如何使用 python 将 html 表导出到 csv 文件？

Question

我从 yahoofinance 网站上抓取了一个 html 表，并尝试将表导出到 csv 文件。 但是，它不会在 csv 文件中返回正确的 output。 我的终端上打印的 output 似乎很好。 我在这里做错了什么？

import requests
from bs4 import BeautifulSoup
import csv
import pandas as pd

mystocks = ["XOM", "CVX", "COP", "EOG"]
stockdata = []

def getData(symbol): 
    headers = {"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0"}
    url = f"https://finance.yahoo.com/quote/{symbol}/key-statistics"
    soup = BeautifulSoup(requests.get(url, headers=headers).content, "html.parser")
    print("Ticker - "+symbol)
    for t in soup.select("table"):
        for tr in t.select("tr:has(td)"):
            for sup in tr.select("sup"):
                sup.extract()
            stockdata = [td.get_text(strip=True) for td in tr.select("td")]
            if len(stockdata) == 2:
                print("{:<50} {}".format(*stockdata))

for item in mystocks:
    stockdata.append(getData(item))

    df = pd.DataFrame(stockdata)
    df.to_csv('file_name.csv')

Answer 1

您正在打印，而不是返回数据。 如果您想要一个表中的所有数据，最好添加一列，其中包含该行的起源符号。 你可以使用这样的东西

import requests
from bs4 import BeautifulSoup
import csv
import pandas as pd

mystocks = ["XOM", "CVX", "COP", "EOG"]
stockdata = []

def getData(symbol): 
    headers = {"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0"}
    url = f"https://finance.yahoo.com/quote/{symbol}/key-statistics"
    soup = BeautifulSoup(requests.get(url, headers=headers).content, "html.parser")
    print("Ticker - "+symbol)
    for t in soup.select("table"):
        for tr in t.select("tr:has(td)"):
            for sup in tr.select("sup"):
                sup.extract()
            stockdata = [td.get_text(strip=True) for td in tr.select("td")]
            if len(stockdata) == 2:
                # add a column with the symbol to help affterwards
                yield [item] + stockdata

# this will concatenate the rows for all the symbols in mystocks
df = pd.DataFrame([r for item in mystocks for r in getData(item)])
df.to_csv('file_name.csv')