如何遍历列表Web抓取的表格列并为每个项目返回一个结果？

Question

I have a python code that web scrape the correct data but the guests column has more than one string in and is currently only pulling through one. So how do I iterate through the list within that column cell and return the 3 guests as a separate columns for each hopefully guest1, guest2, guest3? Thanks

import requests
import pandas as pd
from bs4 import BeautifulSoup
import numpy as np

df = pd.DataFrame(columns=(['NoInSeason', 'Guests', 'Winner', 'OriginalAirDate']))
page = requests.get("https://en.wikipedia.org/wiki/List_of_QI_episodes")
soup = BeautifulSoup(page.content, "lxml")
my_tables = soup.find_all("table",{"class":"wikitable plainrowheaders wikiepisodetable"})
for table in my_tables:
    table_rows = table.find_all("tr")
    for tr in table_rows:
        td = tr.find_all("td")
        if len(td) == 5:
            NoInSeason = td[0].find(text=True)
            Guests = td[2].find_all(text=True)
            Winner  = td[3].find(text=True)
            OriginalAirDate = td[4].find(text=True) 
            if len(Guests) == 3:
                Guest1 = Guests[0]
                Guest2 = Guests[1]
                Guest3 = Guests[2]
                df = df.append({'NoInSeason': NoInSeason, 'Guest1' : Guest1, 'Guest2' : Guest2, 'Guest3' : Guest3, 'Winner': Winner, 'OriginalAirDate' : OriginalAirDate}, ignore_index=True)
df.to_csv("output.csv")
print(df)

Answer 1

Is this what you were looking for?

df = pd.DataFrame(columns=(['NoInSeason', 'Guest 1', 
'Guest 2', 'Guest 3', 'Winner', 'OriginalAirDate']))
page = 
  requests.get("https://en.wikipedia.org/wiki/List_of_QI_episodes")
soup = BeautifulSoup(page.content, "lxml")
my_tables = soup.find_all("table",{"class":"wikitable plainrowheaders wikiepisodetable"})
for table in my_tables:
    table_rows = table.find_all("tr")
    for tr in table_rows:
        td = tr.find_all("td")
        if len(td) == 5:
            NoInSeason = td[0].find(text=True)
            Guests = td[2].find_all(text=True)
            Winner  = td[3].find(text=True)
            OriginalAirDate = td[4].find(text=True)
            print(Guests)
            try:
                df = df.append({'NoInSeason': NoInSeason, 'Guest 1' : Guests[0], 'Guest 2' : Guests[1], 'Guest 3' : Guests[2], 'Winner': Winner, 'OriginalAirDate' : OriginalAirDate}, ignore_index=True)
            except IndexError as index_error:
                continue
print(df)

Edit: I see you changed your code, does it now work? And would it not work better including the Guest1, Guest2, and Guest3 columns in the DataFrame so that you don't get a 'Guests' column full of NaN?