# 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: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 src/

# Create and run as a non-root user.
RUN useradd --create-home apify && \
    chown -R apify:apify ./
USER apify

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

.actor/actor.json

{
  "actorSpecification": 1,
  "name": "finstat-revenue-scraper",
  "title": "Finstat Revenue Scraper",
  "description": "Scrapes Slovak companies from Finstat and extracts revenue, NACE, employees, and VAT info.",
  "version": "0.1",
  "buildTag": "latest",
  "storages": {
    "dataset": {
      "actorSpecification": 1,
      "views": {
        "overview": {
          "title": "Overview",
          "transformation": {
            "fields": [
              "ico",
              "ic_dph",
              "sidlo",
              "sk_nace",
              "established_date",
              "employees_text",
              "min_employees",
              "revenue_2019",
              "revenue_2020",
              "revenue_2021",
              "revenue_2022",
              "revenue_2023",
              "revenue_2024"
            ]
          },
          "display": {
            "component": "table",
            "properties": {
              "ico": { "label": "ICO", "format": "text" },
              "ic_dph": { "label": "IČ DPH", "format": "text" },
              "sidlo": { "label": "Sídlo", "format": "text" },
              "sk_nace": { "label": "SK NACE", "format": "text" },
              "established_date": { "label": "Dátum vzniku", "format": "text" },
              "employees_text": { "label": "Počet zamestnancov", "format": "text" },
              "min_employees": { "label": "Min. zamestnanci", "format": "number" },
              "revenue_2019": { "label": "Tržby 2019", "format": "number" },
              "revenue_2020": { "label": "Tržby 2020", "format": "number" },
              "revenue_2021": { "label": "Tržby 2021", "format": "number" },
              "revenue_2022": { "label": "Tržby 2022", "format": "number" },
              "revenue_2023": { "label": "Tržby 2023", "format": "number" },
              "revenue_2024": { "label": "Tržby 2024", "format": "number" }
            }
          }
        }
      }
    }
  },
  "input": "./input_schema.json",
  "dockerfile": "./Dockerfile"
}

.actor/input_schema.json

{
    "title": "Finstat Revenue Scraper",
    "description": "Scrapes Tržby (Revenue) data from Finstat for given ICOs.",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "icos": {
            "title": "ICO List",
            "type": "array",
            "description": "List of ICOs to process (e.g. company identifiers in Slovakia)",
            "editor": "stringList",
            "prefill": ["35882085", "36468924", "36249955"]
        }
    },
    "required": ["icos"]
}

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 apify import Actor
2from bs4 import BeautifulSoup
3from curl_cffi.requests import AsyncSession
4import asyncio
5import json
6import re
7import time
8
9semaphore = asyncio.Semaphore(3)
10
11
12def extract_trzby_data(text):
13    series_marker = '[{"name":"Tr\\u017Eby","showInLegend":false,"data":['
14    start_idx = text.find(series_marker)
15    if start_idx == -1:
16        return None
17
18    count = 0
19    end_idx = None
20    for i in range(start_idx, len(text)):
21        if text[i] == '[':
22            count += 1
23        elif text[i] == ']':
24            count -= 1
25            if count == 0:
26                end_idx = i + 1
27                break
28
29    if end_idx is None:
30        return None
31
32    series_json_str = text[start_idx:end_idx]
33    categories_match = re.search(r'categories\s*:\s*(\[[^\]]+\])', text)
34    if not categories_match:
35        return None
36
37    try:
38        categories = json.loads(categories_match.group(1))
39        series = json.loads(series_json_str)
40
41        if isinstance(series, list) and series and "data" in series[0]:
42            y_values = [entry.get("y") for entry in series[0]["data"] if "y" in entry]
43            return dict(zip(categories, y_values))
44    except Exception:
45        return None
46
47
48def extract_ic_dph_sidlo(text):
49    soup = BeautifulSoup(text, 'html.parser')
50    ic_dph = None
51    sidlo = None
52
53    ic_dph_element = soup.find('strong', string=lambda t: t and "IČ DPH" in t)
54    if ic_dph_element:
55        span_text = ic_dph_element.find_next('span').get_text(" ", strip=True)
56        match = re.search(r'(SK\d+)', span_text)
57        if match:
58            ic_dph = match.group(1)
59
60    sidlo_element = soup.find('strong', string=lambda t: t and "Sídlo" in t)
61    if sidlo_element:
62        sidlo = sidlo_element.find_next('span').get_text(" ", strip=True)
63
64    return ic_dph, sidlo
65
66
67def extract_sk_nace(text):
68    soup = BeautifulSoup(text, 'html.parser')
69    nace_element = soup.find('strong', string=lambda t: t and "SK NACE" in t)
70    if nace_element:
71        span_element = nace_element.find_next('span')
72        if span_element:
73            div_element = span_element.find('div')
74            return div_element.get_text(" ", strip=True) if div_element else span_element.get_text(" ", strip=True)
75    return None
76
77
78def extract_employees(text):
79    soup = BeautifulSoup(text, 'html.parser')
80    emp_element = soup.find('strong', string=lambda t: t and "Počet zamestnancov" in t)
81    if emp_element:
82        span = emp_element.find_next('span')
83        if span:
84            return span.get_text(" ", strip=True)
85    return None
86
87
88def extract_min_employees(employees_text):
89    if not employees_text:
90        return 0
91    match = re.search(r'(\d+)\s*-\s*\d+', employees_text)
92    return int(match.group(1)) if match else 0
93
94
95def extract_established_date(text):
96    soup = BeautifulSoup(text, 'html.parser')
97    est_element = soup.find('strong', string=lambda t: t and "Dátum vzniku" in t)
98    if est_element:
99        span = est_element.find_next('span')
100        if span:
101            return span.get_text(" ", strip=True)
102    return None
103
104
105async def fetch_and_parse(ico, session):
106    url = f"https://www.finstat.sk/{ico}"
107    async with semaphore:
108        try:
109            resp = await session.get(url, timeout=20)
110            html = resp.text
111
112            revenue_data = extract_trzby_data(html)
113            revenue_by_year = extract_trzby_data(html) or {}
114            flat_revenue = {f"revenue_{year}": value for year, value in revenue_by_year.items()}
115            ic_dph, sidlo = extract_ic_dph_sidlo(html)
116            sk_nace = extract_sk_nace(html)
117            employees = extract_employees(html)
118            min_employees = extract_min_employees(employees)
119            established_date = extract_established_date(html)
120
121            return {
122            "ico": ico,
123            "ic_dph": ic_dph,
124            "sidlo": sidlo,
125            "sk_nace": sk_nace,
126            "employees_text": employees,
127            "min_employees": min_employees,
128            "established_date": established_date,
129            **flat_revenue  # Spread the revenue_YYYY keys directly
130        }
131        except Exception as e:
132            return {
133                "ico": ico,
134                "error": str(e)
135            }
136
137
138async def main():
139    async with Actor:
140        input_data = await Actor.get_input()
141        icos = input_data.get("icos", [])
142        if not icos:
143            Actor.log.warning("No ICOs provided in input.")
144            return
145
146        start = time.time()
147
148        async with AsyncSession() as session:
149            tasks = [fetch_and_parse(ico, session) for ico in icos]
150            results = await asyncio.gather(*tasks)
151
152        await Actor.push_data(results)
153        Actor.log.info(f"Finished in {time.time() - start:.2f} seconds")
154
155
156if __name__ == "__main__":
157    asyncio.run(main())

src/py.typed

.dockerignore

.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/

.gitignore

.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/

# Zed editor
#  Ignores the folder created when setting Project Settings in the Zed editor. Can be commented out
#  to share Project Settings within a team 
.zed

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
5beautifulsoup4[lxml]
6httpx
7types-beautifulsoup4
8curl_cffi

Coronavirus stats in Slovakia

davidrychly/covid-sk-3

Gets an actual number of examined and infected people by COVID-19 in the Slovak Republic from https://korona.gov.sk/koronavirus-na-slovensku-v-cislach/.

David Rychlý

Coronavirus stats in Bulgaria

zuzka/covid-bg

Gets all the charts statistics (actual number of infected, deceased and recovered people) by COVID-19 in Bulgaria from https://www.mh.government.bg/bg/informaciya-za-grazhdani/potvrdeni-sluchai-na-koronavirus-na-teritoriyata-na-r-blgariya/.

Zuzka Pelechová

User Info Generator API

andreylaura/user-info-generator-api

User Info Generator API

Laura Hawkins

namibia-real-estate-scraper

felixcodedhere/namibia-real-estate-scraper

Scrapes real estate listings from property24.com.na for a specified city

Nyambe Felix Matongo

amazon product info

makerechowu/amazon-product-info

夕吴

Facebook Page Contact Info Scraper

powerful_bachelor/Facebook-Page-Contact-Info-Scraper

The Facebook Page Contact Info Scraper 🛠️ is a tool for extracting contact info from Facebook Pages, including addresses, emails, and phone numbers 📞, ideal for market research 📊, competitor analysis 🔍, and strategic planning 📈.

Powerful Bachelor

171

Companies House UK Scraper

lexis-solutions/companies-house-uk-scraper

Scrape company info from UK Companies House. Extract company registration number, address, status, incorporation date, URL, and more.

Lexis Solutions

5.0

Linkedin Company About Scraper

dadhalfdev/linkedin-company-about-scraper

This tool scrapes detailed company information from LinkedIn "About" pages. Supports multiple companies per run, auto-translation of non-English pages, and structured JSON output. Input is a list of companies.

Marco Rodrigues

5.0

🔥 Linkedin Companies & Profiles Bulk Scraper

bebity/linkedin-premium-actor

Companies & Profiles Linkedin scraper. Get comprehensive profiles of individuals and companies based on your keywords and filters. Unleash the power of data! 🌐🔍