Python - 將數據保存到文件

Question

我正在嘗試將數據表保存到 txt 文件，而不是在控制台上顯示結果。 但是，我的代碼導致我在 txt 文件中沒有...有人可以幫助我嗎：

我想保存到 txt 文件的結果：

from bs4 import BeautifulSoup
import requests
import re
import json

# Input
thislist = ["AAPL"]
for symbol in thislist:
    print ('Getting data for ' + symbol + '...\n')
# Set up scraper
url1 = ("http://financials.morningstar.com/finan/financials/getFinancePart.html?&callback=xxx&t=" + symbol.lower())
url2 = ("http://financials.morningstar.com/finan/financials/getKeyStatPart.html?&callback=xxx&t=" + symbol.lower())

soup1 = BeautifulSoup(json.loads(re.findall(r'xxx\((.*)\)', requests.get(url1).text)[0])['componentData'], 'lxml')
soup2 = BeautifulSoup(json.loads(re.findall(r'xxx\((.*)\)', requests.get(url2).text)[0])['componentData'], 'lxml')

def print_table(soup):

    for i, tr in enumerate(soup.select('tr')):

        row_data = [td.text for td in tr.select('td, th') if td.text]

        if not row_data:
            continue

        if len(row_data) < 12:
            row_data = ['X'] + row_data

        for j, td in enumerate(row_data):
            if j==0:
                print('{: >30}'.format(td), end='|')
            else:
                print('{: ^12}'.format(td), end='|')
        print()
  
print_table(soup1)

print()

print_table(soup2)

因此，我編寫了以下代碼將其保存到 txt 文件中，但 txt 文件中的結果為“NONE”，但結果顯示在控制台上：

from bs4 import BeautifulSoup
import requests
import re
import json

# Input
thislist = ["AAPL"]
for symbol in thislist:
    print ('Getting data for ' + symbol + '...\n')

    # Set up scraper
    url1 = ("http://financials.morningstar.com/finan/financials/getFinancePart.html?&callback=xxx&t=" + symbol.lower())
    url2 = ("http://financials.morningstar.com/finan/financials/getKeyStatPart.html?&callback=xxx&t=" + symbol.lower())
    
    soup1 = BeautifulSoup(json.loads(re.findall(r'xxx\((.*)\)', requests.get(url1).text)[0])['componentData'], 'lxml')
    soup2 = BeautifulSoup(json.loads(re.findall(r'xxx\((.*)\)', requests.get(url2).text)[0])['componentData'], 'lxml')
    
    def print_table(soup):
  
        for i, tr in enumerate(soup.select('tr')):
    
            row_data = [td.text for td in tr.select('td, th') if td.text]
    
            if not row_data:
                continue
    
            if len(row_data) < 12:
                row_data = ['X'] + row_data
    
            for j, td in enumerate(row_data):
                if j==0:
                    print('{: >30}'.format(td), end='|')
                else:
                    print('{: ^12}'.format(td), end='|')
            print()
      
    # Save the data tables to a TXT file
    # Open a file with access mode 'a'
    file_object = open('testing aapl data.txt', 'a')
    # Append data at the end of file
    file_object.write(str(print_table(soup1))+"\n")
    file_object.write(str(print_table(soup2))+"\n")
    # Close the file
    file_object.close()

Answer 1

您的 function, print_table格式化 go 上的所有內容並將所有內容傳遞到控制台，沒有任何內容被保留或返回以放入文件中。 由於print_table不返回任何內容，因此給出了None 。

對此的解決方案可能是創建一個字符串finaltext並將格式化后將打印在一起的所有內容連接起來，然后打印finaltext ，然后返回該字符串以供任何其他用途

以下腳本是實現的解決方案以及其他一些改進

from bs4 import BeautifulSoup
import requests
import re
import json

#Only needs to be made once, as the 'for' loop will re-create it repeated
def print_table(soup):
    finaltext = ''
    for i, tr in enumerate(soup.select('tr')):
        row_data = [td.text for td in tr.select('td, th') if td.text]
        if not row_data:
            continue
    
        if len(row_data) < 12:
            row_data = ['X'] + row_data
    
        for j, td in enumerate(row_data):
            if j==0:
                finaltext += '{: >30}'.format(td) + '|'
            else:
                finaltext += '{: ^12}'.format(td) + '|'
        finaltext += '\n'
    print(finaltext)
    return finaltext

# Input
thislist = ["AAPL"]
for symbol in thislist:
    print ('Getting data for ' + symbol + '...\n')

    # Set up scraper
    url1 = ("http://financials.morningstar.com/finan/financials/getFinancePart.html?&callback=xxx&t=" + symbol.lower())
    url2 = ("http://financials.morningstar.com/finan/financials/getKeyStatPart.html?&callback=xxx&t=" + symbol.lower())
    
    soup1 = BeautifulSoup(json.loads(re.findall(r'xxx\((.*)\)', requests.get(url1).text)[0])['componentData'], 'lxml')
    soup2 = BeautifulSoup(json.loads(re.findall(r'xxx\((.*)\)', requests.get(url2).text)[0])['componentData'], 'lxml')
      
    # Save the data tables to a TXT file
    # Open a file with access mode 'a'
    file_object = open('testing_aapl_data.txt', 'a') # Habit of mine to not have spaces in filenames
    # Append data at the end of file
    file_object.write(str(print_table(soup1))+"\n")
    file_object.write(str(print_table(soup2))+"\n")
    # Close the file
    file_object.close()