created a varda spider

2025-02-23 05:27:05 +01:00 · 2025-02-23 05:27:05 +01:00 · 36312daf87
commit 36312daf87
parent cfcb7742e0
1 changed files with 87 additions and 0 deletions
--- a/dagens_lunch/spiders/varda.py
+++ b/dagens_lunch/spiders/varda.py
@ -0,0 +1,87 @@
+import scrapy
+from io import BytesIO
+from PyPDF2 import PdfReader
+from ..items import DagensLunchVarda
+
+class VardaSpider(scrapy.Spider):
+    name = "varda"
+    allowed_domains = ["restaurangvarda.se"]
+    start_urls = ["https://restaurangvarda.se"]
+
+    def extract_pdf(self, response):
+        dagens = response.meta.get("dagens")
+        reader = PdfReader(BytesIO(response.body))
+        all_text = reader.pages[0].extract_text().split("  ")
+        days = []
+        day_price = []
+        is_pasta = False
+        for text in all_text:
+            if text.lower().startswith("lunchmeny"):
+                dagens["about"] = text
+            elif (text.lower().startswith("måndag") or text.lower().startswith("tisdag") or text.lower().startswith("onsdag") or
+                text.lower().startswith("torsdag") or text.lower().startswith("fredag")):
+                s = text.split(':-')
+                d, p = self.get_days(s[0])
+                print(d)
+                for i in range(0, d+1):
+                    days.append(s[1])
+                    day_price.append(p)
+            elif "fisken" in text.lower():
+                s = text.split(":-")
+                dagens["fish"] = f"{s[1].strip()} ({s[0].split(" ")[-1].strip()})"
+            elif "gröna" in text.lower():
+                s = text.split(":-")
+                dagens["green"] = f"{s[1].strip()} ({s[0].split(" ")[-1].strip()}kr)"
+            elif text.lower() == "pasta":
+                is_pasta = True
+            elif "pasta" in text.lower() or is_pasta:
+                is_pasta = False
+                pasta, salad = text.split("SALLAD")
+                sallad_price, salad = salad.split(":-")
+                dagens["salad"] = f"{salad.strip()} ({sallad_price.strip()}kr)"
+                dagens["pasta"] = [f"{x.strip().replace(":-", "kr")}" for x in list(filter(None, pasta.strip().split("*")))]
+            elif "burgare" in text.lower():
+                s = text.split(":-")
+                dagens["burger"] = [f"{x.strip()} ({s[0].split(" ")[-1].strip()}kr)" for x in list(filter(None, s[1].split("*")))]
+            elif "alltid" in text.lower():
+                s = text.split(":-")
+                dagens["always"] = f"{s[2].strip()} (hel: {s[1].split(" ")[-1]}kr / halv: {s[0].split(" ")[-1]}kr)"
+            elif "grillat" in text.lower():
+                s = text.split(":-")
+                dagens["bbq"] = f"{s[1].strip()} ({s[0].split(" ")[-1].strip()}kr)"
+        dagens["monday"] = f"{days[0].strip()} ({day_price[0].strip()}kr)"
+        dagens["tuesday"] = f"{days[1].strip()} ({day_price[1].strip()}kr)"
+        dagens["wednesday"] = f"{days[2].strip()} ({day_price[2].strip()}kr)"
+        dagens["thursday"] = f"{days[3].strip()} ({day_price[3].strip()}kr)"
+        dagens["friday"] = f"{days[4].strip()} ({day_price[4].strip()}kr)"
+        return dagens
+    
+    def get_days(self, string):
+        days = ["måndag", "tisdag", "onsdag", "torsdag", "fredag"]
+        if "–" in string:
+            s = string.split(" ")
+            price = s[3].strip()
+            try:
+                first = days.index(s[0].strip().lower().decode())
+            except AttributeError:
+                first = days.index(s[0].strip().lower())
+
+            try:
+                second = days.index(s[2].strip().lower().decode())
+            except AttributeError:
+                second = days.index(s[2].strip().lower())
+
+            many_days = second - first
+            return (many_days, price)
+        return (0, string.split(" ")[-1])
+
+    def parse(self, response):
+        lunch_url = ""
+        for url in response.xpath("//a[contains(@class, 'elementor-sub-item')]/@href").getall():
+            if "Lunchmenyn" in url:
+                lunch_url = url
+                break
+        dagens = DagensLunchVarda()
+        dagens["place"] = "Varda"
+        yield scrapy.Request(lunch_url, callback=self.extract_pdf, meta={"dagens": dagens})
+        return dagens