From 4622b03777d203af5f0dc375517b418d66dc66c6 Mon Sep 17 00:00:00 2001
From: Brian Bjarke Jensen <bbj@skov.dk>
Date: Fri, 1 Mar 2024 16:56:08 +0100
Subject: [PATCH] added script to download images

---
 image_download/get_images.py | 69 ++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)
 create mode 100644 image_download/get_images.py

diff --git a/image_download/get_images.py b/image_download/get_images.py
new file mode 100644
index 0000000..90b6861
--- /dev/null
+++ b/image_download/get_images.py
@@ -0,0 +1,69 @@
+from __future__ import annotations
+
+import logging
+import shutil
+from pathlib import Path
+
+import pandas as pd
+import requests
+from retry import retry
+
+from image_download.classes import Instagram
+
+
+def get_sources() -> pd.DataFrame:
+    """Get sources dateframe."""
+    input_path = Path(__file__).parent / 'sources.csv'
+    assert input_path.exists()
+    # load in csv
+    df = pd.read_csv(input_path)
+    return df
+
+
+@retry(
+    exceptions=AssertionError,
+    tries=3,
+    delay=5,
+    backoff=1.2,
+    jitter=(1, 10),
+)
+def download_images(ig_inst: Instagram, filename: str, url: str) -> None:
+    """
+    Download images from instagram post found on url
+
+    to files with base name from filename.
+    """
+    # get image urls
+    url_list = ig_inst.get_image_url_list(url)
+    assert len(url_list) > 0
+    # generate filenames
+    chars = 'abcdefghij'
+    filename_list = [name + chars[i] for i in range(len(url_list))]
+    # download images
+    download_dir = Path(__file__).parent / 'imgs'
+    download_dir.mkdir(exist_ok=True)
+    for filename, url in zip(filename_list, url_list):
+        output_path = download_dir / f"{filename}.jpg"
+        response = requests.get(url, stream=True)
+        with open(output_path, 'wb') as fh:
+            shutil.copyfileobj(response.raw, fh)
+        logging.info('downloaded %s', output_path)
+
+
+if __name__ == '__main__':
+    # setup logging
+    logging.basicConfig(level=logging.INFO)
+    # get sources df
+    df = get_sources()
+    # setup Instagram interface
+    igi = Instagram()
+    igi.setup()
+    # begin downloading
+    for idx in range(len(df)):
+        # get info from source dataframe
+        name = df.loc[idx, 'name']
+        url = df.loc[idx, 'url']
+        # download post images
+        download_images(ig_inst=igi, filename=name, url=url)
+    # clean up
+    igi.close()