My Actor

Under maintenance

Try for free

Developed by

Simrandeep Singh

0.0 (0)

Pricing

Pay per usage

Monthly users

Runs succeeded

>99%

Last modified

a month ago

Jobs

Lead generation

Open source

.actor/Dockerfile

1# First, specify the base Docker image.
2# You can see the Docker images from Apify at https://hub.docker.com/r/apify/.
3# You can also use any other image from Docker Hub.
4FROM apify/actor-python-selenium:3.13
5
6# Second, copy just requirements.txt into the Actor image,
7# since it should be the only file that affects the dependency install in the next step,
8# in order to speed up the build
9COPY requirements.txt ./
10
11# Install the packages specified in requirements.txt,
12# Print the installed Python version, pip version
13# and all installed packages with their versions for debugging
14RUN echo "Python version:" \
15 && python --version \
16 && echo "Pip version:" \
17 && pip --version \
18 && echo "Installing dependencies:" \
19 && pip install -r requirements.txt \
20 && echo "All installed Python packages:" \
21 && pip freeze
22
23# Next, copy the remaining files and directories with the source code.
24# Since we do this after installing the dependencies, quick build will be really fast
25# for most source file changes.
26COPY . ./
27
28# Use compileall to ensure the runnability of the Actor Python code.
29RUN python3 -m compileall -q .
30
31# Specify how to launch the source code of your Actor.
32# By default, the "python3 -m src" command is run
33CMD ["python3", "-m", "src"]

.actor/actor.json

1{
2    "actorSpecification": 1,
3    "name": "my-actor",
4    "title": "Getting started with Python and Selenium",
5    "description": "Scrapes titles of websites using Selenium.",
6    "version": "0.0",
7    "buildTag": "latest",
8    "meta": {
9        "templateId": "python-selenium"
10    },
11    "input": "./input_schema.json",
12    "dockerfile": "./Dockerfile"
13}

.actor/input_schema.json

1{
2    "title": "Python Selenium Scraper",
3    "type": "object",
4    "schemaVersion": 1,
5    "properties": {
6        "start_urls": {
7            "title": "Start URLs",
8            "type": "array",
9            "description": "URLs to start with",
10            "prefill": [
11                { "url": "https://apify.com" }
12            ],
13            "editor": "requestListSources"
14        },
15        "max_depth": {
16            "title": "Maximum depth",
17            "type": "integer",
18            "description": "Depth to which to scrape to",
19            "default": 1
20        }
21    },
22    "required": ["start_urls"]
23}

src/init.py

src/main.py

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

src/main.py

1from selenium import webdriver
2from apify import Actor
3import logging
4
5# Set up logging for better feedback
6logging.basicConfig(level=logging.INFO)
7logger = logging.getLogger(__name__)
8
9async def main():
10    async with Actor:
11        # Chrome options
12        options = webdriver.ChromeOptions()
13        options.add_argument('--headless')
14        options.add_argument('--no-sandbox')
15        options.add_argument('--disable-dev-shm-usage')
16
17        # Launch browser
18        driver = webdriver.Chrome(options=options)
19        logger.info("Browser launched")
20
21        # Use your updated Citi URL
22        url = "https://jobs.citi.com/search-jobs/Data%20Analyst/India/287/1/2/1269750/22/79/50/2"
23        driver.get(url)
24        logger.info(f"Opened URL: {url}")
25
26        # Wait longer for jobs to load
27        driver.implicitly_wait(15)
28        logger.info("Waiting for page load")
29
30        # Try a broader selector to find job elements
31        jobs = driver.find_elements("tag name", "li")  # Look for <li> tags (common for lists)
32        logger.info(f"Found {len(jobs)} elements with 'li' tag")
33
34        # Loop through potential jobs
35        for job in jobs:
36            try:
37                title_elem = job.find_element("tag name", "h2")  # Try <h2> for titles
38                title = title_elem.text
39                location = job.find_element("class name", "job-location").text  # Guess class
40                link = job.find_element("tag name", "a").get_attribute("href")
41                if "data analyst" in title.lower():  # Filter for relevant jobs
42                    await Actor.push_data({
43                        "title": title,
44                        "location": location,
45                        "link": link
46                    })
47                    logger.info(f"Found: {title} - {location}")
48            except Exception as e:
49                logger.info(f"Skipped a job - error: {str(e)}")
50
51        # Check page source for debugging
52        page_source = driver.page_source
53        if "data analyst" in page_source.lower():
54            logger.info("Page contains 'data analyst' - selectors might be wrong")
55        else:
56            logger.warning("No 'data analyst' in page source - check URL")
57
58        # Close browser
59        driver.quit()
60        logger.info("Browser closed")

src/py.typed

.dockerignore

1.git
2.mise.toml
3.nvim.lua
4storage
5
6# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore
7
8# Byte-compiled / optimized / DLL files
9__pycache__/
10*.py[cod]
11*$py.class
12
13# C extensions
14*.so
15
16# Distribution / packaging
17.Python
18build/
19develop-eggs/
20dist/
21downloads/
22eggs/
23.eggs/
24lib/
25lib64/
26parts/
27sdist/
28var/
29wheels/
30share/python-wheels/
31*.egg-info/
32.installed.cfg
33*.egg
34MANIFEST
35
36# PyInstaller
37#  Usually these files are written by a python script from a template
38#  before PyInstaller builds the exe, so as to inject date/other infos into it.
39*.manifest
40*.spec
41
42# Installer logs
43pip-log.txt
44pip-delete-this-directory.txt
45
46# Unit test / coverage reports
47htmlcov/
48.tox/
49.nox/
50.coverage
51.coverage.*
52.cache
53nosetests.xml
54coverage.xml
55*.cover
56*.py,cover
57.hypothesis/
58.pytest_cache/
59cover/
60
61# Translations
62*.mo
63*.pot
64
65# Django stuff:
66*.log
67local_settings.py
68db.sqlite3
69db.sqlite3-journal
70
71# Flask stuff:
72instance/
73.webassets-cache
74
75# Scrapy stuff:
76.scrapy
77
78# Sphinx documentation
79docs/_build/
80
81# PyBuilder
82.pybuilder/
83target/
84
85# Jupyter Notebook
86.ipynb_checkpoints
87
88# IPython
89profile_default/
90ipython_config.py
91
92# pyenv
93#   For a library or package, you might want to ignore these files since the code is
94#   intended to run in multiple environments; otherwise, check them in:
95.python-version
96
97# pdm
98#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
99#pdm.lock
100#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
101#   in version control.
102#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
103.pdm.toml
104.pdm-python
105.pdm-build/
106
107# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
108__pypackages__/
109
110# Celery stuff
111celerybeat-schedule
112celerybeat.pid
113
114# SageMath parsed files
115*.sage.py
116
117# Environments
118.env
119.venv
120env/
121venv/
122ENV/
123env.bak/
124venv.bak/
125
126# Spyder project settings
127.spyderproject
128.spyproject
129
130# Rope project settings
131.ropeproject
132
133# mkdocs documentation
134/site
135
136# mypy
137.mypy_cache/
138.dmypy.json
139dmypy.json
140
141# Pyre type checker
142.pyre/
143
144# pytype static type analyzer
145.pytype/
146
147# Cython debug symbols
148cython_debug/
149
150# PyCharm
151#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
152#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
153#  and can be added to the global gitignore or merged into this file.  For a more nuclear
154#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
155.idea/

.gitignore

1.mise.toml
2.nvim.lua
3storage
4
5# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore
6
7# Byte-compiled / optimized / DLL files
8__pycache__/
9*.py[cod]
10*$py.class
11
12# C extensions
13*.so
14
15# Distribution / packaging
16.Python
17build/
18develop-eggs/
19dist/
20downloads/
21eggs/
22.eggs/
23lib/
24lib64/
25parts/
26sdist/
27var/
28wheels/
29share/python-wheels/
30*.egg-info/
31.installed.cfg
32*.egg
33MANIFEST
34
35# PyInstaller
36#  Usually these files are written by a python script from a template
37#  before PyInstaller builds the exe, so as to inject date/other infos into it.
38*.manifest
39*.spec
40
41# Installer logs
42pip-log.txt
43pip-delete-this-directory.txt
44
45# Unit test / coverage reports
46htmlcov/
47.tox/
48.nox/
49.coverage
50.coverage.*
51.cache
52nosetests.xml
53coverage.xml
54*.cover
55*.py,cover
56.hypothesis/
57.pytest_cache/
58cover/
59
60# Translations
61*.mo
62*.pot
63
64# Django stuff:
65*.log
66local_settings.py
67db.sqlite3
68db.sqlite3-journal
69
70# Flask stuff:
71instance/
72.webassets-cache
73
74# Scrapy stuff:
75.scrapy
76
77# Sphinx documentation
78docs/_build/
79
80# PyBuilder
81.pybuilder/
82target/
83
84# Jupyter Notebook
85.ipynb_checkpoints
86
87# IPython
88profile_default/
89ipython_config.py
90
91# pyenv
92#   For a library or package, you might want to ignore these files since the code is
93#   intended to run in multiple environments; otherwise, check them in:
94.python-version
95
96# pdm
97#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
98#pdm.lock
99#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
100#   in version control.
101#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
102.pdm.toml
103.pdm-python
104.pdm-build/
105
106# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
107__pypackages__/
108
109# Celery stuff
110celerybeat-schedule
111celerybeat.pid
112
113# SageMath parsed files
114*.sage.py
115
116# Environments
117.env
118.venv
119env/
120venv/
121ENV/
122env.bak/
123venv.bak/
124
125# Spyder project settings
126.spyderproject
127.spyproject
128
129# Rope project settings
130.ropeproject
131
132# mkdocs documentation
133/site
134
135# mypy
136.mypy_cache/
137.dmypy.json
138dmypy.json
139
140# Pyre type checker
141.pyre/
142
143# pytype static type analyzer
144.pytype/
145
146# Cython debug symbols
147cython_debug/
148
149# PyCharm
150#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
151#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
152#  and can be added to the global gitignore or merged into this file.  For a more nuclear
153#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
154.idea/

requirements.txt

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 < 3.0
5selenium