Created
June 30, 2016 12:32
-
-
Save mfwarren/4355dcb1d68ea97a9775a6a04e985f5e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import scrapy | |
| from twx.botapi import TelegramBot | |
| class LCBOSpider(scrapy.Spider): | |
| name = 'lcbospider' | |
| start_urls = ['http://www.lcbo.com/lcbo/search/filter?showAll=LTO#contentBeginIndex=0&productBeginIndex=0&beginIndex=0&orderBy=&categoryPath=%2F%2F&pageView=&resultType=products&orderByContent=&searchTerm=&facet=&storeId=10151&catalogId=10001&langId=-1&fromPage=&showAll=LTO&objectId=&requesttype=ajax'] | |
| custom_settings = { | |
| 'CONCURRENT_REQUESTS': 2 | |
| } | |
| bot = None | |
| def parse(self, response): | |
| LCBOSpider.bot = TelegramBot('<YOUR BOT TOKEN>') | |
| LCBOSpider.bot.update_bot_info().wait() | |
| count = int(response.css("span.count::text").extract()[0].split()[0]) | |
| num_pages = int(count / 50) | |
| for page in range(num_pages + 1): | |
| start_at = page * 50 | |
| url = "http://www.lcbo.com/webapp/wcs/stores/servlet/CategoryNavigationResultsView?pageSize=50&manufacturer=&searchType=1000&resultCatEntryType=2&catalogId=10001&categoryId=&langId=-1&storeId=10151&sType=SimpleSearch&filterFacet=&metaData=bHRvOnRydWU%3D" | |
| params = {'contentBeginIndex':'0', | |
| 'productBeginIndex':str(start_at), | |
| 'beginIndex':str(start_at), | |
| 'orderBy':'', | |
| 'categoryPath':'//', | |
| 'pageView':'', | |
| 'resultType':'products', | |
| 'orderByContent':'', | |
| 'searchTerm':'', | |
| 'facet':'', | |
| 'storeId':'10151', | |
| 'catalogId':'10001', | |
| 'langId':'-1', | |
| 'fromPage':'', | |
| 'showAll':'LTO', | |
| 'objectId':'', | |
| 'requesttype':'static'} | |
| yield scrapy.FormRequest(url, formdata=params, callback=self.parse_prices, dont_filter=True) | |
| def parse_prices(self, response): | |
| for block in response.css('div.product'): | |
| product_name = block.css('div.product-name a::text').extract()[0] | |
| price = float(block.css('div.price::text').extract()[0].replace('$', '')) | |
| saved = float(block.css('div.saved-price::text').extract()[0].replace('SAVE $', '')) | |
| percentage = saved / (price + saved) | |
| if percentage > 0.12: | |
| result = LCBOSpider.bot.send_message(int('<YOUR TELEGRAM USER ID>), '{} is on sale @ ${:0.2f} ({:2.1f}% off)'.format(product_name, price, percentage*100.0)).wait() | |
| yield {'product': product_name, | |
| 'price': price, | |
| 'save': saved, | |
| 'percentage': percentage} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment