'ValueError: 4 columns passed, passed data had 1 columns
'NEW LEARNER' If data in column from webpage is not an integer, I cannot append the row to my data frame. [webpage data as seen by this image] (https://i.stack.imgur.com/KBjRU.png)
Here is my code:
import pandas as pd import requests from datetime import datetime from bs4 import BeautifulSoup
ticker = input("Type your ticker symbol: ")
def get_balance_sheet_from_yfinance_web(ticker):
url = f"https://finance.yahoo.com/quote/%7Bticker%7D/balance-sheet?p=%7Bticker%7D"
header = {'Connection': 'keep-alive',
'Expires': '-1',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64)
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
}
r = requests.get(url, headers=header)
html = r.text
soup = BeautifulSoup(html, "html.parser")
div = soup.find_all('div', attrs={'class': 'D(tbhg)'})
if len(div) < 1:
print("Fail to retrieve table column header")
exit(0)
col = []
pd.set_option('max_colwidth', None)
for h in div[0].find_all('span'):
text = h.get_text()
if text != "Breakdown":
col.append(datetime.strptime(text, "%m/%d/%Y"))
df = pd.DataFrame(columns=col)
pd.set_option('max_colwidth', None)
for div in soup.find_all('div', attrs={'data-test': 'fin-row'}):
i = 0
idx = ""
val = []
for h in div.find_all('span'):
if i == 0:
idx = h.get_text()
else:
num = int(h.get_text().replace(",", "")) * 1000
val.append(num)
i += 1
row = pd.DataFrame([val], columns=col, index=[idx])
df = df.append(row)
df.to_csv(f'{ticker}.csv')
return df
print(get_balance_sheet_from_yfinance_web(ticker))
I have tried replace('-', 0)
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|
