`, so it must remain an asynchronous function for proper execution.
37    Asynchronous execution is required for communication with Apify platform, and it also enhances performance in
38    the field of web scraping significantly.
39    """
40    # Enter the context of the Actor.
41    async with Actor:
42        # Retrieve the Actor input, and use default values if not provided.
43        actor_input = await Actor.get_input() or {}
44        start_urls = actor_input.get('start_urls')
45        credentials = actor_input.get('credentials')
46
47        if not start_urls:
48            Actor.log.error('No start_urls specified in actor input, exiting...')
49            await Actor.exit()
50        login_url = start_urls[0]
51
52        if not login_url:
53            Actor.log.error('No login url specified in actor input, exiting...')
54            await Actor.exit()
55
56        if not credentials:
57            Actor.log.error('No credentials specified in actor input, exiting...')
58            await Actor.exit()
59
60        user_info = credentials.get("user", {})
61        password_info = credentials.get("password", {})
62        submit_info = credentials.get("submit", {})
63        extra_info = credentials.get("extra", {})
64
65        user = user_info.get("value")
66        password = password_info.get("value")
67
68        if not (user and password):
69            Actor.log.info('User/Password info is not complete, exiting...')
70            await Actor.exit()
71
72        # xpaths info
73        xpath_user = user_info.get("xpath")
74        xpath_password = password_info.get("xpath")
75        xpath_submit = submit_info.get("xpath")
76
77        if not (xpath_user and xpath_password and xpath_submit):
78            Actor.log.info('XPath info for user/password/submit is not complete, exiting...')
79            await Actor.exit()
80
81        Actor.log.debug("All info ok")
82
83        # Optionals: wait time and OK page marker
84        wait_time = extra_info.get("wait_time", 5)
85        if isinstance(wait_time, (str, float)):
86            wait_time = int(wait_time)
87
88        ok_page_xpath = extra_info.get("ok_page_xpath")
89
90        # We got all we need, so we can start
91
92        # Enqueue the Login URL in the default request queue
93        request_queue = await Actor.open_request_queue()
94        for start_url in start_urls:
95            url = start_url.get('url')
96            Actor.log.info(f'Enqueuing {url} ...')
97            new_request = Request.from_url(url, user_data={'depth': 0})
98            await request_queue.add_request(new_request)
99
100        # Launch a new Selenium Chrome WebDriver
101        Actor.log.info('Launching Chrome Headless WebDriver...')
102        chrome_options = Options()
103        chrome_options.add_argument('--headless')
104        chrome_options.add_argument('--no-sandbox')
105        chrome_options.add_argument('--disable-dev-shm-usage')
106        driver = webdriver.Chrome(options=chrome_options)
107
108        # Process the requests in the queue one by one
109        while request := await request_queue.fetch_next_request():
110            url = request.url
111            Actor.log.info(f'Login check: {url} ...')
112
113            try:
114                # Open the URL in the Selenium WebDriver
115                driver.get(url)
116                Actor.log.info(f'Sleeping for this much time: {wait_time} seconds ...')
117                # Wait for the login form to appear
118                wait = WebDriverWait(driver, wait_time)
119
120                # Find elements
121                username_input = wait.until(EC.presence_of_element_located((By.XPATH, xpath_user)))
122                password_input = wait.until(EC.presence_of_element_located((By.XPATH, xpath_password)))
123                submit_button = wait.until(EC.element_to_be_clickable((By.XPATH, xpath_submit)))
124
125                # Populate
126                username_input.send_keys(user)
127                password_input.send_keys(password)
128
129                # Click and wait
130                submit_button.click()
131                wait = WebDriverWait(driver, wait_time)
132                if ok_page_xpath:
133                    wait.until(EC.presence_of_element_located((By.XPATH, ok_page_xpath)))
134                else:
135                    sleep(wait_time)
136                    Actor.log.info("Wake up!")
137
138
139                await Actor.push_data({'url': url, 'cookies': driver.get_cookies()})
140            except Exception:
141                Actor.log.exception(f'Cannot login: URL is {url}.')
142            finally:
143                await request_queue.mark_request_as_handled(request)
144
145        driver.quit()

.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/

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 >= 1.7.0
5selenium ~= 4.14.0
6webdriver_manager