####方便Markdown寫博客

import re,requests from bs4 import BeautifulSoup# ptt = soup.find_all(name='div', attrs={"class":"ptt"})[0] #獲取小標題 def get_title(soup):return soup.find_all(name='p', attrs={"class":"pst"}) #獲取文本 def get_text(soup):return soup.find_all(name='div', attrs={"class":"ptx"}) #獲取樣例 def get_sample(soup):return soup.find_all(name='pre', attrs={"class":"sio"})print("Please input URL:") url = input() html = requests.get(url) soup = BeautifulSoup(html.text, "lxml")text_list = get_text(soup)[0:3] title_list = get_title(soup)[0:5] sample_list = get_sample(soup)text = list() title = list() all = list() #處理文本 加換行符 for i in text_list:text.append(i.text + '\r\n') for i in title_list:title.append("#### " + i.text + '\r\n') for i in sample_list:i = '```\r\n' + i.string + '\r\n' + '```\r\n'text.append(i)for i in range(5):all.append(title[i] + text[i]) URL = '[題目鏈接]' + '(' + url + ')' + '\r\n' f = open('POJ.txt', 'w') f.write(URL) for i in all:f.write(i) f.write("#### AC\n- ") f.close() print("Done!")

總結

以上是生活随笔為你收集整理的爬虫 - POJ题目信息的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。