通过在代码中迭代字符串来创建循环

Question

我有以下代码：

from urllib.request import urlopen
from bs4 import BeautifulSoup
import pandas as pd
import requests 

from requests import get

date = []
tourney_round = []
result = []
winner_odds = []
loser_odds = []
surface = []
players_and_tourney

response = get('http://www.tennisexplorer.com/player/humbert-e2553/?annual=all')

page_html = BeautifulSoup(response.text, 'html.parser')

results2018_containers = page_html.find_all('div', id = 'matches-2018-1-data')

for container in results2018_containers:
played_date_2018 = results2018_containers[0].findAll('td', class_ = 'first time')
for i in played_date_2018:
            date.append(i.text)

string_2018 = '2018'
date = [x + string_2018 for x in date]

for container in results2018_containers:
rounds_2018 = results2018_containers[0].findAll('td', class_ = 'round')
for i in rounds_2018:
            tourney_round.append(i.text)

for container in results2018_containers:
results_2018 = results2018_containers[0].findAll('td', class_ = 'tl')
for i in results_2018:
            result.append(i.text)

for container in results2018_containers:
surfaces_2018 = results2018_containers[0].findAll('td', class_ = 's-color')
for i in surfaces_2018:
            surface.append(i.find('span')['title'])

for container in results2018_containers:
odds_2018 = results2018_containers[0].findAll('td', class_ = 'course')

winner_odds_2018 = odds_2018[0:][::2]
for i in winner_odds_2018:
    winner_odds.append(i.text)

loser_odds_2018 = odds_2018[1:][::2]
for i in loser_odds_2018:
    loser_odds.append(i.text)

for container in results2018_containers:
namesandtourney_2018 = results2018_containers[0].findAll('td', class_ = 't-name')
for i in namesandtourney_2018:
            players_and_tourney.append(i.text)

from itertools import chain, groupby, repeat

chainer = chain.from_iterable

def condition(x):
return x.startswith('\xa0')

elements = [list(j) for i, j in groupby(players_and_tourney, key=condition) if not i]

# create list of headers
headers = [next(j) for i, j in groupby(players_and_tourney, key=condition) if i]

# chain list of lists, and use repeat for headers
initial_df_2018 = pd.DataFrame({'Date': date,
                'Surface': surface,
                'Players': list(chainer(elements)),
                'Tournament': list(chainer(repeat(i, j) for i, j in \
                         zip(headers, map(len, elements)))),
                'Round': tourney_round,
                'Result': result,
                'Winner Odds': winner_odds,
                'Loser Odds' : loser_odds})

initial_df_2018['Winner'], initial_df_2018['Loser'] = 
initial_df_2018['Players'].str.split(' - ', 1).str
del initial_df_2018['Players']

initial_df_2018 = initial_df_2018[['Date','Surface','Tournament','Winner','Loser','Result','Winner Odds','Loser Odds']]

我想创建一个循环，从2005年开始每年运行代码。所以基本上，运行一个循环，在2005年和2018年之间每年替换代码中的2018。如果可能，该代码将首先在2018年运行，然后在2017年运行，依此类推直到2005年。你知道吗

编辑：我添加了用于提取2018年数据的代码，但我希望有一个循环，可以提取页面上所有年份的数据。你知道吗

Answer 1

循环使用它是没有问题的，但是你需要定义你想要的结果。我在这里使用了一个字典，我把你的代码变成了一个可以用变量调用的函数：

def get_data(year):
    date =[]

    response = get('http://www.example.com')

    page_html = BeautifulSoup(response.text, 'html.parser')

    results_containers = page_html.find_all('div', id = 'played-{year}-data'.format(year))

    for container in results_containers:
        played_date = results_containers[0].findAll('td', class_ = 'plays')
        for i in played_date:
            date.append(i.text)

    return date

现在我所要做的就是创建一个range的可能年份，并每次调用函数，这可以简单地做到：

all_data = {year: get_data(year) for year in range(2018, 2004, -1)}

Answer 2

您可以将年份存储为整数，但仍可以在字符串中使用它。你知道吗

for year in range(2018, 2004, -1):
    print(f"Happy New Year {year}")

在字符串中包含数字的其他方法有"Happy New Year {}".format(year)或"it is now " + str(year) + " more text"。你知道吗

另外，我不认为你会这样做，但是如果有人发现这个并且真的想“迭代一个字符串”caesar ciphers是一个很好的地方。你知道吗

Answer 3

如果我对您的理解正确，您希望完成2018年的申请，从2005年到2018年。你知道吗

我所做的是在这些范围内循环你的代码多年，每次都替换id并将所有数据添加到列表中。你知道吗

response = get('http://www.example.com')

page_html = BeautifulSoup(response.text, 'html.parser')
date_dict = {}

for year in range(2019, 1, -1):
    date = []
    string_id = "played-{}-data".format(year)
    results_containers = page_html.find_all('div', id = string_id)

    if (results_containers == None):
        continue
    for container in results_containers :
        played_date = results_containers [0].findAll('td', class_ = 'plays')
        for i in played_date :
            date.append(i.text)
    if not (year in date_dict):
        date_dict[year] = []
    date_dict[year] += date