diff --git a/bricktracker/config.py b/bricktracker/config.py index 36defc6..08db61b 100644 --- a/bricktracker/config.py +++ b/bricktracker/config.py @@ -43,8 +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/{number}'}, # 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'}, + {'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 0c966d3..0dd7f8e 100644 --- a/bricktracker/instructions.py +++ b/bricktracker/instructions.py @@ -1,18 +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 flask import current_app, g, url_for, flash +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 io import BytesIO -import requests -from bs4 import BeautifulSoup - -from .exceptions import ErrorException +from .exceptions import ErrorException, DownloadException +from .parser import parse_set if TYPE_CHECKING: from .rebrickable_set import RebrickableSet @@ -71,6 +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) @@ -118,73 +146,6 @@ class BrickInstructions(object): )) file.save(target) - - # Info - logger.info('The instruction file {file} has been imported'.format( - file=self.filename - )) - - # Compute the url for the rebrickable instructions page - def url_for_instructions(self, /) -> str: - try: - return current_app.config['REBRICKABLE_LINK_INSTRUCTIONS_PATTERN'].format( # noqa: E501 - number=self.filename, - ) - except Exception: - pass - - return '' - - def find_instructions(self, set: str, /) -> None: - - headers = { - 'User-Agent': current_app.config['REBRICKABLE_USER_AGENT'] - } - - response = requests.get(BrickInstructions.url_for_instructions(self), headers=headers) - if response.status_code != 200: - raise ErrorException('Failed to load page. Status 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 = [] - 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'].replace('LEGO Building Instructions for ', ''), a_tag['href'])) # Save alt and href - - return found_tags - - def get_list(self, request_form, /) -> list: - selected_instructions = [] - # Get the list of instructions - for key in request_form: - if key.startswith('instruction-') and request_form.get(key) == 'on': # Checkbox is checked - index = key.split('-')[-1] - alt_text = request_form.get(f'instruction-alt-text-{index}') - href_text = request_form.get(f'instruction-href-text-{index}').replace('/instructions/', '') # Remove the /instructions/ part - selected_instructions.append((href_text,alt_text)) - - return selected_instructions - - def download(self, href: 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(number=href) - - response = requests.get(url) - if response.status_code == 200: - # Save the content to the target path - FileStorage(stream=BytesIO(response.content)).save(target) - else: - raise ErrorException(f"Failed to download {self.filename}. Status code: {response.status_code}") # Info logger.info('The instruction file {file} has been imported'.format( @@ -213,3 +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/views/instructions.py b/bricktracker/views/instructions.py index 585a981..d347b06 100644 --- a/bricktracker/views/instructions.py +++ b/bricktracker/views/instructions.py @@ -4,8 +4,7 @@ from flask import ( redirect, render_template, request, - url_for, - flash + url_for ) from flask_login import login_required from werkzeug.wrappers.response import Response @@ -14,6 +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( @@ -134,40 +134,38 @@ def do_upload() -> Response: @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') + error=request.args.get('error'), + set=set ) - + + # Show search results -@instructions_page.route('/download/', methods=['POST']) +@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: - # get set_id from input field - set_id: str = request.form.get('add-set', '') - - # get list of instructions for the set and offer them to download - instructions = BrickInstructions(set_id).find_instructions(set_id) - - return render_template('instructions.html', download=True, instructions=instructions) - -@instructions_page.route('/confirm_download', methods=['POST']) -@login_required -@exception_handler(__file__, post_redirect='instructions.download') -def confirm_download() -> Response: - - # Get list of selected instructions - selected_instructions = BrickInstructions("").get_list(request.form) - - # No instructions selected - if not selected_instructions: - return redirect(url_for('instructions.download')) - - # Loop over selected instructions and download them - for href, filename in selected_instructions: - BrickInstructions(f"{filename}.pdf").download(href) + BrickInstructions.download_instructions(request.form) BrickInstructionsList(force=True) diff --git a/templates/instructions/download.html b/templates/instructions/download.html index 20cb688..9543702 100644 --- a/templates/instructions/download.html +++ b/templates/instructions/download.html @@ -1,7 +1,8 @@
+ {% if error %}{% endif %}
-
+
Download instructions from Rebrickable
@@ -11,7 +12,7 @@
- +
@@ -23,7 +24,7 @@
Select instructions to download
- +
diff --git a/templates/set/card.html b/templates/set/card.html index 1fe7f72..9fcea3d 100644 --- a/templates/set/card.html +++ b/templates/set/card.html @@ -48,9 +48,11 @@ No instructions file found. {% if g.login.is_authenticated() %} Upload an instructions file - Download instruction from Rebrickable {% endif %} {% endif %} + {% if g.login.is_authenticated() %} + Download instructions from Rebrickable + {% endif %}
{{ accordion.footer() }} {{ accordion.table(item.parts(), 'Parts', 'parts-inventory', 'set-details', 'part/table.html', icon='shapes-line')}}