Convert ticket v3 HTML to JSON tickets

lidlplus/api.py

@@ -7,6 +7,7 @@
 import logging
 import re
 from datetime import datetime, timedelta
+from json import JSONDecodeError
 
 import requests
 
@@ -16,6 +17,7 @@
     LegalTermsException,
     MissingLogin,
 )
+from lidlplus.html_receipt import parse_html_receipt
 
 try:
     from getuseragent import UserAgent
@@ -39,7 +41,7 @@ class LidlPlusApi:
 
     _CLIENT_ID = "LidlPlusNativeClient"
     _AUTH_API = "https://accounts.lidl.com"
-    _TICKET_API = "https://tickets.lidlplus.com/api/v2"
+    _TICKET_API = "https://tickets.lidlplus.com/api"
     _COUPONS_API = "https://coupons.lidlplus.com/api"
     _COUPONS_V1_API = "https://coupons.lidlplus.com/app/api/"
     _PROFILE_API = "https://profile.lidlplus.com/profile/api"
@@ -257,7 +259,7 @@ def tickets(self, only_favorite=False):
             If set to False (the default), all tickets will be retrieved.
         :type onlyFavorite: bool
         """
-        url = f"{self._TICKET_API}/{self._country}/tickets"
+        url = f"{self._TICKET_API}/v2/{self._country}/tickets"
         kwargs = {"headers": self._default_headers(), "timeout": self._TIMEOUT}
         ticket = requests.get(f"{url}?pageNumber=1&onlyFavorite={only_favorite}", **kwargs).json()
         tickets = ticket["tickets"]
@@ -268,8 +270,16 @@ def tickets(self, only_favorite=False):
     def ticket(self, ticket_id):
         """Get full data of single ticket by id"""
         kwargs = {"headers": self._default_headers(), "timeout": self._TIMEOUT}
-        url = f"{self._TICKET_API}/{self._country}/tickets"
-        return requests.get(f"{url}/{ticket_id}", **kwargs).json()
+        url = f"{self._TICKET_API}/v2/{self._country}/tickets/{ticket_id}"
+        try:
+            return requests.get(url, **kwargs).json()
+        except JSONDecodeError:
+            url = f"{self._TICKET_API}/v3/{self._country}/tickets/{ticket_id}"
+            receipt_json = requests.get(url, **kwargs).json()
+            return parse_html_receipt(
+                date=receipt_json["date"],
+                html_receipt=receipt_json["htmlPrintedReceipt"],
+            )
 
     def coupon_promotions_v1(self):
         """Get list of all coupons API V1"""

lidlplus/html_receipt.py

@@ -0,0 +1,65 @@
+from typing import Any
+import re
+
+import lxml.html as html
+
+
+VAT_TYPE_LINE_ENDING_PATTERN = re.compile(r" [A-Z]$")
+
+
+def parse_html_receipt(date: str, html_receipt: str) -> dict[str, Any]:
+    dom = html.document_fromstring(html_receipt)
+
+    receipt = {
+        "date": date,
+        "itemsLine": [],
+    }
+    for node in dom.xpath(r".//span[starts-with(@id, 'purchase_list_line_')]"):
+        if "class" not in node.attrib:
+            if not VAT_TYPE_LINE_ENDING_PATTERN.search(node.text):
+                continue
+
+            *name_parts, price = node.text[:-2].split()
+            receipt["itemsLine"].append(
+                {
+                    "name": " ".join(name_parts),
+                    "originalAmount": price,
+                    "isWeight": True,
+                    "discounts": [],
+                }
+            )
+        elif node.attrib["class"] == "currency":
+            receipt["currency"] = {"code": node.text.strip(), "symbol": node.attrib["data-currency"]}
+        elif node.attrib["class"] == "article":
+            if node.text.startswith(" "):
+                continue
+
+            quantity_text = node.get("data-art-quantity")
+            if quantity_text is None:
+                is_weight = False
+                quantity = 1
+            elif "," in quantity_text:
+                is_weight = True
+                quantity = quantity_text
+            else:
+                is_weight = False
+                quantity = quantity_text
+
+            receipt["itemsLine"].append(
+                {
+                    "name": node.attrib["data-art-description"],
+                    "currentUnitPrice": node.attrib["data-unit-price"],
+                    "isWeight": is_weight,
+                    "quantity": quantity,
+                    "discounts": [],
+                }
+            )
+        elif node.attrib["class"] == "discount":
+            discount = abs(parse_float(node.text.split()[-1]))
+            receipt["itemsLine"][-1]["discounts"].append({"amount": str(discount).replace(".", ",")})
+
+    return receipt
+
+
+def parse_float(text: str) -> float:
+    return float(text.replace(",", "."))

requirements.txt

@@ -3,4 +3,5 @@ oic>=1.4.0
 requests>=2.28.1
 selenium-wire>=5.1.0
 webdriver-manager>=3.8.5
-blinker==1.7.0
+blinker==1.7.0
+lxml>=5.3.0