fix duplicate lines bug

This commit is contained in:
2025-10-22 13:27:04 -07:00
parent 1bc0633c48
commit c046658737

View File

@ -19,12 +19,9 @@ def get_df(html_path):
for row in trs:
# print(type(row))
entries = row.find_all("td")
for e in entries:
# print(e.text.strip())
entry_str = [e.text.strip() for e in entries]
s = dict(zip(cols, entry_str))
rows.append(s)
entry_str = [e.text.strip() for e in entries]
s = dict(zip(cols, entry_str))
rows.append(s)
df = pd.DataFrame(rows)
return df