image_download/prepare_csv.py

@@ -0,0 +1,34 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+import pandas as pd
+
+
+if __name__ == '__main__':
+    # prepare csv path
+    input_path = Path(__file__).parent / 'images_mm.csv'
+    assert input_path.exists()
+    # load in csv
+    df = pd.read_csv(
+        input_path,
+        delimiter=';',
+        header=None,
+        names=['name', 'url'],
+    )
+    # remove last letter from names
+    df['name'] = df['name'].str[:-1]
+    # remove rows with duplicate names
+    df.drop_duplicates(subset='name', inplace=True)
+    # reset index to look more nice
+    df.reset_index(drop=True, inplace=True)
+    # remove query from urls
+    pattern = r'(\?img_.+)'
+    df['url'] = df['url'].str.replace(
+        pat=pattern,
+        repl='',
+        regex=True,
+    )
+    # save df to file
+    output_path = input_path.parent / 'sources.csv'
+    df.to_csv(output_path, index=False)