From 27fcbc379bd21c25acf13754597b884c16e53e78 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bal=C3=A1zs=20Toldi?= <balazs.a.toldi@ericsson.com>
Date: Wed, 16 Jul 2025 15:00:48 +0200
Subject: [PATCH] Refactor

---
 main.py                              |  6 ------
 pyproject.toml                       |  5 +++++
 run.py                               | 16 ++++++++++------
 src/scraper/__init__.py              |  4 ++++
 scraper.py => src/scraper/scraper.py |  8 +++++++-
 5 files changed, 26 insertions(+), 13 deletions(-)
 delete mode 100644 main.py
 create mode 100644 src/scraper/__init__.py
 rename scraper.py => src/scraper/scraper.py (92%)

diff --git a/main.py b/main.py
deleted file mode 100644
index 95a905c..0000000
--- a/main.py
+++ /dev/null
@@ -1,6 +0,0 @@
-def main():
-    print("Hello from hardverapro-mcp!")
-
-
-if __name__ == "__main__":
-    main()
diff --git a/pyproject.toml b/pyproject.toml
index 3fad2c9..3712d93 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -9,3 +9,8 @@ dependencies = [
     "gradio[mcp]>=5.34.2",
     "requests>=2.32.4",
 ]
+[tool.setuptools.package-dir]
+"scraper" = "src/scraper"
+
+[project.scripts]
+run-scraper = "run:main"
\ No newline at end of file
diff --git a/run.py b/run.py
index 5746810..181c3ca 100644
--- a/run.py
+++ b/run.py
@@ -1,4 +1,10 @@
-import scraper
+import sys
+from pathlib import Path
+
+# Add the src directory to Python path
+sys.path.append(str(Path(__file__).parent / "src"))
+
+from scraper import categories, search, fetch
 import gradio as gr
 
 def hardverapro_search(query: str,offset: int = 0, category: str = "All")-> list:
@@ -16,7 +22,7 @@ def hardverapro_search(query: str,offset: int = 0, category: str = "All")-> list
             - 'price' (str): The price listed
             - 'link' (str): A full URL to the listing
     """
-    raw = scraper.search(query,offset=offset,category=category)
+    raw = search(query,offset=offset,category=category)
     return [[r["title"], r["price"], r["link"]] for r in raw]
 
 def hardverapro_fetch(url: str) -> dict:
@@ -32,7 +38,7 @@ def hardverapro_fetch(url: str) -> dict:
             - 'description' (str): The description of the listing
             - 'img' (str): A full URL to the image
     """
-    return scraper.fetch(url)
+    return fetch(url)
 
 
 
@@ -41,7 +47,7 @@ iface_search = gr.Interface(
     inputs=[
         gr.Textbox(label="Search query"),
         gr.Number(label="Offset (e.g. 100, 200)", value=0),
-        gr.Dropdown(choices=scraper.categories, value="All"),
+        gr.Dropdown(choices=categories, value="All"),
         ],
     outputs=gr.Dataframe(headers=["title", "price", "link"], type="array"),
     title="HardverApró Search"
@@ -61,8 +67,6 @@ tabbed_interface = gr.TabbedInterface(
 
 
 def main():
-    #scraper.fetch("https://hardverapro.hu/apro/sff_2_5_10k_15k_sas_hdd-k_1_2tb-ig/friss.html")
-    #iface.launch(mcp_server=True)
     tabbed_interface.launch(mcp_server=True)
 
 if __name__ == "__main__":
diff --git a/src/scraper/__init__.py b/src/scraper/__init__.py
new file mode 100644
index 0000000..48085c4
--- /dev/null
+++ b/src/scraper/__init__.py
@@ -0,0 +1,4 @@
+__version__ = "1.0.0"
+from .scraper import categories, search, fetch
+
+__all__ = ["fetch", "search", "categories"]
\ No newline at end of file
diff --git a/scraper.py b/src/scraper/scraper.py
similarity index 92%
rename from scraper.py
rename to src/scraper/scraper.py
index 515956b..b58efb4 100644
--- a/scraper.py
+++ b/src/scraper/scraper.py
@@ -7,6 +7,7 @@ SEARCH_URL="keres.php?stext="
 
 categoriesMap = {
     "All": "",
+    "Hardver": "hardver",
     "Alaplap": "hardver/alaplap/",
     "Processzor": "hardver/processzor/",
     "Memória": "hardver/memoria/",
@@ -18,6 +19,7 @@ categoriesMap = {
     "Szerver SSD, HDD": "hardver/merevlemez_ssd/szerver_hdd_ssd/",
     "Adathordozó": "hardver/adathordozo/",
     "Hálózati termékek": "hardver/halozati_termekek/",
+    "Switch, HUB": "hardver/halozati_termekek/router_switch_repeater/switch_hub/",
     "3D nyomtatás": "hardver/3d_nyomtatas/",
     "Nyomtató, szkenner": "hardver/nyomtato_szkenner/",
     "Játékvezérlő, szimulátor": "hardver/jatekvezerlo/",
@@ -90,4 +92,8 @@ def findCategories(url= "https://hardverapro.hu/aprok/hardver/index.html"):
         name = a_tag.text.strip()
         href = a_tag['href'] if a_tag and a_tag.has_attr('href') else 'No link'
         href = href.rsplit('/',1)[0][6:] + '/'
-        print(f"\"{name}\": \"{href}\",")
\ No newline at end of file
+        print(f"\"{name}\": \"{href}\",")
+
+
+# Export it explicitly
+__all__ = ['categories', 'search', 'fetch']  # optional, but good practice
\ No newline at end of file