skrypt do scrapowania tresci z lokalnej strony mayo

backend/mayo/mayo1.py

@@ -0,0 +1,127 @@
+from bs4 import BeautifulSoup
+
+def clean(text):
+    return " ".join(text.split())
+
+def parse_html(path):
+    with open(path, encoding="ISO-8859-2") as f:
+        soup = BeautifulSoup(f, "html.parser")
+
+    tresc = soup.find("div", id="tresc")
+
+    result = {
+        "meta": {},
+        "sections": {}
+    }
+
+    # -----------------------
+    # 🔹 1. META (LEPSZE)
+    # -----------------------
+
+    # 👉 Dot. zam.
+    first_table = tresc.find("table")
+
+    if first_table:
+        b_tags = first_table.find_all("b")
+        print(first_table.getText())
+
+        if len(b_tags) >= 2:
+            result["meta"]["nr_zamownia"] = clean(b_tags[1].get_text())
+            result["meta"]["realizacja"] = clean(b_tags[3].get_text())
+        
+        client = first_table.find('span', attrs={'style': "font-weight:bold;"} )
+        if client:
+            print(client.get_text())
+
+
+    # 👉 formularz (Model, Odbiorca itd.)
+    form_table = tresc.find("form")
+
+    if form_table:
+        table = form_table.find_parent("table")
+
+        if table:
+            # 🔥 przeszukujemy CAŁĄ tabelę (wszystkie tr)
+            # Model
+            model_input = table.find("input", {"name": "s_nr_kat"})
+            if model_input:
+                result["meta"]["Model"] = clean(model_input.get("value", ""))
+
+            # Odbiorca
+            odb_input = table.find("input", {"name": "s_odbiorca"})
+            if odb_input:
+                result["meta"]["Odbiorca"] = clean(odb_input.get("value", ""))
+
+            # Grupa
+            grupa_select = table.find("select", {"name": "s_grupa"})
+            if grupa_select:
+                selected = grupa_select.find("option", selected=True)
+                if selected:
+                    result["meta"]["Grupa"] = clean(selected.get_text())
+
+    # -----------------------
+    # 🔹 2. SEKCJE (SZYJKA itd.)
+    # -----------------------
+    current_section = None
+
+    for tr in tresc.find_all("tr"):
+        tds = tr.find_all("td")
+
+        if not tds:
+            continue
+
+        # 🔸 Sekcja (np. SZYJKA)
+        if len(tds) == 1:
+            text = clean(tds[0].get_text())
+
+            if text.isupper() and len(text) < 40:
+                current_section = text
+                result["sections"][current_section] = {}
+                continue
+
+        # 🔸 Element w sekcji
+        if len(tds) >= 2 and current_section:
+            key_tag = tds[0].find("b")
+
+            if not key_tag:
+                continue
+
+            key = clean(key_tag.get_text())
+
+            # usuń linki / śmieci
+            key = key.replace("\xa0", "").strip()
+
+            value_td = tds[1]
+
+            # zbierz wszystkie teksty (ignorując "Notatka")
+            texts = []
+
+            for x in value_td.stripped_strings:
+                if "Notatka" in x:
+                    continue
+                texts.append(x)
+
+            value = clean(" ".join(texts))
+
+            if key:
+                result["sections"][current_section][key] = value
+
+    return result
+
+import time
+
+start = time.perf_counter()
+
+data = parse_html("g.htm")
+
+end = time.perf_counter()
+
+print(f"Czas wykonania: {end - start:.6f} sekund")
+
+# from pprint import pprint
+# pprint(data)
+
+import json
+
+with open("output.json", "w", encoding="utf-8") as f:
+    json.dump(data, f, indent=2, ensure_ascii=False)

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)