diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..c520156 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +specimen_img_raw/*.jpg diff --git a/image_fetch.py b/image_fetch.py index 416a25d..92b567a 100644 --- a/image_fetch.py +++ b/image_fetch.py @@ -1,5 +1,6 @@ import glob import time +import urllib.error import urllib.request import requests @@ -30,7 +31,14 @@ with open("barcode_cleaned.csv") as bcfile: rdf_url = "https://www.botanicalcollections.be/specimen/" + barcode + "/rdf" print("fetching", rdf_url) - img_url = find_image(rdf_url) + try: + img_url = find_image(rdf_url) + except urllib.error.HTTPError as er: + print("Error on ", rdf_url, str(er)) + continue + if img_url is None: + print("Error. No image for barcode.") + continue img_ext = str(img_url).rsplit(".", 1)[1] print("image url:", img_url) save_path = "specimen_img_raw/" + barcode + "." + img_ext