chore: change anthem download to .ogg instead of .mp3

01_scrapy/wikipedia_country_scraper/download_countries.sh

@@ -1,2 +1,3 @@
+#!/bin/bash
 source .venv/bin/activate
 scrapy crawl CountrydownloaderSpider

01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/pipelines.py

@@ -24,5 +24,5 @@ class WikipediaCountryScraperFilesPipeline(FilesPipeline):
         if isinstance(flag_filename, re.Match):
             if (filename := flag_filename[1]).endswith(".svg"):
                 return f"files/flags/{filename}"
-            elif filename.endswith(".ogg.mp3"):
+            elif filename.endswith(".ogg"):
                 return f"files/anthems/{filename}"

01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/spiders/countrydownloader.py

@@ -50,7 +50,7 @@ class CountrydownloaderSpider(scrapy.Spider):
         ).get()
 
         anthem_file_url = response.xpath(
-            "//table[contains(@class, 'infobox')]/tbody/tr/td[contains(@class, 'anthem')]//source[@data-title='MP3']/@src"
+            "//table[contains(@class, 'infobox')]/tbody/tr/td[contains(@class, 'anthem')]//source[contains(@type, 'audio/ogg')]/@src"
         ).get()
         anthem_item = response.xpath(
             "//table[contains(@class, 'infobox')]/tbody/tr/td[contains(@class, 'anthem')]"
@@ -94,7 +94,6 @@ class CountrydownloaderSpider(scrapy.Spider):
         country_item = {**country_item, "flag_image_url": f"https:{flag_image_xpath}"}
 
         country_scrapy_item = WikipediaCountryScraperItem()
-        print(f"ANTHEM: {country_item['anthem']}")
 
         country_scrapy_item["country_url"] = country_item["country_url"]
         country_scrapy_item["short_country_name"] = country_item["short_country_name"]

playground/downloaded_data_inspection/pyproject.toml

@@ -0,0 +1,19 @@
+[tool.poetry]
+name = "downloaded_data_inspection"
+version = "0.1.0"
+description = ""
+authors = ["Daniel Tomlinson <dtomlinson@panaetius.co.uk>"]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+notebook = "^6.4.12"
+pandas = "^1.4.2"
+jupyterthemes = "^0.20.0"
+jupyter-contrib-nbextensions = "^0.5.1"
+jupyter-resource-usage = "^0.6.1"
+
+[tool.poetry.dev-dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"