import curses
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import os
# 文件路径
FAVORITES_FILE = 'favorites.txt'
HISTORY_FILE = 'history.txt'
# 加载数据
def load_list(filename):
try:
with open(filename, 'r', encoding='utf-8') as f:
return [line.strip() for line in f if line.strip()]
except FileNotFoundError:
return []
# 保存数据
def save_list(filename, items):
with open(filename, 'w', encoding='utf-8') as f:
for item in items:
f.write(item + '\n')
# 获取网页纯文本
def fetch_page(url):
try:
res = requests.get(url, timeout=5)
res.raise_for_status()
soup = BeautifulSoup(res.text, 'html.parser')
for tag in soup(['script', 'style']):
tag.decompose()
return soup.get_text()
except Exception as e:
return f"加载失败: {e}"
# 提取超链接和表单（扩展版）
def extract_links_and_forms(html, base_url):
soup = BeautifulSoup(html, 'html.parser')
# 提取超链接
links = []
for a in soup.find_all('a', href=True):
href = a['href']
if not href.startswith('http'):
href = urljoin(base_url, href)
links.append((href, a.get_text(strip=True)))
# 提取表单
forms = []
for form in soup.find_all('form'):
action = form.get('action', '')
if not action.startswith('http'):
action = urljoin(base_url, action)
method = form.get('method', 'get').lower()
inputs = []
# 提取所有输入字段
for input_tag in form.find_all(['input', 'textarea', 'select']):
name = input_tag.get('name')
if not name:
continue
input_type = input_tag.get('type', 'text')
value = input_tag.get('value', '')
required = input_tag.has_attr('required')
placeholder = input_tag.get('placeholder', '')
if input_tag.name == 'textarea':
input_type = 'textarea'
value = input_tag.get_text()
elif input_tag.name == 'select':
input_type = 'select'
options = [(opt.get('value') or opt.text, opt.text) for opt in input_tag.find_all('option')]
inputs.append({
'name': name,
'type': input_type,
'value': value,
'required': required,
'placeholder': placeholder,
'options': options
})
continue
# 处理 checkbox 和 radio
if input_type == 'checkbox' or input_type == 'radio':
inputs.append({
'name': name,
'type': input_type,
'value': value,
'checked': input_tag.has_attr('checked'),
'required': required
})
continue
inputs.append({
'name': name,
'type': input_type,
'value': value,
'required': required,
'placeholder': placeholder
})
forms.append((action, method, inputs))
return links, forms
# 输入框
def input_box(stdscr, prompt):
curses.echo()
stdscr.clear()
stdscr.addstr(0, 0, prompt)
stdscr.refresh()
input_str = stdscr.getstr(1, 0).decode('utf-8')
curses.noecho()
return input_str
# 提交表单（扩展版）
def submit_form(stdscr, form):
action, method, inputs = form
data = {}
for field in inputs:
name = field['name']
input_type = field['type']
required = field.get('required', False)
placeholder = field.get('placeholder', '')
value = field.get('value', '')
prompt = f"{name}"
if placeholder:
prompt += f"（提示：{placeholder}）"
if required:
prompt += " [必填]"
if input_type == 'select':
options = field['options']
stdscr.clear()
stdscr.addstr(0, 0, f"请选择 {name}：")
for i, (val, text) in enumerate(options):
stdscr.addstr(i + 1, 0, f"{i + 1}. {text}")
stdscr.refresh()
idx = int(stdscr.getstr(len(options) + 2, 0).decode('utf-8')) - 1
data[name] = options[idx][0]
elif input_type == 'checkbox':
checked = field.get('checked', False)
res = input_box(stdscr, f"{name} [复选框] 是否选中？(y/n)：")
data[name] = 'on' if res.lower() == 'y' else ''
elif input_type == 'radio':
res = input_box(stdscr, f"{name} [单选] 是否选中？(y/n)：")
data[name] = value if res.lower() == 'y' else ''
else:
default = value if value else ''
user_input = input_box(stdscr, f"{prompt}：")
data[name] = user_input if user_input else default
try:
if method == 'post':
res = requests.post(action, data=data)
else:
res = requests.get(action, params=data)
return res.text
except Exception as e:
return f"表单提交失败：{e}"
# 收藏夹菜单
def favorites_menu(stdscr, favorites, current_url):
while True:
options = ["新添", "删除", "退出"]
action = show_list(stdscr, options, "收藏夹", options)
if action == 0: # 新添
if current_url not in favorites:
favorites.append(current_url)
save_list(FAVORITES_FILE, favorites)
elif action == 1: # 删除
if favorites:
idx = show_list(stdscr, favorites, "选择要删除的收藏")
if idx >= 0:
favorites.pop(idx)
save_list(FAVORITES_FILE, favorites)
elif action == 2 or action == -1:
break
# 历史记录菜单
def history_menu(stdscr, history):
while True:
options = ["清空", "退出"]
action = show_list(stdscr, options, "历史记录", options)
if action == 0: # 清空
history.clear()
save_list(HISTORY_FILE, history)
elif action == 1 or action == -1:
break
elif action >= 0:
return history[action]
return None
# 显示列表（收藏夹/历史记录）
def show_list(stdscr, items, title, actions=None):
selected = 0
while True:
stdscr.clear()
stdscr.addstr(0, 0, title)
if actions:
stdscr.addstr(0, len(title) + 2, f"| {' | '.join(actions)}")
stdscr.addstr(1, 0, "-" * 50)
for i, item in enumerate(items):
if i == selected:
stdscr.attron(curses.A_REVERSE)
stdscr.addstr(i + 2, 0, f"{i + 1}. {item}")
if i == selected:
stdscr.attroff(curses.A_REVERSE)
stdscr.addstr(len(items) + 3, 0, "方向键选择，Enter确认，q退出")
stdscr.refresh()
key = stdscr.getch()
if key == curses.KEY_UP and selected > 0:
selected -= 1
elif key == curses.KEY_DOWN and selected < len(items) - 1:
selected += 1
elif key == ord('\n'):
return selected
elif key == ord('q'):
return -1
def main(stdscr):
curses.curs_set(0) # 隐藏光标
favorites = load_list(FAVORITES_FILE)
history = load_list(HISTORY_FILE)
# 初始页面加载
current_url = input_box(stdscr, "请输入网址：")
page_text = fetch_page(current_url)
if current_url not in history:
history.append(current_url)
if len(history) > 20:
history.pop(0)
save_list(HISTORY_FILE, history)
# 初始数据
menu_options = ["收藏夹", "新的网页", "历史记录"]
selected_menu = 0
links, forms = extract_links_and_forms(page_text, current_url)
selected_link = 0
selected_form = 0
mode = "menu" # 当前模式：menu, link, form
while True:
stdscr.clear()
h, w = stdscr.getmaxyx()
# 显示顶部菜单
for i, opt in enumerate(menu_options):
x = 2 + i * 15
if mode == "menu" and i == selected_menu:
stdscr.attron(curses.A_REVERSE)
stdscr.addstr(0, x, opt)
if mode == "menu" and i == selected_menu:
stdscr.attroff(curses.A_REVERSE)
stdscr.addstr(1, 0, "-" * w)
# 显示网页内容
lines = page_text.split('\n')
for i, line in enumerate(lines[:h - 10]):
stdscr.addstr(i + 2, 0, line[:w - 1])
# 显示超链接
stdscr.addstr(h - 8, 0, "超链接：")
for i, (url, text) in enumerate(links):
label = f"{i + 1}. {text[:30]}..."
if mode == "link" and i == selected_link:
stdscr.attron(curses.A_REVERSE)
stdscr.addstr(h - 7 + i, 0, label[:w - 1])
if mode == "link" and i == selected_link:
stdscr.attroff(curses.A_REVERSE)
# 显示表单
stdscr.addstr(h - 7 + len(links) + 1, 0, "表单：")
for i, (action, method, inputs) in enumerate(forms):
label = f"表单 {i + 1}: {method.upper()} {action[:30]}..."
if mode == "form" and i == selected_form:
stdscr.attron(curses.A_REVERSE)
stdscr.addstr(h - 6 + len(links) + i + 1, 0, label[:w - 1])
if mode == "form" and i == selected_form:
stdscr.attroff(curses.A_REVERSE)
# 底部提示
stdscr.addstr(h - 1, 0, "方向键选择，Enter确认，q返回，Tab切换区域")
stdscr.refresh()
# 用户输入处理
key = stdscr.getch()
if key == ord('q'):
break
elif key == ord('\t'):
# 切换模式：菜单 -> 链接 -> 表单 -> 菜单
if mode == "menu":
mode = "link"
elif mode == "link":
mode = "form"
else:
mode = "menu"
elif key == curses.KEY_UP:
if mode == "menu" and selected_menu > 0:
selected_menu -= 1
elif mode == "link" and selected_link > 0:
selected_link -= 1
elif mode == "form" and selected_form > 0:
selected_form -= 1
elif key == curses.KEY_DOWN:
if mode == "menu" and selected_menu < len(menu_options) - 1:
selected_menu += 1
elif mode == "link" and selected_link < len(links) - 1:
selected_link += 1
elif mode == "form" and selected_form < len(forms) - 1:
selected_form += 1
elif key == ord('\n'):
if mode == "menu":
if selected_menu == 0:
favorites_menu(stdscr, favorites, current_url)
elif selected_menu == 1:
current_url = input_box(stdscr, "请输入网址：")
page_text = fetch_page(current_url)
if current_url not in history:
history.append(current_url)
if len(history) > 20:
history.pop(0)
save_list(HISTORY_FILE, history)
links, forms = extract_links_and_forms(page_text, current_url)
elif selected_menu == 2:
selected_url = history_menu(stdscr, history)
if selected_url:
current_url = selected_url
page_text = fetch_page(current_url)
links, forms = extract_links_and_forms(page_text, current_url)
elif mode == "link":
if links:
current_url = links[selected_link][0]
page_text = fetch_page(current_url)
links, forms = extract_links_and_forms(page_text, current_url)
elif mode == "form":
if forms:
result = submit_form(stdscr, forms[selected_form])
page_text = result
links, forms = extract_links_and_forms(page_text, current_url)
return
# 启动程序
if __name__ == "__main__":
curses.wrapper(main)
这是我的纯文本浏览器的源代码。它报错了：Python 3.11.9 (tags/v3.11.9:de54cf5, Apr 2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license()" for more information.
= RESTART: C:\Users\number one\Desktop\纯文本浏览器.py
Traceback (most recent call last):
File "C:\Users\number one\Desktop\纯文本浏览器.py", line 363, in <module>
curses.wrapper(main)
File "C:\Users\number one\AppData\Local\Programs\Python\Python311\Lib\curses\__init__.py", line 73, in wrapper
stdscr = initscr()
File "C:\Users\number one\AppData\Local\Programs\Python\Python311\Lib\curses\__init__.py", line 30, in initscr
fd=_sys.__stdout__.fileno())
AttributeError: 'NoneType' object has no attribute 'fileno'
最新发布
本文介绍如何使用Python的urllib库抓取小说网站的数据，并通过BeautifulSoup进行解析。在解析过程中，特别提到了一个常见错误：当对象为None时调用'find_all'方法会抛出AttributeError。解决方案是确保在调用该方法前对象已正确初始化。
最低0.47元/天 解锁文章
扫一扫
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
