1

我是 Python 的新手，正在帮助一个学校项目。任何帮助深表感谢。谢谢。到 2004 年和 2003 年时出现错误。这是由 result_list 列表引起的。错误是“ValueError：数组必须都是相同的长度”。我怎样才能引入解决这个问题的代码。分数很重要......

import requests
import pandas as pd
from pandas import ExcelWriter
from bs4 import BeautifulSoup
#from openpyxl.writer.excel import ExcelWriter
import openpyxl
#from openpyxl import load_workbook
import csv

year_id = ['2019','2018','2017','2016','2015','2014','2013','2012','2011','2010','2009','2008','2007','2006','2005','2004','2003']

i=0
while i <= len(year_id)-1: 
    url = 'https://lehighsports.com/sports/mens-soccer/schedule/' + str(year_id[i])
    lehigh = requests.get(url).text
    soup = BeautifulSoup(lehigh,'lxml')

    date_list = []
    for date in soup.find_all('div',class_="sidearm-schedule-game-opponent-date"):
        date_list.append(date.get_text(strip=True, separator=' '))

    name_list = []
    for name in soup.find_all('div',class_="sidearm-schedule-game-opponent-name"):
        name_list.append(name.get_text(strip=True, separator=' '))

    result_list = []
    for result in soup.find_all('div',class_="sidearm-schedule-game-result"):
        result_list.append(result.get_text(strip=True, separator=' '))

    opp_list = []
    for opp in soup.find_all('div',class_="sidearm-schedule-game-opponent-text"):
        opp_list.append(opp.get_text(strip=True, separator=' '))

    conf_list = []
    for conf in soup.find_all('div',class_="sidearm-schedule-game-conference-conference"):
        conf_list.append(conf.get_text(strip=True))

    dict = {'date':date_list,'opponent':name_list,'result':result_list,'list':opp_list,'conference':conf_list}
    df = pd.DataFrame(dict)

    workbook1 = openpyxl.load_workbook('lehigh.xlsx')
    writer = pd.ExcelWriter('lehigh.xlsx', engine='openpyxl') 
    writer.book = workbook1
    df.to_excel(writer, sheet_name=str(year_id[i]),index=False,startrow=0,startcol=0)
    writer.save()
    writer.close()

    i = i+1
4

2 回答 2

2

代码更新：

import requests
from bs4 import BeautifulSoup
import pandas as pd
from itertools import zip_longest

d = []
n = []
res = []
op = []
yr = []
with requests.Session() as req:
    for year in range(2003, 2020):
        print(f"Extracting Year# {year}")
        r = req.get(
            f"https://lehighsports.com/sports/mens-soccer/schedule/{year}")
        if r.status_code == 200:
            soup = BeautifulSoup(r.text, 'html.parser')
            for date in soup.findAll("div", {'class': 'sidearm-schedule-game-opponent-date flex-item-1'}):
                d.append(date.get_text(strip=True, separator=" "))
            for name in soup.findAll("div", {'class': 'sidearm-schedule-game-opponent-name'}):
                n.append(name.get_text(strip=True))
            for result in soup.findAll("div", {'class': 'sidearm-schedule-game-result'}):
                result = result.get_text(strip=True)
                res.append(result)
            if len(d) != len(res):
                res.append("None")
            for opp in soup.findAll("div", {'class': 'sidearm-schedule-game-opponent-text'}):
                op.append(opp.get_text(strip=True, separator=' '))
                yr.append(year)


data = []
for items in zip_longest(yr, d, n, res, op):
    data.append(items)

df = pd.DataFrame(data, columns=['Year', 'Date', 'Name', 'Result', 'Opponent']).to_excel(
    'lehigh.xlsx', index=False)

输出：在线检查

于 2020-01-06T11:21:25.333 回答
2

一些东西：

  1. 您不需要遍历索引。只需简单地遍历列表
  2. 您收到错误的原因是结果列表的长度为 23，而您的其他列表的长度为 24。因此您需要弄清楚如何处理空值，并处理它们是否掉落（它们可能并不总是最后一个条目）

我会怎么做，我会抓取每一行，然后为此拉取数据，而不是将每个实体拉入列表。然后我在网站上获取所有这些行并创建一个表格，并制作一个表格列表（每年一个表格）。处理丢失数据的方法是使用 try/except。我还添加了一个小功能（在此处找到），它将获取表格列表并将它们写入单独的 Excel 表中。

import requests
import pandas as pd
from pandas import ExcelWriter
from bs4 import BeautifulSoup
#from openpyxl.writer.excel import ExcelWriter
import openpyxl
#from openpyxl import load_workbook
import csv

year_id = ['2019','2018','2017','2016','2015','2014','2013','2012','2011','2010','2009','2008','2007','2006','2005','2004','2003']


results = []
for year in year_id: 
    url = 'https://lehighsports.com/sports/mens-soccer/schedule/' + year
    print (url)
    lehigh = requests.get(url).text
    soup = BeautifulSoup(lehigh,'lxml')

    rows = soup.find_all('div',class_="sidearm-schedule-game-row flex flex-wrap flex-align-center row")

    sheet = pd.DataFrame()
    for row in rows:
        date = row.find('div',class_="sidearm-schedule-game-opponent-date").text.strip()
        name = row.find('div',class_="sidearm-schedule-game-opponent-name").text.strip()
        opp = row.find('div',class_="sidearm-schedule-game-opponent-text").text.strip()
        conf = row.find('div',class_="sidearm-schedule-game-conference-conference").text.strip()

        try:
            result = row.find('div',class_="sidearm-schedule-game-result").text.strip()
        except:
            result = ''

        df = pd.DataFrame([[year,date,name,opp,conf,result]], columns=['year','date','opponent','list','conference','result'])
        sheet = sheet.append(df,sort=True).reset_index(drop=True)

    results.append(sheet)



def save_xls(list_dfs, xls_path):
    with ExcelWriter(xls_path) as writer:
        for n, df in enumerate(list_dfs):
            df.to_excel(writer,'%s' %year_id[n],index=False,)
        writer.save()

save_xls(results,'lehigh.xlsx')
于 2020-01-06T11:38:58.390 回答