.

il_supermarket_scarper/scrappers/hazihinam.py

@@ -1,14 +1,76 @@
-from il_supermarket_scarper.engines import Cerberus
-from il_supermarket_scarper.utils import DumpFolderNames
+import urllib.parse
+import datetime
+from il_supermarket_scarper.engines import MultiPageWeb
+from il_supermarket_scarper.utils import DumpFolderNames, FileTypesFilters
 
+# class HaziHinam(Cerberus):
+#     """scrper fro hazi hinam"""
 
-class HaziHinam(Cerberus):
+#     def __init__(self, folder_name=None):
+#         super().__init__(
+#             chain=DumpFolderNames.HAZI_HINAM,
+#             chain_id="7290700100008",
+#             folder_name=folder_name,
+#             ftp_username="HaziHinam",
+#         )
+
+
+class HaziHinam(MultiPageWeb):
     """scrper fro hazi hinam"""
 
     def __init__(self, folder_name=None):
         super().__init__(
             chain=DumpFolderNames.HAZI_HINAM,
             chain_id="7290700100008",
+            url="https://shop.hazi-hinam.co.il/Prices",
             folder_name=folder_name,
-            ftp_username="HaziHinam",
+            total_page_xpath="(//li[contains(concat(' ', normalize-space(@class), ' '),"
+            + "' pagination-item ')])[last()]/a/@href",
+            total_pages_pattern=r"\d+",
+            page_argument="&p",
         )
+
+    def collect_files_details_from_page(self, html):
+        """collect the details deom one page"""
+        links = []
+        filenames = []
+        for link in html.xpath("//table/tbody/tr"):
+            links.append(link.xpath("td[5]/a/@href")[0])
+            filenames.append(link.xpath("td[2]")[0].text.strip() + ".xml.gz")
+        return links, filenames
+
+    def get_file_types_id(self, files_types=None):
+        """get the file type id"""
+        if files_types is None or files_types == FileTypesFilters.all_types():
+            return [{"t": "null", "f": "null"}]
+
+        types = []
+        for ftype in files_types:
+            if ftype == FileTypesFilters.STORE_FILE.name:
+                types.append({"t": "3", "f": "null"})
+            if ftype == FileTypesFilters.PRICE_FILE.name:
+                types.append({"t": "1", "f": "null"})
+            if ftype == FileTypesFilters.PROMO_FILE.name:
+                types.append({"t": "2", "f": "null"})
+            if ftype == FileTypesFilters.PRICE_FULL_FILE.name:
+                types.append({"t": "1", "f": "null"})
+            if ftype == FileTypesFilters.PROMO_FULL_FILE.name:
+                types.append({"t": "2", "f": "null"})
+        return types
+
+    def build_params(self, files_types=None, store_id=None, when_date=None):
+        """build the params for the request"""
+
+        all_params = []
+        for type_params in self.get_file_types_id(files_types):
+            params = {"d": "", "s": ""}
+
+            if store_id:
+                params["s"] = "null"
+            if when_date and isinstance(when_date, datetime.datetime):
+                params["d"] = when_date.strftime("%Y-%m-%d")
+            if files_types:
+                params = {**params, **type_params}
+            all_params.append(params)
+
+        return ["?" + urllib.parse.urlencode(params) for params in all_params]

il_supermarket_scarper/scrappers/tests/test_all.py

@@ -44,7 +44,7 @@ class GoodPharmTestCase(make_test_case(ScraperFactory.GOOD_PHARM, 952)):
     """Test case for ScraperFactory.GOOD_PHARM."""
 
 
-class HaziHinamTestCase(make_test_case(ScraperFactory.HAZI_HINAM, 2)):
+class HaziHinamTestCase(make_test_case(ScraperFactory.HAZI_HINAM, 206)):
     """Test case for ScraperFactory.HAZI_HINAM."""
 
 

tests/test_integration.py

@@ -29,4 +29,4 @@ def test_scrapers_are_updated():
 def test_update_date():
     """test date the site update"""
     date = get_status_date()
-    assert date.date() == datetime.datetime(2024, 10, 28).date(), "gov il site changed"
+    assert date.date() == datetime.datetime(2024, 11, 19).date(), "gov il site changed"