FFXIV FC

# 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:3.11

# 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 .

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

{
    "actorSpecification": 1,
    "name": "my-actor",
    "title": "Getting started with Python and BeautifulSoup",
    "description": "Scrapes titles of websites using BeautifulSoup.",
    "version": "0.0",
    "meta": {
        "templateId": "python-beautifulsoup"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile",
    "storages": {
        "dataset": {
            "actorSpecification": 1,
            "title": "URLs and their titles",
            "views": {
                "titles": {
                    "title": "URLs and their titles",
                    "transformation": {
                        "fields": [
                            "url",
                            "title"
                        ]
                    },
                    "display": {
                        "component": "table",
                        "properties": {
                            "url": {
                                "label": "URL",
                                "format": "text"
                            },
                            "title": {
                                "label": "Title",
                                "format": "text"
                            }
                        }
                    }
                }
            }
        }
    }
}

{
    "title": "Python BeautifulSoup Scraper",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "start_urls": {
            "title": "Start URLs",
            "type": "array",
            "description": "URLs to start with",
            "prefill": [
                { "url": "https://apify.com" }
            ],
            "editor": "requestListSources"
        },
        "max_depth": {
            "title": "Maximum depth",
            "type": "integer",
            "description": "Depth to which to scrape to",
            "default": 1
        }
    },
    "required": ["start_urls"]
}

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())

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)

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
.venv

# git folder
.git

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

# This file tells Git which files shouldn't be added to source control

.idea
.DS_Store

apify_storage
storage

.venv/
.env/
__pypackages__
dist/
build/
*.egg-info/
*.egg

__pycache__

.mypy_cache
.dmypy.json
dmypy.json
.pytest_cache
.ruff_cache

.scrapy
*.log

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