add devcontainer confg for codespaces

Author: David

.devcontainer/devcontainer.json

@@ -0,0 +1,29 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/debian
+{
+	"name": "Debian",
+	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+	"image": "mcr.microsoft.com/devcontainers/base:bullseye",
+	"features": {
+		"ghcr.io/devcontainers-contrib/features/poetry:2": {}
+	},
+
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+
+	"hostRequirements": {
+		"cpus": 2,
+		"memory": "2gb",
+		"storage": "4gb"
+	},
+	"postCreateCommand": "poetry install"
+}

README.md

@@ -1,6 +1,7 @@
 
 ![checks status](https://github.com/dcaribou/transfermarkt-scraper/workflows/Scrapy%20Contracts%20Checks/badge.svg)
 ![docker build status](https://github.com/dcaribou/transfermarkt-scraper/workflows/Dockerhub%20Image/badge.svg)
+
 # transfermarkt-scraper
 
 A web scraper for collecting data from [Transfermarkt](https://www.transfermarkt.co.uk/) website. It recurses into the Transfermarkt hierarchy to find
@@ -16,6 +17,7 @@ A web scraper for collecting data from [Transfermarkt](https://www.transfermarkt
 Each one of these entities can be discovered and refreshed separately by invoking the corresponding crawler.
 
 ## Installation
+> [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/dcaribou/transfermarkt-scraper/tree/main?quickstart=1)
 
 This is a [scrapy](https://scrapy.org/) project, so it needs to be run with the
 `scrapy` command line util. This and all other required dependencies can be installed using [poetry](https://python-poetry.org/docs/).

tfmkt/spiders/common.py

@@ -63,7 +63,7 @@ def __init__(self, base_url=None, parents=None, season=None):
     if season:
       self.season = season
     else:
-      self.season = 2022
+      self.season = 2024
 
     self.entrypoints = parents
 
@@ -84,7 +84,6 @@ def start_requests(self):
       item['seasoned_href'] = self.seasonize_entrypoin_href(item)
       applicable_items.append(item)
 
-
     return [
       Request(
         item['seasoned_href'],

tfmkt/spiders/competitions.py

@@ -45,7 +45,7 @@ def parse(self, response, parent):
 
       total_value = row.css('td:nth-of-type(8)::text').get()
 
-      matches = re.search('([0-9]+)\.png', country_image_url, re.IGNORECASE)
+      matches = re.search(r'([0-9]+)\.png', country_image_url, re.IGNORECASE)
       country_id = matches.group(1)
 
       href = "/wettbewerbe/national/wettbewerbe/" + country_id

tfmkt/spiders/players.py

@@ -121,7 +121,7 @@ def parse_market_history(self, response: Response):
     """
     Parse player's market history from the graph
     """
-    pattern = re.compile('\'data\'\:.*\}\}]')
+    pattern = re.compile(r'\'data\'\:.*\}\}]')
 
     try:
       parsed_script = json.loads(