diff --git a/.env.sample b/.env.sample index 27de81a..7cbc5c0 100644 --- a/.env.sample +++ b/.env.sample @@ -178,6 +178,14 @@ # Default: https://rebrickable.com/parts/{number}/_/{color} # BK_REBRICKABLE_LINK_PART_PATTERN= +# Optional: Pattern of the link to Rebrickable for instructions. Will be passed to Python .format() +# Default: https://rebrickable.com/instructions/{path} +# BK_REBRICKABLE_LINK_INSTRUCTIONS_PATTERN= + +# Optional: User-Agent to use when querying Rebrickable outside of the Rebrick python library +# Default: 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' +# BK_REBRICKABLE_USER_AGENT= + # Optional: Display Rebrickable links wherever applicable # Default: false # Legacy name: LINKS diff --git a/bricktracker/config.py b/bricktracker/config.py index 8cfdbba..08db61b 100644 --- a/bricktracker/config.py +++ b/bricktracker/config.py @@ -43,6 +43,8 @@ CONFIG: Final[list[dict[str, Any]]] = [ {'n': 'REBRICKABLE_IMAGE_NIL_MINIFIGURE', 'd': 'https://rebrickable.com/static/img/nil_mf.jpg'}, # noqa: E501 {'n': 'REBRICKABLE_LINK_MINIFIGURE_PATTERN', 'd': 'https://rebrickable.com/minifigs/{number}'}, # noqa: E501 {'n': 'REBRICKABLE_LINK_PART_PATTERN', 'd': 'https://rebrickable.com/parts/{number}/_/{color}'}, # noqa: E501 + {'n': 'REBRICKABLE_LINK_INSTRUCTIONS_PATTERN', 'd': 'https://rebrickable.com/instructions/{path}'}, # noqa: E501 + {'n': 'REBRICKABLE_USER_AGENT', 'd': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'}, # noqa: E501 {'n': 'REBRICKABLE_LINKS', 'e': 'LINKS', 'c': bool}, {'n': 'REBRICKABLE_PAGE_SIZE', 'd': 100, 'c': int}, {'n': 'RETIRED_SETS_FILE_URL', 'd': 'https://docs.google.com/spreadsheets/d/1rlYfEXtNKxUOZt2Mfv0H17DvK7bj6Pe0CuYwq6ay8WA/gviz/tq?tqx=out:csv&sheet=Sorted%20by%20Retirement%20Date'}, # noqa: E501 diff --git a/bricktracker/instructions.py b/bricktracker/instructions.py index 8f4b4fc..0dd7f8e 100644 --- a/bricktracker/instructions.py +++ b/bricktracker/instructions.py @@ -1,14 +1,18 @@ from datetime import datetime, timezone import logging import os -from typing import TYPE_CHECKING +from shutil import copyfileobj +from typing import Tuple, TYPE_CHECKING +from bs4 import BeautifulSoup from flask import current_app, g, url_for import humanize +import requests from werkzeug.datastructures import FileStorage from werkzeug.utils import secure_filename -from .exceptions import ErrorException +from .exceptions import ErrorException, DownloadException +from .parser import parse_set if TYPE_CHECKING: from .rebrickable_set import RebrickableSet @@ -67,6 +71,34 @@ class BrickInstructions(object): def delete(self, /) -> None: os.remove(self.path()) + # Download an instruction file + def download(self, path: str, /) -> None: + target = self.path(filename=secure_filename(self.filename)) + + if os.path.isfile(target): + raise ErrorException('Cannot download {target} as it already exists'.format( # noqa: E501 + target=self.filename + )) + + url = current_app.config['REBRICKABLE_LINK_INSTRUCTIONS_PATTERN'].format( # noqa: E501 + path=path + ) + + response = requests.get(url, stream=True) + if response.ok: + with open(target, 'wb') as f: + copyfileobj(response.raw, f) + else: + raise DownloadException('Failed to download {file}. Status code: {code}'.format( # noqa: E501 + file=self.filename, + code=response.status_code + )) + + # Info + logger.info('The instruction file {file} has been downloaded'.format( + file=self.filename + )) + # Display the size in a human format def human_size(self) -> str: return humanize.naturalsize(self.size) @@ -142,3 +174,71 @@ class BrickInstructions(object): return 'file-image-line' else: return 'file-line' + + # Download selected instructions for a set + @staticmethod + def download_instructions(form: dict[str, str], /) -> None: + selected_instructions: list[Tuple[str, str]] = [] + + # Get the list of instructions + for key in form: + if key.startswith('instruction-') and form.get(key) == 'on': + _, _, index = key.partition('-') + alt_text = form.get(f'instruction-alt-text-{index}', '') + href_text = form.get(f'instruction-href-text-{index}', '').removeprefix('/instructions/') # Remove the /instructions/ part # noqa: E501 + selected_instructions.append((href_text, alt_text)) + + # Raise if nothing selected + if not len(selected_instructions): + raise ErrorException('No instruction was selected to download') + + # Loop over selected instructions and download them + for href, filename in selected_instructions: + BrickInstructions(f"{filename}.pdf").download(href) + + # Find the instructions for a set + @staticmethod + def find_instructions(form: dict[str, str], /) -> list[Tuple[str, str]]: + # Grab the set ID + set: str = form.get('add-set', '') + + # Parse it + set = parse_set(set) + + response = requests.get( + current_app.config['REBRICKABLE_LINK_INSTRUCTIONS_PATTERN'].format( + path=set, + ), + headers={ + 'User-Agent': current_app.config['REBRICKABLE_USER_AGENT'] + } + ) + + if not response.ok: + raise ErrorException('Failed to load the Rebrickable instructions page. Status code: {code}'.format( # noqa: E501 + code=response.status_code + )) + + # Parse the HTML content + soup = BeautifulSoup(response.content, 'html.parser') + + # Collect all tags with "LEGO Building Instructions" in the + # alt attribute + found_tags: list[Tuple[str, str]] = [] + for a_tag in soup.find_all('a', href=True): + img_tag = a_tag.find('img', alt=True) + if img_tag and "LEGO Building Instructions" in img_tag['alt']: + found_tags.append( + ( + img_tag['alt'].removeprefix('LEGO Building Instructions for '), # noqa: E501 + a_tag['href'] + ) + ) # Save alt and href + + # Raise an error if nothing found + if not len(found_tags): + raise ErrorException('No instruction found for set {set}'.format( + set=set + )) + + return found_tags diff --git a/bricktracker/parser.py b/bricktracker/parser.py new file mode 100644 index 0000000..d3602e2 --- /dev/null +++ b/bricktracker/parser.py @@ -0,0 +1,37 @@ +from .exceptions import ErrorException + + +# Make sense of string supposed to contain a set ID +def parse_set(set: str, /) -> str: + number, _, version = set.partition('-') + + # Making sure both are integers + if version == '': + version = 1 + + try: + number = int(number) + except Exception: + raise ErrorException('Number "{number}" is not a number'.format( + number=number, + )) + + try: + version = int(version) + except Exception: + raise ErrorException('Version "{version}" is not a number'.format( + version=version, + )) + + # Make sure both are positive + if number < 0: + raise ErrorException('Number "{number}" should be positive'.format( + number=number, + )) + + if version < 0: + raise ErrorException('Version "{version}" should be positive'.format( # noqa: E501 + version=version, + )) + + return '{number}-{version}'.format(number=number, version=version) diff --git a/bricktracker/rebrickable_set.py b/bricktracker/rebrickable_set.py index 37e26b3..5a1c41f 100644 --- a/bricktracker/rebrickable_set.py +++ b/bricktracker/rebrickable_set.py @@ -7,6 +7,7 @@ from flask import current_app from .exceptions import ErrorException, NotFoundException from .instructions import BrickInstructions +from .parser import parse_set from .rebrickable import Rebrickable from .rebrickable_image import RebrickableImage from .record import BrickRecord @@ -98,7 +99,7 @@ class RebrickableSet(BrickRecord): try: self.socket.auto_progress(message='Parsing set number') - set = RebrickableSet.parse_number(str(data['set'])) + set = parse_set(str(data['set'])) self.socket.auto_progress( message='Set {set}: loading from Rebrickable'.format( @@ -187,39 +188,3 @@ class RebrickableSet(BrickRecord): 'url': str(data['set_url']), 'last_modified': str(data['last_modified_dt']), } - - # Make sense of the number from the data - @staticmethod - def parse_number(set: str, /) -> str: - number, _, version = set.partition('-') - - # Making sure both are integers - if version == '': - version = 1 - - try: - number = int(number) - except Exception: - raise ErrorException('Number "{number}" is not a number'.format( - number=number, - )) - - try: - version = int(version) - except Exception: - raise ErrorException('Version "{version}" is not a number'.format( - version=version, - )) - - # Make sure both are positive - if number < 0: - raise ErrorException('Number "{number}" should be positive'.format( - number=number, - )) - - if version < 0: - raise ErrorException('Version "{version}" should be positive'.format( # noqa: E501 - version=version, - )) - - return '{number}-{version}'.format(number=number, version=version) diff --git a/bricktracker/views/instructions.py b/bricktracker/views/instructions.py index 047e961..d347b06 100644 --- a/bricktracker/views/instructions.py +++ b/bricktracker/views/instructions.py @@ -13,6 +13,7 @@ from werkzeug.utils import secure_filename from .exceptions import exception_handler from ..instructions import BrickInstructions from ..instructions_list import BrickInstructionsList +from ..parser import parse_set from .upload import upload_helper instructions_page = Blueprint( @@ -126,3 +127,46 @@ def do_upload() -> Response: BrickInstructionsList(force=True) return redirect(url_for('instructions.list')) + + +# Download instructions from Rebrickable +@instructions_page.route('/download/', methods=['GET']) +@login_required +@exception_handler(__file__) +def download() -> str: + # Grab the set number + try: + set = parse_set(request.args.get('set', '')) + except Exception: + set = '' + + return render_template( + 'instructions.html', + download=True, + error=request.args.get('error'), + set=set + ) + + +# Show search results +@instructions_page.route('/download/select', methods=['POST']) +@login_required +@exception_handler(__file__, post_redirect='instructions.download') +def select_download() -> str: + return render_template( + 'instructions.html', + download=True, + instructions=BrickInstructions.find_instructions(request.form) + ) + + +# Download files +@instructions_page.route('/download', methods=['POST']) +@login_required +@exception_handler(__file__, post_redirect='instructions.download') +def do_download() -> Response: + BrickInstructions.download_instructions(request.form) + + BrickInstructionsList(force=True) + + return redirect(url_for('instructions.list')) diff --git a/bricktracker/wish_list.py b/bricktracker/wish_list.py index dfba800..880021b 100644 --- a/bricktracker/wish_list.py +++ b/bricktracker/wish_list.py @@ -4,9 +4,9 @@ from typing import Self from flask import current_app from .exceptions import NotFoundException +from .parser import parse_set from .rebrickable import Rebrickable from .rebrickable_image import RebrickableImage -from .rebrickable_set import RebrickableSet from .record_list import BrickRecordList from .wish import BrickWish @@ -34,7 +34,7 @@ class BrickWishList(BrickRecordList[BrickWish]): @staticmethod def add(set: str, /) -> None: try: - set = RebrickableSet.parse_number(set) + set = parse_set(set) BrickWish().select_specific(set) except NotFoundException: logger.debug('rebrick.lego.get_set("{set}")'.format( diff --git a/requirements.txt b/requirements.txt index aedd691..d2ca909 100644 --- a/requirements.txt +++ b/requirements.txt @@ -7,4 +7,5 @@ humanize jinja2 rebrick requests -tzdata \ No newline at end of file +tzdata +bs4 diff --git a/templates/instructions.html b/templates/instructions.html index 70cd1eb..78d4ce8 100644 --- a/templates/instructions.html +++ b/templates/instructions.html @@ -5,6 +5,8 @@ {% block main %} {% if upload %} {% include 'instructions/upload.html' %} + {% elif download %} + {% include 'instructions/download.html' %} {% elif rename %} {% include 'instructions/rename.html' %} {% elif delete %} @@ -14,6 +16,7 @@ {% if g.login.is_authenticated() %}
Upload an instructions file + Download instructions from Rebrickable Refresh the instructions cache
{% endif %} diff --git a/templates/instructions/download.html b/templates/instructions/download.html new file mode 100644 index 0000000..9543702 --- /dev/null +++ b/templates/instructions/download.html @@ -0,0 +1,50 @@ +