first version

.gitignore

@@ -0,0 +1,3 @@
+.vscode
+dagens_lunch/spiders/__pycache__/*.pyc
+dagens_lunch/__pycache__/*.pyc

dagens_lunch/items.py

@@ -0,0 +1,44 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DagensLunchValsaren(scrapy.Item):
+    place = scrapy.Field()
+    week = scrapy.Field()
+    monday = scrapy.Field()
+    tuesday = scrapy.Field()
+    wednesday = scrapy.Field()
+    thursday = scrapy.Field()
+    friday = scrapy.Field()
+    alltid = scrapy.Field()
+    klassiker = scrapy.Field()
+    price = scrapy.Field()
+    price_takeaway = scrapy.Field()
+    scraped_by = scrapy.Field()
+    scraped_at = scrapy.Field()
+
+class DagensLunchHeat(scrapy.Item):
+    place = scrapy.Field()
+    week = scrapy.Field()
+    monday = scrapy.Field()
+    tuesday = scrapy.Field()
+    wednesday = scrapy.Field()
+    thursday = scrapy.Field()
+    friday = scrapy.Field()
+    scraped_by = scrapy.Field()
+    scraped_at = scrapy.Field()
+
+class DagensLunchMalmens(scrapy.Item):
+    place = scrapy.Field()
+    week = scrapy.Field()
+    monday = scrapy.Field()
+    tuesday = scrapy.Field()
+    wednesday = scrapy.Field()
+    thursday = scrapy.Field()
+    friday = scrapy.Field()
+    scraped_by = scrapy.Field()
+    scraped_at = scrapy.Field()

dagens_lunch/middlewares.py

@@ -0,0 +1,103 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class DagensLunchSpiderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, or item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Request or item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)
+
+
+class DagensLunchDownloaderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)

dagens_lunch/pipelines.py

@@ -0,0 +1,13 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+
+
+class DagensLunchPipeline:
+    def process_item(self, item, spider):
+        return item

dagens_lunch/settings.py

@@ -0,0 +1,92 @@
+# Scrapy settings for dagens_lunch project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = "dagens_lunch"
+
+SPIDER_MODULES = ["dagens_lunch.spiders"]
+NEWSPIDER_MODULE = "dagens_lunch.spiders"
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64; rv:133.0) puckoprutt edition Gecko/20100101 Firefox/133.0"
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+#COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+#    "Accept-Language": "en",
+#}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    "dagens_lunch.middlewares.DagensLunchSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "dagens_lunch.middlewares.DagensLunchDownloaderMiddleware": 543,
+#}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    "scrapy.extensions.telnet.TelnetConsole": None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    "dagens_lunch.pipelines.DagensLunchPipeline": 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = "httpcache"
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = "scrapy.extensions.httpcache.FilesystemCacheStorage"
+
+# Set settings whose default value is deprecated to a future-proof value
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+FEED_EXPORT_ENCODING = "utf-8"

dagens_lunch/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

dagens_lunch/spiders/heat.py

@@ -0,0 +1,59 @@
+from datetime import datetime
+import xml.etree.ElementTree as ET
+import scrapy
+import chompjs
+from ..items import DagensLunchHeat
+
+class HeatSpider(scrapy.Spider):
+    name = "heat"
+    allowed_domains = ["heatrestauranger.se", "castit.nu"]
+    start_urls = ["https://heatrestauranger.se/lunch-heat-vasteras-kopparlunden/#veckans-lunchmeny"]
+
+    def extract_xml(self, response):
+        dagens = response.meta.get("dagens")
+        tree = ET.fromstring(response.body)
+        self.week = tree.find(".//rubrik").text
+        self.monday = []
+        self.tuesday = []
+        self.wednesday = []
+        self.thursday = []
+        self.friday = []
+
+        for idx in range(1, 8):
+            if not tree.find(f".//mandagratt{idx}rubrik") is None:
+                self.monday.append({"rubrik": tree.find(f".//mandagratt{idx}rubrik").text, "text": tree.find(f".//mandagratt{idx}text").text})
+            if not tree.find(f".//tisdagratt{idx}rubrik") is None:
+                self.tuesday.append({"rubrik": tree.find(f".//tisdagratt{idx}rubrik").text, "text": tree.find(f".//tisdagratt{idx}text").text})
+            if not tree.find(f".//onsdagratt{idx}rubrik") is None:
+                self.wednesday.append({"rubrik": tree.find(f".//onsdagratt{idx}rubrik").text, "text": tree.find(f".//onsdagratt{idx}text").text})
+            if not tree.find(f".//torsdagratt{idx}rubrik") is None:
+                self.thursday.append({"rubrik": tree.find(f".//torsdagratt{idx}rubrik").text, "text": tree.find(f".//torsdagratt{idx}text").text})
+            if not tree.find(f".//fredagratt{idx}rubrik") is None:
+                self.friday.append({"rubrik": tree.find(f".//fredagratt{idx}rubrik").text, "text": tree.find(f".//fredagratt{idx}text").text})
+
+        dagens["week"] = self.week
+        dagens["monday"] = self.monday
+        dagens["tuesday"] = self.tuesday
+        dagens["wednesday"] = self.wednesday
+        dagens["thursday"] = self.thursday
+        dagens["friday"] = self.friday
+        return dagens
+
+    def parse(self, response):
+        scripts = response.xpath("//script[not (@id) and not (@src) and not (@class)]/text()").getall()
+        url = ""
+        dagens = DagensLunchHeat()
+        dagens["place"] = "Heat Kopparlunden"
+        dagens["scraped_by"] = f"{self.__class__.__name__}"
+        for js in scripts:
+            if not "jQuery(function( $ ){" in js:
+                continue
+            js = js.split("\n")
+            for line in js:
+                line = line.strip()
+                if "url:\"https://castit.nu/xml" in line:
+                    url = line[5:-2]
+        yield scrapy.Request(url, callback=self.extract_xml, meta={"dagens": dagens})
+        dagens["scraped_at"] = f"{datetime.now().isoformat()}"
+
+        return dagens

dagens_lunch/spiders/malmens.py

@@ -0,0 +1,42 @@
+from datetime import datetime
+import scrapy
+from ..items import DagensLunchMalmens
+
+class MalmensSpider(scrapy.Spider):
+    name = "malmens"
+    allowed_domains = ["gastrogate.com"]
+    start_urls = ["https://malmens.gastrogate.com/lunchbuffe/"]
+
+    def parse(self, response):
+        tbodys = response.xpath("//table[contains(@class, 'lunch_menu')]/tbody")
+        self.monday = []
+        self.tuesday = []
+        self.wednesday = []
+        self.thursday = []
+        self.friday = []
+
+        for idx, body in enumerate(tbodys):
+            for food in body.xpath("./tr/td[contains(@class, 'td_title')]/text()").getall():
+                if idx == 0 and food.strip() != "":
+                    self.monday.append(food.strip())
+                elif idx == 1 and food.strip() != "":
+                    self.tuesday.append(food.strip())
+                elif idx == 2 and food.strip() != "":
+                    self.wednesday.append(food.strip())
+                elif idx == 3 and food.strip() != "":
+                    self.thursday.append(food.strip())
+                elif idx == 4 and food.strip() != "":
+                    self.friday.append(food.strip())
+        
+        dagens = DagensLunchMalmens()
+        dagens["place"] = "Malmens"
+        dagens["week"] = response.xpath("//a[contains(@class, 'dropdown-toggle')]/text()").get().strip()
+        dagens["monday"] = self.monday
+        dagens["tuesday"] = self.tuesday
+        dagens["wednesday"] = self.wednesday
+        dagens["thursday"] = self.thursday
+        dagens["friday"] = self.friday
+        dagens["scraped_by"] = self.__class__.__name__
+        dagens["scraped_at"] = f"{datetime.now().isoformat()}"
+
+        return dagens

dagens_lunch/spiders/valsaren.py

@@ -0,0 +1,140 @@
+from io import BytesIO
+from pathlib import Path
+from datetime import datetime
+import chompjs
+import re
+from PyPDF2 import PdfReader
+import scrapy
+from ..items import DagensLunchValsaren
+
+
+class ValsarenSpider(scrapy.Spider):
+    name = "valsaren"
+    allowed_domains = ["valsaren.se", "misssite.com", "files.builder.misssite.com"]
+    start_urls = ["https://valsaren.se/maten"]
+
+    def __init__(self, name = None, **kwargs):
+        super().__init__(name, **kwargs)
+        self.week = ""
+        self.days = []
+        self.klassiker = ""
+        self.alltid = ""
+        self.price = ""
+        self.price_takeaway = ""
+
+    def get_menu_url(self, script):
+        sp = dict()
+        for line in script.split("\n"):
+            l = line.strip()
+            if l.startswith("Server.comp"):
+                sp = chompjs.parse_js_object(l)
+                break
+        
+        for obj in sp.keys():
+            if "data" in sp[obj].keys():
+                if isinstance(sp[obj]["data"], dict):
+                    if "url" in sp[obj]["data"].keys() and "fileName" in sp[obj]["data"].keys():
+                        if sp[obj]["data"]["fileName"].lower().endswith(".pdf"):
+                            return sp[obj]["data"]["url"]
+        return None
+    
+    def get_menu(self, response):
+        yield scrapy.Request(response, callback=self.extract_menu)
+    
+    def extract_menu(self, response):
+        dagens = response.meta.get("dagens")
+        reader = PdfReader(BytesIO(response.body))
+        all_text = reader.pages[0].extract_text().split("\n")
+        dagens["week"] = all_text.pop(0).strip()
+        words = ["VECKANS KLASSIKER", "ALLTID PÅ VALSAREN"]
+        current = 0
+        jump_over = False
+        days = []
+        klassiker = ""
+        alltid = ""
+        for idx, t in enumerate(all_text):
+            if jump_over:
+                jump_over = False
+                continue
+
+            if current == 0b1000:
+                if words[0] in t:
+                    days.append(t.replace(words[0], ""))
+                    current = 0b10
+                elif words[1] in t:
+                    days.append(t.replace(words[1], ""))
+                    current = 0b100
+                else:
+                    if t.endswith(","):
+                        days.append(" ".join([all_text[idx], all_text[idx+1]]))
+                        jump_over = True
+                    else:
+                        days.append(t)
+                    current = 0
+
+            elif current == 0b100:
+                if t.endswith(","):
+                    alltid = " ".join([all_text[idx], all_text[idx+1]])
+                    jump_over = True
+                else:
+                    alltid = t
+                current = 0
+
+            elif current == 0b10:
+                if t.endswith(","):
+                    klassiker = " ".join([all_text[idx], all_text[idx+1]])
+                    jump_over = True
+                else:
+                    klassiker = t
+                current = 0
+
+            if words[0] in t:
+                current = 0b10
+            elif words[1] in t:
+                current = 0b100
+            elif "måndag" in t.lower():
+                current = 0b1000
+            elif "tisdag" in t.lower():
+                current = 0b1000
+            elif "onsdag" in t.lower():
+                current = 0b1000
+            elif "torsdag" in t.lower():
+                current = 0b1000
+            elif "fredag" in t.lower():
+                current = 0b1000
+            else:
+                current = 0
+
+        dagens["alltid"] = re.sub(r'(& )(\w)( )', r"\1\2", alltid)
+        dagens["klassiker"] = re.sub(r'(& )(\w)( )', r"\1\2", klassiker)
+        dagens["monday"] = re.sub(r'(& )(\w)( )', r"\1\2", days[0])
+        dagens["tuesday"] = re.sub(r'(& )(\w)( )', r"\1\2", days[1])
+        dagens["wednesday"] = re.sub(r'(& )(\w)( )', r"\1\2", days[2])
+        dagens["thursday"] = re.sub(r'(& )(\w)( )', r"\1\2", days[3])
+        dagens["friday"] = re.sub(r'(& )(\w)( )', r"\1\2", days[4])
+        return dagens
+
+    def parse(self, response):
+        SECTION_UUID = "Wr8Wn2H9iFvL7hh"
+        section = response.selector.xpath(f"//section[contains(@data-uniqueid, '{SECTION_UUID}')]")
+        p = section.xpath("//p[contains(@class, 'contentgroup__body')]/text()").getall()
+        dagens = DagensLunchValsaren()
+        dagens["price"] = int(p.pop(0).strip().replace(" kr", "").split(" ")[-1])
+        dagens["price_takeaway"] = int(p.pop(0).strip().replace(" kr", "").split(" ")[-1])
+        js_scripts = response.xpath("//script[contains(@nonce, '')]/text()").getall()
+        menu_url = self.get_menu_url(js_scripts[4])
+        if menu_url is None:
+            for x in js_scripts:
+                url = self.get_menu_url(x)
+                if not url is None:
+                    menu_url = url
+                    break
+        if menu_url is None:
+            raise ValueError("could not get menu.")
+        
+        #response.follow(menu_url, callback=self.extract_menu)
+        yield scrapy.Request(menu_url, callback=self.extract_menu, meta={"dagens": dagens})
+        dagens["place"] = "Valsaren - Hotell & Kök"
+        dagens["scraped_by"] = self.__class__.__name__
+        dagens["scraped_at"] = f"{datetime.now().isoformat()}"
+        return dagens

scrapy.cfg

@@ -0,0 +1,12 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = dagens_lunch.settings
+ROBOTSTXT_OBEY = False
+
+[deploy]
+#url = http://localhost:6800/
+project = dagens_lunch