Parsing Python: Cum să copiezi o secţiune de date dintr-un fişier html în alte fişiere html

<title></title>, <meta name="description" content=" "/>, all from <!-- ARTICLE START --> to <!-- ARTICLE FINAL -->, all from <!-- FLAGS_1 --> to <!-- FLAGS -->, all from <!-- MENU START --> to <!-- MENU FINAL -->

   

<title>YOUR FIRST PAGE</title>

<meta name="description" content="I LOVE HTML and CSS"/>

<!-- ARTICLE START -->
	Text Text
<!-- ARTICLE FINAL -->



<!-- FLAGS_1 -->
	Text Text
<!-- FLAGS -->


<!-- MENU START -->
 Text Text
<!-- MENU FINAL -->

import requests
import re

# The folder that contains the file you want to parse
english_folder1 = r"d:\Downloads\A"

# The folder with the files you want to change
english_folder2 = r"d:\Downloads\B"

# The file you want to make parsing
file_to_parse_from = 'example.html'

extension_file = ".html"

use_parse_folder = True

import os

en1_directory = os.fsencode(english_folder1)
en2_directory = os.fsencode(english_folder2)

print('Going through english folder')
for file in os.listdir(en2_directory):
    filename = os.fsdecode(file)
    print(filename)
    if filename == 'y_key_e479323ce281e459.html' or filename == 'directory.html':
        continue
    if filename.endswith(extension_file):
        with open(os.path.join(english_folder1, file_to_parse_from), encoding='utf-8') as html:
            html = html.read()

            try:
                with open(os.path.join(english_folder2, filename), encoding='utf-8') as en_html:
                    en_html = en_html.read()
                    
                    title = re.search('<title.+/title>', html)[0]
                    meta = re.search('<meta name="description".+>', html)[0]
                    comment_body = re.search('<!-- ARTICLE START -->.+<!-- ARTICLE FINAL -->', html, flags=re.DOTALL)[0]

                    try:
                        comment_body2 = re.search('<!-- FLAGS_1 -->.+<!-- FLAGS -->', html, flags=re.DOTALL)[0]
                        en_html = re.sub('<!-- FLAGS_1 -->.+<!-- FLAGS -->', comment_body2, en_html, flags=re.DOTALL)
                    except:
                        pass

                    try:
                        comment_body3 = re.search('<!-- MENU START -->.+<!-- MENU FINAL -->', html, flags=re.DOTALL)[0]
                        en_html = re.sub('<!-- MENU START -->.+<!-- MENU FINAL -->', comment_body3, en_html, flags=re.DOTALL)
                    except:
                        pass
                    
                    en_html = re.sub('<!-- ARTICLE START -->.+<!-- ARTICLE FINAL -->', comment_body, en_html, flags=re.DOTALL)
                    en_html = re.sub('<meta name="description".+>', meta, en_html)
                    en_html = re.sub('<title.+/title>', title, en_html)
            except FileNotFoundError:
                continue

        print(f'{filename} parsed')
        if use_parse_folder:
            try:
                with open(os.path.join(english_folder2+r'\parsed', 'parsed_'+filename), 'w', encoding='utf-8') as new_html:
                    new_html.write(en_html)
            except:
                os.mkdir(english_folder2+r'\parsed')
                with open(os.path.join(english_folder2+r'\parsed', 'parsed_'+filename), 'w', encoding='utf-8') as new_html:
                    new_html.write(en_html)
        else:
            with open(os.path.join(english_folder2, 'parsed_'+filename), 'w', encoding='utf-8') as html:
                html.write(en_html)