Haldirams-Apify-Client
Pricing
Pay per usage
Go to Store
Haldirams-Apify-Client
**Haldirams-Apify-Client** is a web scraper that extracts product titles, links, and prices from the Haldiram’s website. It uses **BeautifulSoup** for parsing and **HTTPX** for fast, asynchronous requests, ensuring efficient data extraction for analysis, price tracking, or automation. 🚀
0.0 (0)
Pricing
Pay per usage
1
Total users
2
Monthly users
1
Runs succeeded
>99%
Last modified
3 months ago
.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:3.12
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": "Scrape single page in Python",
5 "description": "Scrape data from single page with provided URL.",
6 "version": "0.0",
7 "buildTag": "latest",
8 "meta": {
9 "templateId": "python-start"
10 },
11 "input": "./input_schema.json",
12 "dockerfile": "./Dockerfile"
13}.actor/input_schema.json
1{
2 "title": "Scrape data from a web page",
3 "type": "object",
4 "schemaVersion": 1,
5 "properties": {
6
7 },
8 "required": []
9}.actor/output_schema.json
1{
2 "actorSpecification": 1,
3 "title": "Haldirams Product Data",
4 "type": "object",
5 "properties": {
6 "items": {
7 "title": "Extracted Product List",
8 "type": "array",
9 "items": {
10 "type": "object",
11 "title": "Product",
12 "properties": {
13 "title": {
14 "type": "string",
15 "description": "Name of the product"
16 },
17 "Link": {
18 "type": "string",
19 "format": "uri",
20 "description": "Product URL"
21 },
22 "price": {
23 "type": "string",
24 "description": "Price of the product"
25 },
26 "views": {
27 "type": "integer",
28 "description": "Number of times the product was viewed"
29 },
30 "collections": {
31 "type": "array",
32 "items": {
33 "type": "string"
34 },
35 "description": "Collections or categories the product belongs to"
36 }
37 },
38 "required": ["title", "Link", "price", "views", "collections"]
39 }
40 }
41 },
42 "required": ["items"]
43}src/__main__.py
1import asyncio
2
3from .main import main
4
5# Execute the Actor entry point.
6asyncio.run(main())src/main.py
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
9# Beautiful Soup - A library for pulling data out of HTML and XML files. Read more at:
10# https://www.crummy.com/software/BeautifulSoup/bs4/doc
11from bs4 import BeautifulSoup
12import urllib.request
13import requests
14
15# HTTPX - A library for making asynchronous HTTP requests in Python. Read more at:
16# https://www.python-httpx.org/
17from httpx import AsyncClient
18
19# Apify SDK - A toolkit for building Apify Actors. Read more at:
20# https://docs.apify.com/sdk/python
21from apify import Actor
22
23
24async def main() -> None:
25 """Main entry point for the Apify Actor.
26
27 This coroutine is executed using `asyncio.run()`, so it must remain an asynchronous function for proper execution.
28 Asynchronous execution is required for communication with Apify platform, and it also enhances performance in
29 the field of web scraping significantly.
30 """
31 async with Actor:
32 # Retrieve the input object for the Actor. The structure of input is defined in input_schema.json.
33 actor_input = await Actor.get_input() or {'Search_Word': 'Teddy Bear'}
34 print("Received Input:", actor_input);
35 item_name = actor_input.get("Search_Word")
36 url = "https://www.haldirams.com/sweets-73.html"
37
38 # amazon = urllib.request.urlopen(url)
39 # html_content = amazon.read()
40
41
42
43 # Create an asynchronous HTTPX client for making HTTP requests.
44 async with AsyncClient() as client:
45 # Fetch the HTML content of the page, following redirects if necessary.
46 Actor.log.info(f'Sending a request to {url}')
47 response = requests.get(url)
48 html_content = response.text
49
50 # Parse the HTML content using Beautiful Soup html parser
51 first_n_results = 100
52
53
54 soup = BeautifulSoup(html_content, 'html.parser')
55 elements = soup.find_all("div", class_='product-info flex flex-col flex-grow sm:flex-grow-0 px-4 lg:px-6')[:first_n_results]
56 extarcted_data = []
57 print(len(elements))
58 for element in elements:
59 data = {}
60 title = element.find("a", class_='product-item-link line-clamp-2 text-black min-h-[42px] md:min-h-[50px]')
61 data["title"] = title.get_text(strip=True) if title else "N/A"
62 print(data["title"])
63 data["Link"] = title.get("href") if title else "N/A"
64 data["price"] = element.find("span", class_='price').get_text(strip=True) if element else "N/A"
65
66 extarcted_data.append(data)
67
68
69 # Save the extracted headings to the dataset, which is a table-like storage.
70 await Actor.push_data(extarcted_data).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
5beautifulsoup4[lxml]
6httpx
7types-beautifulsoup4
