Text-Based browser
Ce script fait partie des projets Python de HyperSkill.
j'ai fait toute la formation python de Hyperskill pendant le Confinement 2020.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import sys | |
| import os | |
| from collections import deque | |
| from bs4 import BeautifulSoup | |
| import requests | |
| from colorama import Fore | |
| args = sys.argv | |
| folder = args[1] # "Yolo" | |
| history = deque() | |
| list_tag = ["p", "h1", "h2", "h3", "h4", "h5", "h6", "a", "ul", "ol", "li"] | |
| def validate_url(_url): | |
| if "https://" in _url: | |
| return _url, _url.strip("https://").split(".")[0] | |
| else: | |
| if len(_url.split(".")) != 1: | |
| return f"https://{_url}", _url.split(".")[0] | |
| return False, None | |
| print(Fore.BLUE) | |
| while True: | |
| if not os.path.exists(folder): | |
| os.mkdir(folder) | |
| user_input = input("Url ?") | |
| if user_input == "exit": | |
| exit(0) | |
| if user_input == "back": | |
| history.pop() | |
| user_input = history[-1] | |
| url, filename = validate_url(user_input) | |
| print(url, filename) | |
| if url: | |
| history.append(url) | |
| req = requests.get(url) | |
| with open(f"{folder}/{filename}", "w") as file: | |
| raw_text = req.content | |
| soup = BeautifulSoup(raw_text, "html.parser") | |
| text = [] | |
| for tags in soup.findAll(list_tag): | |
| if tags.get_text() != "\n": | |
| raw = tags.get_text().replace("\t", "").replace("\r", "").replace("\n", "") | |
| text.append(raw) | |
| file.write("\n".join(text)) | |
| print("\n".join(text)) | |
| else: | |
| if os.path.exists(f"{folder}/{user_input}"): | |
| with open(f"{folder}/{user_input}", "r") as file: | |
| print(file.read()) | |
| else: | |
| print("Error: Incorrect URL") |
cyvax - 2024