Add scraper code.

Should have added this earlier, whoops.

yellowstone/core.py

@@ -8,6 +8,7 @@
 import pugsql
 
 from .config import Config, getenv
+from .jobs import site_home_raw
 from .s3 import S3
 from .wikidot import Wikidot
 

yellowstone/scraper.py

@@ -0,0 +1,23 @@
+"""
+Utilities to assist with scraping.
+"""
+
+import re
+
+import requests
+
+from .exceptions import ScrapingError
+
+
+def download_html(url: str) -> str:
+    r = requests.get(url)
+    r.raise_for_status()
+    return r.text()
+
+
+def regex_extract(source: str, body: str, regex: re.Pattern) -> re.Match:
+    match = regex.search(body)
+    if match is None:
+        raise ScrapingError(f"Pattern {regex.pattern} failed for {source}")
+
+    return match