.gitignore

@@ -1,3 +1,4 @@
 .vscode
+latest
 dagens_lunch/spiders/__pycache__/*.pyc
-dagens_lunch/__pycache__/*.pyc
+dagens_lunch/__pycache__/*.pyc

dagens_lunch/items.py

@@ -42,3 +42,13 @@ class DagensLunchMalmens(scrapy.Item):
     friday = scrapy.Field()
     scraped_by = scrapy.Field()
     scraped_at = scrapy.Field()
+
+class DagensLunchMax(scrapy.Item):
+    place = 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/settings.py

@@ -89,4 +89,12 @@ ROBOTSTXT_OBEY = False
 
 # Set settings whose default value is deprecated to a future-proof value
 TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+FEEDS = {
+    "items.json": {
+        "format": "json",
+        "encoding": "utf8"
+    }
+}
 FEED_EXPORT_ENCODING = "utf-8"
+
+LOG_ENABLED = False

dagens_lunch/spiders/max.py

@@ -0,0 +1,24 @@
+from datetime import datetime
+import scrapy
+from ..items import DagensLunchMax
+
+class MaxSpider(scrapy.Spider):
+    name = "max"
+    allowed_domains = ["max.se"]
+    start_urls = ["https://max.se/maten/meny/maltider/dagens-lunch/"]
+
+    def parse(self, response):
+        days = []
+        lista = response.xpath("//div/div[2]/div[contains(@class, 'o-product-info')]/ul[contains(@class, 'o-product-info__variations')]")
+        for li in lista.xpath("./li/text()").getall():
+            days.append(li.split(" ")[-1])
+        return DagensLunchMax(
+            place="Max",
+            monday=days[0],
+            tuesday=days[1],
+            wednesday=days[2],
+            thursday=days[3],
+            friday=days[4],
+            scraped_by=self.__class__.__name__,
+            scraped_at=f"{datetime.now().isoformat()}"
+        )

run_spiders.py

@@ -0,0 +1,89 @@
+import pathlib
+import json
+
+from scrapy import spiderloader
+from scrapy import signals
+from scrapy.crawler import CrawlerProcess
+from scrapy.signalmanager import dispatcher
+from scrapy.utils.project import get_project_settings
+
+dir = pathlib.Path(__file__).resolve().parent
+dir = dir / "latest"
+file = dir / "all.json"
+valsaren_file = dir / "valsaren.json"
+malmens_file = dir / "malmens.json"
+heat_file = dir / "heat.json"
+max_file = dir / "max.json"
+
+def dagens_lunch_results():
+    results = []
+    settings = get_project_settings()
+    process = CrawlerProcess(settings)
+    spider_loader = spiderloader.SpiderLoader.from_settings(settings)
+
+    def crawler_results(signal, sender, item, response, spider):
+        results.append(item)
+        print(f"{spider.name} is done!")
+
+
+    if file.is_file() and file.exists():
+        print(f"removing {file.name}")
+        file.unlink()
+    if valsaren_file.is_file and valsaren_file.exists():
+        print(f"removing {valsaren_file.name}")
+        valsaren_file.unlink()
+    if malmens_file.is_file() and malmens_file.exists():
+        print(f"removing {malmens_file.name}")
+        malmens_file.unlink()
+    if heat_file.is_file and heat_file.exists():
+        print(f"removing {heat_file.name}")
+        heat_file.unlink()
+    if max_file.is_file() and max_file.exists():
+        print(f"removing {max_file.name}")
+        max_file.unlink()
+
+    dispatcher.connect(crawler_results, signal=signals.item_scraped)
+
+    for spider_name in spider_loader.list():
+        print(f"getting menu from {spider_name}")
+        process.crawl(spider_name)
+
+    process.start()
+    return results
+
+if __name__ == "__main__":
+    _valsaren = None
+    _malmens = None
+    _heat = None
+    _max = None
+    res = dagens_lunch_results()
+    with file.open("a") as f:
+        f.write("[\n")
+        for idx, item in enumerate(res):
+            if idx > 0:
+                f.write(",")
+            f.write(json.dumps(dict(item), indent=4))
+            if item["place"].split(" ")[0].lower() == "valsaren":
+                _valsaren = json.dumps(dict(item))
+            elif item["place"].split(" ")[0].lower() == "malmens":
+                _malmens = json.dumps(dict(item))
+            elif item["place"].split(" ")[0].lower() == "heat":
+                _heat = json.dumps(dict(item))
+            elif item["place"].split(" ")[0].lower() == "max":
+                _max = json.dumps(dict(item))
+            elif item["place"].split(" ")[0].lower() == "unknown":
+                print(f"please learn me more about {item['place']}")
+        f.write("\n]")
+    print(f"created: {file}")
+
+    valsaren_file.write_text(_valsaren)
+    print(f"created: {valsaren_file}")
+
+    malmens_file.write_text(_malmens)
+    print(f"created: {malmens_file}")
+
+    heat_file.write_text(_heat)
+    print(f"created: {heat_file}")
+
+    max_file.write_text(_max)
+    print(f"created: {max_file}")