Parse NLM Catalog journal list

00_parse_nlmcatalog.py

import pandas as pd

dl = []
d={}
with open("J_Medline.txt","r") as f:
    for l in f:
        l = l.strip()
        if "----" in l:
            dl.append(pd.Series(d))
            d={}
            continue
        ll = l.split(":",maxsplit=1)
        if len(ll)==1:
            ll.append("")
        d[ll[0]]=ll[1].lstrip(" ")

df = pd.DataFrame(dl)
df.to_csv("J_Medline.csv")
df.to_excel("J_Medline.xlsx")