s3platform_pandas_w_links for so_q_75828625

## for https://stackoverflow.com/q/75828625/6146136

# !!pip install --upgrade --pre pandas==1.5.0 ## this solution requires pandas 1.5.0
import pandas as pd

output_fp = 'digital-innovation-hubs.csv'
dfList, pg_num, max_pg = [], 0, 3
base_url = 'https://s3platform.jrc.ec.europa.eu/digital-innovation-hubs-tool'
while (pg_num:=pg_num+1) and (not isinstance(max_pg,int) or pg_num<max_pg):
    pg_url = f'{base_url}?_eu_europa_ec_jrc_dih_web_DihWebPortlet_cur={pg_num}'
    try: dfList += pd.read_html(pg_url, extract_links='all')[:1]
    except Exception as e: pg_num, _ = -1, print(f'\n{e!r} from {pg_url}')
    else: print('', end=f'\rScraped {len(dfList[-1])} rows from {pg_url}')

# df = pd.concat(dfList) ## if you don't want to add a column for page numbers
df = pd.concat(
    dfList, keys=list(range(1,len(dfList)+1)), names=['from_pg','pgi']
).reset_index().drop('pgi',axis='columns')

## clean up - separate links from text
orig_cols = [c for c in df.columns if c != 'from_pg']
for ocn in orig_cols:
    if any(vals:=[cv for cv,*_ in df[ocn]]): df[ocn[0]] = vals
    if any(links:=[c[1] for c in df[ocn]]): df[ocn[0].split()[0]+' Links'] = links
if 'Email Links' in df.columns:
    df['Email'] = df['Email Links'].str.replace('mailto:', '', 1)
    df = df.drop('Email Links', axis='columns')
df = df.drop(orig_cols, axis='columns')

## save csv file
df.to_csv(output_fp, index=False)