Python实现一键提取页面所有链接

def read_text_file(file_path):
    with open(file_path, encoding='utf-8') as f:
        return f.read()

import re
def extract_urls(text):
    pattern = r"(?:(?:https?|ftp):\/\/)?[\w/\-?=%.]+\.[\w/\-?=%.]+"
    return re.findall(pattern, text)

def export_urls(urls, file_path):
    with open(file_path.replace(".txt", "_links.txt"), "w", encoding='utf-8') as f:
        f.write("\n".join(urls))

if __name__ == "__main__":
    import sys
    get_urls(sys.argv[1])

import glob, os
all_urls = []
for txt_file in glob.glob("*.txt"):
    all_urls.extend(extract_urls(read_text_file(txt_file)))
with open("all_links.txt", "w", encoding='utf-8') as f:
    f.write("\n".join(set(all_urls)))  # set 去重

import tkinter as tk
from tkinter.filedialog import askopenfilename

root = tk.Tk()
root.withdraw()  # 隐藏主窗口
file = askopenfilename(filetypes=[("Text files", "*.txt")])
if file:
    get_urls(file)
    tk.messagebox.showinfo("完成", f"已生成 {file}_links.txt")

import os
import requests
from bs4 import BeautifulSoup
 
# 目标网页的URL
url = "https://"  # 请将此处替换为实际的网页URL
# 指定下载文件的文件夹路径
# 使用原始字符串
download_folder = r"D:\"
# 或者使用双反斜杠
# download_folder = "D:\\AScholarFolder\\"
# 创建下载文件夹（如果不存在）
if not os.path.exists(download_folder):
    os.makedirs(download_folder)
# 获取网页内容
response = requests.get(url)
if response.status_code == 200:
    soup = BeautifulSoup(response.text, 'html.parser')
    # 找到所有的 <a> 标签
    for a_tag in soup.find_all('a'):
        href = a_tag.get('href')
        if href:
            # 下载文件
            file_name = href.split('/')[-1]
            file_path = os.path.join(download_folder, file_name)
            try:
                file_response = requests.get(href)
                if file_response.status_code == 200:
                    with open(file_path, 'wb') as file:
                        file.write(file_response.content)
                    print(f"已下载: {file_name}")
                else:
                    print(f"下载失败: {href}")
            except:
                print(f"下载失败: {href}")
else:
    print(f"无法获取网页内容: {url}")