skrypt do scrapowania tresci z lokalnej strony mayo

backend/mayo/mayo_session.py

@@ -0,0 +1,176 @@
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin
+import re
+import logging
+from pprint import pprint
+
+class MayoSession:
+    def __init__(self, base_url, login, password, db="1"):
+        """
+        base_url: np. 'http://192.168.0.152/mayo2'
+        login, password: dane logowania
+        db: numer bazy (np. "1" = Mayones 2)
+        """
+        self.session = requests.Session()
+        self.base_url = base_url
+        self.login_url = f"{self.base_url}/login.php"
+        self.credentials = {
+            "login": login,
+            "pass": password,
+            "baza": db
+        }
+
+    def login(self):
+        """Loguje się do systemu lokalnego."""
+        r = self.session.post(self.login_url, data=self.credentials)
+        if "Zaloguj się" in r.text or "login" in r.url:
+            raise Exception("Nie udało się zalogować do Mayo.")
+        logging.info("✅ Zalogowano poprawnie do systemu Mayo.")
+
+    def ensure_logged_in(self):
+        test_url = f"{self.base_url}/index.php"
+
+        r = self.session.get(test_url)
+
+        if "Wyloguj" not in r.text:
+            logging.info("🔐 Sesja wygasła — loguję ponownie...")
+            self.login()
+
+    def get_order_page(self, url):
+        self.ensure_logged_in()
+
+        r = self.session.get(url)
+
+        if "login" in r.url or "Zaloguj" in r.text:
+            self.login()
+            r = self.session.get(url)
+
+        return r.text
+    
+    def search_order(self, order_number):
+        self.ensure_logged_in()
+
+        url = f"{self.base_url}/index.php?filtr=1&strona=0&sort_order=1"
+
+        payload = {
+            "zaw": "",
+            "r_od": "",
+            "nr_zam": str(order_number).zfill(4),  # 🔥 ważne
+            "typ_kl": "",
+            "klient": "",
+            "r_do": "",
+            "row_count": "25"
+        }
+
+        # headers = {
+        #     "Content-Type": "application/x-www-form-urlencoded",
+        #     "Referer": f"{self.base_url}/index.php",
+        #     "Origin": self.base_url
+        # }
+
+        r = self.session.post(url, data=payload)
+
+        # 🔥 fallback jeśli sesja padła w trakcie
+        if "login" in r.url or "Zaloguj" in r.text:
+            logging.warning("⚠️ Sesja padła — ponawiam logowanie...")
+            self.login()
+            r = self.session.post(url, data=payload)
+
+        return r.text
+
+
+    def parse_search_results(self, html):
+        soup = BeautifulSoup(html, "html.parser")
+
+        results = []
+
+        # tabela wyników
+        table = soup.find("table", class_="std2")
+
+        if not table:
+            return results
+
+        # rows = table.find_all("tr")
+        tbody = table.find("tbody")
+        rows = tbody.find_all("tr") if tbody else table.find_all("tr")
+
+        for row in rows:
+            tds = row.find_all("td")
+
+            # pomijamy header / dziwne wiersze
+            if len(tds) < 3:
+                continue
+
+            link_tag = tds[0].find("a")
+
+            if not link_tag:
+                continue
+
+            # 🔹 order_id
+            order_id = link_tag.get_text(strip=True)
+
+            # 🔹 url (pełny)
+            relative_url = link_tag.get("href")
+            # full_url = urljoin(self.base_url, relative_url)
+            full_url = f"{self.base_url}/{relative_url}"
+
+            # 🔹 prod_list
+            prod_list = tds[1].get_text(strip=True).replace("\xa0", "")
+
+            # 🔹 client
+            client = tds[2].get_text(strip=True)
+
+            results.append({
+                "order_id": order_id,
+                "client": client,
+                "prod_list": prod_list,
+                "url": full_url,
+                "guitars_url": []
+            })
+
+        return results
+    
+    def parse_order_list(self, html):
+        soup = BeautifulSoup(html, "html.parser")
+
+        results = []
+
+        # tabela wyników
+        table = soup.find("table", class_="std2")
+
+        if not table:
+            return results
+
+        # rows = table.find_all("tr")
+        tbody = table.find("tbody")
+        rows = tbody.find_all("tr") if tbody else table.find_all("tr")
+
+        for row in rows:
+            links = row.find_all("a", href=True)
+
+            for link in links:
+                relative_url = link.get("href")
+
+                if "id_zestawu=" in relative_url:
+                    full_url = f"{self.base_url}/{relative_url}"
+                    results.append(full_url)
+                    break  # jeden link na wiersz
+
+        return results
+    
+
+if __name__ == "__main__" :
+    mayo = MayoSession("http://10.8.0.6/mayo2", "nowakb", "def")
+    req = mayo.search_order("0027")
+
+    orders = mayo.parse_search_results(req)
+    pprint(orders)
+
+    for order in orders:
+        html = mayo.get_order_page(order["url"])
+        guitars = mayo.parse_order_list(html)
+        order["guitars_url"] = guitars
+    
+    print("---------------")
+    pprint(orders)