download second page

Author: tswast

2025/national-jukebox/download_first_page.py

@@ -27,7 +27,8 @@
 DATA_DIR = pathlib.Path(__file__).parent / "data"
 
 
-target_url = "https://www.loc.gov/collections/national-jukebox/?sb=date_desc&c=100"
+# target_url = "https://www.loc.gov/collections/national-jukebox/?sb=date_desc&c=100"
+target_url = "https://www.loc.gov/collections/national-jukebox/?c=100&sb=date_desc&sp=2"
 item_urls = list_urls.get_national_jukebox_song_detail_urls(target_url)
 
 

2025/national-jukebox/download_mp3s.py

@@ -42,7 +42,8 @@ def download_mp3(base_url):
 jukebox_path = DATA_DIR / "jukebox.jsonl"
 jukebox = pandas.read_json(jukebox_path, lines=True, orient="records")
 
-for _, row in jukebox.iterrows():
+# for _, row in jukebox.iterrows():
+for _, row in jukebox.iloc[100:].iterrows():
     jukebox_id = row["URL"].split("/")[-2]
     mp3_path = (DATA_DIR / jukebox_id).with_suffix(".mp3")
     if mp3_path.exists():