问将SEC 10-K年度报告文本保存到文件中(解码问题)

EN

import re
import requests
import unicodedata
from bs4 import BeautifulSoup

def restore_windows_1252_characters(restore_string):
    def to_windows_1252(match):
        try:
            return bytes([ord(match.group(0))]).decode('windows-1252')
        except UnicodeDecodeError:
            # No character at the corresponding code point: remove it.
            return ''

    return re.sub(r'[\u0080-\u0099]', to_windows_1252, restore_string)

# define the url to specific html_text file
new_html_text = r"https://www.sec.gov/Archives/edgar/data/796343/0000796343-14-000004.txt"

# grab the response
response = requests.get(new_html_text)
page_soup = BeautifulSoup(response.content,'html5lib')

page_text = page_soup.html.body.get_text(' ',strip = True)

# normalize the text, remove characters. Additionally, restore missing window characters.
page_text_norm = restore_windows_1252_characters(unicodedata.normalize('NFKD', page_text)) 

# print: this works however gives me weird special characters in the print (e.g., at the very end)
print(page_text_norm)

# save to file: this only gives me an empty text file
with open('testfile.txt','w') as file:
    file.write(page_text_norm)