chore: add initial scrapy code

01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/pipelines.py

@@ -0,0 +1,28 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+import re
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+from scrapy.pipelines.files import FilesPipeline
+
+
+class WikipediaCountryScraperPipeline:
+    def process_item(self, item, spider):
+        return item
+
+
+class WikipediaCountryScraperFilesPipeline(FilesPipeline):
+    def file_path(self, request, response=None, info=None, *, item=None):
+        print(f"request URLs: {request.url}")
+        flag_filename = re.search(r"([^\/]*)$", request.url)
+        anthem_filename = re.search(r"(?P<filename>(?<=File\:)[^\$]*)", request.url)
+
+        if isinstance(flag_filename, re.Match):
+            return f"files/{flag_filename[1]}"
+        elif anthem_filename["filename"].endswith(".mp3"):
+            return f"files/{anthem_filename['filename']}"