You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

56 lines
2.1 KiB

import requests
import re
import tkinter as tk
from tkinter import Toplevel
headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 SLBrowser/9.0.3.1311 SLBChan/11"
}
def show_data_window():
def fetch_data():
urls = [f"https://www.gushiwen.cn/default_{i}.aspx" for i in range(1, 5)]
gushici = []
for url in urls:
response = requests.get(url, headers=headers)
content = response.text
titles = re.findall('<b>(.*?)</b>', content, re.DOTALL)
authors = re.findall('<p class="source">.*?<a.*?<a.*?>(.*?)</a>', content, re.DOTALL)
dynastys = re.findall('<p class="source">.*?<a.*?<a.*?>(.*?)</a>', content, re.DOTALL)
poetics = re.findall('<div class="contson.*?">(.*?)</div>', content, re.DOTALL)
new_poetics = [''.join(re.split('<.*?>|<.*? />', p)).strip() for p in poetics]
for title, author, dynasty, poetic in zip(titles, authors, dynastys, new_poetics):
gushici.append({"title": title, "author": author, "dynasty": dynasty, "poetic": poetic})
with open("gushi.txt", "w", encoding="utf-8") as file:
for item in gushici:
file.write(f"标题: {item['title']}, 作者: {item['author']}, 朝代: {item['dynasty']}, 内容: {item['poetic']}\n")
# 在新窗口显示数据
show_data_window(gushici)
def show_data_window(data):
window = Toplevel(root)
window.title("古诗词信息")
text_widget = tk.Text(window)
text_widget.pack(expand=True, fill='both')
for item in data[:10]: # 仅显示前10条数据作为示例
text_widget.insert(tk.END, f"标题: {item['title']}\n作者: {item['author']}\n朝代: {item['dynasty']}\n内容: {item['poetic']}\n\n")
window.mainloop()
root = tk.Tk()
root.title("古诗词爬虫")
fetch_button = tk.Button(root, text="开始爬取", command=fetch_data)
fetch_button.pack(pady=20)
root.mainloop()