1 files changed, 27 insertions, 0 deletions
diff --git a/scraper.py b/scraper.py
new file mode 100755
index 0000000..7f6144b
--- /dev/null
+++ b/scraper.py
@@ -0,0 +1,27 @@
+#!/usr/bin/env python3
+
+# yes, html is not a regular language
+
+import requests, sys
+uris = sys.argv[1:]
+import re
+for uri in uris:
+    resp = requests.get(uri).text
+    lines = resp.split('\n')
+    license = None
+    author = None
+    for idx, line in enumerate(lines):
+        if 'Original file' in line:
+            uri = re.match(r'.*href="(.*?)".*', line).group(1)
+        elif 'licensetpl_short' in line:
+            license = line.rsplit('>')[-1]
+        elif author is None and 'Author</td' in line:
+            author = re.match(r'(.*?>)?(.*?)<.*', lines[idx+2]).group(2)
+    if not uri.startswith('http'):
+        uri = 'https:' + uri
+    r = requests.get(uri, allow_redirects=True)
+    local_filename = uri.split('/')[-1]
+    open("./static/assets/" + local_filename, 'wb').write(r.content)
+    print('[[mediums.works.figures]]')
+    print('file = "' + local_filename + '"')
+    print(f'byline = "{license}{author}"')