Deprecated

This Actor is deprecated

This Actor is unavailable because the developer has decided to deprecate it. Would you like to try a similar Actor instead?

See alternative Actors

FFXIV FC

hol/ffxiv-fc

Scrapes the FFXIV lodestone page of a free company for member names, ID's, and avatar.

.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:3.11
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"]

.actor/actor.json

1{
2    "actorSpecification": 1,
3    "name": "my-actor",
4    "title": "Getting started with Python and BeautifulSoup",
5    "description": "Scrapes titles of websites using BeautifulSoup.",
6    "version": "0.0",
7    "meta": {
8        "templateId": "python-beautifulsoup"
9    },
10    "input": "./input_schema.json",
11    "dockerfile": "./Dockerfile",
12    "storages": {
13        "dataset": {
14            "actorSpecification": 1,
15            "title": "URLs and their titles",
16            "views": {
17                "titles": {
18                    "title": "URLs and their titles",
19                    "transformation": {
20                        "fields": [
21                            "url",
22                            "title"
23                        ]
24                    },
25                    "display": {
26                        "component": "table",
27                        "properties": {
28                            "url": {
29                                "label": "URL",
30                                "format": "text"
31                            },
32                            "title": {
33                                "label": "Title",
34                                "format": "text"
35                            }
36                        }
37                    }
38                }
39            }
40        }
41    }
42}

.actor/input_schema.json

1{
2    "title": "Python BeautifulSoup 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/main.py

1"""
2This module serves as the entry point for executing the Apify Actor. It handles the configuration of logging
3settings. The `main()` coroutine is then executed using `asyncio.run()`.
4
5Feel free to modify this file to suit your specific needs.
6"""
7
8import asyncio
9import logging
10
11from apify.log import ActorLogFormatter
12
13from .main import main
14
15# Configure loggers
16handler = logging.StreamHandler()
17handler.setFormatter(ActorLogFormatter())
18
19apify_client_logger = logging.getLogger('apify_client')
20apify_client_logger.setLevel(logging.INFO)
21apify_client_logger.addHandler(handler)
22
23apify_logger = logging.getLogger('apify')
24apify_logger.setLevel(logging.DEBUG)
25apify_logger.addHandler(handler)
26
27# Execute the Actor main coroutine
28asyncio.run(main())

src/main.py

1from urllib.parse import urljoin
2from bs4 import BeautifulSoup
3from httpx import AsyncClient
4from apify import Actor
5
6async def main() -> None:
7    async with Actor:
8        # Read the Actor input
9        actor_input = await Actor.get_input() or {}
10        fc_id = actor_input.get('fc_id')
11
12        if not fc_id:
13            Actor.log.error('Free Company ID is missing in the actor input.')
14            await Actor.exit()
15
16        start_url = f'https://na.finalfantasyxiv.com/lodestone/freecompany/{fc_id}/member/'
17
18        # Enqueue the starting URL in the default request queue
19        default_queue = await Actor.open_request_queue()
20        await default_queue.add_request({'url': start_url})
21
22        # Process the requests in the queue one by one
23        while request := await default_queue.fetch_next_request():
24            url = request['url']
25            Actor.log.info(f'Scraping {url} ...')
26
27            try:
28                # Fetch the URL using `httpx`
29                async with AsyncClient() as client:
30                    response = await client.get(url, follow_redirects=True)
31
32                # Parse the response using `BeautifulSoup`
33                soup = BeautifulSoup(response.content, 'html.parser')
34
35                # Extract member data from the page
36                members = []
37                for member in soup.select('li.entry'):
38                    name_element = member.select_one('.entry__name')
39                    if name_element:
40                        name = name_element.text.strip()
41                        id_link = member.select_one('.entry__bg')['href']
42                        member_id = id_link.split('/')[-2]
43                        avatar_url = member.select_one('.entry__chara__face img')['src']
44
45                        members.append({
46                            'name': name,
47                            'id': member_id,
48                            'avatar_url': avatar_url
49                        })
50
51                # Push the extracted data into the default dataset
52                await Actor.push_data({'url': url, 'members': members})
53
54                # Check for pagination and enqueue the next page URL
55                next_page = soup.select_one('.btn__pager__next')
56                if next_page and 'btn__pager__no' not in next_page.get('class', []):
57                    next_url = urljoin(url, next_page['href'])
58                    await default_queue.add_request({'url': next_url})
59
60            except Exception:
61                Actor.log.exception(f'Cannot extract data from {url}.')
62
63            finally:
64                # Mark the request as handled so it's not processed again
65                await default_queue.mark_request_as_handled(request)

.dockerignore

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

.editorconfig

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

.gitignore

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
9.venv/
10.env/
11__pypackages__
12dist/
13build/
14*.egg-info/
15*.egg
16
17__pycache__
18
19.mypy_cache
20.dmypy.json
21dmypy.json
22.pytest_cache
23.ruff_cache
24
25.scrapy
26*.log

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 ~= 1.7.0
5beautifulsoup4 ~= 4.12.2
6httpx ~= 0.25.2
7types-beautifulsoup4 ~= 4.12.0.7