Beautifulsoup 検索ページに取得したいデータがないときの飛ばし方がわからない

Question

問題点
race_id_listからfor文で回してスクレイピングをする際にデータが空のページがあるので
'NoneType' object has no attribute 'find_all'
とエラーが出て止まってしまう。

try、exceptで改善しよう試みたが解決できなかった。

どのようにコードを書けばエラーなくスクレイピングできるか教えていただきたいです。

race_id_list = []
venue_list = ["3601","1006","1106","1813","1914","2015","2135","2218","2320","2433","2726","2826","3129","3230"]
for venue in venue_list:
    for month in range(1, 13, 1):
        for day in range(1, 32, 1):
             for r in range(1, 13, 1):
                    race_id = "2020" + str(venue) + str(month)+str(day) + str(r)
                    race_id_list.append(race_id)

def result_scrape(race_id_list):
    race_results={}
    for race_id in tqdm(race_id_list):
        time.sleep(1)
        try:
            url = "https://keiba.rakuten.co.jp/race_performance/list/RACEID/"+ race_id
            html = requests.get(url)
            html.encoding = "UTF-8"
            soup = BeautifulSoup(html.text, "html.parser")

            #着順
            Ranks= soup.find_all("td",class_="order")
            Ranks_list = []
            for Rank in Ranks:
                Rank = Rank.get_text()
                Ranks_list.append(Rank)
            #Ranks_list = pd.DataFrame(Ranks_list)

            #枠
            Positions_a= soup.find("tbody",class_="record")
            Positions_b = Positions_a.find_all("th",class_="position")
            Positions_list = []
            for Position in Positions_b:
                Position = Position.get_text()
                Positions_list.append(Position)
            #Positions_list = pd.DataFrame(Positions_list)
            
            #内枠か外枠か　　　内枠０　　外枠１
            in_out_list = []
            for in_out_ in Positions_list:
                if int(in_out_) <= 4:
                    in_ = 0
                    in_out_list.append(str(in_))
                else:
                    out = str(1)
                    in_out_list.append(out)            
            
            #馬番　find_next_siblings()の説明はhttps://senablog.com/python-bs4-method/#toc_id_6
            horse_len_list = []
            a = soup.find_all("td",class_="order")
            for a_1 in a:
                b = a_1.find_next_siblings()[1]
                b  =b.get_text()
                horse_len_list.append(b)
            #horse_len_list  = pd.DataFrame(horse_len_list)
            #horse_len_list = [ho.find_next_siblings()[1] for ho in soup.find_all("td",class_="order")]もあり
            
            #頭数    strにしているのはｐｄ.DataFrameをするときにエラーが出るのを防ぐため
            horse_head = str(len(horse_len_list))
            
            
            #馬名
            horse_names= soup.find_all("td",class_="horse")
            horse_name_list = []
            for horse_name in horse_names:
                horse_name = horse_name.get_text()
                horse_name = horse_name.replace("\n","").lstrip()#replaceで\を消し　lstripで前のインデント（空白）をさくじょ
                horse_name  = horse_name.rstrip()#lstripで後ろのインデントを削除
                horse_name_list.append(horse_name)
            #horse_name_list = pd.DataFrame(horse_name_list)



            #斤量
            weight_Tax = soup.find_all("td",class_="weightTax")
            weight_Tax_list = []
            for weight_Tax_1 in weight_Tax:
                weight_Tax_1 = weight_Tax_1.get_text()
                weight_Tax_list.append(weight_Tax_1)
            #weight_Tax_list = pd.DataFrame(weight_Tax_list)

            #馬体重と増減を分ける
            weight = soup.find_all("td",class_="weight")
            weight_list = []
            for weight_1 in weight:
                weight_1 = weight_1.get_text()
                weight_1 = weight_1.replace("\n","").lstrip().rstrip()#replaceで\を消し　lstripで前のインデント（空白）をさくじょ 連結パターン
                weight_list.append(weight_1)

            #馬体重
            weight_lists = []
            for a in weight_list:
                a = a[:3]    
                weight_lists.append(a)
            #weight_lists = pd.DataFrame(weight_lists)

            #増減
            weiget_zougen_list = []
            weiget_zougen_lists = []#修正したやつ
            for b in weight_list:
                b = b[3:]
                weiget_zougen_list.append(b)

            for c in weiget_zougen_list:
                c = c.replace("±","")
                c = c.replace("+","")
                weiget_zougen_lists.append(c)
            #weiget_zougen_lists = pd.DataFrame(weiget_zougen_lists)

            #ジョッキー
            jockey = soup.find_all("td",class_="jockey")
            jockey_list = []
            for jockey_1 in jockey:

                jockey_1 = jockey_1.lstrip().rstrip()#replaceで\を消し　lstripで前のインデント（空白）をさくじょ 連結パターン
                jockey_list.append(jockey_1)

            #jockey_list = pd.DataFrame(jockey_list)

            #タイム  　　　　　　　　注意：　import time があるから名前をtimeにするとエラーが起きる。
            times = soup.find("tbody",class_="record") #classの中にあるclassを抜くとき、最初はfind
            race_time = times.find_all("td",class_="time")
            time_list = []
            for time_1 in race_time:
                time_1 = time_1.get_text()
                time_1 = time_1.replace("\n","").lstrip().rstrip()#replaceで\を消し　lstripで前のインデント（空白）をさくじょ 連結パターン
                time_list.append(time_1)
            #time_list = pd.DataFrame(time_list)

            #着差
            lead = soup.find_all("td", class_="lead")
            lead_list = []
            for lead_1 in lead:
                lead_1 = lead_1.get_text()
                lead_1 = lead_1.replace("\n","")
                lead_1 = lead_1.replace("\u3000"," ")
                lead_1 = lead_1.lstrip().rstrip()
                lead_list.append(lead_1)
            #lead_list = pd.DataFrame(lead_list)

            #上がり
            spurt = soup.find_all("td", class_="spurt")
            spurt_list = []
            for spurt_1 in spurt:
                spurt_1 = spurt_1.get_text()
                spurt_list.append(spurt_1)
            #spurt_list = pd.DataFrame(spurt_list)

            #調教師
            tamer = soup.find_all("td", class_="tamer")
            tamer_list = []
            for tamer_1 in tamer:
                tamer_1 = tamer_1.get_text()
                tamer_list.append(tamer_1)
            #tamer_list = pd.DataFrame(tamer_list)

            #人気
            # 一度、着順情報があるテーブルだけを取り出す
            table = soup.find("table", class_="dataTable")
            # HTML全体ではなく、上記テーブルのみから、条件を満たす要素を取り出す
            rank = table.find_all("td", class_="rank")
            rank_list = []
            for rank_1 in rank:
                rank_1 = rank_1.get_text()
                rank_list.append(rank_1)
            #rank_list = pd.DataFrame(rank_list)
            
            
            
            
            
            ##コース情報
            #距離
            info = soup.find("ul", class_="trackState trackMainState")
            distance = info.find_all("li", class_="distance")[0]
            distance = distance.get_text().replace("\n","").lstrip().rstrip()
            #distanceをべつの場所で実行していらない文字をコピペしてreplaceする 消したい文字をキーボードで入力してもなぜかきえない
            distance = distance.replace("ダ","")
            distance = distance.replace("m","")
            distance = distance.replace(",","")

            info = soup.find("ul", class_="trackState trackMainState")
            info_1 = info.find_all("dt")

            #馬場
            grand = info_1[1]
            grand = grand.get_text().replace("：","")

            info_2 = info.find_all("dd")
            #天候
            wether_1 = info_2[0]
            wether_1 = wether_1.get_text()

            #馬場状態
            grand_state  = info_2[1].get_text()
            
            
            #horse_id
            id = soup.find("tbody",class_="record") 
            id_a = id.find_all("td", class_="horse")
            id_b = id.find_all("td",attrs = {'class': 'horse'})
            horse_id_list=[]
            for td in id_b:
                horse_id = re.findall(r'\d+', td.find('a')['href'])[0]
                horse_id_list.append(horse_id)

            df = pd.DataFrame({
                #"レース_id":''.join(race_id),
                "距離":''.join(distance),
                "天候":"".join(wether_1),
                "馬場状態":''.join(grand_state),
                "馬場":"".join(grand),
                "着順":Ranks_list,
                "枠":Positions_list,
                "内or外": in_out_list,
                "馬番":horse_len_list,
                "頭数":''.join(horse_head),
                "馬名":horse_name_list,
                "斤量":weight_Tax_list,
                "馬体重":weight_lists,
                "増減":weiget_zougen_lists,
                "騎手":jockey_list,
                "タイム":time_list,
                "着差":lead_list,
                "上がり":spurt_list,
                "調教師":tamer_list,
                "人気":rank_list,
                "horse_id":horse_id_list
            })
            
            
            #race_id を辞書型のkeyにする方法
            race_results[race_id] = df
        
        #存在しないrace_idを飛ばす
        except IndexError:
            continue
        
        #wify切れたとき
        except Exception as e:
            print(e)
            break
        
        #jupyterの停止ボタンの処理        
        except:
            break

    return race_results

Answer 1

try exceptで対処

Comments

[otn]

初心者には使いこなしが難しい機能ですが。
想定した例外（指定したタグが存在しない）だけを捕まえて、
それ以外の例外（ネットワーク障害とかその他全部）を捕まえないように出来ていますか？

Answer 2

結果が空リストかどうかifで判断すれば良いだけでしょう。

xxx = soup.find_all(～～～)
if xxx:
  for x in xxx:
    ～～～～
else:
  空の時の処理