Linkedin Url Scrape

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:3.11
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"]

1{
2    "actorSpecification": 1,
3    "name": "my-actor-15",
4    "title": "Scrape single page in Python",
5    "description": "Scrape data from single page with provided URL.",
6    "version": "0.0",
7    "meta": {
8        "templateId": "python-start"
9    },
10    "input": "./input_schema.json",
11    "dockerfile": "./Dockerfile"
12}

1{
2    "title": "Scrape LinkedIn profiles based on keywords",
3    "type": "object",
4    "schemaVersion": 1,
5    "properties": {
6        "keywords": {
7            "title": "Search Keywords",
8            "type": "array",
9            "description": "Enter the keywords to search for LinkedIn profiles, e.g., job titles, industries, locations.",
10            "editor": "stringList",
11            "items": {
12                "type": "string"
13            },
14            "prefill": ["chief product officer", "united states", "insurance"]
15        },
16        "numPages": {
17            "title": "Number of Pages",
18            "type": "integer",
19            "description": "The number of pages to scrape (each page corresponds to a set of search results).",
20            "editor": "number",
21            "minimum": 1,
22            "default": 1
23        }
24    },
25    "required": ["keywords", "numPages"]
26}

1# configurations
2.idea
3
4# crawlee and apify storage folders
5apify_storage
6crawlee_storage
7storage
8
9# installed files
10.venv
11
12# git folder
13.git

1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf

1# This file tells Git which files shouldn't be added to source control
2
3.idea
4.DS_Store
5
6apify_storage
7storage/*
8!storage/key_value_stores
9storage/key_value_stores/*
10!storage/key_value_stores/default
11storage/key_value_stores/default/*
12!storage/key_value_stores/default/INPUT.json
13
14.venv/
15.env/
16__pypackages__
17dist/
18build/
19*.egg-info/
20*.egg
21
22__pycache__
23
24.mypy_cache
25.dmypy.json
26dmypy.json
27.pytest_cache
28.ruff_cache
29
30.scrapy
31*.log