如何使用 python 將 html 表導出到 csv 文件？

Question

我從 yahoofinance 網站上抓取了一個 html 表，並嘗試將表導出到 csv 文件。 但是，它不會在 csv 文件中返回正確的 output。 我的終端上打印的 output 似乎很好。 我在這里做錯了什么？

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，而不是返回數據。 如果您想要一個表中的所有數據，最好添加一列，其中包含該行的起源符號。 你可以使用這樣的東西

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')