獲取CSDN文章內容並轉換為markdown文字的python
阿新 • • 發佈:2020-09-08
自己寫的小工具,可以直接獲取csdn文章並轉換為markdown格式
效果圖
核心程式碼
from PySide2.QtWidgets import QApplication,QMainWindow,QPushButton,QPlainTextEdit,QMessageBox import re import parsel import tomd import requests class CSDN(): def __init__(self): self.windows = QMainWindow() self.windows.resize(450,300) self.windows.setWindowTitle("輕鬆獲取csdn文章--by tansty") self.setup_ui() self.set_connect() def set_connect(self): #設定建立聯絡 self.button.clicked.connect(self.spider_csdn) def setup_ui(self): #設定ui介面的建立 self.button = QPushButton(self.windows) self.button.resize(100,100) self.button.move(150,150) self.button.setText("獲取文章") self.text = QPlainTextEdit(self.windows) self.text.setPlaceholderText("請輸入需要獲取文章的連結") self.text.resize(450,100) def spider_csdn(self): # 目標文章的連結 title_url=self.text.toPlainText() MessageBox = QMessageBox(self.windows) if not title_url: MessageBox.critical(self.windows,"錯誤","請輸入網址") return head={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/84.0.4147.105 Safari/537.36 Edg/84.0.522.52" } html=requests.get(url=title_url,headers=head).text page=parsel.Selector(html) #建立直譯器 title=page.css(".title-article::text").get() res = re.compile("[^\u4e00-\u9fa5^a-z^A-Z^0-9]") restr = '' res.sub(restr,title) content=page.css("article").get() content=re.sub("<a.*?a>","",content) content = re.sub("<br>",content) texts=tomd.Tomd(content).markdown #轉換為markdown 檔案 with open(title+".md",mode="w",encoding="utf-8") as f: f.write("#"+title) f.write(texts) MessageBox.information(self.windows,"正確","獲取文章完成") if __name__ == '__main__': app = QApplication() csdn=CSDN() csdn.windows.show() app.exec_()
檔案打包下載 連結: https://pan.baidu.com/s/1R6RcrDagwf1vWzmRCBja4w 提取碼: ug6n