Merge pull request #222 from Crinibus/create-folder-models

Move dataclasses to new folder "models"

scraper/domains.py

@@ -5,7 +5,9 @@
 import json
 import logging
 from abc import ABC, abstractmethod
-from scraper.format import Format, Info
+
+from scraper.models import Info
+from scraper.format import Format
 from scraper.constants import REQUEST_HEADER, REQUEST_COOKIES
 from scraper.filemanager import Config
 

scraper/format.py

@@ -1,18 +1,6 @@
-from dataclasses import dataclass
 from scraper.filemanager import Config
 
 
-@dataclass
-class Info:
-    """Scraped info about product"""
-
-    name: str
-    price: float
-    currency: str
-    id: str
-    valid: bool = True
-
-
 class Format:
     @staticmethod
     def get_user_product_name(product_name: str) -> str:

scraper/models/__init__.py

@@ -0,0 +1 @@
+from scraper.models.product import Datapoint, Info, Product, MasterProduct

scraper/models/product.py

@@ -0,0 +1,80 @@
+from dataclasses import dataclass, field
+import re
+
+
+@dataclass
+class Info:
+    """Scraped info about product"""
+
+    name: str
+    price: float
+    currency: str
+    id: str
+    valid: bool = True
+
+
+@dataclass
+class Datapoint:
+    date: str
+    price: float
+
+
+@dataclass
+class Product:
+    product_name: str
+    category: str
+    url: str
+    id: str
+    currency: str
+    website: str
+    datapoints: list[Datapoint]
+    is_up_to_date: bool
+
+    def get_all_dates(self) -> list[str]:
+        return [datapoint.date for datapoint in self.datapoints]
+
+    def get_all_prices(self) -> list[float]:
+        return [datapoint.price for datapoint in self.datapoints]
+
+    def to_string_format(self, format: str) -> str:
+        """Return a string representing the product, controlled by an explicit format string.
+
+        >>> p = Product("ASUS RTX 4090", "GPU", "https://www.example.com/", "123", "USD", "example", [datepoints], True)
+        >>> p.to_string_format("Name: %name, Category: %category, URL: %url, ID: %id, Website: %website")
+        'Name: ASUS RTX 4090, Category: GPU, URL: https://www.example.com/, ID: 123, Website: example'
+        """
+        # inspiration from https://docs.python.org/3/library/re.html#writing-a-tokenizer
+        token_specification = [
+            ("NAME", r"(%name)"),
+            ("CATEGORY", r"(%category)"),
+            ("URL", r"(%url)"),
+            ("ID", r"(%id)"),
+            ("CURRENCY", r"(%currency)"),
+            ("WEBSITE", r"(%website)"),
+        ]
+        format_to = {
+            "NAME": self.product_name,
+            "CATEGORY": self.category,
+            "URL": self.url,
+            "ID": self.id,
+            "CURRENCY": self.currency,
+            "WEBSITE": self.website,
+        }
+
+        tok_regex = "|".join("(?P<%s>%s)" % pair for pair in token_specification)
+        new_string = format
+
+        for mo in re.finditer(tok_regex, format):
+            kind = mo.lastgroup
+            value = mo.group()
+
+            new_string = new_string.replace(value, format_to[kind], 1)
+
+        return new_string
+
+
+@dataclass
+class MasterProduct:
+    product_name: str
+    category: str
+    products: list[Product] = field(default_factory=list)

scraper/scrape.py

@@ -2,9 +2,10 @@
 import threading
 import logging
 from datetime import datetime
+
+from scraper.models import Info
 from scraper.domains import BaseWebsiteHandler, get_website_handler
 from scraper.filemanager import Filemanager
-from scraper.format import Info
 
 
 class Scraper:

scraper/visualize.py

@@ -1,80 +1,12 @@
-from dataclasses import dataclass, field
 from typing import Iterable, Iterator
 import plotly.graph_objs as go
 from datetime import datetime
-import re
 
+from scraper.models import Datapoint, MasterProduct, Product
 from scraper import Filemanager
 from scraper.constants import WEBSITE_COLORS
 
 
-@dataclass
-class Datapoint:
-    date: str
-    price: float
-
-
-@dataclass
-class Product:
-    product_name: str
-    category: str
-    url: str
-    id: str
-    currency: str
-    website: str
-    datapoints: list[Datapoint]
-    is_up_to_date: bool
-
-    def get_all_dates(self) -> list[str]:
-        return [datapoint.date for datapoint in self.datapoints]
-
-    def get_all_prices(self) -> list[float]:
-        return [datapoint.price for datapoint in self.datapoints]
-
-    def to_string_format(self, format: str) -> str:
-        """Return a string representing the product, controlled by an explicit format string.
-
-        >>> p = Product("ASUS RTX 4090", "GPU", "https://www.example.com/", "123", "USD", "example", [datepoints], True)
-        >>> p.to_string_format("Name: %name, Category: %category, URL: %url, ID: %id, Website: %website")
-        'Name: ASUS RTX 4090, Category: GPU, URL: https://www.example.com/, ID: 123, Website: example'
-        """
-        # inspiration from https://docs.python.org/3/library/re.html#writing-a-tokenizer
-        token_specification = [
-            ("NAME", r"(%name)"),
-            ("CATEGORY", r"(%category)"),
-            ("URL", r"(%url)"),
-            ("ID", r"(%id)"),
-            ("CURRENCY", r"(%currency)"),
-            ("WEBSITE", r"(%website)"),
-        ]
-        format_to = {
-            "NAME": self.product_name,
-            "CATEGORY": self.category,
-            "URL": self.url,
-            "ID": self.id,
-            "CURRENCY": self.currency,
-            "WEBSITE": self.website,
-        }
-
-        tok_regex = "|".join("(?P<%s>%s)" % pair for pair in token_specification)
-        new_string = format
-
-        for mo in re.finditer(tok_regex, format):
-            kind = mo.lastgroup
-            value = mo.group()
-
-            new_string = new_string.replace(value, format_to[kind], 1)
-
-        return new_string
-
-
-@dataclass
-class MasterProduct:
-    product_name: str
-    category: str
-    products: list[Product] = field(default_factory=list)
-
-
 def visualize_data(
     show_all: bool, categories: list[str], ids: list[str], names: list[str], only_up_to_date: bool, compare: bool
 ) -> None: